Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
6920be192e |
No files matched your search
@@ -7,29 +7,35 @@ body:
|
||||
value: >
|
||||
Thank you for taking the time to file a bug report.
|
||||
|
||||
Use this to report BUGS in LangGraph. For usage questions, feature requests and general design questions, please use [GitHub Discussions](https://github.com/langchain-ai/langgraph/discussions).
|
||||
Use this to report bugs in LangChain.
|
||||
|
||||
If you're not certain that your issue is due to a bug in LangChain, please use [GitHub Discussions](https://github.com/langchain-ai/langchain/discussions)
|
||||
to ask for help with your issue.
|
||||
|
||||
Relevant links to check before filing a bug report to see if your issue has already been reported, fixed or
|
||||
if there's another way to solve your problem:
|
||||
|
||||
[LangGraph Github Discussions](https://github.com/langchain-ai/langgraph/discussions),
|
||||
[LangGraph Github Issues](https://github.com/langchain-ai/langgraph/issues),
|
||||
[LangGraph how-to guides](https://langchain-ai.github.io/langgraph/how-tos/).
|
||||
[LangGraph documentation](https://langchain-ai.github.io/langgraph/).
|
||||
[LangChain documentation with the integrated search](https://python.langchain.com/docs/get_started/introduction),
|
||||
[GitHub search](https://github.com/langchain-ai/langgraph),
|
||||
[LangChain Github Discussions](https://github.com/langchain-ai/langgraph/discussions),
|
||||
[LangChain Github Issues](https://github.com/langchain-ai/langgraph/issues),
|
||||
[LangChain ChatBot](https://chat.langchain.com/)
|
||||
- type: checkboxes
|
||||
id: checks
|
||||
attributes:
|
||||
label: Checked other resources
|
||||
description: Before submitting this issue, please confirm that you have completed all the steps below by checking each option. These steps help ensure your issue is well-defined, relevant, and actionable.
|
||||
description: Please confirm and check all the following options.
|
||||
options:
|
||||
- label: This is a bug, not a usage question. For questions, please use GitHub Discussions.
|
||||
- label: I added a very descriptive title to this issue.
|
||||
required: true
|
||||
- label: I added a clear and detailed title that summarizes the issue.
|
||||
- label: I searched the [LangGraph](https://langchain-ai.github.io/langgraph/)/LangChain documentation with the integrated search.
|
||||
required: true
|
||||
- label: I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example).
|
||||
- label: I used the GitHub search to find a similar question and didn't find it.
|
||||
required: true
|
||||
- label: I included a self-contained, minimal example that demonstrates the issue INCLUDING all the relevant imports. The code run AS IS to reproduce the issue.
|
||||
- label: I am sure that this is a bug in LangGraph/LangChain rather than my code.
|
||||
required: true
|
||||
- label: I am sure this is better as an issue [rather than a GitHub discussion](https://github.com/langchain-ai/langgraph/discussions/new/choose), since this is a LangGraph bug and not a design question.
|
||||
required: true
|
||||
- type: textarea
|
||||
id: reproduction
|
||||
@@ -39,6 +45,14 @@ body:
|
||||
label: Example Code
|
||||
description: |
|
||||
Please add a self-contained, [minimal, reproducible, example](https://stackoverflow.com/help/minimal-reproducible-example) with your use case.
|
||||
|
||||
If a maintainer can copy it, run it, and see it right away, there's a much higher chance that you'll be able to get help.
|
||||
|
||||
**Important!**
|
||||
|
||||
* Reduce your code to the minimum required to reproduce the issue if possible. This makes it much easier for others to help you.
|
||||
* Avoid screenshots when possible, as they are hard to read and (more importantly) don't allow others to copy-and-paste your code.
|
||||
|
||||
placeholder: |
|
||||
from langgraph.graph import StateGraph
|
||||
|
||||
@@ -78,8 +92,25 @@ body:
|
||||
attributes:
|
||||
label: System Info
|
||||
description: |
|
||||
Please share your system info with us.
|
||||
|
||||
"pip freeze | grep langchain"
|
||||
platform (windows / linux / mac)
|
||||
python version
|
||||
|
||||
OR if you're on a recent version of langchain-core you can paste the output of:
|
||||
|
||||
python -m langchain_core.sys_info
|
||||
placeholder: |
|
||||
"pip freeze | grep langgraph"
|
||||
platform
|
||||
python version
|
||||
|
||||
Alternatively, if you're on a recent version of langchain-core you can paste the output of:
|
||||
|
||||
python -m langchain_core.sys_info
|
||||
|
||||
These will only surface LangChain packages, don't forget to include any other relevant
|
||||
packages you're using (if you're not sure what's relevant, you can paste the entire output of `pip freeze`).
|
||||
validations:
|
||||
required: true
|
||||
@@ -22,7 +22,8 @@ def test(
|
||||
# check docker available
|
||||
capabilities = langgraph_cli.docker.check_capabilities(runner)
|
||||
# open config
|
||||
config_json = langgraph_cli.config.validate_config_file(config)
|
||||
with open(config) as f:
|
||||
config_json = langgraph_cli.config.validate_config(json.load(f))
|
||||
|
||||
set("Running...")
|
||||
args = [
|
||||
|
||||
@@ -42,6 +42,7 @@ jobs:
|
||||
with:
|
||||
python-version: ${{ matrix.python-version }}
|
||||
poetry-version: ${{ env.POETRY_VERSION }}
|
||||
working-directory: ${{ inputs.working-directory }}
|
||||
cache-key: lint-${{ inputs.working-directory }}
|
||||
|
||||
- name: Check Poetry File
|
||||
|
||||
@@ -31,6 +31,7 @@ jobs:
|
||||
with:
|
||||
python-version: ${{ matrix.python-version }}
|
||||
poetry-version: ${{ env.POETRY_VERSION }}
|
||||
working-directory: ${{ inputs.working-directory }}
|
||||
cache-key: test-${{ inputs.working-directory }}
|
||||
- name: Login to Docker Hub
|
||||
uses: docker/login-action@v3
|
||||
|
||||
@@ -60,7 +60,7 @@ jobs:
|
||||
env:
|
||||
LANGGRAPH_FF_SEND_V2: ${{ matrix.ff-send-v2 }}
|
||||
run: |
|
||||
make test_parallel
|
||||
make test
|
||||
|
||||
- name: Ensure the tests did not create any additional files
|
||||
shell: bash
|
||||
|
||||
@@ -29,6 +29,7 @@ jobs:
|
||||
with:
|
||||
python-version: ${{ env.PYTHON_VERSION }}
|
||||
poetry-version: ${{ env.POETRY_VERSION }}
|
||||
working-directory: ${{ inputs.working-directory }}
|
||||
cache-key: release
|
||||
|
||||
# We want to keep this build stage *separate* from the release stage,
|
||||
|
||||
@@ -88,8 +88,6 @@ jobs:
|
||||
--check-links-ignore "https://(api|web|docs)\.smith\.langchain\.com/.*" \
|
||||
--check-links-ignore "https://x.com/.*" \
|
||||
--check-links-ignore "https://github\.com/.*" \
|
||||
--check-links-ignore "http://localhost:8123/.*" \
|
||||
--check-links-ignore "http://localhost:2024/.*" \
|
||||
--check-links-ignore "/.*\.(ipynb|html)$" \
|
||||
--check-links-ignore "https://python\.langchain\.com/.*" \
|
||||
--check-links-ignore "https://openai\.com/.*" \
|
||||
@@ -106,8 +104,6 @@ jobs:
|
||||
echo "Running link check on HTML files matching changed notebook files..."
|
||||
poetry run pytest -v \
|
||||
--check-links-ignore "https://(api|web|docs)\.smith\.langchain\.com/.*" \
|
||||
--check-links-ignore "http://localhost:8123/.*" \
|
||||
--check-links-ignore "http://localhost:2024/.*" \
|
||||
--check-links-ignore "https://x.com/.*" \
|
||||
--check-links-ignore "https://github\.com/.*" \
|
||||
--check-links-ignore "/.*\.(ipynb|html)$" \
|
||||
|
||||
@@ -31,6 +31,7 @@ jobs:
|
||||
with:
|
||||
python-version: ${{ env.PYTHON_VERSION }}
|
||||
poetry-version: ${{ env.POETRY_VERSION }}
|
||||
working-directory: ${{ inputs.working-directory }}
|
||||
cache-key: release
|
||||
|
||||
# We want to keep this build stage *separate* from the release stage,
|
||||
@@ -168,6 +169,7 @@ jobs:
|
||||
with:
|
||||
python-version: ${{ env.PYTHON_VERSION }}
|
||||
poetry-version: ${{ env.POETRY_VERSION }}
|
||||
working-directory: ${{ inputs.working-directory }}
|
||||
|
||||
- name: Import published package
|
||||
shell: bash
|
||||
@@ -254,6 +256,7 @@ jobs:
|
||||
with:
|
||||
python-version: ${{ env.PYTHON_VERSION }}
|
||||
poetry-version: ${{ env.POETRY_VERSION }}
|
||||
working-directory: ${{ inputs.working-directory }}
|
||||
cache-key: release
|
||||
|
||||
- uses: actions/download-artifact@v4
|
||||
@@ -295,6 +298,7 @@ jobs:
|
||||
with:
|
||||
python-version: ${{ env.PYTHON_VERSION }}
|
||||
poetry-version: ${{ env.POETRY_VERSION }}
|
||||
working-directory: ${{ inputs.working-directory }}
|
||||
cache-key: release
|
||||
|
||||
- uses: actions/download-artifact@v4
|
||||
|
||||
@@ -49,7 +49,7 @@ gain understanding of concepts and how they interact by showing one way to achie
|
||||
|
||||
They should **avoid** giving
|
||||
multiple permutations of ways to achieve that goal in-depth. Choice is burdensome. Instead, they should guide a new user through a recommended path to accomplishing a concrete goal. While the end result of a tutorial does not necessarily need to
|
||||
be completely production-ready, it should be useful and practically satisfy the goal that you clearly stated in the tutorial's introduction.
|
||||
be completely production-ready, it should be useful and practically satisfy the the goal that you clearly stated in the tutorial's introduction.
|
||||
|
||||
To quote the Diataxis website:
|
||||
|
||||
|
||||
@@ -13,7 +13,7 @@ serve-clean-docs: clean-docs
|
||||
poetry run python -m mkdocs serve -c -f docs/mkdocs.yml --strict -w ./libs/langgraph
|
||||
|
||||
serve-docs: build-typedoc
|
||||
poetry run python -m mkdocs serve -f docs/mkdocs.yml -w ./libs/langgraph -w ./libs/checkpoint -w ./libs/sdk-py --dirty
|
||||
poetry run python -m mkdocs serve -f docs/mkdocs.yml -w ./libs/langgraph --dirty
|
||||
|
||||
clean-docs:
|
||||
find ./docs/docs -name "*.ipynb" -type f -delete
|
||||
|
||||
@@ -238,7 +238,7 @@ final_state["messages"][-1].content
|
||||
* [How-to Guides](https://langchain-ai.github.io/langgraph/how-tos/): Accomplish specific things within LangGraph, from streaming, to adding memory & persistence, to common design patterns (branching, subgraphs, etc.), these are the place to go if you want to copy and run a specific code snippet.
|
||||
* [Conceptual Guides](https://langchain-ai.github.io/langgraph/concepts/high_level/): In-depth explanations of the key concepts and principles behind LangGraph, such as nodes, edges, state and more.
|
||||
* [API Reference](https://langchain-ai.github.io/langgraph/reference/graphs/): Review important classes and methods, simple examples of how to use the graph and checkpointing APIs, higher-level prebuilt components and more.
|
||||
* [LangGraph Platform](https://langchain-ai.github.io/langgraph/concepts/#langgraph-platform): LangGraph Platform is a commercial solution for deploying agentic applications in production, built on the open-source LangGraph framework.
|
||||
* [Cloud (beta)](https://langchain-ai.github.io/langgraph/cloud/): With one click, deploy LangGraph applications to LangGraph Cloud.
|
||||
|
||||
## Contributing
|
||||
|
||||
|
||||
@@ -1 +0,0 @@
|
||||
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
|
||||
@@ -1 +0,0 @@
|
||||
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 truncated
|
||||
@@ -1 +0,0 @@
|
||||
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 truncated
|
||||
@@ -1 +0,0 @@
|
||||
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
|
||||
@@ -1 +1 @@
|
||||
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 truncated
|
||||
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
|
||||
@@ -1 +1 @@
|
||||
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 truncated
|
||||
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
|
||||
@@ -1 +1 @@
|
||||
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 truncated
|
||||
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
|
||||
@@ -1 +0,0 @@
|
||||
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 truncated
|
||||
@@ -1 +0,0 @@
|
||||
eNqNVXtcE1cWlqWtSl3LVn9dXXEdIgICkwfvZOsDIiJQHguIGnk4mdwkI5OZODNJoZQtAkVXtHZQaquIAiFoVB4FgVasski3FqWsu3aXan3UWtTqSqXqQgV6E4LKSrX5JzP3fud83z3nO3dyq4yAYQmacjhIUBxgMJyDLyyfW8WAdQbAcvlmHeC0tMoUF5uQWGFgiO55Wo7TszKRCNMTQozitAytJ3AhTutERolIB1gW0wDWpKRVmV85nM8S6LCMNI5OBxQrkCESsa+/DyIYRcGV1VkChiYBfBIYWMAI4C5OQykUZ10ikNcxisIQDY2wtA68rgUMgEuMDiEohNMCBMcYQqkEGCXITrEmplWAtAbiJGZQAdQPDUBZmqIAh5IYB89jzc9mshzQWVGraAOCwYyQAFDw9CTCMZgRkAjI0AOGgwwYBykohAHwfDpAqUYBKpiLoDBbtRBPINQIEZw2UBxDANYHwQnO9g84fL4QiVAjmZCIAkCFaGkORj9MN5LAB8HYdMTDtpeGqYwESzMeiJpmEC0g9UKrZo6mSXu5KExnKxdUQrFqwMDqpo0JteKhPpwh9Nb0VmwIzD9CbceMzU5QegOXxuJaoMMgPEugh02FBSBsLcrKtgrI1NtYaeVagHOC7OyU7CotwFTQPhcmOJu0NMvxdU9YogbDcaDnUEDhtIqgNPwhzRuE3geWT23thwW39sbmOd6SDoAexUjCCMwjUXwtpteTBG4rkmgt7ONBuzVQq5onty1WB6HQWBTHN4WM6hDFZUIHU4hY6CcVimszUJbDCIqEFoSegJLMetv+kcc39BieDvOg9ungzSPB1Y9jaJavjMbw2IQxKTEG1/KV0KGB/vWPrzPQHIQO8FXyuCfp7JuP6PyEEolQWjcmMZtJ4XylGiNZUPewyA9DLL5iXz9UHIiKJU1jUgOOyURt3uTLxNWjBSQBpeG0fIV/UOA+BrB66EKQZ4ZhnIHNNcFmgVOfVdnHtDw26lGrf29aAhvHH000AB9EEoQsATgCqf0RXz+Z2FcmCUDCoxMPyu00ieP2qS7Rbl00bNQXVbjWQKUDlUU+riO6BY9OzEB+ktARHGq/o2Afra+8yV8sFne7PxXJQIcTlJXR5CeVSp+RF1YGcHyD9XyoxBeVBCWOnFIcrBifxzZI6Mh1Z1dltqqCuryeiX+kbTTG/VfEjK9QEqDo9hgvmjZwT0isDLaxeT8b/0iiPcbj18T8skRkvPD/K98IkdtTkI8XbgSNPBX9i3os9s6jhIpvgc9pYkkkCFcsiVwR5ifBl+sjqdAYX41B6V9hJDDeIhFK4JeJ1pCgRr4UlWPw/kQTbCPEVy1ZFRMSHSE/uBKNp5U09FIiBj1H0RQwJwAGTi1vwUnaoIL3IAPMMDw+ZBXfEKz2w4IxsQTHlMogXI2hYSvia0eH6eGwmKyXqO0Lux6OLAOX2h3L5xROmmD7OXLLW6lZQc6DxfNFMTnFa7xjtt2I/xd1pjnMpWLyJXnKpPpvbwq9hR9dnnI4actQwieuaUnvenu/XFTSoOh8tTOLVt8LWVXxnqXHaHjDOHhlUdPwO4MDn1y/SH48dPbWrejhoaOW7eTEz/98YjO6P7L90p0XVY0+18KWW14qKFF43RLP3Llg14I963pLVY3BKSV7dgtfscTLMlxFa/v/3TZ3X1d2jGhRlMGg3Ot+TT+jEXGQMY6kPLe1bGJ+1ObG6skLGtyCv7k38X9d/2hN7xDHkcte9Hf928a6DXycbFNtyBZlXo+0pWxZDp8jj118f2fJXNGaje0D870u1uRp0j2Ftx/sXrSrraas6cLaH3s9frvfmHSxf+aDy23XOrIDsJfPue3Yw4VP6ayeTBXtSG75u8tQNeHpu5f1+/5wFBn0HB+85LLT0umbjrf9+NLR9VrDRJk0gmeGaD5u79INqdPyv/uh2imu8OuVdQ0d5/dGzbsa+H3tvM31M4qCxIrri/fN8VQWgHdvrQmQNb29U+V2p/eb/ptX+77Yk9q2rb2f/OGfPbE7YuudCqUP3lmgSGlu+XShm/D8IXFwgzqpItUxck7GtU2dHzgeRs+4FhbWmD5cuDr3T6cvfJdKOCZfakSSE2Yd6vig5p4xwPV9p4ETSbH5Hm9yi+87hkWlTrvdHzXl7blaTdb0gQKn4JN9d7jYwXaHuxq2+fjULJ/3d6zriO+adEU1a4dgZdH9L5u2nmB6T4ck3NH+dGGg8Tf3XKtPFveUSDOH29tL+gOldXlza2927TrzHreo2Xl/rnvBH2+cWN28VP1afy/+oVuvcHJy9MzK/5z/rGTD7Qx3Y/6xK3f7XRaamku1KeVn12/96WhbtLvC7OmPzG6dUe7nMSWgzsVLf03xHB6l5NNFoWWzBCF/WFmxS1bVdbL4v7NuFJaFf6nzVO4KOXblgm5Z53YQP3CgquL5K5JPxbknT5nmuk9qa3hhrcrX+c2pHXkRXwUm5d0N5VfOKJ3eQk/Fdr8WFe/w19JFgzP/ss7Fqza6QCZJmJ11XDhJutEkv7gt6Mi87e2hx77e38E1lHs157ZsdivvKVBiAgembJrLzi1XnT1OR3TJfHNkF39n9s5JOKc+1TLj7Ftvrdg0b8qBVze2HqgU0ElF5SuOOJq3zv+iWDHwbXJlfL+7z5ztd+VFxfkBmUkdffX1kdd9Tkb2ZIO8tNnhJQtLw0P77nYPfy5CQ16RBEoOHHoeDuPwsOOEcxF9lpoXJkz4Gdjtv6Q=
|
||||
@@ -1 +0,0 @@
|
||||
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 truncated
|
||||
@@ -1 +0,0 @@
|
||||
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
|
||||
@@ -1 +0,0 @@
|
||||
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
|
||||
@@ -0,0 +1 @@
|
||||
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
|
||||
@@ -1 +0,0 @@
|
||||
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
|
||||
@@ -0,0 +1 @@
|
||||
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
|
||||
@@ -1 +0,0 @@
|
||||
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
|
||||
@@ -1 +0,0 @@
|
||||
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
|
||||
@@ -1 +1 @@
|
||||
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
|
||||
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
|
||||
@@ -1 +1 @@
|
||||
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
|
||||
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
|
||||
@@ -1 +1 @@
|
||||
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
|
||||
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
|
||||
@@ -0,0 +1 @@
|
||||
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 truncated
|
||||
@@ -1 +1 @@
|
||||
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
|
||||
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
|
||||
@@ -1 +0,0 @@
|
||||
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
|
||||
@@ -1 +1 @@
|
||||
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
|
||||
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
|
||||
@@ -0,0 +1 @@
|
||||
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
|
||||
@@ -1 +1 @@
|
||||
eNqNVWtsFFUUbkWNPARSmyBRcRyFRunszuxul26L0nYLSklt2a4WWpt6O3O3O+3snWHu3aUPaqQSEy1IJxKNhQSl211YSh+xiUQ0aIjEGIzwB1NMKqmGoAExEiTKj/XOPtpiX+yfvTPnO+d853zn3OmMhqCOZRVl9suIQB2IhD5gozOqwx1BiMmeSAASvyqFKyuqvL1BXR5d7SdEwwVWK9BkC0DEr6uaLFpENWANCdYAxBg0QhxuUKXWS5nr2tkAaKknajNEmC1gBN7myGXYNIq+qW1ndVWB9MQGMdRZahVVSgUR89VOPyA5mCF+yOyEgP7pjIwY7NvAdtSZcVQJKiZOVEBQgpydy+OwihAknAIIpW+GI6qqpDIhEEhkSsWqxxDoot8ESRCLuqyZ1ZuAqoSB8an61NwmUEZakNRj0Q8DgCLbWY3WD3UiJ6ppZ0WZtCYOpFVL5MJEl1Ej29FBnc2myjqUTDZJpFlFGqk2NEGRUGRdR9QPgUSV2R/2q5gYw9N6PQhEEWqEg0hUJRrfONHYJmu5jAR9ZuUx0exCQkwj1gyhxgFFDsFI0ssYApqmyCIw7dYm2rH+VM85k8t0c8yUhqOKIWJ8VpzmYa1spaOBGN5id1hsQy0cJkBGCtWWdp9SimgJ+6mpBg2IzTQOlxo7I5J0HpiKUbHRVw7Eiqq7QpqCGH1ADzgdn059rwcRkQPQiLorp6dLGSfT2S2CYHEN3xUYtyLR6PMBBcPhiSZPuMRsvM3O8U6OFwbSXVIgaiR+o9cuCEd1iDW6MvCtCA1JgrgzTBWB576Npob8SMWWtJpjGSvCpVQd48tqKOUygsCUQpGh8R2MkF/A8wWCnXmx3NvvTqXxzijGsFcHCPuoIBvT4kdFfxA1QynmnlH2UXayLJ3mV+SATLjUhlOxzEcj7OB5fnTNnEidDr2MzIxhu8vlmicu7QwkxohZHyfYOEHwpqoUambOk9gtLnlZpFhFTFaU13Pz4ie5pX3W3IPPLAztNaM5M3mrQTKNYl9+Itva+fGTFFM+OffiMztFZib3/7UvmeiZOZBTG5dEM3OiZ+UTSynPyZLxBT3X88JWZ1mz0+aR2lBbiTvf0xTSBM9Wf29IBkZMsAhMo6o2KnDQvYlzA3qlclWJFTKipdtfLi7f7O7fxnnUBpXOkhfQmUMqgpEqqNPVNGKiogYletnpMELdPcXbjZF8H78uz+cUgYvP431OB7ex2jOUXqaJZQmbN2Xi+7Q7krycv8nknux6KCPxW+DtLt9ypmj52/HvbCusj232/DS+6vire8ZXv76YBadWHjz/Per5qO9sd9zyTtktx7nCmy/cvOB+5c3OnqWth3JvrHqXnF4YDew7fPv4wLHYNfhw1slm7VoJ21HUfb6tcFHPUfbie8Ul1xePfPzVticW7fVdWM/eeFw/cPa38qzosy/xY0LBg7cuxUtWbth0Jzt7fd32tWUj+67uWh4pxdmvHcnvvZJVu9VlyDkXT4Qi7C+DoHvFgdvOZQ5Lfl3elaf2vx/8MfzA4Q/337nuG15bDf8+tLqw+zJ5/t83Lrs+QeWuz+seedS7LDK+NPt84ZIzB+9v+PlXrumvP+InjxW1LLq6pFP/umYhaPvg99M7XHeeLrgvr3as7M/d8aauf/hdmRkZ8fiCjNAPy1Z10fN/12s1SQ==
|
||||
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
|
||||
@@ -1 +1 @@
|
||||
eNqNVt1vFFUUL5AYjSaCSjTGxGGgbYKd3Zl2u3RrGty0RUFKobsCbQOb25k7O5fO3jude2fpWvpQRB80gmPUKDExge0ubgptFQUiJpDIxwNEVBSKHyQ8kPgHiAmJ4J3Z3X7z0Zfu3nPO7/zO+Z1zsrvzaWhTRPCCEYQZtIHK+Bfq7s7bsM+BlO3JpSAziJbd2B6LH3RsNFFpMGbRxmAQWCgAMDNsYiE1oJJUMK0EU5BSkIQ020O0zLWFIwNiCvQnGOmFmIqNgiLXhmoEsezFX7oHRJuYkH8SHQptkVtVwqlg5j3tNACrpgIzoLATAv7PFhAWqL5aHKwRpiIBpYgyTmZmOMdmsN8HWlttmoIBTUvIEEdQDaj2zkaNASyssQFWEVVJwENiGcuH90H8hJMvhJgJztfzwiDlv5WgEhQCWzU8C8KW42UfEFXEMp4P1T0cEWllECchK+GOaESFfTrKRCJbk0ZEfw2v6+8SB7fNqHFud7pn8bEhdcxZLRBjDsaZZX41Jc6Jh8rusaQJaNvE5t46MCnkhLZ54hENmh6CagJHg1KdVC9RgjFkkgkYn5lyspK89+6PBqlqI8sbOZ+qbxB0Yk+XZrKRCcplSwG/nxYfOmgz5I/QZHun+kGZjXBSHPSa7U0ysqFXdHfRc9s0bUnPDqhydXlxeQMCja/DvqxBKHPH5wz4KFBVaDEJYpVoHN89nHwTWTWCBnWv8oLqdcHfILfQC6ElAROlYa4Y5Y4ByzKRCjx7cAfv2EhJJsnjMtdc8BSX+Jpg5h6LlnkEN2b4PmJBDtSFArVj/RKfe4RNvlC8+5xSzvLt3003WEDt5ThSadfdXDH4yHQfQt3hNqC2x2ZAeoK4w8BOhUNfT3+3HcxQCrr55o1z05WMU+nqAooSiIzPAKYZrLrD/lyNTzZ5MqRQK9fWSXJYkpUj5S6ZECeZ4R4MN4QO8VG3+J2Cb+U4JHPo7ixXBF44ny9dlgPtr5fV/Kvi2WwLV8f9fgvUagRFEVqgKnD8kKA0NMpyoyILr7bFR5pLaeLzijEe55eB6lyQ1rL4edVwcC/UCs3zyj4hTpVl8/wmSiEmlc4qF8v76mZDsixPVN3X0+ZDj7CXMVsXiUQegMs7A5l71KtPUmolRYkXq5QjXfPn8XdLKl7oEqucx4rzWvlA/ylu5Ziqh4iZn6Eid01UzxdNHDaH4nCDn+2lB/tPUSzFVD9MzL0pCvOFz2pfMdGK+3hOb1zRW7iv9z35FErKS0hzT/LP/KJvskOd0VV96zo6N7e2bGjr60LpekM/mEbALSgBRUgSkjThaPMaqRnwkyrF/BVy8y2dG6Jta5tHtkodpIfwWYoDPnOYYJiLQZuvpltQTeJo/NjZMMfDO6Kd7tEGXV5Vr4frG2CoTtbDIal1S8dYeZkmlyXrXUr/R8FQrnicf7j54nuPVvh/i9bvvbhjzyuL9yTOXIbB5Yc6l9z85IWFYOKX7QuXnZfDehjvu9a0eMn1puMrPoid3rL68ruXTt+oGuz+KOl+mW6/8mPsbtXFyrdvn/hsg3wJZptaxSPVz13ouzr09GMH9i595NjVnyoeX3388qY7n1450aL/fHJlQe2ML31il1a5+eq//5D43wOj18/ceOPJD9f2bP/q1MSZvlu1L9+K7roQSuPMqVtAeP5cuqraBdE/vtmvnx1dFqrsaR/7/J3Twp+J35cOncsePhvsGWr67f3o+ttffPzrt//xgu7eXVQxsvzOU88sqKj4H6D2kjg=
|
||||
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
|
||||
@@ -1 +0,0 @@
|
||||
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 truncated
|
||||
@@ -1 +0,0 @@
|
||||
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 truncated
|
||||
@@ -1 +0,0 @@
|
||||
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 truncated
|
||||
@@ -1 +0,0 @@
|
||||
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 truncated
|
||||
@@ -1 +0,0 @@
|
||||
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 truncated
|
||||
@@ -1 +0,0 @@
|
||||
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 truncated
|
||||
@@ -1 +0,0 @@
|
||||
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 truncated
|
||||
@@ -0,0 +1 @@
|
||||
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 truncated
|
||||
@@ -1 +1 @@
|
||||
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
|
||||
eNrtVwt0FNUZDsRXFAsVsUAPMm4tD8lsZnZ2s7uJgMkmm8QQkuzmLWGdnbm7O9l57TySbGIoEtRTqMAgRqxaWxI2ECA8TYFAMLWpFT3aQEBjRLQ+kIoPQO3xaE3vbDYYBC09R0+Pp8w5Ozv3/v/9n9/97/2XtFYDSWYEftRmhleARFIKHMirl7RKIKQCWVka4YASEOiWgnx3UbMqMf23BRRFlFOSkkiRMQoi4EnGSAlcUjWeRAVIJQl+iyyIimnxCnT41fhV9QYOyDLpB7IhBbmr3kAJUBevwIGhWAaIEgCIDEiJCiCKILDwhZByMDqtykBCagJAinKFEVICifoXj7CCEERUMcpVA0j4J+nfEjAkIgZJYIEuXV9uaEhERqrkVZYdwULKMiMrJCTBSV29hyJZNmaoEhajTD6VjwZG52FofUZn8oi13hKayy7Kwuc702wugVcdbJioM+ls55akQO08yUXlpMnBbJUjo3JIya9y0CRdlaF+gSEabrhgARwvMJRGfYbuImFBhc5SpALouQsMDYaGhspveGSQSR7xSSRPMTIljPRf9+c8vzyXYn1DJVzCCTRgdV6/qKDmqFTdFxz+y4oESA4OfCQrA1084ESIHUWVdK2Y0RpT+R1RvGh4hkCgk2kgUxIjxjgMDmivDgtZlXyxjHuNOp9ISnAtBK4cFSRKEJCSwoChIQypFI5+DZsATWd4P4yhHiSIcEYCekDuirHqjg+zCt4qQCmQNRrtS/ZhZIq/4UVaDNQBnY6QyHDGL8kR+ZymS/FliPvi7lQ2tAYASUNVr8eNawkIsqK1n7+Xt5IUBWDaAU8JNNShbfHXMWIiQgMfC3HYBqHHg6jrWlsQABElWaYaRIZWadtIUWQZCFhIT6qSBX5zDKqobsuF5DZ9l6KwOvCKtisfGpGWk1QQhkWHR3Cj2WbEttWicIcyPAuLCMqS0J6IGKV3jiSIJBWEQtBYQdMiQ4vbR/IIsrY+j6Ty3eeJ1EGnrSclLtm8c+S8pPIKwwGt1VFwoboY8Wt1hBHHjfbt5wmWwzylrY9ukz+etxgoUhilBChD+wMWoWAtY4DWf8bjoXweLzfbrJL+UpWvshe6M2pLeMLmszEhTmayy102a14wK905PznXY3IV1daguNVkJSxWq92E4kbMiBtxFGDBEoEBvmxTmSufZAh3IJQlODP4nAoTDjhnRu68Uh4LZkg4Ueahidz0kjRrWoXDL3JFSjlTnlboDAeEQjcj5XkKatMr6mxZHgqU16Qi0Dq1mqFn52R6sr18rSVD4EJBW6iMKAsVhIu9mLkYo6stmVk+xlLGloous888wjxbMo5iMQuTMbMN05/2YWywgPcrAa3Zjps2SEAW4fEBGiMwZIoqL2mBOAQv/LU1doysy8/9GsITWjIgJrX9RQE1ETElI24gIibMZEZwIoVITiEIJCuvaLMjpqboohDcXgSrp+yDMMwchnwrFVD5IKDbHBcF+34d7DCTuvmw2qKgVhRkgMas0jaXoa6hAxTNydg5tLNQQfKTPFMXVatt1IEMD0yG3xUjwz2vi4TKUU7Wms12oj1GGcZYG/QLQ3EMxfA9+u6n4JbSDRcFSUFlQMHjWQlr/YkcWavvp9kEbiGSYZBTEYanWJUGbtULcwZ1yqmIKAFWIOm9tSis3IBlOAYmIfqOHf1wr+B6inZfyKEIQcDL2gYCG3q6RrJIQNegu3FOUIsdPvsuzjQsy6Tz2C3WveezyWCEQc3JnLz7QnpMxDpM3lw7zIwytNZ/Kxx4bJSJxCw2HBA+ykwSZquZtFhImiTsFpuNtpNbHU7UQVIBgLqjaNNaM8rnp+XlODrK0JGwQfOjlRzSeUHmGZ8v4gYSTI3WRrGCSsPSKIEIlOVKK9d22Sg7QZq9NOU1YWaTjUAzS13bhqWdA1mLXlejt6R7I0PlvGfUi1OXXxMXfeLhb3BQcXVLj2Hj9p+dkFqfPGXbQwVyrskhZY/Nc58o8E8sX3jHr1dtuLXCvXJwf/xf7rg94eoHfVM/+uDwwLH6uBkdE+PPLLEvLDl0oOunnUcOHHG4507ol6X6WTMqpj3/bIG/dG7oqOmTdx/enbq9S6wsWf343/5xjex4oXDTZOfZQGhS5vOZV6+py92x/p2Hzybtmjv23Z8tEk8+sPx3ZYHu57xjDtwet7ihpuOmI03VEx1YavGdO5reWXr64/Fxk9GBa03B+9R59scfRF4+qFVVbqo4mPDGrqaZfteKB1ceXyRNlb2uiBCpbegqfO7YYTV0oH7eV/cMRt4+0vboJ6l3Wov9MzZNmHrm0Tccs+cEr1q87OEpL99A7LNRoxEiXLla2hJ8bevpmrxIObXPufDnjoPdHm87Ep/ePTaC4PNC5J6Fb406vnHKvpUfJj30mzHgKbBj7NatU+9nsp8odQqnynevTfglq032dtS/bQ5+1Lfl/cZPO0NeoJTv6TtpdW1hJ36289nQwLRAX+P81GnTPw1/MmnWsdXUusc+3+bLejL9neZ07JVTC5d3bF9x0Dz+tunuSb3ojb7iyVd5Gnvu/xPb+Hr3F2P1pMXH7X/maa4cZvD7vElfmXn5Jv3jukn/YAELSoGq0nTemVWUFsiudTmrC/N4NrkkfAl364uESwoPxQqeIBKknIMBwyNuGBHncES+JWo5UQwBGqIoBflPMoyIC8gqq6QgOcp0GV7peT58AVMi4lWVaMLg1oS34iGQCnCO8enT0/WUIlmAg2cIskClbQQN3wCzGS85ad8awcvtz+X253L7c7n9+V+0Py04YbZ/v/2P+Ufa/xBW/P+w/zHh33//QwO7zUsAAmA+3Ou14Mk2s4U2+4Dd6zUBn/0H7H8oHJAm4r/rf5Z9s//R8vgBbNx9/0zpWROctWpw3dHOiWL1B9O4cciMK357c868Dbd0T7olFH/89/7s9rW/uGLNlIFK5ZmeL96dvW9SFx13kO8bvYZ5aq1x95dVzJPCI6W/6jreu7JzkTqwuYk7pU468WZpQfPbH79/tfnMyb1Y13U/6al7lRpfeF2kL2Sf2Xp2x5fJU+44YX1v9ZaE1S/dM2fmtJ371p5462T3K3XBVUdGf0jELX7kzbwJTONLVaN63nOfXFVu3XDTs7fETdifu+zQC02ZD23oTZicv8S866t+w9o5zlvvnd53yHtFrtic0N48jeqv3TbmtfFc0t2ZYxddd8h7w+6nlnre+NcHH70frvvzXv8TTc2v72nsSj2qdiX0bv386ZV13HPSXZl9p2YWU6fTrlceGfXlzS8eGty58dremrTbTq/MnineYx84sfFw1uOH429MevWJk57lg3varl/WseKlFZs+ux61tC79e5n8ivt005WdbR19d4/p/VCofKBqTi+YPetoTwXoPBU/1Lscu6/nSWV0XNy/AYBmICg=
|
||||
@@ -1 +1 @@
|
||||
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
|
||||
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
|
||||
@@ -0,0 +1 @@
|
||||
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 truncated
|
||||
|
Before Width: | Height: | Size: 736 KiB |
|
Before Width: | Height: | Size: 72 KiB |
|
Before Width: | Height: | Size: 304 KiB |
|
Before Width: | Height: | Size: 265 KiB |
|
Before Width: | Height: | Size: 376 KiB |
|
Before Width: | Height: | Size: 400 KiB |
|
Before Width: | Height: | Size: 461 KiB |
|
Before Width: | Height: | Size: 642 KiB |
@@ -1,123 +0,0 @@
|
||||
# How to add semantic search to your LangGraph deployment
|
||||
|
||||
This guide explains how to add semantic search to your LangGraph deployment's cross-thread [store](../../concepts/persistence.md#memory-store), so that your agent can search for memories and other documents by semantic similarity.
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- A LangGraph deployment (see [how to deploy](setup_pyproject.md))
|
||||
- API keys for your embedding provider (in this case, OpenAI)
|
||||
- `langchain >= 0.3.8` (if you specify using the string format below)
|
||||
|
||||
## Steps
|
||||
|
||||
1. Update your `langgraph.json` configuration file to include the store configuration:
|
||||
|
||||
```json
|
||||
{
|
||||
...
|
||||
"store": {
|
||||
"index": {
|
||||
"embed": "openai:text-embeddings-3-small",
|
||||
"dims": 1536,
|
||||
"fields": ["$"]
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
This configuration:
|
||||
|
||||
- Uses OpenAI's text-embeddings-3-small model for generating embeddings
|
||||
- Sets the embedding dimension to 1536 (matching the model's output)
|
||||
- Indexes all fields in your stored data (`["$"]` means index everything, or specify specific fields like `["text", "metadata.title"]`)
|
||||
|
||||
2. To use the string embedding format above, make sure your dependencies include `langchain >= 0.3.8`:
|
||||
|
||||
```toml
|
||||
# In pyproject.toml
|
||||
[project]
|
||||
dependencies = [
|
||||
"langchain>=0.3.8"
|
||||
]
|
||||
```
|
||||
|
||||
Or if using requirements.txt:
|
||||
|
||||
```
|
||||
langchain>=0.3.8
|
||||
```
|
||||
|
||||
## Usage
|
||||
|
||||
Once configured, you can use semantic search in your LangGraph nodes. The store requires a namespace tuple to organize memories:
|
||||
|
||||
```python
|
||||
def search_memory(state: State, *, store: BaseStore):
|
||||
# Search the store using semantic similarity
|
||||
# The namespace tuple helps organize different types of memories
|
||||
# e.g., ("user_facts", "preferences") or ("conversation", "summaries")
|
||||
results = store.search(
|
||||
namespace=("memory", "facts"), # Organize memories by type
|
||||
query="your search query",
|
||||
limit=3 # number of results to return
|
||||
)
|
||||
return results
|
||||
```
|
||||
|
||||
## Custom Embeddings
|
||||
|
||||
If you want to use custom embeddings, you can pass a path to a custom embedding function:
|
||||
|
||||
```json
|
||||
{
|
||||
...
|
||||
"store": {
|
||||
"index": {
|
||||
"embed": "path/to/embedding_function.py:embed",
|
||||
"dims": 1536,
|
||||
"fields": ["$"]
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
The deployment will look for the function in the specified path. The function must be async and accept a list of strings:
|
||||
|
||||
```python
|
||||
# path/to/embedding_function.py
|
||||
from openai import AsyncOpenAI
|
||||
|
||||
client = AsyncOpenAI()
|
||||
|
||||
async def aembed_texts(texts: list[str]) -> list[list[float]]:
|
||||
"""Custom embedding function that must:
|
||||
1. Be async
|
||||
2. Accept a list of strings
|
||||
3. Return a list of float arrays (embeddings)
|
||||
"""
|
||||
response = await client.embeddings.create(
|
||||
model="text-embedding-3-small",
|
||||
input=texts
|
||||
)
|
||||
return [e.embedding for e in response.data]
|
||||
```
|
||||
|
||||
## Querying via the API
|
||||
|
||||
You can also query the store using the LangGraph SDK. Since the SDK uses async operations:
|
||||
|
||||
```python
|
||||
from langgraph_sdk import get_client
|
||||
|
||||
async def search_store():
|
||||
client = get_client()
|
||||
results = await client.store.search_items(
|
||||
("memory", "facts"),
|
||||
query="your search query",
|
||||
limit=3 # number of results to return
|
||||
)
|
||||
return results
|
||||
|
||||
# Use in an async context
|
||||
results = await search_store()
|
||||
```
|
||||
@@ -36,8 +36,8 @@ Dependencies can optionally be specified in one of the following files: `pyproje
|
||||
The dependencies below will be included in the image, you can also use them in your code, as long as with a compatible version range:
|
||||
|
||||
```
|
||||
langgraph>=0.2.56,<0.3.0
|
||||
langgraph-checkpoint>=2.0.5,<3.0
|
||||
langgraph>=0.2.30,<0.3.0
|
||||
langgraph-checkpoint>=1.0.14
|
||||
langchain-core>=0.2.38,<0.4.0
|
||||
langsmith>=0.1.63
|
||||
orjson>=3.9.7
|
||||
|
||||
@@ -36,8 +36,8 @@ Dependencies can optionally be specified in one of the following files: `pyproje
|
||||
The dependencies below will be included in the image, you can also use them in your code, as long as with a compatible version range:
|
||||
|
||||
```
|
||||
langgraph>=0.2.56,<0.3.0
|
||||
langgraph-checkpoint>=2.0.5,<3.0
|
||||
langgraph>=0.2.30,<0.3.0
|
||||
langgraph-checkpoint>=1.0.14
|
||||
langchain-core>=0.2.38,<0.4.0
|
||||
langsmith>=0.1.63
|
||||
orjson>=3.9.7
|
||||
|
||||
@@ -83,7 +83,7 @@ We can now call `.get_schemas` to get schemas associated with this graph:
|
||||
assistant_id=assistant["assistant_id"]
|
||||
)
|
||||
# There are multiple types of schemas
|
||||
# We can get the `config_schema` to look at the configurable parameters
|
||||
# We can get the `config_schema` to look at the the configurable parameters
|
||||
print(schemas["config_schema"])
|
||||
```
|
||||
|
||||
@@ -94,7 +94,7 @@ We can now call `.get_schemas` to get schemas associated with this graph:
|
||||
assistant["assistant_id"]
|
||||
);
|
||||
// There are multiple types of schemas
|
||||
// We can get the `config_schema` to look at the configurable parameters
|
||||
// We can get the `config_schema` to look at the the configurable parameters
|
||||
console.log(schemas.config_schema);
|
||||
```
|
||||
|
||||
|
||||
@@ -1,17 +0,0 @@
|
||||
# Adding nodes as dataset examples in Studio
|
||||
|
||||
In LangGraph Studio you can create dataset examples from the thread history in the right-hand pane. This can be especially useful when you want to evaluate intermediate steps of the agent.
|
||||
|
||||
1. Click on the `Add to Dataset` button to enter the dataset mode.
|
||||
1. Select nodes which you want to add to dataset.
|
||||
1. Select the target dataset to create the example in.
|
||||
|
||||
You can edit the example payload before sending it to the dataset, which is useful if you need to make changes to conform the example to the dataset schema.
|
||||
|
||||
Finally, you can customise the target dataset by clicking on the `Settings` button.
|
||||
|
||||
See [Evaluating intermediate steps](https://docs.smith.langchain.com/evaluation/how_to_guides/langgraph#evaluating-intermediate-steps) for more details on how to evaluate intermediate steps.
|
||||
|
||||
<video controls allowfullscreen="true" poster="../img/studio_datasets.jpg">
|
||||
<source src="https://langgraph-docs-assets.pages.dev/studio_datasets.mp4" type="video/mp4">
|
||||
</video>
|
||||
|
Before Width: | Height: | Size: 170 KiB |
@@ -83,7 +83,7 @@ Now, let's import our required packages and instantiate our client, assistant, a
|
||||
|
||||
## Create runs
|
||||
|
||||
Now we can start our two runs and join the second one until it has completed:
|
||||
Now we can start our two runs and join the second on euntil it has completed:
|
||||
|
||||
=== "Python"
|
||||
|
||||
|
||||
@@ -1,273 +1,462 @@
|
||||
# Quickstart: Deploy on LangGraph Cloud
|
||||
# LangGraph Cloud Quick Start
|
||||
|
||||
!!! note "Prerequisites"
|
||||
In this tutorial you will build and deploy a simple chatbot agent that can look things up on the internet. You will be using [LangGraph Cloud](../concepts/langgraph_cloud.md), [LangGraph Studio](../concepts/langgraph_studio.md) to visualize and test it out, and [LangGraph SDK](./reference/sdk/python_sdk_ref.md) to interact with the deployed agent.
|
||||
|
||||
Before you begin, ensure you have the following:
|
||||
If you want to learn how to build an agent like this from scratch, take a look at the [LangGraph Quick Start tutorial](../tutorials/introduction.ipynb).
|
||||
|
||||
- [GitHub account](https://github.com/)
|
||||
- [LangSmith account](https://smith.langchain.com/)
|
||||
## Set up requirements
|
||||
|
||||
## Create a repository on GitHub
|
||||
This tutorial will use:
|
||||
|
||||
To deploy a LangGraph application to **LangGraph Cloud**, your application code must reside in a GitHub repository. Both public and private repositories are supported.
|
||||
- Anthropic for the LLM - sign up and get an API key [here](https://console.anthropic.com/)
|
||||
- Tavily for the search engine - sign up and get an API key [here](https://app.tavily.com/)
|
||||
- LangSmith for hosting - sign up and get an API key [here](https://smith.langchain.com/)
|
||||
|
||||
You can deploy any [LangGraph Application](../concepts/application_structure.md) to LangGraph Cloud.
|
||||
## Create and configure your app
|
||||
|
||||
For this guide, we'll use the pre-built Python [**ReAct Agent**](https://github.com/langchain-ai/react-agent) template.
|
||||
First, let's set create all of the necessary files for our LangGraph application.
|
||||
|
||||
??? note "Get Required API Keys for the ReAct Agent template"
|
||||
1. __Create application directory and files__
|
||||
|
||||
This **ReAct Agent** application requires an API key from [Anthropic](https://console.anthropic.com/) and [Tavily](https://app.tavily.com/). You can get these API keys by signing up on their respective websites.
|
||||
Create a new application `my-app` with the following file structure:
|
||||
|
||||
**Alternative**: If you'd prefer a scaffold application that doesn't require API keys, use the [**New LangGraph Project**](https://github.com/langchain-ai/new-langgraph-project) template instead of the **ReAct Agent** template.
|
||||
```shell
|
||||
mkdir my-app
|
||||
```
|
||||
|
||||
=== "Python"
|
||||
|
||||
my-app/
|
||||
|-- agent.py # code for your LangGraph agent
|
||||
|-- requirements.txt # Python packages required for your graph
|
||||
|-- langgraph.json # configuration file for LangGraph
|
||||
|-- .env # environment files with API keys
|
||||
|
||||
=== "Javascript"
|
||||
|
||||
my-app/
|
||||
|-- agent.ts # code for your LangGraph agent
|
||||
|-- package.json # Javascript packages required for your graph
|
||||
|-- langgraph.json # configuration file for LangGraph
|
||||
|-- .env # environment files with API keys
|
||||
|
||||
|
||||
1. Go to the [ReAct Agent](https://github.com/langchain-ai/react-agent) repository.
|
||||
2. Fork the repository to your GitHub account by clicking the `Fork` button in the top right corner.
|
||||
1. __Define your graph__
|
||||
|
||||
=== "Python"
|
||||
The `agent.py` file should contain code with your graph.
|
||||
|
||||
=== "Javascript"
|
||||
The `agent.ts` file should contain code with your graph.
|
||||
|
||||
The following code example is a simple chatbot agent (similar to the one in the [previous tutorial](../tutorials/introduction.ipynb)). Specifically, it uses [create_react_agent][langgraph.prebuilt.chat_agent_executor.create_react_agent], a prebuilt [ReAct](../concepts/agentic_concepts.md#react-implementation)-style agent.
|
||||
|
||||
The `agent` file needs to have a variable with a [CompiledGraph][langgraph.graph.graph.CompiledGraph] (in this case the `graph` variable).
|
||||
|
||||
=== "Python"
|
||||
|
||||
```python
|
||||
# agent.py
|
||||
from langchain_anthropic import ChatAnthropic
|
||||
from langchain_community.tools.tavily_search import TavilySearchResults
|
||||
from langgraph.prebuilt import create_react_agent
|
||||
|
||||
model = ChatAnthropic(model="claude-3-5-sonnet-20240620")
|
||||
|
||||
tools = [TavilySearchResults(max_results=2)]
|
||||
|
||||
# compiled graph
|
||||
graph = create_react_agent(model, tools)
|
||||
```
|
||||
|
||||
=== "Javascript"
|
||||
|
||||
```ts
|
||||
// agent.ts
|
||||
import { ChatAnthropic } from "@langchain/anthropic";
|
||||
import { TavilySearchResults } from "@langchain/community/tools/tavily_search";
|
||||
import { createReactAgent } from "@langchain/langgraph/prebuilt";
|
||||
|
||||
const model = new ChatAnthropic({
|
||||
model: "claude-3-5-sonnet-20240620",
|
||||
});
|
||||
|
||||
const tools = [
|
||||
new TavilySearchResults({ maxResults: 3, }),
|
||||
];
|
||||
|
||||
// compiled graph
|
||||
export const graph = createReactAgent({ llm: model, tools });
|
||||
```
|
||||
|
||||
1. __Specify dependencies__
|
||||
|
||||
=== "Python"
|
||||
You should add dependencies for your graph(s) to `requirements.txt`.
|
||||
|
||||
=== "Javascript"
|
||||
You should add dependencies for your graph(s) to `package.json`.
|
||||
|
||||
In this case we only require four packages for our graph to run:
|
||||
|
||||
=== "Python"
|
||||
|
||||
```python
|
||||
langgraph
|
||||
langchain_anthropic
|
||||
tavily-python
|
||||
langchain_community
|
||||
```
|
||||
|
||||
=== "Javascript"
|
||||
|
||||
```js
|
||||
{
|
||||
"name": "my-app",
|
||||
"packageManager": "yarn@1.22.22",
|
||||
"dependencies": {
|
||||
"@langchain/community": "^0.3.11",
|
||||
"@langchain/core": "^0.3.16",
|
||||
"@langchain/langgraph": "0.2.18",
|
||||
"@langchain/anthropic": "^0.3.7"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
1. __Create LangGraph configuration file__
|
||||
|
||||
The [`langgraph.json`][langgraph.json] file is a configuration file that describes what graph(s) you are going to deploy. In this case we only have one graph: the compiled `graph` object from `agent.py` / `agent.ts`.
|
||||
|
||||
=== "Python"
|
||||
|
||||
```json
|
||||
{
|
||||
"dependencies": ["."],
|
||||
"graphs": {
|
||||
"agent": "./agent.py:graph"
|
||||
},
|
||||
"env": ".env"
|
||||
}
|
||||
```
|
||||
|
||||
=== "Javascript"
|
||||
|
||||
```json
|
||||
{
|
||||
"node_version": "20",
|
||||
"dockerfile_lines": [],
|
||||
"dependencies": ["."],
|
||||
"graphs": {
|
||||
"agent": "./src/agent.ts:graph"
|
||||
},
|
||||
"env": ".env"
|
||||
}
|
||||
```
|
||||
|
||||
Learn more about the LangGraph CLI configuration file [here](./reference/cli.md#configuration-file).
|
||||
|
||||
1. __Specify environment variables__
|
||||
|
||||
The `.env` file should have any environment variables needed to run your graph. This will only be used for local testing, so if you are not testing locally you can skip this step.
|
||||
|
||||
!!! warning
|
||||
The `.env` file should NOT be included with the rest of source code in your Github repository. When creating a deployment using LangGraph Cloud, you will be able to specify the environment variables manually.
|
||||
|
||||
For this graph, we need two environment variables:
|
||||
|
||||
```shell
|
||||
ANTHROPIC_API_KEY=...
|
||||
TAVILY_API_KEY=...
|
||||
```
|
||||
|
||||
!!! tip
|
||||
Learn more about different application structure options [here](../how-tos/index.md#application-structure).
|
||||
|
||||
Now that we have set everything up on our local file system, we are ready to test our graph locally.
|
||||
|
||||
## Test the app locally
|
||||
|
||||
To test the LangGraph app before deploying it using LangGraph Cloud, you can start the [LangGraph server](../concepts/langgraph_server.md) locally or use [LangGraph Studio](../concepts/langgraph_studio.md).
|
||||
|
||||
## Using local server
|
||||
|
||||
You can test your app by running [LangGraph server](../concepts/langgraph_server.md) locally. This is useful to make sure you have configured our [CLI configuration file][langgraph.json] correctly and can interact with your graph.
|
||||
|
||||
To run the server locally, you need to first install the LangGraph CLI:
|
||||
|
||||
```shell
|
||||
pip install langgraph-cli
|
||||
```
|
||||
|
||||
You can then test our API server locally. In order to run the server locally, you will need to add your `LANGSMITH_API_KEY` to the `.env` file.
|
||||
|
||||
```shell
|
||||
langgraph up
|
||||
```
|
||||
|
||||
This will start up the LangGraph API server locally. If this runs successfully, you should see something like:
|
||||
|
||||
```shell
|
||||
Ready!
|
||||
- API: http://localhost:8123
|
||||
```
|
||||
|
||||
First, let's verify that the server is running correctly by calling `/ok` endpoint:
|
||||
|
||||
```shell
|
||||
curl --request GET --url http://localhost:8123/ok
|
||||
```
|
||||
|
||||
Output:
|
||||
|
||||
```
|
||||
{"ok": "true"}
|
||||
```
|
||||
|
||||
Now we're ready to test the app with the real inputs!
|
||||
|
||||
```shell
|
||||
curl --request POST \
|
||||
--url http://localhost:8123/runs/stream \
|
||||
--header 'Content-Type: application/json' \
|
||||
--data '{
|
||||
"assistant_id": "agent",
|
||||
"input": {
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "What is the weather in NYC?"
|
||||
}
|
||||
]
|
||||
},
|
||||
"stream_mode": "updates"
|
||||
}'
|
||||
```
|
||||
|
||||
Output:
|
||||
|
||||
```
|
||||
...
|
||||
|
||||
data: {
|
||||
"agent": {
|
||||
"messages": [
|
||||
{
|
||||
"content": "The search results from Tavily provide the current weather conditions in New York City, including temperature, wind speed, precipitation, humidity, and cloud cover. According to the results, as of 3:00pm on October 30th, 2024, it is overcast in NYC with a temperature of around 66°F (19°C), light winds from the southwest around 8 mph (13 km/h), and 66% humidity.\n\nSo in summary, the current weather in NYC is overcast with mild temperatures in the mid 60sF and light winds, based on the search results. Let me know if you need any other details!",
|
||||
"type": "ai",
|
||||
...
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
You can see that our agent responds with the up-to-date search results!
|
||||
|
||||
### Using LangGraph Studio Desktop
|
||||
|
||||
You can also test your app locally with [LangGraph Studio](../concepts/langgraph_studio.md). LangGraph Studio offers a new way to develop LLM applications by providing a specialized agent IDE that enables visualization, interaction, and debugging of complex agentic applications.
|
||||
|
||||
With visual graphs and the ability to edit state, you can better understand agent workflows and iterate faster. LangGraph Studio integrates with LangSmith allowing you to collaborate with teammates to debug failure modes.
|
||||
|
||||
LangGraph Studio is available as a [desktop app](https://studio.langchain.com/) for MacOS users. Once you have installed the app, you can select `my-app` directory, which will automatically start the server locally and load the graph in the UI.
|
||||
|
||||
To interact with your chatbot agent in LangGraph Studio, you can add a new message in the `Input` section and press `Submit`.
|
||||
|
||||

|
||||
|
||||
## Deploy to LangGraph Cloud
|
||||
|
||||
??? note "1. Log in to [LangSmith](https://smith.langchain.com/)"
|
||||
Once you've tested your graph locally and verified that it works as expected, you can deploy it to the LangGraph Cloud.
|
||||
|
||||
<figure markdown="1">
|
||||
[{: style="max-height:300px"}](deployment/img/01_login.png)
|
||||
<figcaption>
|
||||
Go to [LangSmith](https://smith.langchain.com/) and log in. If you don't have an account, you can sign up for free.
|
||||
</figcaption>
|
||||
</figure>
|
||||
First, you'll need to turn the `my-app` directory into a GitHub repo and [push it to GitHub](https://docs.github.com/en/migrations/importing-source-code/using-the-command-line-to-import-source-code/adding-locally-hosted-code-to-github).
|
||||
|
||||
Once you have created your GitHub repository with a Python file containing your compiled graph as well as a `langgraph.json` with the configuration, you can head over to [LangSmith](https://smith.langchain.com/) and click on the graph icon (`LangGraph Cloud`) on the bottom of the left navbar. This will open the LangGraph deployments page. On this page, click the `+ New Deployment` button in the top right corner.
|
||||
|
||||
??? note "2. Click on <em>LangGraph Platform</em> (the left sidebar)"
|
||||

|
||||
|
||||
<figure markdown="1">
|
||||
[{: style="max-height:300px"}](deployment/img/02_langgraph_platform.png)
|
||||
<figcaption>
|
||||
Select **LangGraph Platform** from the left sidebar.
|
||||
</figcaption>
|
||||
</figure>
|
||||
**_If you have not deployed to LangGraph Cloud before:_** there will be a button that shows up saying `Import from GitHub`. You’ll need to follow that flow to connect LangGraph Cloud to GitHub.
|
||||
|
||||
??? note "3. Click on + New Deployment (top right corner)"
|
||||
**_Once you have set up your GitHub connection:_** the new deployment page will look as follows:
|
||||
|
||||
<figure markdown="1">
|
||||
[{: style="max-height:300px"}](deployment/img/03_deployments_page.png)
|
||||
<figcaption>
|
||||
Click on **+ New Deployment** to create a new deployment. This button is located in the top right corner.
|
||||
It'll open a new modal where you can fill out the required fields.
|
||||
</figcaption>
|
||||
</figure>
|
||||

|
||||
|
||||
??? note "4. Click on Import from GitHub (first time users)"
|
||||
To deploy your application, you should do the following:
|
||||
|
||||
<figure markdown="1">
|
||||
[](deployment/img/04_create_new_deployment.png)
|
||||
<figcaption>
|
||||
Click on **Import from GitHub** and follow the instructions to connect your GitHub account. This step is needed for **first-time users** or to add private repositories that haven't been connected before.</figcaption>
|
||||
</figure>
|
||||
1. Select your GitHub username or organization from the selector
|
||||
1. Search for your repo to deploy in the search bar and select it
|
||||
1. Choose a name for your deployment
|
||||
1. In the `Git Branch` field, you can specify either the branch for the code you want to deploy, or the exact commit SHA.
|
||||
1. In the `LangGraph API config file` field, enter the path to your `langgraph.json` file (which in this case is just `langgraph.json`)
|
||||
1. If your application needs environment variables, add those in the `Environment Variables` section. They will be propagated to the underlying server so your code can access them. In this case, we will need `ANTHROPIC_API_KEY` and `TAVILY_API_KEY`.
|
||||
|
||||
??? note "5. Select the repository, configure ENV vars etc"
|
||||
Hit `Submit` and your application will start deploying!
|
||||
|
||||
<figure markdown="1">
|
||||
[{: style="max-height:300px"}](deployment/img/05_configure_deployment.png)
|
||||
<figcaption>
|
||||
Select the <strong>repository</strong>, add env variables and secrets, and set other configuration options.
|
||||
</figcaption>
|
||||
</figure>
|
||||
After your deployment is complete, your deployments page should look as follows:
|
||||
|
||||
- **Repository**: Select the repository you forked earlier (or any other repository you want to deploy).
|
||||
- Set the secrets and environment variables required by your application. For the **ReAct Agent** template, you need to set the following secrets:
|
||||
- **ANTHROPIC_API_KEY**: Get an API key from [Anthropic](https://console.anthropic.com/).
|
||||
- **TAVILY_API_KEY**: Get an API key on the [Tavily website](https://app.tavily.com/).
|
||||

|
||||
|
||||
??? note "6. Click Submit to Deploy!"
|
||||
## Interact with your deployment
|
||||
|
||||
### Using LangGraph Studio (Cloud)
|
||||
|
||||
<figure markdown="1">
|
||||
[{: style="max-height:300px"}](deployment/img/05_configure_deployment.png)
|
||||
<figcaption>
|
||||
Please note that this step may ~15 minutes to complete. You can check the status of your deployment in the **Deployments** view.
|
||||
Click the <strong>Submit</strong> button at the top right corner to deploy your application.
|
||||
</figcaption>
|
||||
</figure>
|
||||
On the deployment page for your application,, you should see a button in the top right corner that says `LangGraph Studio`. Clicking on this button will take you to the web version of LangGraph Studio. This is the same UI that you interacted with when [testing the app locally](#using-langgraph-studio-recommended), but instead of using a local LangGraph server, it uses the one from your LangGraph Cloud deployment.
|
||||
|
||||

|
||||
|
||||
## Lagraph Studio Web UI
|
||||
### Using LangGraph SDK
|
||||
|
||||
Once your application is deployed, you can test it in **LangGraph Studio**.
|
||||
You can also interact with your deployed LangGraph application programmatically, using [LangGraph SDK](./reference/sdk/python_sdk_ref.md).
|
||||
|
||||
??? note "1. Click on an existing deployment"
|
||||
First, make sure you have the SDK installed:
|
||||
|
||||
<figure markdown="1">
|
||||
[{: style="max-height:300px"}](deployment/img/07_deployments_page.png)
|
||||
<figcaption>
|
||||
Click on the deployment you just created to view more details.
|
||||
</figcaption>
|
||||
</figure>
|
||||
=== "Python"
|
||||
|
||||
??? note "2. Click on LangGraph Studio"
|
||||
```shell
|
||||
pip install langgraph_sdk
|
||||
```
|
||||
|
||||
<figure markdown="1">
|
||||
[{: style="max-height:300px"}](deployment/img/08_deployment_view.png)
|
||||
<figcaption>
|
||||
Click on the <strong>LangGraph Studio</strong> button to open LangGraph Studio.
|
||||
</figcaption>
|
||||
</figure>
|
||||
=== "Javascript"
|
||||
|
||||
<figure markdown="1">
|
||||
[{: style="max-height:400px"}](deployment/img/09_langgraph_studio.png)
|
||||
<figcaption>
|
||||
Sample graph run in LangGraph Studio.
|
||||
</figcaption>
|
||||
</figure>
|
||||
```shell
|
||||
yarn add @langchain/langgraph-sdk
|
||||
```
|
||||
|
||||
## Test the API
|
||||
Before using, you need to get the URL of your LangGraph deployment. You can find this in the `Deployment` view. Click the URL to copy it to the clipboard.
|
||||
|
||||
!!! note
|
||||
|
||||
The API calls below are for the **ReAct Agent** template. If you're deploying a different application, you may need to adjust the API calls accordingly.
|
||||
|
||||
Before using, you need to get the `URL` of your LangGraph deployment. You can find this in the `Deployment` view. Click the `URL` to copy it to the clipboard.
|
||||
|
||||
You also need to make sure you have set up your API key properly, so you can authenticate with LangGraph Cloud.
|
||||
You also need to make sure you have set up your API key properly so you can authenticate with LangGraph Cloud.
|
||||
|
||||
```shell
|
||||
export LANGSMITH_API_KEY=...
|
||||
```
|
||||
|
||||
=== "Python SDK (Async)"
|
||||
The first thing to do when using the SDK is to setup our client, access our assistant, and create a thread to execute a run on:
|
||||
|
||||
**Install the LangGraph Python SDK**
|
||||
=== "Python"
|
||||
|
||||
```shell
|
||||
pip install langgraph-sdk
|
||||
```
|
||||
```python
|
||||
from langgraph_sdk import get_client
|
||||
|
||||
**Send a message to the assistant (threadless run)**
|
||||
client = get_client(url=<DEPLOYMENT_URL>)
|
||||
# get default assistant
|
||||
assistants = await client.assistants.search(metadata={"created_by": "system"})
|
||||
assistant = assistants[0]
|
||||
# create thread
|
||||
thread = await client.threads.create()
|
||||
print(thread)
|
||||
```
|
||||
|
||||
=== "Javascript"
|
||||
|
||||
```js
|
||||
import { Client } from "@langchain/langgraph-sdk";
|
||||
|
||||
const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
|
||||
// get default assistant
|
||||
const assistants = await client.assistants.search({ metadata: {"created_by": "system"} })
|
||||
const assistant = assistants[0];
|
||||
// create thread
|
||||
const thread = await client.threads.create();
|
||||
console.log(thread)
|
||||
```
|
||||
|
||||
=== "CURL"
|
||||
|
||||
```bash
|
||||
curl --request POST \
|
||||
--url <DEPLOYMENT_URL>/assistants/search \
|
||||
--header 'Content-Type: application/json' \
|
||||
--data '{
|
||||
"limit": 10,
|
||||
"offset": 0,
|
||||
"metadata": {"created_by": "system"}
|
||||
}' &&
|
||||
curl --request POST \
|
||||
--url <DEPLOYMENT_URL>/threads \
|
||||
--header 'Content-Type: application/json' \
|
||||
--data '{}'
|
||||
```
|
||||
|
||||
We can then execute a run on the thread:
|
||||
|
||||
=== "Python"
|
||||
|
||||
```python
|
||||
from langgraph_sdk import get_client
|
||||
|
||||
client = get_client(url="your-deployment-url", api_key="your-langsmith-api-key")
|
||||
input = {
|
||||
"messages": [{"role": "user", "content": "What is the weather in NYC?"}]
|
||||
}
|
||||
|
||||
async for chunk in client.runs.stream(
|
||||
None, # Threadless run
|
||||
"agent", # Name of assistant. Defined in langgraph.json.
|
||||
input={
|
||||
"messages": [{
|
||||
"role": "human",
|
||||
"content": "What is LangGraph?",
|
||||
}],
|
||||
},
|
||||
thread["thread_id"],
|
||||
assistant["assistant_id"],
|
||||
input=input,
|
||||
stream_mode="updates",
|
||||
):
|
||||
print(f"Receiving new event of type: {chunk.event}...")
|
||||
print(chunk.data)
|
||||
print("\n\n")
|
||||
if chunk.data:
|
||||
print(chunk.data)
|
||||
```
|
||||
|
||||
=== "Python SDK (Sync)"
|
||||
|
||||
**Install the LangGraph Python SDK**
|
||||
|
||||
```shell
|
||||
pip install langgraph-sdk
|
||||
```
|
||||
|
||||
**Send a message to the assistant (threadless run)**
|
||||
|
||||
```python
|
||||
from langgraph_sdk import get_sync_client
|
||||
|
||||
client = get_sync_client(url="your-deployment-url", api_key="your-langsmith-api-key")
|
||||
|
||||
for chunk in client.runs.stream(
|
||||
None, # Threadless run
|
||||
"agent", # Name of assistant. Defined in langgraph.json.
|
||||
input={
|
||||
"messages": [{
|
||||
"role": "human",
|
||||
"content": "What is LangGraph?",
|
||||
}],
|
||||
},
|
||||
stream_mode="updates",
|
||||
):
|
||||
print(f"Receiving new event of type: {chunk.event}...")
|
||||
print(chunk.data)
|
||||
print("\n\n")
|
||||
```
|
||||
|
||||
=== "Javascript SDK"
|
||||
|
||||
**Install the LangGraph JS SDK**
|
||||
|
||||
```shell
|
||||
npm install @langchain/langgraph-sdk
|
||||
```
|
||||
|
||||
**Send a message to the assistant (threadless run)**
|
||||
=== "Javascript"
|
||||
|
||||
```js
|
||||
const { Client } = await import("@langchain/langgraph-sdk");
|
||||
|
||||
// only set the apiUrl if you changed the default port when calling langgraph up
|
||||
const client = new Client({ apiUrl: "your-deployment-url", apiKey: "your-langsmith-api-key" });
|
||||
const input = { "messages": [{ "role": "user", "content": "What is the weather in NYC?" }] };
|
||||
|
||||
const streamResponse = client.runs.stream(
|
||||
null, // Threadless run
|
||||
"agent", // Assistant ID
|
||||
{
|
||||
input: {
|
||||
"messages": [
|
||||
{ "role": "user", "content": "What is LangGraph?"}
|
||||
]
|
||||
},
|
||||
streamMode: "messages",
|
||||
}
|
||||
thread["thread_id"],
|
||||
assistant["assistant_id"],
|
||||
{
|
||||
input,
|
||||
streamMode: "updates"
|
||||
}
|
||||
);
|
||||
|
||||
for await (const chunk of streamResponse) {
|
||||
console.log(`Receiving new event of type: ${chunk.event}...`);
|
||||
console.log(JSON.stringify(chunk.data));
|
||||
console.log("\n\n");
|
||||
if (chunk.data) {
|
||||
console.log(chunk.data);
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
=== "Rest API"
|
||||
=== "CURL"
|
||||
|
||||
```bash
|
||||
curl -s --request POST \
|
||||
--url <DEPLOYMENT_URL> \
|
||||
--header 'Content-Type: application/json' \
|
||||
--data "{
|
||||
\"assistant_id\": \"agent\",
|
||||
\"input\": {
|
||||
\"messages\": [
|
||||
{
|
||||
\"role\": \"human\",
|
||||
\"content\": \"What is LangGraph?\"
|
||||
}
|
||||
]
|
||||
},
|
||||
\"stream_mode\": \"updates\"
|
||||
}"
|
||||
curl --request POST \
|
||||
--url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/stream \
|
||||
--header 'Content-Type: application/json' \
|
||||
--data '{
|
||||
"assistant_id": <ASSISTANT_ID>,
|
||||
"input": {
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "What is the weather in NYC?"
|
||||
}
|
||||
]
|
||||
},
|
||||
"stream_mode": "updates"
|
||||
}'
|
||||
```
|
||||
|
||||
Output:
|
||||
|
||||
## Next Steps
|
||||
```
|
||||
...
|
||||
|
||||
data: {
|
||||
"agent": {
|
||||
"messages": [
|
||||
{
|
||||
"content": "The search results from Tavily provide the current weather conditions in New York City, including temperature, wind speed, precipitation, humidity, and cloud cover. According to the results, as of 3:00pm on October 30th, 2024, it is overcast in NYC with a temperature of around 66°F (19°C), light winds from the southwest around 8 mph (13 km/h), and 66% humidity.\n\nSo in summary, the current weather in NYC is overcast with mild temperatures in the mid 60sF and light winds, based on the search results. Let me know if you need any other details!",
|
||||
"type": "ai",
|
||||
...
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## Next steps
|
||||
|
||||
Congratulations! If you've worked your way through this tutorial you are well on your way to becoming a LangGraph Cloud expert. Here are some other resources to check out to help you out on the path to expertise:
|
||||
|
||||
### LangGraph Framework
|
||||
|
||||
- **[LangGraph Tutorial](../tutorials/introduction.ipynb)**: Get started with LangGraph framework.
|
||||
- **[LangGraph Concepts](../concepts/index.md)**: Learn the foundational concepts of LangGraph.
|
||||
- **[LangGraph How-to Guides](../how-tos/index.md)**: Guides for common tasks with LangGraph.
|
||||
|
||||
### 📚 Learn More about LangGraph Platform
|
||||
|
||||
Expand your knowledge with these resources:
|
||||
|
||||
- **[LangGraph Platform Concepts](../concepts/index.md#langgraph-platform)**: Understand the foundational concepts of the LangGraph Platform.
|
||||
- **[LangGraph Platform How-to Guides](../how-tos/index.md#langgraph-platform)**: Discover step-by-step guides to build and deploy applications.
|
||||
- **[Launch Local LangGraph Server](../tutorials/langgraph-platform/local-server.md)**: This quick start guide shows how to start a LangGraph Server locally for the **ReAct Agent** template. The steps are similar for other templates.
|
||||
|
||||
|
||||
* [LangGraph How-to guides](../how-tos/index.md)
|
||||
* [LangGraph Tutorials](../tutorials/index.md)
|
||||
@@ -0,0 +1,19 @@
|
||||
<!doctype html>
|
||||
<html>
|
||||
<head>
|
||||
<title>Open Assistants API Specification</title>
|
||||
<meta charset="utf-8" />
|
||||
<meta
|
||||
name="viewport"
|
||||
content="width=device-width, initial-scale=1" />
|
||||
</head>
|
||||
<body>
|
||||
<script id="api-reference" data-url="./open_agent_api.json"></script>
|
||||
<script>
|
||||
var configuration = {}
|
||||
document.getElementById('api-reference').dataset.configuration =
|
||||
JSON.stringify(configuration)
|
||||
</script>
|
||||
<script src="https://cdn.jsdelivr.net/npm/@scalar/api-reference"></script>
|
||||
</body>
|
||||
</html>
|
||||
@@ -1557,11 +1557,8 @@
|
||||
"200": {
|
||||
"description": "Success",
|
||||
"content": {
|
||||
"text/event-stream": {
|
||||
"schema": {
|
||||
"type": "string",
|
||||
"description": "The server will send a stream of events in SSE format.\n\n**Example event**:\n\nid: 1\n\nevent: message\n\ndata: {}"
|
||||
}
|
||||
"application/json": {
|
||||
"schema": {}
|
||||
}
|
||||
}
|
||||
},
|
||||
@@ -1908,11 +1905,8 @@
|
||||
"200": {
|
||||
"description": "Success",
|
||||
"content": {
|
||||
"text/event-stream": {
|
||||
"schema": {
|
||||
"type": "string",
|
||||
"description": "The server will send a stream of events in SSE format.\n\n**Example event**:\n\nid: 1\n\nevent: message\n\ndata: {}"
|
||||
}
|
||||
"application/json": {
|
||||
"schema": {}
|
||||
}
|
||||
}
|
||||
},
|
||||
@@ -2149,11 +2143,8 @@
|
||||
"200": {
|
||||
"description": "Success",
|
||||
"content": {
|
||||
"text/event-stream": {
|
||||
"schema": {
|
||||
"type": "string",
|
||||
"description": "The server will send a stream of events in SSE format.\n\n**Example event**:\n\nid: 1\n\nevent: message\n\ndata: {}"
|
||||
}
|
||||
"application/json": {
|
||||
"schema": {}
|
||||
}
|
||||
}
|
||||
},
|
||||
|
||||
@@ -26,11 +26,10 @@ The LangGraph command line interface includes commands to build and run a LangGr
|
||||
The LangGraph CLI requires a JSON configuration file with the following keys:
|
||||
|
||||
| Key | Description |
|
||||
| ------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
|--------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
||||
| `dependencies` | **Required**. Array of dependencies for LangGraph Cloud API server. Dependencies can be one of the following: (1) `"."`, which will look for local Python packages, (2) `pyproject.toml`, `setup.py` or `requirements.txt` in the app directory `"./local_package"`, or (3) a package name. |
|
||||
| `graphs` | **Required**. Mapping from graph ID to path where the compiled graph or a function that makes a graph is defined. Example: <ul><li>`./your_package/your_file.py:variable`, where `variable` is an instance of `langgraph.graph.state.CompiledStateGraph`</li><li>`./your_package/your_file.py:make_graph`, where `make_graph` is a function that takes a config dictionary (`langchain_core.runnables.RunnableConfig`) and creates an instance of `langgraph.graph.state.StateGraph` / `langgraph.graph.state.CompiledStateGraph`.</li></ul> |
|
||||
| `env` | Path to `.env` file or a mapping from environment variable to its value. |
|
||||
| `store` | Configuration for adding semantic search to the BaseStore. Contains the following fields: <ul><li>`index`: Configuration for semantic search indexing with fields:<ul><li>`embed`: Embedding provider (e.g., "openai:text-embedding-3-small") or path to custom embedding function</li><li>`dims`: Dimension size of the embedding model. Used to initialize the vector table.</li><li>`fields` (optional): List of fields to index. Defaults to `["$"]`, meaningto index entire documents. Can be specific fields like `["text", "summary", "some.value"]`</li></ul></li></ul> |
|
||||
| `python_version` | `3.11` or `3.12`. Defaults to `3.11`. |
|
||||
| `pip_config_file` | Path to `pip` config file. |
|
||||
| `dockerfile_lines` | Array of additional lines to add to Dockerfile following the import from parent image. |
|
||||
@@ -42,84 +41,33 @@ The LangGraph CLI requires a JSON configuration file with the following keys:
|
||||
</p>
|
||||
</div>
|
||||
|
||||
### Examples
|
||||
|
||||
#### Basic Configuration
|
||||
Example:
|
||||
|
||||
```json
|
||||
{
|
||||
"dependencies": ["."],
|
||||
"dependencies": ["langchain_openai", "./your_package"],
|
||||
"graphs": {
|
||||
"chat": "./chat/graph.py:graph"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
#### Adding semantic search to the store
|
||||
|
||||
All deployments come with a DB-backed BaseStore. Adding an "index" configuration to your `langgraph.json` will enable [semantic search](../deployment/semantic_search.md) within the BaseStore of your deployment.
|
||||
|
||||
The `fields` configuration determines which parts of your documents to embed:
|
||||
- If omitted or set to `["$"]`, the entire document will be embedded
|
||||
- To embed specific fields, use JSON path notation: `["metadata.title", "content.text"]`
|
||||
- Documents missing specified fields will still be stored but won't have embeddings for those fields
|
||||
- You can still override which fields to embed on a specific item at `put` time using the `index` parameter
|
||||
|
||||
```json
|
||||
{
|
||||
"dependencies": ["."],
|
||||
"graphs": {
|
||||
"memory_agent": "./agent/graph.py:graph"
|
||||
"my_graph_id": "./your_package/your_file.py:variable"
|
||||
},
|
||||
"store": {
|
||||
"index": {
|
||||
"embed": "openai:text-embedding-3-small",
|
||||
"dims": 1536,
|
||||
"fields": ["$"]
|
||||
}
|
||||
}
|
||||
"env": "./.env"
|
||||
}
|
||||
```
|
||||
|
||||
!!! note "Common model dimensions"
|
||||
- openai:text-embedding-3-large: 3072
|
||||
- openai:text-embedding-3-small: 1536
|
||||
- openai:text-embedding-ada-002: 1536
|
||||
- cohere:embed-english-v3.0: 1024
|
||||
- cohere:embed-english-light-v3.0: 384
|
||||
- cohere:embed-multilingual-v3.0: 1024
|
||||
- cohere:embed-multilingual-light-v3.0: 384
|
||||
|
||||
#### Semantic search with a custom embedding function
|
||||
|
||||
If you want to use semantic search with a custom embedding function, you can pass a path to a custom embedding function:
|
||||
Example with environment variables:
|
||||
|
||||
```json
|
||||
{
|
||||
"dependencies": ["."],
|
||||
"python_version": "3.11",
|
||||
"dependencies": ["langchain_openai", "."],
|
||||
"graphs": {
|
||||
"memory_agent": "./agent/graph.py:graph"
|
||||
"my_graph_id": "./your_package/your_file.py:make_graph"
|
||||
},
|
||||
"store": {
|
||||
"index": {
|
||||
"embed": "./embeddings.py:embed_texts",
|
||||
"dims": 768,
|
||||
"fields": ["text", "summary"]
|
||||
}
|
||||
"env": {
|
||||
"OPENAI_API_KEY": "secret-key"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
The `embed` field in store configuration can reference a custom function that takes a list of strings and returns a list of embeddings. Example implementation:
|
||||
|
||||
```python
|
||||
# embeddings.py
|
||||
def embed_texts(texts: list[str]) -> list[list[float]]:
|
||||
"""Custom embedding function for semantic search."""
|
||||
# Implementation using your preferred embedding model
|
||||
return [[0.1, 0.2, ...] for _ in texts] # dims-dimensional vectors
|
||||
```
|
||||
|
||||
## Commands
|
||||
|
||||
The base command for the LangGraph CLI is `langgraph`.
|
||||
@@ -134,11 +82,6 @@ langgraph [OPTIONS] COMMAND [ARGS]
|
||||
|
||||
Run LangGraph API server in development mode with hot reloading and debugging capabilities. This lightweight server requires no Docker installation and is suitable for development and testing. State is persisted to a local directory.
|
||||
|
||||
!!! note "Python only"
|
||||
|
||||
Currently, the CLI only supports Python >= 3.11.
|
||||
JS support is coming soon.
|
||||
|
||||
**Installation**
|
||||
|
||||
This command requires the "inmem" extra to be installed:
|
||||
@@ -155,16 +98,16 @@ langgraph dev [OPTIONS]
|
||||
|
||||
**Options**
|
||||
|
||||
| Option | Default | Description |
|
||||
| ----------------------------- | ---------------- | ----------------------------------------------------------------------------------- |
|
||||
| `-c, --config FILE` | `langgraph.json` | Path to configuration file declaring dependencies, graphs and environment variables |
|
||||
| `--host TEXT` | `127.0.0.1` | Host to bind the server to |
|
||||
| `--port INTEGER` | `2024` | Port to bind the server to |
|
||||
| `--no-reload` | | Disable auto-reload |
|
||||
| `--n-jobs-per-worker INTEGER` | | Number of jobs per worker. Default is 10 |
|
||||
| `--no-browser` | | Disable automatic browser opening |
|
||||
| `--debug-port INTEGER` | | Port for debugger to listen on |
|
||||
| `--help` | | Display command documentation |
|
||||
| Option | Default | Description |
|
||||
|----------------------------|------------------|--------------------------------------------------------------------------------------------|
|
||||
| `-c, --config FILE` | `langgraph.json` | Path to configuration file declaring dependencies, graphs and environment variables |
|
||||
| `--host TEXT` | `127.0.0.1` | Host to bind the server to |
|
||||
| `--port INTEGER` | `2024` | Port to bind the server to |
|
||||
| `--no-reload` | | Disable auto-reload |
|
||||
| `--n-jobs-per-worker INTEGER` | | Number of jobs per worker. Default is 10 |
|
||||
| `--no-browser` | | Disable automatic browser opening |
|
||||
| `--debug-port INTEGER` | | Port for debugger to listen on |
|
||||
| `--help` | | Display command documentation |
|
||||
|
||||
### `build`
|
||||
|
||||
@@ -179,7 +122,7 @@ langgraph build [OPTIONS]
|
||||
**Options**
|
||||
|
||||
| Option | Default | Description |
|
||||
| -------------------- | ---------------- | ---------------------------------------------------------------------------------------------------------------------------- |
|
||||
|----------------------|------------------|------------------------------------------------------------------------------------------------------------------------------|
|
||||
| `--platform TEXT` | | Target platform(s) to build the Docker image for. Example: `langgraph build --platform linux/amd64,linux/arm64` |
|
||||
| `-t, --tag TEXT` | | **Required**. Tag for the Docker image. Example: `langgraph build -t my-image` |
|
||||
| `--pull / --no-pull` | `--pull` | Build with latest remote Docker image. Use `--no-pull` for running the LangGraph Cloud API server with locally built images. |
|
||||
@@ -198,20 +141,20 @@ langgraph up [OPTIONS]
|
||||
|
||||
**Options**
|
||||
|
||||
| Option | Default | Description |
|
||||
| ---------------------------- | ------------------------- | ----------------------------------------------------------------------------------------------------------------------- |
|
||||
| `--wait` | | Wait for services to start before returning. Implies --detach |
|
||||
| `--postgres-uri TEXT` | Local database | Postgres URI to use for the database. |
|
||||
| `--watch` | | Restart on file changes |
|
||||
| `--debugger-base-url TEXT` | `http://127.0.0.1:[PORT]` | URL used by the debugger to access LangGraph API. |
|
||||
| `--debugger-port INTEGER` | | Pull the debugger image locally and serve the UI on specified port |
|
||||
| `--verbose` | | Show more output from the server logs. |
|
||||
| `-c, --config FILE` | `langgraph.json` | Path to configuration file declaring dependencies, graphs and environment variables. |
|
||||
| `-d, --docker-compose FILE` | | Path to docker-compose.yml file with additional services to launch. |
|
||||
| `-p, --port INTEGER` | `8123` | Port to expose. Example: `langgraph up --port 8000` |
|
||||
| Option | Default | Description |
|
||||
|------------------------------|---------------------------|-----------------------------------------------------------------------------------------------------------------------|
|
||||
| `--wait` | | Wait for services to start before returning. Implies --detach |
|
||||
| `--postgres-uri TEXT` | Local database | Postgres URI to use for the database. |
|
||||
| `--watch` | | Restart on file changes |
|
||||
| `--debugger-base-url TEXT` | `http://127.0.0.1:[PORT]` | URL used by the debugger to access LangGraph API. |
|
||||
| `--debugger-port INTEGER` | | Pull the debugger image locally and serve the UI on specified port |
|
||||
| `--verbose` | | Show more output from the server logs. |
|
||||
| `-c, --config FILE` | `langgraph.json` | Path to configuration file declaring dependencies, graphs and environment variables. |
|
||||
| `-d, --docker-compose FILE` | | Path to docker-compose.yml file with additional services to launch. |
|
||||
| `-p, --port INTEGER` | `8123` | Port to expose. Example: `langgraph up --port 8000` |
|
||||
| `--pull / --no-pull` | `pull` | Pull latest images. Use `--no-pull` for running the server with locally-built images. Example: `langgraph up --no-pull` |
|
||||
| `--recreate / --no-recreate` | `no-recreate` | Recreate containers even if their configuration and image haven't changed |
|
||||
| `--help` | | Display command documentation. |
|
||||
| `--recreate / --no-recreate` | `no-recreate` | Recreate containers even if their configuration and image haven't changed |
|
||||
| `--help` | | Display command documentation. |
|
||||
|
||||
### `dockerfile`
|
||||
|
||||
@@ -226,7 +169,7 @@ langgraph dockerfile [OPTIONS] SAVE_PATH
|
||||
**Options**
|
||||
|
||||
| Option | Default | Description |
|
||||
| ------------------- | ---------------- | --------------------------------------------------------------------------------------------------------------- |
|
||||
|---------------------|------------------|-----------------------------------------------------------------------------------------------------------------|
|
||||
| `-c, --config FILE` | `langgraph.json` | Path to the [configuration file](#configuration-file) declaring dependencies, graphs and environment variables. |
|
||||
| `--help` | | Show this message and exit. |
|
||||
|
||||
@@ -258,4 +201,3 @@ RUN set -ex && \
|
||||
RUN PIP_CONFIG_FILE=/pipconfig.txt PYTHONDONTWRITEBYTECODE=1 pip install --no-cache-dir -c /api/constraints.txt -e /deps/*
|
||||
|
||||
ENV LANGSERVE_GRAPHS='{"agent": "/deps/__outer_graphs/src/agent.py:graph", "storm": "/deps/__outer_graphs/src/storm.py:graph"}'
|
||||
```
|
||||
@@ -6,25 +6,3 @@
|
||||
|
||||
::: langgraph_sdk.schema
|
||||
handler: python
|
||||
|
||||
|
||||
::: langgraph_sdk.auth
|
||||
handler: python
|
||||
|
||||
::: langgraph_sdk.auth.types.Authenticator
|
||||
handler: python
|
||||
|
||||
::: langgraph_sdk.auth.types.Handler
|
||||
handler: python
|
||||
|
||||
::: langgraph_sdk.auth.types.HandlerResult
|
||||
handler: python
|
||||
|
||||
::: langgraph_sdk.auth.types.FilterType
|
||||
handler: python
|
||||
|
||||
::: langgraph_sdk.auth.types.AuthContext
|
||||
handler: python
|
||||
|
||||
::: langgraph_sdk.auth.exceptions
|
||||
handler: python
|
||||
@@ -1,132 +0,0 @@
|
||||
# Breakpoints
|
||||
|
||||
Breakpoints pause graph execution at specific points and enable stepping through execution step by step. Breakpoints are powered by LangGraph's [**persistence layer**](./persistence.md), which saves the state after each graph step. Breakpoints can also be used to enable [**human-in-the-loop**](./human_in_the_loop.md) workflows, though we recommend using the [`interrupt` function](./human_in_the_loop.md#interrupt) for this purpose.
|
||||
|
||||
## Requirements
|
||||
|
||||
To use breakpoints, you will need to:
|
||||
|
||||
1. [**Specify a checkpointer**](persistence.md#checkpoints) to save the graph state after each step.
|
||||
2. [**Set breakpoints**](#setting-breakpoints) to specify where execution should pause.
|
||||
3. **Run the graph** with a [**thread ID**](./persistence.md#threads) to pause execution at the breakpoint.
|
||||
4. **Resume execution** using `invoke`/`ainvoke`/`stream`/`astream` (see [**The `Command` primitive**](./human_in_the_loop.md#the-command-primitive)).
|
||||
|
||||
## Setting breakpoints
|
||||
|
||||
There are two places where you can set breakpoints:
|
||||
|
||||
1. **Before** or **after** a node executes by setting breakpoints at **compile time** or **run time**. We call these [**static breakpoints**](#static-breakpoints).
|
||||
2. **Inside** a node using the [`NodeInterrupt` exception](#nodeinterrupt-exception).
|
||||
|
||||
### Static breakpoints
|
||||
|
||||
Static breakpoints are triggered either **before** or **after** a node executes. You can set static breakpoints by specifying `interrupt_before` and `interrupt_after` at **"compile" time** or **run time**.
|
||||
|
||||
=== "Compile time"
|
||||
|
||||
```python
|
||||
graph = graph_builder.compile(
|
||||
interrupt_before=["node_a"],
|
||||
interrupt_after=["node_b", "node_c"],
|
||||
checkpointer=..., # Specify a checkpointer
|
||||
)
|
||||
|
||||
thread_config = {
|
||||
"configurable": {
|
||||
"thread_id": "some_thread"
|
||||
}
|
||||
}
|
||||
|
||||
# Run the graph until the breakpoint
|
||||
graph.invoke(inputs, config=thread_config)
|
||||
|
||||
# Optionally update the graph state based on user input
|
||||
graph.update_state(update, config=thread_config)
|
||||
|
||||
# Resume the graph
|
||||
graph.invoke(None, config=thread_config)
|
||||
```
|
||||
|
||||
=== "Run time"
|
||||
|
||||
```python
|
||||
graph.invoke(
|
||||
inputs,
|
||||
config={"configurable": {"thread_id": "some_thread"}},
|
||||
interrupt_before=["node_a"],
|
||||
interrupt_after=["node_b", "node_c"]
|
||||
)
|
||||
|
||||
thread_config = {
|
||||
"configurable": {
|
||||
"thread_id": "some_thread"
|
||||
}
|
||||
}
|
||||
|
||||
# Run the graph until the breakpoint
|
||||
graph.invoke(inputs, config=thread_config)
|
||||
|
||||
# Optionally update the graph state based on user input
|
||||
graph.update_state(update, config=thread_config)
|
||||
|
||||
# Resume the graph
|
||||
graph.invoke(None, config=thread_config)
|
||||
```
|
||||
|
||||
!!! note
|
||||
|
||||
You cannot set static breakpoints at runtime for **sub-graphs**.
|
||||
If you have a sub-graph, you must set the breakpoints at compilation time.
|
||||
|
||||
Static breakpoints can be especially useful for debugging if you want to step through the graph execution one
|
||||
node at a time or if you want to pause the graph execution at specific nodes.
|
||||
|
||||
### `NodeInterrupt` exception
|
||||
|
||||
We recommend that you [**use the `interrupt` function instead**](#the-interrupt-function) of the `NodeInterrupt` exception if you're trying to implement
|
||||
[human-in-the-loop](./human_in_the_loop.md) workflows. The `interrupt` function is easier to use and more flexible.
|
||||
|
||||
??? node "`NodeInterrupt` exception"
|
||||
|
||||
The developer can define some *condition* that must be met for a breakpoint to be triggered. This concept of [dynamic breakpoints](./low_level.md#dynamic-breakpoints) is useful when the developer wants to halt the graph under *a particular condition*. This uses a `NodeInterrupt`, which is a special type of exception that can be raised from within a node based upon some condition. As an example, we can define a dynamic breakpoint that triggers when the `input` is longer than 5 characters.
|
||||
|
||||
```python
|
||||
def my_node(state: State) -> State:
|
||||
if len(state['input']) > 5:
|
||||
raise NodeInterrupt(f"Received input that is longer than 5 characters: {state['input']}")
|
||||
|
||||
return state
|
||||
```
|
||||
|
||||
|
||||
Let's assume we run the graph with an input that triggers the dynamic breakpoint and then attempt to resume the graph execution simply by passing in `None` for the input.
|
||||
|
||||
```python
|
||||
# Attempt to continue the graph execution with no change to state after we hit the dynamic breakpoint
|
||||
for event in graph.stream(None, thread_config, stream_mode="values"):
|
||||
print(event)
|
||||
```
|
||||
|
||||
The graph will *interrupt* again because this node will be *re-run* with the same graph state. We need to change the graph state such that the condition that triggers the dynamic breakpoint is no longer met. So, we can simply edit the graph state to an input that meets the condition of our dynamic breakpoint (< 5 characters) and re-run the node.
|
||||
|
||||
```python
|
||||
# Update the state to pass the dynamic breakpoint
|
||||
graph.update_state(config=thread_config, values={"input": "foo"})
|
||||
for event in graph.stream(None, thread_config, stream_mode="values"):
|
||||
print(event)
|
||||
```
|
||||
|
||||
Alternatively, what if we want to keep our current input and skip the node (`my_node`) that performs the check? To do this, we can simply perform the graph update with `as_node="my_node"` and pass in `None` for the values. This will make no update the graph state, but run the update as `my_node`, effectively skipping the node and bypassing the dynamic breakpoint.
|
||||
|
||||
```python
|
||||
# This update will skip the node `my_node` altogether
|
||||
graph.update_state(config=thread_config, values=None, as_node="my_node")
|
||||
for event in graph.stream(None, thread_config, stream_mode="values"):
|
||||
print(event)
|
||||
```
|
||||
|
||||
## Additional Resources 📚
|
||||
|
||||
- [**Conceptual Guide: Persistence**](persistence.md): Read the persistence guide for more context about persistence.
|
||||
- [**Conceptual Guide: Human-in-the-loop**](human_in_the_loop.md): Read the human-in-the-loop guide for more context on integrating human feedback into LangGraph applications using breakpoints.
|
||||
- [**How to View and Update Past Graph State**](../how-tos/human_in_the_loop/time-travel.ipynb): Step-by-step instructions for working with graph state that demonstrate the **replay** and **fork** actions.
|
||||
@@ -16,7 +16,7 @@ If you do not want to use LangGraph Platform, we describe the options we have im
|
||||
|
||||
## Reject
|
||||
|
||||
This is the simplest option, this just rejects any follow-up runs and does not allow double texting.
|
||||
This is the simplest option, this just rejects any follow up runs and does not allow double texting.
|
||||
See the [how-to guide](../cloud/how-tos/reject_concurrent.md) for configuring the reject double text option.
|
||||
|
||||
## Enqueue
|
||||
|
||||
@@ -22,21 +22,21 @@ Yes. LangGraph is an MIT-licensed open-source library and is free to use.
|
||||
|
||||
LangGraph is a stateful, orchestration framework that brings added control to agent workflows. LangGraph Platform is a service for deploying and scaling LangGraph applications, with an opinionated API for building agent UXs, plus an integrated developer studio.
|
||||
|
||||
| Features | LangGraph (open source) | LangGraph Platform |
|
||||
|---------------------|-----------------------------------------------------------|--------------------------------------------------------------------------------------------------------|
|
||||
| Description | Stateful orchestration framework for agentic applications | Scalable infrastructure for deploying LangGraph applications |
|
||||
| SDKs | Python and JavaScript | Python and JavaScript |
|
||||
| HTTP APIs | None | Yes - useful for retrieving & updating state or long-term memory, or creating a configurable assistant |
|
||||
| Streaming | Basic | Dedicated mode for token-by-token messages |
|
||||
| Checkpointer | Community contributed | Supported out-of-the-box |
|
||||
| Persistence Layer | Self-managed | Managed Postgres with efficient storage |
|
||||
| Deployment | Self-managed | • Cloud SaaS <br> • Free self-hosted <br> • Enterprise (BYOC or paid self-hosted) |
|
||||
| Scalability | Self-managed | Auto-scaling of task queues and servers |
|
||||
| Fault-tolerance | Self-managed | Automated retries |
|
||||
| Concurrency Control | Simple threading | Supports double-texting |
|
||||
| Scheduling | None | Cron scheduling |
|
||||
| Monitoring | None | Integrated with LangSmith for observability |
|
||||
| IDE integration | LangGraph Studio for Desktop | LangGraph Studio for Desktop & Cloud |
|
||||
| Features | LangGraph (open source) | LangGraph Platform |
|
||||
|----------|------------------------|-------------------|
|
||||
| Description | Stateful orchestration framework for agentic applications | Scalable infrastructure for deploying LangGraph applications |
|
||||
| SDKs | Python and JavaScript | Python and JavaScript |
|
||||
| HTTP APIs | None | Yes - useful for retrieving & updating state or long-term memory, or creating a configurable assistant |
|
||||
| Streaming | Basic | Dedicated mode for token-by-token messages |
|
||||
| Checkpointer | Community contributed | Supported out-of-the-box |
|
||||
| Persistence Layer | Self-managed | Managed Postgres with efficient storage |
|
||||
| Deployment | Self-managed | • Cloud SaaS <br> • Free self-hosted <br> • Enterprise (BYOC or paid self-hosted) |
|
||||
| Scalability | Self-managed | Auto-scaling of task queues and servers |
|
||||
| Fault-tolerance | Self-managed | Automated retries |
|
||||
| Concurrency Control | Simple threading | Supports double-texting |
|
||||
| Scheduling | None | Cron scheduling |
|
||||
| Monitoring | None | Integrated with LangSmith for observability |
|
||||
| IDE integration | LangGraph Studio for Desktop | LangGraph Studio for Desktop & Cloud |
|
||||
|
||||
## What are my deployment options for LangGraph Platform?
|
||||
|
||||
|
||||
@@ -1,744 +1,322 @@
|
||||
# Human-in-the-loop
|
||||
|
||||
!!! tip "This guide uses the new `interrupt` function."
|
||||
Human-in-the-loop (or "on-the-loop") enhances agent capabilities through several common user interaction patterns.
|
||||
|
||||
As of LangGraph 0.2.57, the recommended way to set breakpoints is using the [`interrupt` function][langgraph.types.interrupt] as it simplifies **human-in-the-loop** patterns.
|
||||
Common interaction patterns include:
|
||||
|
||||
If you're looking for the previous version of this conceptual guide, which relied on static breakpoints and `NodeInterrupt` exception, it is available [here](v0-human-in-the-loop.md).
|
||||
(1) `Approval` - We can interrupt our agent, surface the current state to a user, and allow the user to accept an action.
|
||||
|
||||
A **human-in-the-loop** (or "on-the-loop") workflow integrates human input into automated processes, allowing for decisions, validation, or corrections at key stages. This is especially useful in **LLM-based applications**, where the underlying model may generate occasional inaccuracies. In low-error-tolerance scenarios like compliance, decision-making, or content generation, human involvement ensures reliability by enabling review, correction, or override of model outputs.
|
||||
(2) `Editing` - We can interrupt our agent, surface the current state to a user, and allow the user to edit the agent state.
|
||||
|
||||
(3) `Input` - We can explicitly create a graph node to collect human input and pass that input directly to the agent state.
|
||||
|
||||
## Use cases
|
||||
Use-cases for these interaction patterns include:
|
||||
|
||||
Key use cases for **human-in-the-loop** workflows in LLM-based applications include:
|
||||
(1) `Reviewing tool calls` - We can interrupt an agent to review and edit the results of tool calls.
|
||||
|
||||
1. [**🛠️ Reviewing tool calls**](#review-tool-calls): Humans can review, edit, or approve tool calls requested by the LLM before tool execution.
|
||||
2. **✅ Validating LLM outputs**: Humans can review, edit, or approve content generated by the LLM.
|
||||
3. **💡 Providing context**: Enable the LLM to explicitly request human input for clarification or additional details or to support multi-turn conversations.
|
||||
(2) `Time Travel` - We can manually re-play and / or fork past actions of an agent.
|
||||
|
||||
## `interrupt`
|
||||
## Persistence
|
||||
|
||||
The [`interrupt` function][langgraph.types.interrupt] in LangGraph enables human-in-the-loop workflows by pausing the graph at a specific node, presenting information to a human, and resuming the graph with their input. This function is useful for tasks like approvals, edits, or collecting additional input. The [`interrupt` function][langgraph.types.interrupt] is used in conjunction with the [`Command`](../reference/types.md#langgraph.types.Command) object to resume the graph with a value provided by the human.
|
||||
All of these interaction patterns are enabled by LangGraph's built-in [persistence](./persistence.md) layer, which will write a checkpoint of the graph state at each step. Persistence allows the graph to stop so that a human can review and / or edit the current state of the graph and then resume with the human's input.
|
||||
|
||||
### Breakpoints
|
||||
|
||||
Adding a [breakpoint](./low_level.md#breakpoints) a specific location in the graph flow is one way to enable human-in-the-loop. In this case, the developer knows *where* in the workflow human input is needed and simply places a breakpoint prior to or following that particular graph node.
|
||||
|
||||
Here, we compile our graph with a checkpointer and a breakpoint at the node we want to interrupt before, `step_for_human_in_the_loop`. We then perform one of the above interaction patterns, which will create a new checkpoint if a human edits the graph state. The new checkpoint is saved to the `thread` and we can resume the graph execution from there by passing in `None` as the input.
|
||||
|
||||
```python
|
||||
from langgraph.types import interrupt
|
||||
# Compile our graph with a checkpoitner and a breakpoint before "step_for_human_in_the_loop"
|
||||
graph = builder.compile(checkpointer=checkpoitner, interrupt_before=["step_for_human_in_the_loop"])
|
||||
|
||||
def human_node(state: State):
|
||||
value = interrupt(
|
||||
# Any JSON serializable value to surface to the human.
|
||||
# For example, a question or a piece of text or a set of keys in the state
|
||||
{
|
||||
"text_to_revise": state["some_text"]
|
||||
}
|
||||
)
|
||||
# Update the state with the human's input or route the graph based on the input.
|
||||
return {
|
||||
"some_text": value
|
||||
}
|
||||
|
||||
graph = graph_builder.compile(
|
||||
checkpointer=checkpointer # Required for `interrupt` to work
|
||||
)
|
||||
|
||||
# Run the graph until the interrupt
|
||||
thread_config = {"configurable": {"thread_id": "some_id"}}
|
||||
graph.invoke(some_input, config=thread_config)
|
||||
# Run the graph up to the breakpoint
|
||||
thread_config = {"configurable": {"thread_id": "1"}}
|
||||
for event in graph.stream(inputs, thread_config, stream_mode="values"):
|
||||
print(event)
|
||||
|
||||
# Resume the graph with the human's input
|
||||
graph.invoke(Command(resume=value_from_human), config=thread_config)
|
||||
# Perform some action that requires human in the loop
|
||||
|
||||
# Continue the graph execution from the current checkpoint
|
||||
for event in graph.stream(None, thread_config, stream_mode="values"):
|
||||
print(event)
|
||||
```
|
||||
|
||||
```pycon
|
||||
{'some_text': 'Edited text'}
|
||||
```
|
||||
### Dynamic Breakpoints
|
||||
|
||||
!!! warning
|
||||
Interrupts are both powerful and ergonomic. However, while they may resemble Python's input() function in terms of developer experience, it's important to note that they do not automatically resume execution from the interruption point. Instead, they rerun the entire node where the interrupt was used.
|
||||
For this reason, interrupts are typically best placed at the start of a node or in a dedicated node. Please read the [resuming from an interrupt](#how-does-resuming-from-an-interrupt-work) section for more details.
|
||||
|
||||
??? "Full Code"
|
||||
|
||||
Here's a full example of how to use `interrupt` in a graph, if you'd like
|
||||
to see the code in action.
|
||||
|
||||
```python
|
||||
from typing import TypedDict
|
||||
import uuid
|
||||
|
||||
from langgraph.checkpoint.memory import MemorySaver
|
||||
from langgraph.constants import START
|
||||
from langgraph.graph import StateGraph
|
||||
from langgraph.types import interrupt, Command
|
||||
|
||||
class State(TypedDict):
|
||||
"""The graph state."""
|
||||
some_text: str
|
||||
|
||||
def human_node(state: State):
|
||||
value = interrupt(
|
||||
# Any JSON serializable value to surface to the human.
|
||||
# For example, a question or a piece of text or a set of keys in the state
|
||||
{
|
||||
"text_to_revise": state["some_text"]
|
||||
}
|
||||
)
|
||||
return {
|
||||
# Update the state with the human's input
|
||||
"some_text": value
|
||||
}
|
||||
|
||||
|
||||
# Build the graph
|
||||
graph_builder = StateGraph(State)
|
||||
# Add the human-node to the graph
|
||||
graph_builder.add_node("human_node", human_node)
|
||||
graph_builder.add_edge(START, "human_node")
|
||||
|
||||
# A checkpointer is required for `interrupt` to work.
|
||||
checkpointer = MemorySaver()
|
||||
graph = graph_builder.compile(
|
||||
checkpointer=checkpointer
|
||||
)
|
||||
|
||||
# Pass a thread ID to the graph to run it.
|
||||
thread_config = {"configurable": {"thread_id": uuid.uuid4()}}
|
||||
|
||||
# Using stream() to directly surface the `__interrupt__` information.
|
||||
for chunk in graph.stream({"some_text": "Original text"}, config=thread_config):
|
||||
print(chunk)
|
||||
|
||||
# Resume using Command
|
||||
for chunk in graph.stream(Command(resume="Edited text"), config=thread_config):
|
||||
print(chunk)
|
||||
```
|
||||
|
||||
```pycon
|
||||
{'__interrupt__': (
|
||||
Interrupt(
|
||||
value={'question': 'Please revise the text', 'some_text': 'Original text'},
|
||||
resumable=True,
|
||||
ns=['human_node:10fe492f-3688-c8c6-0d0a-ec61a43fecd6'],
|
||||
when='during'
|
||||
),
|
||||
)
|
||||
}
|
||||
{'human_node': {'some_text': 'Edited text'}}
|
||||
```
|
||||
|
||||
## Requirements
|
||||
|
||||
To use `interrupt` in your graph, you need to:
|
||||
|
||||
1. [**Specify a checkpointer**](persistence.md#checkpoints) to save the graph state after each step.
|
||||
2. **Call `interrupt()`** in the appropriate place. See the [Design Patterns](#design-patterns) section for examples.
|
||||
3. **Run the graph** with a [**thread ID**](./persistence.md#threads) until the `interrupt` is hit.
|
||||
4. **Resume execution** using `invoke`/`ainvoke`/`stream`/`astream` (see [**The `Command` primitive**](#the-command-primitive)).
|
||||
|
||||
## Design Patterns
|
||||
|
||||
There are typically three different **actions** that you can do with a human-in-the-loop workflow:
|
||||
|
||||
1. **Approve or Reject**: Pause the graph before a critical step, such as an API call, to review and approve the action. If the action is rejected, you can prevent the graph from executing the step, and potentially take an alternative action. This pattern often involve **routing** the graph based on the human's input.
|
||||
2. **Edit Graph State**: Pause the graph to review and edit the graph state. This is useful for correcting mistakes or updating the state with additional information. This pattern often involves **updating** the state with the human's input.
|
||||
3. **Get Input**: Explicitly request human input at a particular step in the graph. This is useful for collecting additional information or context to inform the agent's decision-making process or for supporting **multi-turn conversations**.
|
||||
|
||||
Below we show different design patterns that can be implemented using these **actions**.
|
||||
|
||||
### Approve or Reject
|
||||
|
||||
<figure markdown="1">
|
||||
{: style="max-height:400px"}
|
||||
<figcaption>Depending on the human's approval or rejection, the graph can proceed with the action or take an alternative path.</figcaption>
|
||||
</figure>
|
||||
|
||||
Pause the graph before a critical step, such as an API call, to review and approve the action. If the action is rejected, you can prevent the graph from executing the step, and potentially take an alternative action.
|
||||
Alternatively, the developer can define some *condition* that must be met for a breakpoint to be triggered. This concept of [dynamic breakpoints](./low_level.md#dynamic-breakpoints) is useful when the developer wants to halt the graph under *a particular condition*. This uses a `NodeInterrupt`, which is a special type of exception that can be raised from within a node based upon some condition. As an example, we can define a dynamic breakpoint that triggers when the `input` is longer than 5 characters.
|
||||
|
||||
```python
|
||||
|
||||
from typing import Literal
|
||||
from langgraph.types import interrupt, Command
|
||||
|
||||
def human_approval(state: State) -> Command[Literal["some_node", "another_node"]]:
|
||||
is_approved = interrupt(
|
||||
{
|
||||
"question": "Is this correct?",
|
||||
# Surface the output that should be
|
||||
# reviewed and approved by the human.
|
||||
"llm_output": state["llm_output"]
|
||||
}
|
||||
)
|
||||
|
||||
if is_approved:
|
||||
return Command(goto="some_node")
|
||||
else:
|
||||
return Command(goto="another_node")
|
||||
|
||||
# Add the node to the graph in an appropriate location
|
||||
# and connect it to the relevant nodes.
|
||||
graph_builder.add_node("human_approval", human_approval)
|
||||
graph = graph_builder.compile(checkpointer=checkpointer)
|
||||
|
||||
# After running the graph and hitting the interrupt, the graph will pause.
|
||||
# Resume it with either an approval or rejection.
|
||||
thread_config = {"configurable": {"thread_id": "some_id"}}
|
||||
graph.invoke(Command(resume=True), config=thread_config)
|
||||
def my_node(state: State) -> State:
|
||||
if len(state['input']) > 5:
|
||||
raise NodeInterrupt(f"Received input that is longer than 5 characters: {state['input']}")
|
||||
return state
|
||||
```
|
||||
|
||||
See [how to review tool calls](../how-tos/human_in_the_loop/review-tool-calls.ipynb) for a more detailed example.
|
||||
|
||||
### Review & Edit State
|
||||
|
||||
<figure markdown="1">
|
||||
{: style="max-height:400px"}
|
||||
<figcaption>A human can review and edit the state of the graph. This is useful for correcting mistakes or updating the state with additional information.
|
||||
</figcaption>
|
||||
</figure>
|
||||
Let's assume we run the graph with an input that triggers the dynamic breakpoint and then attempt to resume the graph execution simply by passing in `None` for the input.
|
||||
|
||||
```python
|
||||
from langgraph.types import interrupt
|
||||
|
||||
def human_editing(state: State):
|
||||
...
|
||||
result = interrupt(
|
||||
# Interrupt information to surface to the client.
|
||||
# Can be any JSON serializable value.
|
||||
{
|
||||
"task": "Review the output from the LLM and make any necessary edits.",
|
||||
"llm_generated_summary": state["llm_generated_summary"]
|
||||
}
|
||||
)
|
||||
|
||||
# Update the state with the edited text
|
||||
return {
|
||||
"llm_generated_summary": result["edited_text"]
|
||||
}
|
||||
|
||||
# Add the node to the graph in an appropriate location
|
||||
# and connect it to the relevant nodes.
|
||||
graph_builder.add_node("human_editing", human_editing)
|
||||
graph = graph_builder.compile(checkpointer=checkpointer)
|
||||
|
||||
...
|
||||
|
||||
# After running the graph and hitting the interrupt, the graph will pause.
|
||||
# Resume it with the edited text.
|
||||
thread_config = {"configurable": {"thread_id": "some_id"}}
|
||||
graph.invoke(
|
||||
Command(resume={"edited_text": "The edited text"}),
|
||||
config=thread_config
|
||||
)
|
||||
# Attempt to continue the graph execution with no change to state after we hit the dynamic breakpoint
|
||||
for event in graph.stream(None, thread_config, stream_mode="values"):
|
||||
print(event)
|
||||
```
|
||||
|
||||
See [How to wait for user input using interrupt](../how-tos/human_in_the_loop/wait-user-input.ipynb) for a more detailed example.
|
||||
The graph will *interrupt* again because this node will be *re-run* with the same graph state. We need to change the graph state such that the condition that triggers the dynamic breakpoint is no longer met. So, we can simply edit the graph state to an input that meets the condition of our dynamic breakpoint (< 5 characters) and re-run the node.
|
||||
|
||||
### Review Tool Calls
|
||||
```python
|
||||
# Update the state to pass the dynamic breakpoint
|
||||
graph.update_state(config=thread_config, values={"input": "foo"})
|
||||
for event in graph.stream(None, thread_config, stream_mode="values"):
|
||||
print(event)
|
||||
```
|
||||
|
||||
<figure markdown="1">
|
||||
{: style="max-height:400px"}
|
||||
<figcaption>A human can review and edit the output from the LLM before proceeding. This is particularly
|
||||
critical in applications where the tool calls requested by the LLM may be sensitive or require human oversight.
|
||||
</figcaption>
|
||||
</figure>
|
||||
Alternatively, what if we want to keep our current input and skip the node (`my_node`) that performs the check? To do this, we can simply perform the graph update with `as_node="my_node"` and pass in `None` for the values. This will make no update the graph state, but run the update as `my_node`, effectively skipping the node and bypassing the dynamic breakpoint.
|
||||
|
||||
```python
|
||||
def human_review_node(state) -> Command[Literal["call_llm", "run_tool"]]:
|
||||
# This is the value we'll be providing via Command(resume=<human_review>)
|
||||
human_review = interrupt(
|
||||
{
|
||||
"question": "Is this correct?",
|
||||
# Surface tool calls for review
|
||||
"tool_call": tool_call
|
||||
}
|
||||
)
|
||||
|
||||
review_action, review_data = human_review
|
||||
|
||||
# Approve the tool call and continue
|
||||
if review_action == "continue":
|
||||
return Command(goto="run_tool")
|
||||
|
||||
# Modify the tool call manually and then continue
|
||||
elif review_action == "update":
|
||||
...
|
||||
updated_msg = get_updated_msg(review_data)
|
||||
# Remember that to modify an existing message you will need
|
||||
# to pass the message with a matching ID.
|
||||
return Command(goto="run_tool", update={"messages": [updated_message]})
|
||||
|
||||
# Give natural language feedback, and then pass that back to the agent
|
||||
elif review_action == "feedback":
|
||||
...
|
||||
feedback_msg = get_feedback_msg(review_data)
|
||||
return Command(goto="call_llm", update={"messages": [feedback_msg]})
|
||||
# This update will skip the node `my_node` altogether
|
||||
graph.update_state(config=thread_config, values=None, as_node="my_node")
|
||||
for event in graph.stream(None, thread_config, stream_mode="values"):
|
||||
print(event)
|
||||
```
|
||||
|
||||
See [how to review tool calls](../how-tos/human_in_the_loop/review-tool-calls.ipynb) for a more detailed example.
|
||||
See [our guide](../how-tos/human_in_the_loop/dynamic_breakpoints.ipynb) for a detailed how-to on doing this!
|
||||
|
||||
### Multi-turn conversation
|
||||
## Interaction Patterns
|
||||
|
||||
<figure markdown="1">
|
||||
{: style="max-height:400px"}
|
||||
<figcaption>A <strong>multi-turn conversation</strong> architecture where an <strong>agent</strong> and <strong>human node</strong> cycle back and forth until the agent decides to hand off the conversation to another agent or another part of the system.
|
||||
</figcaption>
|
||||
</figure>
|
||||
### Approval
|
||||
|
||||
A **multi-turn conversation** involves multiple back-and-forth interactions between an agent and a human, which can allow the agent to gather additional information from the human in a conversational manner.
|
||||

|
||||
|
||||
This design pattern is useful in an LLM application consisting of [multiple agents](./multi_agent.md). One or more agents may need to carry out multi-turn conversations with a human, where the human provides input or feedback at different stages of the conversation. For simplicity, the agent implementation below is illustrated as a single node, but in reality
|
||||
it may be part of a larger graph consisting of multiple nodes and include a conditional edge.
|
||||
Sometimes we want to approve certain steps in our agent's execution.
|
||||
|
||||
We can interrupt our agent at a [breakpoint](./low_level.md#breakpoints) prior to the step that we want to approve.
|
||||
|
||||
=== "Using a human node per agent"
|
||||
|
||||
In this pattern, each agent has its own human node for collecting user input.
|
||||
This can be achieved by either naming the human nodes with unique names (e.g., "human for agent 1", "human for agent 2") or by
|
||||
using subgraphs where a subgraph contains a human node and an agent node.
|
||||
|
||||
```python
|
||||
from langgraph.types import interrupt
|
||||
|
||||
def human_input(state: State):
|
||||
human_message = interrupt("human_input")
|
||||
return {
|
||||
"messages": [
|
||||
{
|
||||
"role": "human",
|
||||
"content": human_message
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
def agent(state: State):
|
||||
# Agent logic
|
||||
...
|
||||
|
||||
graph_builder.add_node("human_input", human_input)
|
||||
graph_builder.add_edge("human_input", "agent")
|
||||
graph = graph_builder.compile(checkpointer=checkpointer)
|
||||
|
||||
# After running the graph and hitting the interrupt, the graph will pause.
|
||||
# Resume it with the human's input.
|
||||
graph.invoke(
|
||||
Command(resume="hello!"),
|
||||
config=thread_config
|
||||
)
|
||||
```
|
||||
|
||||
|
||||
=== "Sharing human node across multiple agents"
|
||||
|
||||
In this pattern, a single human node is used to collect user input for multiple agents. The active agent is determined from the state, so after human input is collected, the graph can route to the correct agent.
|
||||
|
||||
```python
|
||||
from langgraph.types import interrupt
|
||||
|
||||
def human_node(state: MessagesState) -> Command[Literal["agent_1", "agent_2", ...]]:
|
||||
"""A node for collecting user input."""
|
||||
user_input = interrupt(value="Ready for user input.")
|
||||
|
||||
# Determine the **active agent** from the state, so
|
||||
# we can route to the correct agent after collecting input.
|
||||
# For example, add a field to the state or use the last active agent.
|
||||
# or fill in `name` attribute of AI messages generated by the agents.
|
||||
active_agent = ...
|
||||
|
||||
return Command(
|
||||
update={
|
||||
"messages": [{
|
||||
"role": "human",
|
||||
"content": user_input,
|
||||
}]
|
||||
},
|
||||
goto=active_agent,
|
||||
)
|
||||
```
|
||||
|
||||
See [how to implement multi-turn conversations](../how-tos/multi-agent-multi-turn-convo.ipynb) for a more detailed example.
|
||||
|
||||
### Validating human input
|
||||
|
||||
If you need to validate the input provided by the human within the graph itself (rather than on the client side), you can achieve this by using multiple interrupt calls within a single node.
|
||||
This is generally recommend for sensitive actions (e.g., using external APIs or writing to a database).
|
||||
|
||||
With persistence, we can surface the current agent state as well as the next step to a user for review and approval.
|
||||
|
||||
If approved, the graph resumes execution from the last saved checkpoint, which is saved to the `thread`:
|
||||
|
||||
```python
|
||||
from langgraph.types import interrupt
|
||||
# Compile our graph with a checkpoitner and a breakpoint before the step to approve
|
||||
graph = builder.compile(checkpointer=checkpoitner, interrupt_before=["node_2"])
|
||||
|
||||
def human_node(state: State):
|
||||
"""Human node with validation."""
|
||||
question = "What is your age?"
|
||||
# Run the graph up to the breakpoint
|
||||
for event in graph.stream(inputs, thread, stream_mode="values"):
|
||||
print(event)
|
||||
|
||||
# ... Get human approval ...
|
||||
|
||||
while True:
|
||||
answer = interrupt(question)
|
||||
|
||||
# Validate answer, if the answer isn't valid ask for input again.
|
||||
if not isinstance(answer, int) or answer < 0:
|
||||
question = f"'{answer} is not a valid age. What is your age?"
|
||||
answer = None
|
||||
continue
|
||||
else:
|
||||
# If the answer is valid, we can proceed.
|
||||
break
|
||||
|
||||
print(f"The human in the loop is {answer} years old.")
|
||||
return {
|
||||
"age": answer
|
||||
}
|
||||
# If approved, continue the graph execution from the last saved checkpoint
|
||||
for event in graph.stream(None, thread, stream_mode="values"):
|
||||
print(event)
|
||||
```
|
||||
|
||||
## The `Command` primitive
|
||||
See [our guide](../how-tos/human_in_the_loop/breakpoints.ipynb) for a detailed how-to on doing this!
|
||||
|
||||
When using the `interrupt` function, the graph will pause at the interrupt and wait for user input.
|
||||
### Editing
|
||||
|
||||
Graph execution can be resumed using the [Command](../reference/types.md#langgraph.types.Command) primitive which can be passed through the `invoke`, `ainvoke`, `stream` or `astream` methods.
|
||||

|
||||
|
||||
The `Command` primitive provides several options to control and modify the graph's state during resumption:
|
||||
Sometimes we want to review and edit the agent's state.
|
||||
|
||||
As with approval, we can interrupt our agent at a [breakpoint](./low_level.md#breakpoints) prior the the step we want to check.
|
||||
|
||||
We can surface the current state to a user and allow the user to edit the agent state.
|
||||
|
||||
This can, for example, be used to correct the agent if it made a mistake (e.g., see the section on tool calling below).
|
||||
|
||||
1. **Pass a value to the `interrupt`**: Provide data, such as a user's response, to the graph using `Command(resume=value)`. Execution resumes from the beginning of the node where the `interrupt` was used, however, this time the `interrupt(...)` call will return the value passed in the `Command(resume=value)` instead of pausing the graph.
|
||||
We can edit the graph state by forking the current checkpoint, which is saved to the `thread`.
|
||||
|
||||
```python
|
||||
# Resume graph execution with the user's input.
|
||||
graph.invoke(Command(resume={"age": "25"}), thread_config)
|
||||
```
|
||||
|
||||
2. **Update the graph state**: Modify the graph state using `Command(update=update)`. Note that resumption starts from the beginning of the node where the `interrupt` was used. Execution resumes from the beginning of the node where the `interrupt` was used, but with the updated state.
|
||||
|
||||
```python
|
||||
# Update the graph state and resume.
|
||||
# You must provide a `resume` value if using an `interrupt`.
|
||||
graph.invoke(Command(update={"foo": "bar"}, resume="Let's go!!!"), thread_config)
|
||||
```
|
||||
|
||||
By leveraging `Command`, you can resume graph execution, handle user inputs, and dynamically adjust the graph's state.
|
||||
|
||||
## Using with `invoke` and `ainvoke`
|
||||
|
||||
When you use `stream` or `astream` to run the graph, you will receive an `Interrupt` event that let you know the `interrupt` was triggered.
|
||||
|
||||
`invoke` and `ainvoke` do not return the interrupt information. To access this information, you must use the [get_state](../reference/graphs.md#langgraph.graph.graph.CompiledGraph.get_state) method to retrieve the graph state after calling `invoke` or `ainvoke`.
|
||||
We can then proceed with the graph from our forked checkpoint as done before.
|
||||
|
||||
```python
|
||||
# Run the graph up to the interrupt
|
||||
result = graph.invoke(inputs, thread_config)
|
||||
# Get the graph state to get interrupt information.
|
||||
state = graph.get_state(thread_config)
|
||||
# Print the state values
|
||||
print(state.values)
|
||||
# Print the pending tasks
|
||||
print(state.tasks)
|
||||
# Resume the graph with the user's input.
|
||||
graph.invoke(Command(resume={"age": "25"}), thread_config)
|
||||
# Compile our graph with a checkpoitner and a breakpoint before the step to review
|
||||
graph = builder.compile(checkpointer=checkpoitner, interrupt_before=["node_2"])
|
||||
|
||||
# Run the graph up to the breakpoint
|
||||
for event in graph.stream(inputs, thread, stream_mode="values"):
|
||||
print(event)
|
||||
|
||||
# Review the state, decide to edit it, and create a forked checkpoint with the new state
|
||||
graph.update_state(thread, {"state": "new state"})
|
||||
|
||||
# Continue the graph execution from the forked checkpoint
|
||||
for event in graph.stream(None, thread, stream_mode="values"):
|
||||
print(event)
|
||||
```
|
||||
|
||||
```pycon
|
||||
{'foo': 'bar'} # State values
|
||||
(
|
||||
PregelTask(
|
||||
id='5d8ffc92-8011-0c9b-8b59-9d3545b7e553',
|
||||
name='node_foo',
|
||||
path=('__pregel_pull', 'node_foo'),
|
||||
error=None,
|
||||
interrupts=(Interrupt(value='value_in_interrupt', resumable=True, ns=['node_foo:5d8ffc92-8011-0c9b-8b59-9d3545b7e553'], when='during'),), state=None,
|
||||
result=None
|
||||
),
|
||||
) # Pending tasks. interrupts
|
||||
```
|
||||
See [this guide](../how-tos/human_in_the_loop/edit-graph-state.ipynb) for a detailed how-to on doing this!
|
||||
|
||||
## How does resuming from an interrupt work?
|
||||
### Input
|
||||
|
||||
!!! warning
|
||||

|
||||
|
||||
Resuming from an `interrupt` is **different** from Python's `input()` function, where execution resumes from the exact point where the `input()` function was called.
|
||||
Sometimes we want to explicitly get human input at a particular step in the graph.
|
||||
|
||||
We can create a graph node designated for this (e.g., `human_input` in our example diagram).
|
||||
|
||||
As with approval and editing, we can interrupt our agent at a [breakpoint](./low_level.md#breakpoints) prior to this node.
|
||||
|
||||
We can then perform a state update that includes the human input, just as we did with editing state.
|
||||
|
||||
A critical aspect of using `interrupt` is understanding how resuming works. When you resume execution after an `interrupt`, graph execution starts from the **beginning** of the **graph node** where the last `interrupt` was triggered.
|
||||
But, we add one thing:
|
||||
|
||||
**All** code from the beginning of the node to the `interrupt` will be re-executed.
|
||||
We can use `as_node=human_input` with the state update to specify that the state update *should be treated as a node*.
|
||||
|
||||
The is subtle, but important:
|
||||
|
||||
With editing, the user makes a decision about whether or not to edit the graph state.
|
||||
|
||||
With input, we explicitly define a node in our graph for collecting human input!
|
||||
|
||||
The the state update with the human input then runs *as this node*.
|
||||
|
||||
```python
|
||||
counter = 0
|
||||
def node(state: State):
|
||||
# All the code from the beginning of the node to the interrupt will be re-executed
|
||||
# when the graph resumes.
|
||||
global counter
|
||||
counter += 1
|
||||
print(f"> Entered the node: {counter} # of times")
|
||||
# Pause the graph and wait for user input.
|
||||
answer = interrupt()
|
||||
print("The value of counter is:", counter)
|
||||
...
|
||||
# Compile our graph with a checkpoitner and a breakpoint before the step to to collect human input
|
||||
graph = builder.compile(checkpointer=checkpoitner, interrupt_before=["human_input"])
|
||||
|
||||
# Run the graph up to the breakpoint
|
||||
for event in graph.stream(inputs, thread, stream_mode="values"):
|
||||
print(event)
|
||||
|
||||
# Update the state with the user input as if it was the human_input node
|
||||
graph.update_state(thread, {"user_input": user_input}, as_node="human_input")
|
||||
|
||||
# Continue the graph execution from the checkpoint created by the human_input node
|
||||
for event in graph.stream(None, thread, stream_mode="values"):
|
||||
print(event)
|
||||
```
|
||||
|
||||
Upon **resuming** the graph, the counter will be incremented a second time, resulting in the following output:
|
||||
See [this guide](../how-tos/human_in_the_loop/wait-user-input.ipynb) for a detailed how-to on doing this!
|
||||
|
||||
```pycon
|
||||
> Entered the node: 2 # of times
|
||||
The value of counter is: 2
|
||||
```
|
||||
## Use-cases
|
||||
|
||||
## Common Pitfalls
|
||||
### Reviewing Tool Calls
|
||||
|
||||
### Side-effects
|
||||
Some user interaction patterns combine the above ideas.
|
||||
|
||||
Place code with side effects, such as API calls, **after** the `interrupt` to avoid duplication, as these are re-triggered every time the node is resumed.
|
||||
For example, many agents use [tool calling](https://python.langchain.com/docs/how_to/tool_calling/) to make decisions.
|
||||
|
||||
=== "Side effects before interrupt (BAD)"
|
||||
Tool calling presents a challenge because the agent must get two things right:
|
||||
|
||||
This code will re-execute the API call another time when the node is resumed from
|
||||
the `interrupt`.
|
||||
(1) The name of the tool to call
|
||||
|
||||
This can be problematic if the API call is not idempotent or is just expensive.
|
||||
(2) The arguments to pass to the tool
|
||||
|
||||
```python
|
||||
from langgraph.types import interrupt
|
||||
Even if the tool call is correct, we may also want to apply discretion:
|
||||
|
||||
def human_node(state: State):
|
||||
"""Human node with validation."""
|
||||
api_call(...) # This code will be re-executed when the node is resumed.
|
||||
answer = interrupt(question)
|
||||
```
|
||||
(3) The tool call may be a sensitive operation that we want to approve
|
||||
|
||||
=== "Side effects after interrupt (OK)"
|
||||
|
||||
```python
|
||||
from langgraph.types import interrupt
|
||||
|
||||
def human_node(state: State):
|
||||
"""Human node with validation."""
|
||||
|
||||
answer = interrupt(question)
|
||||
|
||||
api_call(answer) # OK as it's after the interrupt
|
||||
```
|
||||
|
||||
=== "Side effects in a separate node (OK)"
|
||||
|
||||
```python
|
||||
from langgraph.types import interrupt
|
||||
|
||||
def human_node(state: State):
|
||||
"""Human node with validation."""
|
||||
|
||||
answer = interrupt(question)
|
||||
|
||||
return {
|
||||
"answer": answer
|
||||
}
|
||||
|
||||
def api_call_node(state: State):
|
||||
api_call(...) # OK as it's in a separate node
|
||||
```
|
||||
|
||||
### Subgraphs called as functions
|
||||
|
||||
When invoking a subgraph [as a function](low_level.md#as-a-function), the **parent graph** will resume execution from the **beginning of the node** where the subgraph was invoked (and where an `interrupt` was triggered). Similarly, the **subgraph**, will resume from the **beginning of the node** where the `interrupt()` function was called.
|
||||
|
||||
For example,
|
||||
With these points in mind, we can combine the above ideas to create a human-in-the-loop review of a tool call.
|
||||
|
||||
```python
|
||||
def node_in_parent_graph(state: State):
|
||||
some_code() # <-- This will re-execute when the subgraph is resumed.
|
||||
# Invoke a subgraph as a function.
|
||||
# The subgraph contains an `interrupt` call.
|
||||
subgraph_result = subgraph.invoke(some_input)
|
||||
...
|
||||
# Compile our graph with a checkpoitner and a breakpoint before the step to to review the tool call from the LLM
|
||||
graph = builder.compile(checkpointer=checkpoitner, interrupt_before=["human_review"])
|
||||
|
||||
# Run the graph up to the breakpoint
|
||||
for event in graph.stream(inputs, thread, stream_mode="values"):
|
||||
print(event)
|
||||
|
||||
# Review the tool call and update it, if needed, as the human_review node
|
||||
graph.update_state(thread, {"tool_call": "updated tool call"}, as_node="human_review")
|
||||
|
||||
# Otherwise, approve the tool call and proceed with the graph execution with no edits
|
||||
|
||||
# Continue the graph execution from either:
|
||||
# (1) the forked checkpoint created by human_review or
|
||||
# (2) the checkpoint saved when the tool call was originally made (no edits in human_review)
|
||||
for event in graph.stream(None, thread, stream_mode="values"):
|
||||
print(event)
|
||||
```
|
||||
|
||||
??? "**Example: Parent and Subgraph Execution Flow**"
|
||||
See [this guide](../how-tos/human_in_the_loop/review-tool-calls.ipynb) for a detailed how-to on doing this!
|
||||
|
||||
Say we have a parent graph with 3 nodes:
|
||||
### Time Travel
|
||||
|
||||
**Parent Graph**: `node_1` → `node_2` (subgraph call) → `node_3`
|
||||
When working with agents, we often want closely examine their decision making process:
|
||||
|
||||
And the subgraph has 3 nodes, where the second node contains an `interrupt`:
|
||||
(1) Even when they arrive a desired final result, the reasoning that led to that result is often important to examine.
|
||||
|
||||
**Subgraph**: `sub_node_1` → `sub_node_2` (`interrupt`) → `sub_node_3`
|
||||
(2) When agents make mistakes, it is often valuable to understand why.
|
||||
|
||||
When resuming the graph, the execution will proceed as follows:
|
||||
(3) In either of the above cases, it is useful to manually explore alternative decision making paths.
|
||||
|
||||
1. **Skip `node_1`** in the parent graph (already executed, graph state was saved in snapshot).
|
||||
2. **Re-execute `node_2`** in the parent graph from the start.
|
||||
3. **Skip `sub_node_1`** in the subgraph (already executed, graph state was saved in snapshot).
|
||||
4. **Re-execute `sub_node_2`** in the subgraph from the beginning.
|
||||
5. Continue with `sub_node_3` and subsequent nodes.
|
||||
Collectively, we call these debugging concepts `time-travel` and they are composed of `replaying` and `forking`.
|
||||
|
||||
Here is abbreviated example code that you can use to understand how subgraphs work with interrupts.
|
||||
It counts the number of times each node is entered and prints the count.
|
||||
#### Replaying
|
||||
|
||||
```python
|
||||
import uuid
|
||||
from typing import TypedDict
|
||||

|
||||
|
||||
from langgraph.graph import StateGraph
|
||||
from langgraph.constants import START
|
||||
from langgraph.types import interrupt, Command
|
||||
from langgraph.checkpoint.memory import MemorySaver
|
||||
Sometimes we want to simply replay past actions of an agent.
|
||||
|
||||
Above, we showed the case of executing an agent from the current state (or checkpoint) of the graph.
|
||||
|
||||
We by simply passing in `None` for the input with a `thread`.
|
||||
|
||||
class State(TypedDict):
|
||||
"""The graph state."""
|
||||
state_counter: int
|
||||
```
|
||||
thread = {"configurable": {"thread_id": "1"}}
|
||||
for event in graph.stream(None, thread, stream_mode="values"):
|
||||
print(event)
|
||||
```
|
||||
|
||||
Now, we can modify this to replay past actions from a *specific* checkpoint by passing in the checkpoint ID.
|
||||
|
||||
counter_node_in_subgraph = 0
|
||||
To get a specific checkpoint ID, we can easily get all of the checkpoints in the thread and filter to the one we want.
|
||||
|
||||
def node_in_subgraph(state: State):
|
||||
"""A node in the sub-graph."""
|
||||
global counter_node_in_subgraph
|
||||
counter_node_in_subgraph += 1 # This code will **NOT** run again!
|
||||
print(f"Entered `node_in_subgraph` a total of {counter_node_in_subgraph} times")
|
||||
```python
|
||||
all_checkpoints = []
|
||||
for state in app.get_state_history(thread):
|
||||
all_checkpoints.append(state)
|
||||
```
|
||||
|
||||
counter_human_node = 0
|
||||
Each checkpoint has a unique ID, which we can use to replay from a specific checkpoint.
|
||||
|
||||
def human_node(state: State):
|
||||
global counter_human_node
|
||||
counter_human_node += 1 # This code will run again!
|
||||
print(f"Entered human_node in sub-graph a total of {counter_human_node} times")
|
||||
answer = interrupt("what is your name?")
|
||||
print(f"Got an answer of {answer}")
|
||||
Assume from reviewing the checkpoints that we want to replay from one, `xxx`.
|
||||
|
||||
We just pass in the checkpoint ID when we run the graph.
|
||||
|
||||
checkpointer = MemorySaver()
|
||||
```python
|
||||
config = {'configurable': {'thread_id': '1', 'checkpoint_id': 'xxx'}}
|
||||
for event in graph.stream(None, config, stream_mode="values"):
|
||||
print(event)
|
||||
```
|
||||
|
||||
Importantly, the graph knows which checkpoints have been previously executed.
|
||||
|
||||
subgraph_builder = StateGraph(State)
|
||||
subgraph_builder.add_node("some_node", node_in_subgraph)
|
||||
subgraph_builder.add_node("human_node", human_node)
|
||||
subgraph_builder.add_edge(START, "some_node")
|
||||
subgraph_builder.add_edge("some_node", "human_node")
|
||||
subgraph = subgraph_builder.compile(checkpointer=checkpointer)
|
||||
So, it will re-play any previously executed nodes rather than re-executing them.
|
||||
|
||||
See [this additional conceptual guide](https://langchain-ai.github.io/langgraph/concepts/persistence/#replay) for related context on replaying.
|
||||
|
||||
counter_parent_node = 0
|
||||
See see [this guide](../how-tos/human_in_the_loop/time-travel.ipynb) for a detailed how-to on doing time-travel!
|
||||
|
||||
def parent_node(state: State):
|
||||
"""This parent node will invoke the subgraph."""
|
||||
global counter_parent_node
|
||||
#### Forking
|
||||
|
||||
counter_parent_node += 1 # This code will run again on resuming!
|
||||
print(f"Entered `parent_node` a total of {counter_parent_node} times")
|
||||
|
||||
# Please note that we're intentionally incrementing the state counter
|
||||
# in the graph state as well to demonstrate that the subgraph update
|
||||
# of the same key will not conflict with the parent graph (until
|
||||
subgraph_state = subgraph.invoke(state)
|
||||
return subgraph_state
|
||||

|
||||
|
||||
Sometimes we want to fork past actions of an agent, and explore different paths through the graph.
|
||||
|
||||
builder = StateGraph(State)
|
||||
builder.add_node("parent_node", parent_node)
|
||||
builder.add_edge(START, "parent_node")
|
||||
`Editing`, as discussed above, is *exactly* how we do this for the *current* state of the graph!
|
||||
|
||||
# A checkpointer must be enabled for interrupts to work!
|
||||
checkpointer = MemorySaver()
|
||||
graph = builder.compile(checkpointer=checkpointer)
|
||||
But, what if we want to fork *past* states of the graph?
|
||||
|
||||
config = {
|
||||
"configurable": {
|
||||
"thread_id": uuid.uuid4(),
|
||||
}
|
||||
}
|
||||
For example, let's say we want to edit a particular checkpoint, `xxx`.
|
||||
|
||||
for chunk in graph.stream({"state_counter": 1}, config):
|
||||
print(chunk)
|
||||
We pass this `checkpoint_id` when we update the state of the graph.
|
||||
|
||||
print('--- Resuming ---')
|
||||
```python
|
||||
config = {"configurable": {"thread_id": "1", "checkpoint_id": "xxx"}}
|
||||
graph.update_state(config, {"state": "updated state"}, )
|
||||
```
|
||||
|
||||
for chunk in graph.stream(Command(resume="35"), config):
|
||||
print(chunk)
|
||||
```
|
||||
This creates a new forked checkpoint, `xxx-fork`, which we can then run the graph from.
|
||||
|
||||
This will print out
|
||||
```python
|
||||
config = {'configurable': {'thread_id': '1', 'checkpoint_id': 'xxx-fork'}}
|
||||
for event in graph.stream(None, config, stream_mode="values"):
|
||||
print(event)
|
||||
```
|
||||
|
||||
```pycon
|
||||
--- First invocation ---
|
||||
In parent node: {'foo': 'bar'}
|
||||
Entered `parent_node` a total of 1 times
|
||||
Entered `node_in_subgraph` a total of 1 times
|
||||
Entered human_node in sub-graph a total of 1 times
|
||||
{'__interrupt__': (Interrupt(value='what is your name?', resumable=True, ns=['parent_node:0b23d72f-aaba-0329-1a59-ca4f3c8bad3b', 'human_node:25df717c-cb80-57b0-7410-44e20aac8f3c'], when='during'),)}
|
||||
See [this additional conceptual guide](https://langchain-ai.github.io/langgraph/concepts/persistence/#update-state) for related context on forking.
|
||||
|
||||
--- Resuming ---
|
||||
In parent node: {'foo': 'bar'}
|
||||
Entered `parent_node` a total of 2 times
|
||||
Entered human_node in sub-graph a total of 2 times
|
||||
Got an answer of 35
|
||||
{'parent_node': None}
|
||||
```
|
||||
|
||||
|
||||
|
||||
### Using multiple interrupts
|
||||
|
||||
Using multiple interrupts within a **single** node can be helpful for patterns like [validating human input](#validating-human-input). However, using multiple interrupts in the same node can lead to unexpected behavior if not handled carefully.
|
||||
|
||||
When a node contains multiple interrupt calls, LangGraph keeps a list of resume values specific to the task executing the node. Whenever execution resumes, it starts at the beginning of the node. For each interrupt encountered, LangGraph checks if a matching value exists in the task's resume list. Matching is **strictly index-based**, so the order of interrupt calls within the node is critical.
|
||||
|
||||
To avoid issues, refrain from dynamically changing the node's structure between executions. This includes adding, removing, or reordering interrupt calls, as such changes can result in mismatched indices. These problems often arise from unconventional patterns, such as mutating state via `Command(resume=..., update=SOME_STATE_MUTATION)` or relying on global variables to modify the node’s structure dynamically.
|
||||
|
||||
??? "Example of incorrect code"
|
||||
|
||||
```python
|
||||
import uuid
|
||||
from typing import TypedDict, Optional
|
||||
|
||||
from langgraph.graph import StateGraph
|
||||
from langgraph.constants import START
|
||||
from langgraph.types import interrupt, Command
|
||||
from langgraph.checkpoint.memory import MemorySaver
|
||||
|
||||
|
||||
class State(TypedDict):
|
||||
"""The graph state."""
|
||||
|
||||
age: Optional[str]
|
||||
name: Optional[str]
|
||||
|
||||
|
||||
def human_node(state: State):
|
||||
if not state.get('name'):
|
||||
name = interrupt("what is your name?")
|
||||
else:
|
||||
name = "N/A"
|
||||
|
||||
if not state.get('age'):
|
||||
age = interrupt("what is your age?")
|
||||
else:
|
||||
age = "N/A"
|
||||
|
||||
print(f"Name: {name}. Age: {age}")
|
||||
|
||||
return {
|
||||
"age": age,
|
||||
"name": name,
|
||||
}
|
||||
|
||||
|
||||
builder = StateGraph(State)
|
||||
builder.add_node("human_node", human_node)
|
||||
builder.add_edge(START, "human_node")
|
||||
|
||||
# A checkpointer must be enabled for interrupts to work!
|
||||
checkpointer = MemorySaver()
|
||||
graph = builder.compile(checkpointer=checkpointer)
|
||||
|
||||
config = {
|
||||
"configurable": {
|
||||
"thread_id": uuid.uuid4(),
|
||||
}
|
||||
}
|
||||
|
||||
for chunk in graph.stream({"age": None, "name": None}, config):
|
||||
print(chunk)
|
||||
|
||||
for chunk in graph.stream(Command(resume="John", update={"name": "foo"}), config):
|
||||
print(chunk)
|
||||
```
|
||||
|
||||
```pycon
|
||||
{'__interrupt__': (Interrupt(value='what is your name?', resumable=True, ns=['human_node:3a007ef9-c30d-c357-1ec1-86a1a70d8fba'], when='during'),)}
|
||||
Name: N/A. Age: John
|
||||
{'human_node': {'age': 'John', 'name': 'N/A'}}
|
||||
```
|
||||
|
||||
## Additional Resources 📚
|
||||
|
||||
- [**Conceptual Guide: Persistence**](persistence.md#replay): Read the persistence guide for more context on replaying.
|
||||
- [**How to Guides: Human-in-the-loop**](../how-tos/index.md#human-in-the-loop): Learn how to implement human-in-the-loop workflows in LangGraph.
|
||||
- [**How to implement multi-turn conversations**](../how-tos/multi-agent-multi-turn-convo.ipynb): Learn how to implement multi-turn conversations in LangGraph.
|
||||
See see [this guide](../how-tos/human_in_the_loop/time-travel.ipynb) for a detailed how-to on doing time-travel!
|
||||
|
Before Width: | Height: | Size: 92 KiB |
|
Before Width: | Height: | Size: 39 KiB |
|
Before Width: | Height: | Size: 41 KiB |
|
Before Width: | Height: | Size: 54 KiB |
@@ -24,15 +24,13 @@ The conceptual guide does not cover step-by-step instructions or specific implem
|
||||
- [LangGraph Glossary](low_level.md): LangGraph workflows are designed as graphs, with nodes representing different components and edges representing the flow of information between them. This guide provides an overview of the key concepts associated with LangGraph graph primitives.
|
||||
- [Common Agentic Patterns](agentic_concepts.md): An agent uses an LLM to pick its own control flow to solve more complex problems! Agents are a key building block in many LLM applications. This guide explains the different types of agent architectures and how they can be used to control the flow of an application.
|
||||
- [Multi-Agent Systems](multi_agent.md): Complex LLM applications can often be broken down into multiple agents, each responsible for a different part of the application. This guide explains common patterns for building multi-agent systems.
|
||||
- [Breakpoints](breakpoints.md): Breakpoints allow pausing the execution of a graph at specific points. Breakpoints allow stepping through graph execution for debugging purposes.
|
||||
- [Human-in-the-Loop](human_in_the_loop.md): Explains different ways of integrating human feedback into a LangGraph application.
|
||||
- [Time Travel](time-travel.md): Time travel allows you to replay past actions in your LangGraph application to explore alternative paths and debug issues.
|
||||
- [Persistence](persistence.md): LangGraph has a built-in persistence layer, implemented through checkpointers. This persistence layer helps to support powerful capabilities like human-in-the-loop, memory, time travel, and fault-tolerance.
|
||||
- [Memory](memory.md): Memory in AI applications refers to the ability to process, store, and effectively recall information from past interactions. With memory, your agents can learn from feedback and adapt to users' preferences.
|
||||
- [Streaming](streaming.md): Streaming is crucial for enhancing the responsiveness of applications built on LLMs. By displaying output progressively, even before a complete response is ready, streaming significantly improves user experience (UX), particularly when dealing with the latency of LLMs.
|
||||
- [FAQ](faq.md): Frequently asked questions about LangGraph.
|
||||
|
||||
## LangGraph Platform
|
||||
## LangGraph Platform
|
||||
|
||||
LangGraph Platform is a commercial solution for deploying agentic applications in production, built on the open-source LangGraph framework.
|
||||
|
||||
|
||||
@@ -33,11 +33,6 @@ The `langgraph build` command builds a Docker image for the [LangGraph API serve
|
||||
!!! note "New in version 0.1.55"
|
||||
The `langgraph dev` command was introduced in langgraph-cli version 0.1.55.
|
||||
|
||||
!!! note "Python only"
|
||||
|
||||
Currently, the CLI only supports Python >= 3.11.
|
||||
JS support is coming soon.
|
||||
|
||||
The `langgraph dev` command starts a lightweight development server that requires no Docker installation. This server is ideal for rapid development and testing, with features like:
|
||||
|
||||
- Hot reloading: Changes to your code are automatically detected and reloaded
|
||||
|
||||
@@ -14,25 +14,6 @@ A **deployment** is an instance of a LangGraph API. A single deployment can have
|
||||
|
||||
See the [how-to guide](../cloud/deployment/cloud.md#create-new-deployment) for creating a new deployment.
|
||||
|
||||
## Resource Allocation
|
||||
|
||||
| **Deployment Type** | **CPU** | **Memory** | **Scaling** |
|
||||
|---------------------|---------|------------|---------------------|
|
||||
| Development | 1 CPU | 1 GB | Up to 1 container |
|
||||
| Production | 1 CPU | 2 GB | Up to 10 containers |
|
||||
|
||||
## Autoscaling
|
||||
`Production` type deployments automatically scale up to 10 containers. Scaling is based on the current request load for a single container. Specifically, the autoscaling implementation scales the deployment so that each container is processing about 10 concurrent requests. For example...
|
||||
|
||||
- If the deployment is processing 20 concurrent requests, the deployment will scale up from 1 container to 2 containers (20 requests / 2 containers = 10 requests per container).
|
||||
- If a deployment of 2 containers is processing 10 requests, the deployment will scale down from 2 containers to 1 container (10 requests / 1 container = 10 requests per container).
|
||||
|
||||
10 concurrent requests per container is the target threshold. However, 10 concurrent requests per container is not a hard limit. The number of concurrent requests can exceed 10 if there is a sudden burst of requests.
|
||||
|
||||
Scale down actions are delayed for 30 minutes before any action is taken. In other words, if the autoscaling implementation decides to scale down a deployment, it will first wait for 30 minutes before scaling down. After 30 minutes, the concurrency metric is recomputed and the deployment will scale down if the concurrency metric has met the target threshold. Otherwise, the deployment remains scaled up. This "cool down" period ensures that deployments do not scale up and down too frequently.
|
||||
|
||||
In the future, the autoscaling implementation may evolve to accommodate other metrics such as background run queue size.
|
||||
|
||||
## Revision
|
||||
|
||||
A revision is an iteration of a [deployment](#deployment). When a new deployment is created, an initial revision is automatically created. To deploy new code changes or update environment variable configurations for a deployment, a new revision must be created. When a revision is created, a new container image is built automatically.
|
||||
@@ -43,12 +24,6 @@ See the [how-to guide](../cloud/deployment/cloud.md#create-new-revision) for cre
|
||||
|
||||
Infrastructure for [deployments](#deployment) and [revisions](#revision) are provisioned and deployed asynchronously. They are not deployed immediately after submission. Currently, deployment can take up to several minutes.
|
||||
|
||||
- When a new deployment is created, a new database is created for the deployment. Database creation is a one-time step. This step contributes to a longer deployment time for the initial revision of the deployment.
|
||||
- When a subsequent revision is created for a deployment, there is no database creation step. The deployment time for a subsequent revision is significantly faster compared to the deployment time of the initial revision.
|
||||
- The deployment process for each revision contains a build step, which can take up to a few minutes.
|
||||
|
||||
!!! info "Database creation for `Development` type deployments takes longer than database creation for `Production` type deployments."
|
||||
|
||||
## Architecture
|
||||
|
||||
!!! warning "Subject to Change"
|
||||
|
||||
@@ -18,7 +18,32 @@ The LangGraph Platform offers a few different deployment options described in th
|
||||
|
||||
## Why Use LangGraph Platform?
|
||||
|
||||
**LangGraph Platform** handles common issues that arise when deploying LLM applications to production, allowing you to focus on agent logic instead of managing server infrastructure.
|
||||
LangGraph Platform is designed to make deploying agentic applications seamless and production-ready.
|
||||
|
||||
For simpler applications, deploying a LangGraph agent can be as straightforward as using your own server logic—for example, setting up a FastAPI endpoint and invoking LangGraph directly.
|
||||
|
||||
### Option 1: Deploying with Custom Server Logic
|
||||
|
||||
For basic LangGraph applications, you may choose to handle deployment using your custom server infrastructure. Setting up endpoints with frameworks like [FastAPI](https://fastapi.tiangolo.com/) allows you to quickly deploy and run LangGraph as you would any other Python application:
|
||||
|
||||
```python
|
||||
from fastapi import FastAPI
|
||||
from your_agent_package import graph
|
||||
|
||||
app = FastAPI()
|
||||
|
||||
@app.get("/foo")
|
||||
async def foo(...):
|
||||
return await graph.ainvoke({...})
|
||||
```
|
||||
|
||||
This approach works well for simple applications with straightforward needs and provides you with full control over the deployment setup. For example, you might use this for a single-assistant application that doesn’t require long-running sessions or persistent memory.
|
||||
|
||||
### Option 2: Leveraging LangGraph Platform for Complex Deployments
|
||||
|
||||
As your applications scale or add complex features, the deployment requirements often evolve. Running an application with more nodes, longer processing times, or a need for persistent memory can introduce challenges that quickly become time-consuming and difficult to manage manually. [LangGraph Platform](./langgraph_platform.md) is built to handle these challenges seamlessly, allowing you to focus on agent logic rather than server infrastructure.
|
||||
|
||||
Here are some common issues that arise in complex deployments, which LangGraph Platform addresses:
|
||||
|
||||
- **[Streaming Support](streaming.md)**: As agents grow more sophisticated, they often benefit from streaming both token outputs and intermediate states back to the user. Without this, users are left waiting for potentially long operations with no feedback. LangGraph Server provides [multiple streaming modes](streaming.md) optimized for various application needs.
|
||||
|
||||
|
||||
@@ -283,9 +283,6 @@ You can optionally provide a dictionary that maps the `routing_function`'s outpu
|
||||
graph.add_conditional_edges("node_a", routing_function, {True: "node_b", False: "node_c"})
|
||||
```
|
||||
|
||||
!!! tip
|
||||
Use [`Command`](#command) instead of conditional edges if you want to combine state updates and routing in a single function.
|
||||
|
||||
### Entry Point
|
||||
|
||||
The entry point is the first node(s) that are run when the graph starts. You can use the [`add_edge`][langgraph.graph.StateGraph.add_edge] method from the virtual [`START`][langgraph.constants.START] node to the first node to execute to specify where to enter the graph.
|
||||
@@ -325,68 +322,6 @@ def continue_to_jokes(state: OverallState):
|
||||
graph.add_conditional_edges("node_a", continue_to_jokes)
|
||||
```
|
||||
|
||||
## `Command`
|
||||
|
||||
It can be useful to combine control flow (edges) and state updates (nodes). For example, you might want to BOTH perform state updates AND decide which node to go to next in the SAME node. LangGraph provides a way to do so by returning a [`Command`][langgraph.types.Command] object from node functions:
|
||||
|
||||
```python
|
||||
def my_node(state: State) -> Command[Literal["my_other_node"]]:
|
||||
return Command(
|
||||
# state update
|
||||
update={"foo": "bar"},
|
||||
# control flow
|
||||
goto="my_other_node"
|
||||
)
|
||||
```
|
||||
|
||||
With `Command` you can also achieve dynamic control flow behavior (identical to [conditional edges](#conditional-edges)):
|
||||
|
||||
```python
|
||||
def my_node(state: State) -> Command[Literal["my_other_node"]]:
|
||||
if state["foo"] == "bar":
|
||||
return Command(update={"foo": "baz"}, goto="my_other_node")
|
||||
```
|
||||
|
||||
!!! important
|
||||
|
||||
When returning `Command` in your node functions, you must add return type annotations with the list of node names the node is routing to, e.g. `Command[Literal["my_other_node"]]`. This is necessary for the graph rendering and tells LangGraph that `my_node` can navigate to `my_other_node`.
|
||||
|
||||
Check out this [how-to guide](../how-tos/command.ipynb) for an end-to-end example of how to use `Command`.
|
||||
|
||||
### When should I use Command instead of conditional edges?
|
||||
|
||||
Use `Command` when you need to **both** update the graph state **and** route to a different node. For example, when implementing [multi-agent handoffs](./multi_agent.md#handoffs) where it's important to route to a different agent and pass some information to that agent.
|
||||
|
||||
Use [conditional edges](#conditional-edges) to route between nodes conditionally without updating the state.
|
||||
|
||||
### Using inside tools
|
||||
|
||||
A common use case is updating graph state from inside a tool. For example, in a customer support application you might want to look up customer information based on their account number or ID in the beginning of the conversation. To update the graph state from the tool, you can return `Command(update={"my_custom_key": "foo", "messages": [...]})` from the tool:
|
||||
|
||||
```python
|
||||
@tool
|
||||
def lookup_user_info(tool_call_id: Annotated[str, InjectedToolCallId], config: RunnableConfig):
|
||||
"""Use this to look up user information to better assist them with their questions."""
|
||||
user_info = get_user_info(config.get("configurable", {}).get("user_id"))
|
||||
return Command(
|
||||
update={
|
||||
# update the state keys
|
||||
"user_info": user_info,
|
||||
# update the message history
|
||||
"messages": [ToolMessage("Successfully looked up user information", tool_call_id=tool_call_id)]
|
||||
}
|
||||
)
|
||||
```
|
||||
|
||||
!!! important
|
||||
You MUST include `messages` (or any state key used for the message history) in `Command.update` when returning `Command` from a tool and the list of messages in `messages` MUST contain a `ToolMessage`. This is necessary for the resulting message history to be valid (LLM providers require AI messages with tool calls to be followed by the tool result messages).
|
||||
|
||||
If you are using tools that update state via `Command`, we recommend using prebuilt [`ToolNode`][langgraph.prebuilt.tool_node.ToolNode] which automatically handles tools returning `Command` objects and propagates them to the graph state. If you're writing a custom node that calls tools, you would need to manually propagate `Command` objects returned by the tools as the update from node.
|
||||
|
||||
### Human-in-the-loop
|
||||
|
||||
`Command` is an important part of human-in-the-loop workflows: when using `interrupt()` to collect user input, `Command` is then used to supply the input and resume execution via `Command(resume="User input")`. Check out [this conceptual guide](./human_in_the_loop.md) for more information.
|
||||
|
||||
## Persistence
|
||||
|
||||
LangGraph provides built-in persistence for your agent's state using [checkpointers][langgraph.checkpoint.base.BaseCheckpointSaver]. Checkpointers save snapshots of the graph state at every superstep, allowing resumption at any time. This enables features like human-in-the-loop interactions, memory management, and fault-tolerance. You can even directly manipulate a graph's state after its execution using the
|
||||
@@ -452,32 +387,35 @@ graph.invoke(inputs, config={"recursion_limit": 5, "configurable":{"llm": "anthr
|
||||
|
||||
Read [this how-to](https://langchain-ai.github.io/langgraph/how-tos/recursion-limit/) to learn more about how the recursion limit works.
|
||||
|
||||
## `interrupt`
|
||||
|
||||
Use the [interrupt](../reference/types.md/#langgraph.types.interrupt) function to **pause** the graph at specific points to collect user input. The `interrupt` function surfaces interrupt information to the client, allowing the developer to collect user input, validate the graph state, or make decisions before resuming execution.
|
||||
|
||||
```python
|
||||
from langgraph.types import interrupt
|
||||
|
||||
def human_approval_node(state: State):
|
||||
...
|
||||
answer = interrupt(
|
||||
# This value will be sent to the client.
|
||||
# It can be any JSON serializable value.
|
||||
{"question": "is it ok to continue?"},
|
||||
)
|
||||
...
|
||||
```
|
||||
|
||||
Resuming the graph is done by passing a [`Command`](#command) object to the graph with the `resume` key set to the value returned by the `interrupt` function.
|
||||
|
||||
Read more about how the `interrupt` is used for **human-in-the-loop** workflows in the [Human-in-the-loop conceptual guide](./human_in_the_loop.md).
|
||||
|
||||
## Breakpoints
|
||||
|
||||
Breakpoints pause graph execution at specific points and enable stepping through execution step by step. Breakpoints are powered by LangGraph's [**persistence layer**](./persistence.md), which saves the state after each graph step. Breakpoints can also be used to enable [**human-in-the-loop**](./human_in_the_loop.md) workflows, though we recommend using the [`interrupt` function](#interrupt-function) for this purpose.
|
||||
It can often be useful to set breakpoints before or after certain nodes execute. This can be used to wait for human approval before continuing. These can be set when you ["compile" a graph](#compiling-your-graph). You can set breakpoints either _before_ a node executes (using `interrupt_before`) or after a node executes (using `interrupt_after`.)
|
||||
|
||||
Read more about breakpoints in the [Breakpoints conceptual guide](./breakpoints.md).
|
||||
You **MUST** use a [checkpointer](./persistence.md) when using breakpoints. This is because your graph needs to be able to resume execution.
|
||||
|
||||
In order to resume execution, you can just invoke your graph with `None` as the input.
|
||||
|
||||
```python
|
||||
# Initial run of graph
|
||||
graph.invoke(inputs, config=config)
|
||||
|
||||
# Let's assume it hit a breakpoint somewhere, you can then resume by passing in None
|
||||
graph.invoke(None, config=config)
|
||||
```
|
||||
|
||||
See [this guide](../how-tos/human_in_the_loop/breakpoints.ipynb) for a full walkthrough of how to add breakpoints.
|
||||
|
||||
### Dynamic Breakpoints
|
||||
|
||||
It may be helpful to **dynamically** interrupt the graph from inside a given node based on some condition. In `LangGraph` you can do so by using `NodeInterrupt` -- a special exception that can be raised from inside a node.
|
||||
|
||||
```python
|
||||
def my_node(state: State) -> State:
|
||||
if len(state['input']) > 5:
|
||||
raise NodeInterrupt(f"Received input that is longer than 5 characters: {state['input']}")
|
||||
|
||||
return state
|
||||
```
|
||||
|
||||
## Subgraphs
|
||||
|
||||
@@ -518,7 +456,7 @@ The simplest way to create subgraph nodes is by using a [compiled subgraph](#com
|
||||
If you pass extra keys to the subgraph node (i.e., in addition to the shared keys), they will be ignored by the subgraph node. Similarly, if you return extra keys from the subgraph, they will be ignored by the parent graph.
|
||||
|
||||
```python
|
||||
from langgraph.graph import StateGraph
|
||||
from langgraph.graph import START, StateGraph
|
||||
from typing import TypedDict
|
||||
|
||||
class State(TypedDict):
|
||||
|
||||
@@ -171,7 +171,7 @@ trim_messages(
|
||||
|
||||
## Long-term memory
|
||||
|
||||
Long-term memory in LangGraph allows systems to retain information across different conversations or sessions. Unlike short-term memory, which is **thread-scoped**, long-term memory is saved within custom "namespaces."
|
||||
Long-term memory in LangGraph allows systems to retain information across different conversations or sessions. Unlike short-term memory, which is thread-scoped, long-term memory is saved within custom "namespaces."
|
||||
|
||||
### Storing memories
|
||||
|
||||
@@ -180,34 +180,16 @@ LangGraph stores long-term memories as JSON documents in a [store](persistence.m
|
||||
```python
|
||||
from langgraph.store.memory import InMemoryStore
|
||||
|
||||
|
||||
def embed(texts: list[str]) -> list[list[float]]:
|
||||
# Replace with an actual embedding function or LangChain embeddings object
|
||||
return [[1.0, 2.0] * len(texts)]
|
||||
|
||||
|
||||
# InMemoryStore saves data to an in-memory dictionary. Use a DB-backed store in production use.
|
||||
store = InMemoryStore(index={"embed": embed, "dims": 2})
|
||||
store = InMemoryStore()
|
||||
user_id = "my-user"
|
||||
application_context = "chitchat"
|
||||
namespace = (user_id, application_context)
|
||||
store.put(
|
||||
namespace,
|
||||
"a-memory",
|
||||
{
|
||||
"rules": [
|
||||
"User likes short, direct language",
|
||||
"User only speaks English & python",
|
||||
],
|
||||
"my-key": "my-value",
|
||||
},
|
||||
)
|
||||
store.put(namespace, "a-memory", {"rules": ["User likes short, direct language", "User only speaks English & python"], "my-key": "my-value"})
|
||||
# get the "memory" by ID
|
||||
item = store.get(namespace, "a-memory")
|
||||
# search for "memories" within this namespace, filtering on content equivalence, sorted by vector similarity
|
||||
items = store.search(
|
||||
namespace, filter={"my-key": "my-value"}, query="language preferences"
|
||||
)
|
||||
# list "memories" within this namespace, filtering on content equivalence
|
||||
items = store.search(namespace, filter={"my-key": "my-value"})
|
||||
```
|
||||
|
||||
### Framework for thinking about long-term memory
|
||||
@@ -236,9 +218,6 @@ Different applications require various types of memory. Although the analogy isn
|
||||
|
||||
[Semantic memory](https://en.wikipedia.org/wiki/Semantic_memory), both in humans and AI agents, involves the retention of specific facts and concepts. In humans, it can include information learned in school and the understanding of concepts and their relationships. For AI agents, semantic memory is often used to personalize applications by remembering facts or concepts from past interactions.
|
||||
|
||||
> Note: Not to be confused with "semantic search" which is a technique for finding similar content using "meaning" (usually as embeddings). Semantic memory is a term from psychology, referring to storing facts and knowledge, while semantic search is a method for retrieving information based on meaning rather than exact matches.
|
||||
|
||||
|
||||
#### Profile
|
||||
|
||||
Semantic memories can be managed in different ways. For example, memories can be a single, continuously updated "profile" of well-scoped and specific information about a user, organization, or other entity (including the agent itself). A profile is generally just a JSON document with various key-value pairs you've selected to represent your domain.
|
||||
@@ -253,7 +232,7 @@ Alternatively, memories can be a collection of documents that are continuously u
|
||||
|
||||
However, this shifts some complexity memory updating. The model must now _delete_ or _update_ existing items in the list, which can be tricky. In addition, some models may default to over-inserting and others may default to over-updating. See the [Trustcall](https://github.com/hinthornw/trustcall) package for one way to manage this and consider evaluation (e.g., with a tool like [LangSmith](https://docs.smith.langchain.com/tutorials/Developers/evaluation)) to help you tune the behavior.
|
||||
|
||||
Working with document collections also shifts complexity to memory **search** over the list. The `Store` currently supports both [semantic search](https://langchain-ai.github.io/langgraph/reference/store/#langgraph.store.base.SearchOp.query) and [filtering by content](https://langchain-ai.github.io/langgraph/reference/store/#langgraph.store.base.SearchOp.filter).
|
||||
Working with document collections also shifts complexity to memory **search** over the list. The `Store` currently supports [filtering by metadata](https://langchain-ai.github.io/langgraph/reference/store/#storage) and will soon add [semantic search shortly](https://python.langchain.com/docs/concepts/vectorstores/), but selecting the most relevant documents can be tricky as the list grows.
|
||||
|
||||
Finally, using a collection of memories can make it challenging to provide comprehensive context to the model. While individual memories may follow a specific schema, this structure might not capture the full context or relationships between memories. As a result, when using these memories to generate responses, the model may lack important contextual information that would be more readily available in a unified profile approach.
|
||||
|
||||
|
||||
@@ -26,88 +26,18 @@ There are several ways to connect agents in a multi-agent system:
|
||||
- **Hierarchical**: you can define a multi-agent system with [a supervisor of supervisors](https://langchain-ai.github.io/langgraph/tutorials/multi_agent/hierarchical_agent_teams/). This is a generalization of the supervisor architecture and allows for more complex control flows.
|
||||
- **Custom multi-agent workflow**: each agent communicates with only a subset of agents. Parts of the flow are deterministic, and only some agents can decide which other agents to call next.
|
||||
|
||||
### Handoffs
|
||||
|
||||
In multi-agent architectures, agents can be represented as graph nodes. Each agent node executes its step(s) and decides whether to finish execution or route to another agent, including potentially routing to itself (e.g., running in a loop). A common pattern in multi-agent interactions is handoffs, where one agent hands off control to another. Handoffs allow you to specify:
|
||||
|
||||
- __destination__: target agent to navigate to (e.g., name of the node to go to)
|
||||
- __payload__: [information to pass to that agent](#communication-between-agents) (e.g., state update)
|
||||
|
||||
To implement handoffs in LangGraph, agent nodes can return [`Command`](./low_level.md#command) object that allows you to combine both control flow and state updates:
|
||||
|
||||
```python
|
||||
def agent(state) -> Command[Literal["agent", "another_agent"]]:
|
||||
# the condition for routing/halting can be anything, e.g. LLM tool call / structured output, etc.
|
||||
goto = get_next_agent(...) # 'agent' / 'another_agent'
|
||||
return Command(
|
||||
# Specify which agent to call next
|
||||
goto=goto,
|
||||
# Update the graph state
|
||||
update={"my_state_key": "my_state_value"}
|
||||
)
|
||||
```
|
||||
|
||||
In a more complex scenario where each agent node is itself a graph (i.e., a [subgraph](./low_level.md#subgraphs)), a node in one of the agent subgraphs might want to navigate to a different agent. For example, if you have two agents, `alice` and `bob` (subgraph nodes in a parent graph), and `alice` needs to navigate to `bob`, you can set `graph=Command.PARENT` in the `Command` object:
|
||||
|
||||
```python
|
||||
def some_node_inside_alice(state)
|
||||
return Command(
|
||||
goto="bob",
|
||||
update={"my_state_key": "my_state_value"},
|
||||
# specify which graph to navigate to (defaults to the current graph)
|
||||
graph=Command.PARENT,
|
||||
)
|
||||
```
|
||||
|
||||
!!! note
|
||||
If you need to support visualization for subgraphs communicating using `Command(graph=Command.PARENT)` you would need to wrap them in a node function with `Command` annotation, e.g. instead of this:
|
||||
|
||||
```python
|
||||
builder.add_node(alice)
|
||||
```
|
||||
|
||||
you would need to do this:
|
||||
|
||||
```python
|
||||
def call_alice(state) -> Command[Literal["bob"]]:
|
||||
return alice.invoke(state)
|
||||
|
||||
builder.add_node("alice", call_alice)
|
||||
```
|
||||
|
||||
#### Handoffs as tools
|
||||
|
||||
One of the most common agent types is a ReAct-style tool-calling agents. For those types of agents, a common pattern is wrapping a handoff in a tool call, e.g.:
|
||||
|
||||
```python
|
||||
def transfer_to_bob(state):
|
||||
"""Transfer to bob."""
|
||||
return Command(
|
||||
goto="bob",
|
||||
update={"my_state_key": "my_state_value"},
|
||||
graph=Command.PARENT,
|
||||
)
|
||||
```
|
||||
|
||||
This is a special case of updating the graph state from tools where in addition the state update, the control flow is included as well.
|
||||
|
||||
!!! important
|
||||
|
||||
If you want to use tools that return `Command`, you can either use prebuilt [`create_react_agent`][langgraph.prebuilt.chat_agent_executor.create_react_agent] / [`ToolNode`][langgraph.prebuilt.tool_node.ToolNode] components, or implement your own tool-executing node that collects `Command` objects returned by the tools and returns a list of them, e.g.:
|
||||
|
||||
```python
|
||||
def call_tools(state):
|
||||
...
|
||||
commands = [tools_by_name[tool_call["name"]].invoke(tool_call) for tool_call in tool_calls]
|
||||
return commands
|
||||
```
|
||||
|
||||
Let's now take a closer look at the different multi-agent architectures.
|
||||
|
||||
### Network
|
||||
|
||||
In this architecture, agents are defined as graph nodes. Each agent can communicate with every other agent (many-to-many connections) and can decide which agent to call next. This architecture is good for problems that do not have a clear hierarchy of agents or a specific sequence in which agents should be called.
|
||||
In this architecture, agents are defined as graph nodes. Each agent can communicate with every other agent (many-to-many connections) and can decide which agent to call next. While very flexible, this architecture doesn't scale well as the number of agents grows:
|
||||
|
||||
- hard to enforce which agent should be called next
|
||||
- hard to determine how much [information](#shared-message-list) should be passed between the agents
|
||||
|
||||
We recommend avoiding this architecture in production and using one of the below architectures instead.
|
||||
|
||||
### Supervisor
|
||||
|
||||
In this architecture, we define agents as nodes and add a supervisor node (LLM) that decides which agent nodes should be called next. We use [conditional edges](./low_level.md#conditional-edges) to route execution to the appropriate agent node based on supervisor's decision. This architecture also lends itself well to running multiple agents in parallel or using [map-reduce](../how-tos/map-reduce.ipynb) pattern.
|
||||
|
||||
```python
|
||||
from typing import Literal
|
||||
@@ -116,83 +46,39 @@ from langgraph.graph import StateGraph, MessagesState, START
|
||||
|
||||
model = ChatOpenAI()
|
||||
|
||||
def agent_1(state: MessagesState) -> Command[Literal["agent_2", "agent_3", END]]:
|
||||
class AgentState(MessagesState):
|
||||
next: Literal["agent_1", "agent_2", "__end__"]
|
||||
|
||||
def supervisor(state: AgentState):
|
||||
# you can pass relevant parts of the state to the LLM (e.g., state["messages"])
|
||||
# to determine which agent to call next. a common pattern is to call the model
|
||||
# with a structured output (e.g. force it to return an output with a "next_agent" field)
|
||||
response = model.invoke(...)
|
||||
# route to one of the agents or exit based on the LLM's decision
|
||||
# if the LLM returns "__end__", the graph will finish execution
|
||||
return Command(
|
||||
goto=response["next_agent"],
|
||||
update={"messages": [response["content"]]},
|
||||
)
|
||||
# the "next" key will be used by the conditional edges to route execution
|
||||
# to the appropriate agent
|
||||
return {"next": response["next_agent"]}
|
||||
|
||||
def agent_2(state: MessagesState) -> Command[Literal["agent_1", "agent_3", END]]:
|
||||
response = model.invoke(...)
|
||||
return Command(
|
||||
goto=response["next_agent"],
|
||||
update={"messages": [response["content"]]},
|
||||
)
|
||||
|
||||
def agent_3(state: MessagesState) -> Command[Literal["agent_1", "agent_2", END]]:
|
||||
...
|
||||
return Command(
|
||||
goto=response["next_agent"],
|
||||
update={"messages": [response["content"]]},
|
||||
)
|
||||
|
||||
builder = StateGraph(MessagesState)
|
||||
builder.add_node(agent_1)
|
||||
builder.add_node(agent_2)
|
||||
builder.add_node(agent_3)
|
||||
|
||||
builder.add_edge(START, "agent_1")
|
||||
network = builder.compile()
|
||||
```
|
||||
|
||||
### Supervisor
|
||||
|
||||
In this architecture, we define agents as nodes and add a supervisor node (LLM) that decides which agent nodes should be called next. We use [`Command`](./low_level.md#command) to route execution to the appropriate agent node based on supervisor's decision. This architecture also lends itself well to running multiple agents in parallel or using [map-reduce](../how-tos/map-reduce.ipynb) pattern.
|
||||
|
||||
```python
|
||||
from typing import Literal
|
||||
from langchain_openai import ChatOpenAI
|
||||
from langgraph.graph import StateGraph, MessagesState, START, END
|
||||
|
||||
model = ChatOpenAI()
|
||||
|
||||
def supervisor(state: MessagesState) -> Command[Literal["agent_1", "agent_2", END]]:
|
||||
# you can pass relevant parts of the state to the LLM (e.g., state["messages"])
|
||||
# to determine which agent to call next. a common pattern is to call the model
|
||||
# with a structured output (e.g. force it to return an output with a "next_agent" field)
|
||||
response = model.invoke(...)
|
||||
# route to one of the agents or exit based on the supervisor's decision
|
||||
# if the supervisor returns "__end__", the graph will finish execution
|
||||
return Command(goto=response["next_agent"])
|
||||
|
||||
def agent_1(state: MessagesState) -> Command[Literal["supervisor"]]:
|
||||
def agent_1(state: AgentState):
|
||||
# you can pass relevant parts of the state to the LLM (e.g., state["messages"])
|
||||
# and add any additional logic (different models, custom prompts, structured output, etc.)
|
||||
response = model.invoke(...)
|
||||
return Command(
|
||||
goto="supervisor",
|
||||
update={"messages": [response]},
|
||||
)
|
||||
return {"messages": [response]}
|
||||
|
||||
def agent_2(state: MessagesState) -> Command[Literal["supervisor"]]:
|
||||
def agent_2(state: AgentState):
|
||||
response = model.invoke(...)
|
||||
return Command(
|
||||
goto="supervisor",
|
||||
update={"messages": [response]},
|
||||
)
|
||||
return {"messages": [response]}
|
||||
|
||||
builder = StateGraph(MessagesState)
|
||||
builder = StateGraph(AgentState)
|
||||
builder.add_node(supervisor)
|
||||
builder.add_node(agent_1)
|
||||
builder.add_node(agent_2)
|
||||
|
||||
builder.add_edge(START, "supervisor")
|
||||
# route to one of the agents or exit based on the supervisor's decisiion
|
||||
# if the supervisor returns "__end__", the graph will finish execution
|
||||
builder.add_conditional_edges("supervisor", lambda state: state["next"])
|
||||
builder.add_edge("agent_1", "supervisor")
|
||||
builder.add_edge("agent_2", "supervisor")
|
||||
|
||||
supervisor = builder.compile()
|
||||
```
|
||||
@@ -240,29 +126,37 @@ To address this, you can design your system _hierarchically_. For example, you c
|
||||
```python
|
||||
from typing import Literal
|
||||
from langchain_openai import ChatOpenAI
|
||||
from langgraph.graph import StateGraph, MessagesState, START, END
|
||||
from langgraph.graph import StateGraph, MessagesState, START
|
||||
|
||||
model = ChatOpenAI()
|
||||
|
||||
# define team 1 (same as the single supervisor example above)
|
||||
class Team1State(MessagesState):
|
||||
next: Literal["team_1_agent_1", "team_1_agent_2", "__end__"]
|
||||
|
||||
def team_1_supervisor(state: MessagesState) -> Command[Literal["team_1_agent_1", "team_1_agent_2", END]]:
|
||||
def team_1_supervisor(state: Team1State):
|
||||
response = model.invoke(...)
|
||||
return Command(goto=response["next_agent"])
|
||||
return {"next": response["next_agent"]}
|
||||
|
||||
def team_1_agent_1(state: MessagesState) -> Command[Literal["team_1_supervisor"]]:
|
||||
def team_1_agent_1(state: Team1State):
|
||||
response = model.invoke(...)
|
||||
return Command(goto="team_1_supervisor", update={"messages": [response]})
|
||||
return {"messages": [response]}
|
||||
|
||||
def team_1_agent_2(state: MessagesState) -> Command[Literal["team_1_supervisor"]]:
|
||||
def team_1_agent_2(state: Team1State):
|
||||
response = model.invoke(...)
|
||||
return Command(goto="team_1_supervisor", update={"messages": [response]})
|
||||
return {"messages": [response]}
|
||||
|
||||
team_1_builder = StateGraph(Team1State)
|
||||
team_1_builder.add_node(team_1_supervisor)
|
||||
team_1_builder.add_node(team_1_agent_1)
|
||||
team_1_builder.add_node(team_1_agent_2)
|
||||
team_1_builder.add_edge(START, "team_1_supervisor")
|
||||
# route to one of the agents or exit based on the supervisor's decisiion
|
||||
# if the supervisor returns "__end__", the graph will finish execution
|
||||
team_1_builder.add_conditional_edges("team_1_supervisor", lambda state: state["next"])
|
||||
team_1_builder.add_edge("team_1_agent_1", "team_1_supervisor")
|
||||
team_1_builder.add_edge("team_1_agent_2", "team_1_supervisor")
|
||||
|
||||
team_1_graph = team_1_builder.compile()
|
||||
|
||||
# define team 2 (same as the single supervisor example above)
|
||||
@@ -285,22 +179,31 @@ team_2_graph = team_2_builder.compile()
|
||||
|
||||
# define top-level supervisor
|
||||
|
||||
builder = StateGraph(MessagesState)
|
||||
def top_level_supervisor(state: MessagesState):
|
||||
class TopLevelState(MessagesState):
|
||||
next: Literal["team_1", "team_2", "__end__"]
|
||||
|
||||
builder = StateGraph(TopLevelState)
|
||||
def top_level_supervisor(state: TopLevelState):
|
||||
# you can pass relevant parts of the state to the LLM (e.g., state["messages"])
|
||||
# to determine which team to call next. a common pattern is to call the model
|
||||
# with a structured output (e.g. force it to return an output with a "next_team" field)
|
||||
response = model.invoke(...)
|
||||
# route to one of the teams or exit based on the supervisor's decision
|
||||
# if the supervisor returns "__end__", the graph will finish execution
|
||||
return Command(goto=response["next_team"])
|
||||
# the "next" key will be used by the conditional edges to route execution
|
||||
# to the appropriate team
|
||||
return {"next": response["next_team"]}
|
||||
|
||||
builder = StateGraph(MessagesState)
|
||||
builder = StateGraph(TopLevelState)
|
||||
builder.add_node(top_level_supervisor)
|
||||
builder.add_node(team_1_graph)
|
||||
builder.add_node(team_2_graph)
|
||||
|
||||
builder.add_edge(START, "top_level_supervisor")
|
||||
# route to one of the teams or exit based on the supervisor's decision
|
||||
# if the top-level supervisor returns "__end__", the graph will finish execution
|
||||
builder.add_conditional_edges("top_level_supervisor", lambda state: state["next"])
|
||||
builder.add_edge("team_1_graph", "top_level_supervisor")
|
||||
builder.add_edge("team_2_graph", "top_level_supervisor")
|
||||
|
||||
graph = builder.compile()
|
||||
```
|
||||
|
||||
@@ -310,7 +213,7 @@ In this architecture we add individual agents as graph nodes and define the orde
|
||||
|
||||
- **Explicit control flow (normal edges)**: LangGraph allows you to explicitly define the control flow of your application (i.e. the sequence of how agents communicate) explicitly, via [normal graph edges](./low_level.md#normal-edges). This is the most deterministic variant of this architecture above — we always know which agent will be called next ahead of time.
|
||||
|
||||
- **Dynamic control flow (Command)**: in LangGraph you can allow LLMs to decide parts of your application control flow. This can be achieved by using [`Command`](./low_level.md#command). A special case of this is a [supervisor tool-calling](#supervisor-tool-calling) architecture. In that case, the tool-calling LLM powering the supervisor agent will make decisions about the order in which the tools (agents) are being called.
|
||||
- **Dynamic control flow (conditional edges)**: in LangGraph you can allow LLMs to decide parts of your application control flow. This can be achieved by using [conditional edges](./low_level.md#conditional-edges). A special case of this is a [supervisor tool-calling](#supervisor-tool-calling) architecture. In that case, the tool-calling LLM powering the supervisor agent will make decisions about the order in which the tools (agents) are being called.
|
||||
|
||||
```python
|
||||
from langchain_openai import ChatOpenAI
|
||||
|
||||
@@ -168,7 +168,7 @@ Importantly, LangGraph knows whether a particular checkpoint has been executed p
|
||||
|
||||
### Update state
|
||||
|
||||
In addition to re-playing the graph from specific `checkpoints`, we can also *edit* the graph state. We do this using `graph.update_state()`. This method accepts three different arguments:
|
||||
In addition to re-playing the graph from specific `checkpoints`, we can also *edit* the graph state. We do this using `graph.update_state()`. This method three different arguments:
|
||||
|
||||
#### `config`
|
||||
|
||||
@@ -218,16 +218,13 @@ The final thing you can optionally specify when calling `update_state` is `as_no
|
||||
|
||||
## Memory Store
|
||||
|
||||

|
||||

|
||||
|
||||
A [state schema](low_level.md#schema) specifies a set of keys that are populated as a graph is executed. As discussed above, state can be written by a checkpointer to a thread at each graph step, enabling state persistence.
|
||||
|
||||
But, what if we want to retain some information *across threads*? Consider the case of a chatbot where we want to retain specific information about the user across *all* chat conversations (e.g., threads) with that user!
|
||||
|
||||
With checkpointers alone, we cannot share information across threads. This motivates the need for the [`Store`](../reference/store.md#langgraph.store.base.BaseStore) interface. As an illustration, we can define an `InMemoryStore` to store information about a user across threads. We simply compile our graph with a checkpointer, as before, and with our new `in_memory_store` variable.
|
||||
|
||||
### Basic Usage
|
||||
But, what if we want to retrain some information *across threads*? Consider the case of a chatbot where we want to retain specific information about the user across *all* chat conversations (e.g., threads) with that user!
|
||||
|
||||
With checkpointers alone, we cannot share information across threads. This motivates the need for the `Store` interface. As an illustration, we can define an `InMemoryStore` to store information about a user across threads. We simply compile our graph with a checkpointer, as before, and will our new `in_memory_store`.
|
||||
First, let's showcase this in isolation without using LangGraph.
|
||||
|
||||
```python
|
||||
@@ -242,7 +239,7 @@ user_id = "1"
|
||||
namespace_for_memory = (user_id, "memories")
|
||||
```
|
||||
|
||||
We use the `store.put` method to save memories to our namespace in the store. When we do this, we specify the namespace, as defined above, and a key-value pair for the memory: the key is simply a unique identifier for the memory (`memory_id`) and the value (a dictionary) is the memory itself.
|
||||
We use the `store.put` to save memories to our namespace in the store. When we do this, we specify the namespace, as defined above, and a key-value pair for the memory: the key is simply a unique identifier for the memory (`memory_id`) and the value (a dictionary) is the memory itself.
|
||||
|
||||
```python
|
||||
memory_id = str(uuid.uuid4())
|
||||
@@ -250,7 +247,7 @@ memory = {"food_preference" : "I like pizza"}
|
||||
in_memory_store.put(namespace_for_memory, memory_id, memory)
|
||||
```
|
||||
|
||||
We can read out memories in our namespace using the `store.search` method, which will return all memories for a given user as a list. The most recent memory is the last in the list.
|
||||
We can read out memories in our namespace using `store.search`, which will return all memories for a given user as a list. The most recent memory is the last in the list.
|
||||
|
||||
```python
|
||||
memories = in_memory_store.search(namespace_for_memory)
|
||||
@@ -262,69 +259,16 @@ memories[-1].dict()
|
||||
'updated_at': '2024-10-02T17:22:31.590605+00:00'}
|
||||
```
|
||||
|
||||
Each memory type is a Python class ([`Item`](https://langchain-ai.github.io/langgraph/reference/store/#langgraph.store.base.Item)) with certain attributes. We can access it as a dictionary by converting via `.dict` as above.
|
||||
Each memory type is a Python class with certain attributes. We can access it as a dictionary by converting via `.dict` as above.
|
||||
The attributes it has are:
|
||||
|
||||
- `value`: The value (itself a dictionary) of this memory
|
||||
- `key`: A unique key for this memory in this namespace
|
||||
- `key`: The UUID for this memory in this namespace
|
||||
- `namespace`: A list of strings, the namespace of this memory type
|
||||
- `created_at`: Timestamp for when this memory was created
|
||||
- `updated_at`: Timestamp for when this memory was updated
|
||||
|
||||
### Semantic Search
|
||||
|
||||
Beyond simple retrieval, the store also supports semantic search, allowing you to find memories based on meaning rather than exact matches. To enable this, configure the store with an embedding model:
|
||||
|
||||
```python
|
||||
from langchain.embeddings import init_embeddings
|
||||
|
||||
store = InMemoryStore(
|
||||
index={
|
||||
"embed": init_embeddings("openai:text-embedding-3-small"), # Embedding provider
|
||||
"dims": 1536, # Embedding dimensions
|
||||
"fields": ["food_preference", "$"] # Fields to embed
|
||||
}
|
||||
)
|
||||
```
|
||||
|
||||
Now when searching, you can use natural language queries to find relevant memories:
|
||||
|
||||
```python
|
||||
# Find memories about food preferences
|
||||
# (This can be done after putting memories into the store)
|
||||
memories = store.search(
|
||||
namespace_for_memory,
|
||||
query="What does the user like to eat?",
|
||||
limit=3 # Return top 3 matches
|
||||
)
|
||||
```
|
||||
|
||||
You can control which parts of your memories get embedded by configuring the `fields` parameter or by specifying the `index` parameter when storing memories:
|
||||
|
||||
```python
|
||||
# Store with specific fields to embed
|
||||
store.put(
|
||||
namespace_for_memory,
|
||||
str(uuid.uuid4()),
|
||||
{
|
||||
"food_preference": "I love Italian cuisine",
|
||||
"context": "Discussing dinner plans"
|
||||
},
|
||||
index=["food_preference"] # Only embed "food_preferences" field
|
||||
)
|
||||
|
||||
# Store without embedding (still retrievable, but not searchable)
|
||||
store.put(
|
||||
namespace_for_memory,
|
||||
str(uuid.uuid4()),
|
||||
{"system_info": "Last updated: 2024-01-01"},
|
||||
index=False
|
||||
)
|
||||
```
|
||||
|
||||
### Using in LangGraph
|
||||
|
||||
With this all in place, we use the `in_memory_store` in LangGraph. The `in_memory_store` works hand-in-hand with the checkpointer: the checkpointer saves state to threads, as discussed above, and the `in_memory_store` allows us to store arbitrary information for access *across* threads. We compile the graph with both the checkpointer and the `in_memory_store` as follows.
|
||||
With this all in place, we use the `in_memory_store` in LangGraph. The `in_memory_store` works hand-in-hand with the checkpointer: the checkpointer saves state to threads, as discussed above, and the the `in_memory_store` allows us to store arbitrary information for access *across* threads. We compile the graph with both the checkpointer and the `in_memory_store` as follows.
|
||||
|
||||
```python
|
||||
from langgraph.checkpoint.memory import MemorySaver
|
||||
@@ -352,7 +296,7 @@ for update in graph.stream(
|
||||
print(update)
|
||||
```
|
||||
|
||||
We can access the `in_memory_store` and the `user_id` in *any node* by passing `store: BaseStore` and `config: RunnableConfig` as node arguments. Here's how we might use semantic search in a node to find relevant memories:
|
||||
We can access the `in_memory_store` and the `user_id` in *any node* by passing `store: BaseStore` and `config: RunnableConfig` as node arguments. Just as we saw above, simply use the `put` method to save memories to the store.
|
||||
|
||||
```python
|
||||
def update_memory(state: MessagesState, config: RunnableConfig, *, store: BaseStore):
|
||||
@@ -373,7 +317,7 @@ def update_memory(state: MessagesState, config: RunnableConfig, *, store: BaseSt
|
||||
|
||||
```
|
||||
|
||||
As we showed above, we can also access the store in any node and use the `store.search` method to get memories. Recall the the memories are returned as a list of objects that can be converted to a dictionary.
|
||||
As we showed above, we can also access the store in any node and use `search` to get memories. Recall the the memories are returned as a list of objects that can be converted to a dictionary.
|
||||
|
||||
```python
|
||||
memories[-1].dict()
|
||||
@@ -388,15 +332,12 @@ We can access the memories and use them in our model call.
|
||||
|
||||
```python
|
||||
def call_model(state: MessagesState, config: RunnableConfig, *, store: BaseStore):
|
||||
|
||||
# Get the user id from the config
|
||||
user_id = config["configurable"]["user_id"]
|
||||
|
||||
# Search based on the most recent message
|
||||
memories = store.search(
|
||||
namespace,
|
||||
query=state["messages"][-1].content,
|
||||
limit=3
|
||||
)
|
||||
# Get the memories for the user from the store
|
||||
memories = store.search(("memories", user_id))
|
||||
info = "\n".join([d.value["memory"] for d in memories])
|
||||
|
||||
# ... Use memories in the model call
|
||||
@@ -415,22 +356,7 @@ for update in graph.stream(
|
||||
print(update)
|
||||
```
|
||||
|
||||
When we use the LangGraph Platform, either locally (e.g., in LangGraph Studio) or with LangGraph Cloud, the base store is available to use by default and does not need to be specified during graph compilation. To enable semantic search, however, you **do** need to configure the indexing settings in your `langgraph.json` file. For example:
|
||||
|
||||
```json
|
||||
{
|
||||
...
|
||||
"store": {
|
||||
"index": {
|
||||
"embed": "openai:text-embeddings-3-small",
|
||||
"dims": 1536,
|
||||
"fields": ["$"]
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
See the [deployment guide](../cloud/deployment/semantic_search.md) for more details and configuration options.
|
||||
When we use the LangGraph API, either locally (e.g., in LangGraph Studio) or with LangGraph Cloud, the memory store is available to use by default and does not need to be specified during graph compilation.
|
||||
|
||||
## Checkpointer libraries
|
||||
|
||||
@@ -471,7 +397,7 @@ Second, checkpointers allow for ["memory"](agentic_concepts.md#memory) between i
|
||||
|
||||
### Time Travel
|
||||
|
||||
Third, checkpointers allow for ["time travel"](time-travel.md), allowing users to replay prior graph executions to review and / or debug specific graph steps. In addition, checkpointers make it possible to fork the graph state at arbitrary checkpoints to explore alternative trajectories.
|
||||
Third, checkpointers allow for ["time travel"](../how-tos/human_in_the_loop/time-travel.ipynb), allowing users to replay prior graph executions to review and / or debug specific graph steps. In addition, checkpointers make it possible to fork the graph state at arbitrary checkpoints to explore alternative trajectories.
|
||||
|
||||
### Fault-tolerance
|
||||
|
||||
@@ -479,4 +405,4 @@ Lastly, checkpointing also provides fault-tolerance and error recovery: if one o
|
||||
|
||||
#### Pending writes
|
||||
|
||||
Additionally, when a graph node fails mid-execution at a given superstep, LangGraph stores pending checkpoint writes from any other nodes that completed successfully at that superstep, so that whenever we resume graph execution from that superstep we don't re-run the successful nodes.
|
||||
Additionally, when a graph node fails mid-execution at a given superstep, LangGraph stores pending checkpoint writes from any other nodes that completed successfully at that superstep, so that whenever we resume graph execution from that superstep we don't re-run the successful nodes.
|
||||
@@ -7,7 +7,7 @@
|
||||
|
||||
## Versions
|
||||
|
||||
There are two versions of the self-hosted deployment: [Self-Hosted Enterprise](./deployment_options.md#self-hosted-enterprise) and [Self-Hosted Lite](./deployment_options.md#self-hosted-lite).
|
||||
There are two versions of the self hosted deployment: [Self-Hosted Enterprise](./deployment_options.md#self-hosted-enterprise) and [Self-Hosted Lite](./deployment_options.md#self-hosted-lite).
|
||||
|
||||
### Self-Hosted Lite
|
||||
|
||||
@@ -34,10 +34,6 @@ To use the Self-Hosted Enterprise version, you must acquire a license key that y
|
||||
|
||||
For step-by-step instructions, see [How to set up a self-hosted deployment of LangGraph](../how-tos/deploy-self-hosted.md).
|
||||
|
||||
## Helm Chart
|
||||
|
||||
If you would like to deploy LangGraph Cloud on Kubernetes, you can use this [Helm chart](https://github.com/langchain-ai/helm/blob/main/charts/langgraph-cloud/README.md).
|
||||
|
||||
## Related
|
||||
|
||||
- [How to set up a self-hosted deployment of LangGraph](../how-tos/deploy-self-hosted.md).
|
||||
@@ -1,21 +1,14 @@
|
||||
# Template Applications
|
||||
|
||||
!!! note Prerequisites
|
||||
|
||||
- [LangGraph Studio](./langgraph_studio.md)
|
||||
|
||||
Templates are open source reference applications designed to help you get started quickly when building with LangGraph. They provide working examples of common agentic workflows that can be customized to your needs.
|
||||
|
||||
You can create an application from a template using the LangGraph CLI.
|
||||
Templates can be accessed via [LangGraph Studio (macOS only)](langgraph_studio.md), or cloned directly from Github. You can download LangGraph Studio and see available templates [here](https://studio.langchain.com/).
|
||||
|
||||
!!! info "Requirements"
|
||||
|
||||
- Python >= 3.11
|
||||
- [LangGraph CLI](https://langchain-ai.github.io/langgraph/cloud/reference/cli/): Requires langchain-cli[inmem] >= 0.1.58
|
||||
|
||||
## Install the LangGraph CLI
|
||||
|
||||
```bash
|
||||
pip install "langgraph-cli[inmem]" --upgrade
|
||||
```
|
||||
|
||||
## Available Templates
|
||||
## Available templates
|
||||
|
||||
| Template | Description | Python | JS/TS |
|
||||
|---------------------------|------------------------------------------------------------------------------------------|------------------------------------------------------------------|---------------------------------------------------------------------|
|
||||
@@ -24,39 +17,3 @@ pip install "langgraph-cli[inmem]" --upgrade
|
||||
| **Memory Agent** | A ReAct-style agent with an additional tool to store memories for use across threads. | [Repo](https://github.com/langchain-ai/memory-agent) | [Repo](https://github.com/langchain-ai/memory-agent-js) |
|
||||
| **Retrieval Agent** | An agent that includes a retrieval-based question-answering system. | [Repo](https://github.com/langchain-ai/retrieval-agent-template) | [Repo](https://github.com/langchain-ai/retrieval-agent-template-js) |
|
||||
| **Data-Enrichment Agent** | An agent that performs web searches and organizes its findings into a structured format. | [Repo](https://github.com/langchain-ai/data-enrichment) | [Repo](https://github.com/langchain-ai/data-enrichment-js) |
|
||||
|
||||
|
||||
## 🌱 Create a LangGraph App
|
||||
|
||||
To create a new app from a template, use the `langgraph new` command.
|
||||
|
||||
```bash
|
||||
langgraph new
|
||||
```
|
||||
|
||||
## Next Steps
|
||||
|
||||
Review the `README.md` file in the root of your new LangGraph app for more information about the template and how to customize it.
|
||||
|
||||
After configuring the app properly and adding your API keys, you can start the app using the LangGraph CLI:
|
||||
|
||||
```bash
|
||||
langgraph dev
|
||||
```
|
||||
|
||||
See the following guides for more information on how to deploy your app:
|
||||
|
||||
- **[Launch Local LangGraph Server](../tutorials/langgraph-platform/local-server.md)**: This quick start guide shows how to start a LangGraph Server locally for the **ReAct Agent** template. The steps are similar for other templates.
|
||||
- **[Deploy to LangGraph Cloud](../cloud/quick_start.md)**: Deploy your LangGraph app using LangGraph Cloud.
|
||||
|
||||
### LangGraph Framework
|
||||
|
||||
- **[LangGraph Concepts](../concepts/index.md)**: Learn the foundational concepts of LangGraph.
|
||||
- **[LangGraph How-to Guides](../how-tos/index.md)**: Guides for common tasks with LangGraph.
|
||||
|
||||
### 📚 Learn More about LangGraph Platform
|
||||
|
||||
Expand your knowledge with these resources:
|
||||
|
||||
- **[LangGraph Platform Concepts](../concepts/index.md#langgraph-platform)**: Understand the foundational concepts of the LangGraph Platform.
|
||||
- **[LangGraph Platform How-to Guides](../how-tos/index.md#langgraph-platform)**: Discover step-by-step guides to build and deploy applications.
|
||||
@@ -1,72 +0,0 @@
|
||||
# Time Travel ⏱️
|
||||
|
||||
!!! note "Prerequisites"
|
||||
|
||||
This guide assumes that you are familiar with LangGraph's checkpoints and states. If not, please review the [persistence](./persistence.md) concept first.
|
||||
|
||||
|
||||
When working with non-deterministic systems that make model-based decisions (e.g., agents powered by LLMs), it can be useful to examine their decision-making process in detail:
|
||||
|
||||
1. 🤔 **Understand Reasoning**: Analyze the steps that led to a successful result.
|
||||
2. 🐞 **Debug Mistakes**: Identify where and why errors occurred.
|
||||
3. 🔍 **Explore Alternatives**: Test different paths to uncover better solutions.
|
||||
|
||||
We call these debugging techniques **Time Travel**, composed of two key actions: [**Replaying**](#replaying) 🔁 and [**Forking**](#forking) 🔀 .
|
||||
|
||||
## Replaying
|
||||
|
||||

|
||||
|
||||
Replaying allows us to revisit and reproduce an agent's past actions. This can be done either from the current state (or checkpoint) of the graph or from a specific checkpoint.
|
||||
|
||||
To replay from the current state, simply pass `None` as the input along with a `thread`:
|
||||
|
||||
```python
|
||||
thread = {"configurable": {"thread_id": "1"}}
|
||||
for event in graph.stream(None, thread, stream_mode="values"):
|
||||
print(event)
|
||||
```
|
||||
|
||||
To replay actions from a specific checkpoint, start by retrieving all checkpoints for the thread:
|
||||
|
||||
```python
|
||||
all_checkpoints = []
|
||||
for state in graph.get_state_history(thread):
|
||||
all_checkpoints.append(state)
|
||||
```
|
||||
|
||||
Each checkpoint has a unique ID. After identifying the desired checkpoint, for instance, `xyz`, include its ID in the configuration:
|
||||
|
||||
```python
|
||||
config = {'configurable': {'thread_id': '1', 'checkpoint_id': 'xyz'}}
|
||||
for event in graph.stream(None, config, stream_mode="values"):
|
||||
print(event)
|
||||
```
|
||||
|
||||
The graph efficiently replays previously executed nodes instead of re-executing them, leveraging its awareness of prior checkpoint executions.
|
||||
|
||||
## Forking
|
||||
|
||||

|
||||
|
||||
Forking allows you to revisit an agent's past actions and explore alternative paths within the graph.
|
||||
|
||||
To edit a specific checkpoint, such as `xyz`, provide its `checkpoint_id` when updating the graph's state:
|
||||
|
||||
```python
|
||||
config = {"configurable": {"thread_id": "1", "checkpoint_id": "xyz"}}
|
||||
graph.update_state(config, {"state": "updated state"})
|
||||
```
|
||||
|
||||
This creates a new forked checkpoint, xyz-fork, from which you can continue running the graph:
|
||||
|
||||
```python
|
||||
config = {'configurable': {'thread_id': '1', 'checkpoint_id': 'xyz-fork'}}
|
||||
for event in graph.stream(None, config, stream_mode="values"):
|
||||
print(event)
|
||||
```
|
||||
|
||||
## Additional Resources 📚
|
||||
|
||||
- [**Conceptual Guide: Persistence**](https://langchain-ai.github.io/langgraph/concepts/persistence/#replay): Read the persistence guide for more context on replaying.
|
||||
- [**How to View and Update Past Graph State**](../how-tos/human_in_the_loop/time-travel.ipynb): Step-by-step instructions for working with graph state that demonstrate the **replay** and **fork** actions.
|
||||
@@ -1,329 +0,0 @@
|
||||
# Human-in-the-loop
|
||||
|
||||
!!! note "Use the `interrupt` function instead."
|
||||
|
||||
As of LangGraph 0.2.57, the recommended way to set breakpoints is using the [`interrupt` function][langgraph.types.interrupt] as it simplifies **human-in-the-loop** patterns.
|
||||
|
||||
Please see the revised [human-in-the-loop guide](./human_in_the_loop.md) for the latest version that uses the `interrupt` function.
|
||||
|
||||
|
||||
Human-in-the-loop (or "on-the-loop") enhances agent capabilities through several common user interaction patterns.
|
||||
|
||||
Common interaction patterns include:
|
||||
|
||||
(1) `Approval` - We can interrupt our agent, surface the current state to a user, and allow the user to accept an action.
|
||||
|
||||
(2) `Editing` - We can interrupt our agent, surface the current state to a user, and allow the user to edit the agent state.
|
||||
|
||||
(3) `Input` - We can explicitly create a graph node to collect human input and pass that input directly to the agent state.
|
||||
|
||||
Use-cases for these interaction patterns include:
|
||||
|
||||
(1) `Reviewing tool calls` - We can interrupt an agent to review and edit the results of tool calls.
|
||||
|
||||
(2) `Time Travel` - We can manually re-play and / or fork past actions of an agent.
|
||||
|
||||
## Persistence
|
||||
|
||||
All of these interaction patterns are enabled by LangGraph's built-in [persistence](./persistence.md) layer, which will write a checkpoint of the graph state at each step. Persistence allows the graph to stop so that a human can review and / or edit the current state of the graph and then resume with the human's input.
|
||||
|
||||
### Breakpoints
|
||||
|
||||
Adding a [breakpoint](./breakpoints.md) a specific location in the graph flow is one way to enable human-in-the-loop. In this case, the developer knows *where* in the workflow human input is needed and simply places a breakpoint prior to or following that particular graph node.
|
||||
|
||||
Here, we compile our graph with a checkpointer and a breakpoint at the node we want to interrupt before, `step_for_human_in_the_loop`. We then perform one of the above interaction patterns, which will create a new checkpoint if a human edits the graph state. The new checkpoint is saved to the `thread` and we can resume the graph execution from there by passing in `None` as the input.
|
||||
|
||||
```python
|
||||
# Compile our graph with a checkpointer and a breakpoint before "step_for_human_in_the_loop"
|
||||
graph = builder.compile(checkpointer=checkpointer, interrupt_before=["step_for_human_in_the_loop"])
|
||||
|
||||
# Run the graph up to the breakpoint
|
||||
thread_config = {"configurable": {"thread_id": "1"}}
|
||||
for event in graph.stream(inputs, thread_config, stream_mode="values"):
|
||||
print(event)
|
||||
|
||||
# Perform some action that requires human in the loop
|
||||
|
||||
# Continue the graph execution from the current checkpoint
|
||||
for event in graph.stream(None, thread_config, stream_mode="values"):
|
||||
print(event)
|
||||
```
|
||||
|
||||
### Dynamic Breakpoints
|
||||
|
||||
Alternatively, the developer can define some *condition* that must be met for a breakpoint to be triggered. This concept of [dynamic breakpoints](./breakpoints.md) is useful when the developer wants to halt the graph under *a particular condition*. This uses a `NodeInterrupt`, which is a special type of exception that can be raised from within a node based upon some condition. As an example, we can define a dynamic breakpoint that triggers when the `input` is longer than 5 characters.
|
||||
|
||||
```python
|
||||
def my_node(state: State) -> State:
|
||||
if len(state['input']) > 5:
|
||||
raise NodeInterrupt(f"Received input that is longer than 5 characters: {state['input']}")
|
||||
return state
|
||||
```
|
||||
|
||||
Let's assume we run the graph with an input that triggers the dynamic breakpoint and then attempt to resume the graph execution simply by passing in `None` for the input.
|
||||
|
||||
```python
|
||||
# Attempt to continue the graph execution with no change to state after we hit the dynamic breakpoint
|
||||
for event in graph.stream(None, thread_config, stream_mode="values"):
|
||||
print(event)
|
||||
```
|
||||
|
||||
The graph will *interrupt* again because this node will be *re-run* with the same graph state. We need to change the graph state such that the condition that triggers the dynamic breakpoint is no longer met. So, we can simply edit the graph state to an input that meets the condition of our dynamic breakpoint (< 5 characters) and re-run the node.
|
||||
|
||||
```python
|
||||
# Update the state to pass the dynamic breakpoint
|
||||
graph.update_state(config=thread_config, values={"input": "foo"})
|
||||
for event in graph.stream(None, thread_config, stream_mode="values"):
|
||||
print(event)
|
||||
```
|
||||
|
||||
Alternatively, what if we want to keep our current input and skip the node (`my_node`) that performs the check? To do this, we can simply perform the graph update with `as_node="my_node"` and pass in `None` for the values. This will make no update the graph state, but run the update as `my_node`, effectively skipping the node and bypassing the dynamic breakpoint.
|
||||
|
||||
```python
|
||||
# This update will skip the node `my_node` altogether
|
||||
graph.update_state(config=thread_config, values=None, as_node="my_node")
|
||||
for event in graph.stream(None, thread_config, stream_mode="values"):
|
||||
print(event)
|
||||
```
|
||||
|
||||
See [our guide](../how-tos/human_in_the_loop/dynamic_breakpoints.ipynb) for a detailed how-to on doing this!
|
||||
|
||||
## Interaction Patterns
|
||||
|
||||
### Approval
|
||||
|
||||

|
||||
|
||||
Sometimes we want to approve certain steps in our agent's execution.
|
||||
|
||||
We can interrupt our agent at a [breakpoint](./breakpoints.md) prior to the step that we want to approve.
|
||||
|
||||
This is generally recommend for sensitive actions (e.g., using external APIs or writing to a database).
|
||||
|
||||
With persistence, we can surface the current agent state as well as the next step to a user for review and approval.
|
||||
|
||||
If approved, the graph resumes execution from the last saved checkpoint, which is saved to the `thread`:
|
||||
|
||||
```python
|
||||
# Compile our graph with a checkpointer and a breakpoint before the step to approve
|
||||
graph = builder.compile(checkpointer=checkpointer, interrupt_before=["node_2"])
|
||||
|
||||
# Run the graph up to the breakpoint
|
||||
for event in graph.stream(inputs, thread, stream_mode="values"):
|
||||
print(event)
|
||||
|
||||
# ... Get human approval ...
|
||||
|
||||
# If approved, continue the graph execution from the last saved checkpoint
|
||||
for event in graph.stream(None, thread, stream_mode="values"):
|
||||
print(event)
|
||||
```
|
||||
|
||||
See [our guide](../how-tos/human_in_the_loop/breakpoints.ipynb) for a detailed how-to on doing this!
|
||||
|
||||
### Editing
|
||||
|
||||

|
||||
|
||||
Sometimes we want to review and edit the agent's state.
|
||||
|
||||
As with approval, we can interrupt our agent at a [breakpoint](./breakpoints.md) prior to the step we want to check.
|
||||
|
||||
We can surface the current state to a user and allow the user to edit the agent state.
|
||||
|
||||
This can, for example, be used to correct the agent if it made a mistake (e.g., see the section on tool calling below).
|
||||
|
||||
We can edit the graph state by forking the current checkpoint, which is saved to the `thread`.
|
||||
|
||||
We can then proceed with the graph from our forked checkpoint as done before.
|
||||
|
||||
```python
|
||||
# Compile our graph with a checkpointer and a breakpoint before the step to review
|
||||
graph = builder.compile(checkpointer=checkpointer, interrupt_before=["node_2"])
|
||||
|
||||
# Run the graph up to the breakpoint
|
||||
for event in graph.stream(inputs, thread, stream_mode="values"):
|
||||
print(event)
|
||||
|
||||
# Review the state, decide to edit it, and create a forked checkpoint with the new state
|
||||
graph.update_state(thread, {"state": "new state"})
|
||||
|
||||
# Continue the graph execution from the forked checkpoint
|
||||
for event in graph.stream(None, thread, stream_mode="values"):
|
||||
print(event)
|
||||
```
|
||||
|
||||
See [this guide](../how-tos/human_in_the_loop/edit-graph-state.ipynb) for a detailed how-to on doing this!
|
||||
|
||||
### Input
|
||||
|
||||

|
||||
|
||||
Sometimes we want to explicitly get human input at a particular step in the graph.
|
||||
|
||||
We can create a graph node designated for this (e.g., `human_input` in our example diagram).
|
||||
|
||||
As with approval and editing, we can interrupt our agent at a [breakpoint](./breakpoints.md) prior to this node.
|
||||
|
||||
We can then perform a state update that includes the human input, just as we did with editing state.
|
||||
|
||||
But, we add one thing:
|
||||
|
||||
We can use `as_node=human_input` with the state update to specify that the state update *should be treated as a node*.
|
||||
|
||||
The is subtle, but important:
|
||||
|
||||
With editing, the user makes a decision about whether or not to edit the graph state.
|
||||
|
||||
With input, we explicitly define a node in our graph for collecting human input!
|
||||
|
||||
The state update with the human input then runs *as this node*.
|
||||
|
||||
```python
|
||||
# Compile our graph with a checkpointer and a breakpoint before the step to to collect human input
|
||||
graph = builder.compile(checkpointer=checkpointer, interrupt_before=["human_input"])
|
||||
|
||||
# Run the graph up to the breakpoint
|
||||
for event in graph.stream(inputs, thread, stream_mode="values"):
|
||||
print(event)
|
||||
|
||||
# Update the state with the user input as if it was the human_input node
|
||||
graph.update_state(thread, {"user_input": user_input}, as_node="human_input")
|
||||
|
||||
# Continue the graph execution from the checkpoint created by the human_input node
|
||||
for event in graph.stream(None, thread, stream_mode="values"):
|
||||
print(event)
|
||||
```
|
||||
|
||||
See [this guide](../how-tos/human_in_the_loop/wait-user-input.ipynb) for a detailed how-to on doing this!
|
||||
|
||||
## Use-cases
|
||||
|
||||
### Reviewing Tool Calls
|
||||
|
||||
Some user interaction patterns combine the above ideas.
|
||||
|
||||
For example, many agents use [tool calling](https://python.langchain.com/docs/how_to/tool_calling/) to make decisions.
|
||||
|
||||
Tool calling presents a challenge because the agent must get two things right:
|
||||
|
||||
(1) The name of the tool to call
|
||||
|
||||
(2) The arguments to pass to the tool
|
||||
|
||||
Even if the tool call is correct, we may also want to apply discretion:
|
||||
|
||||
(3) The tool call may be a sensitive operation that we want to approve
|
||||
|
||||
With these points in mind, we can combine the above ideas to create a human-in-the-loop review of a tool call.
|
||||
|
||||
```python
|
||||
# Compile our graph with a checkpointer and a breakpoint before the step to to review the tool call from the LLM
|
||||
graph = builder.compile(checkpointer=checkpointer, interrupt_before=["human_review"])
|
||||
|
||||
# Run the graph up to the breakpoint
|
||||
for event in graph.stream(inputs, thread, stream_mode="values"):
|
||||
print(event)
|
||||
|
||||
# Review the tool call and update it, if needed, as the human_review node
|
||||
graph.update_state(thread, {"tool_call": "updated tool call"}, as_node="human_review")
|
||||
|
||||
# Otherwise, approve the tool call and proceed with the graph execution with no edits
|
||||
|
||||
# Continue the graph execution from either:
|
||||
# (1) the forked checkpoint created by human_review or
|
||||
# (2) the checkpoint saved when the tool call was originally made (no edits in human_review)
|
||||
for event in graph.stream(None, thread, stream_mode="values"):
|
||||
print(event)
|
||||
```
|
||||
|
||||
See [this guide](../how-tos/human_in_the_loop/review-tool-calls.ipynb) for a detailed how-to on doing this!
|
||||
|
||||
### Time Travel
|
||||
|
||||
When working with agents, we often want closely examine their decision making process:
|
||||
|
||||
(1) Even when they arrive a desired final result, the reasoning that led to that result is often important to examine.
|
||||
|
||||
(2) When agents make mistakes, it is often valuable to understand why.
|
||||
|
||||
(3) In either of the above cases, it is useful to manually explore alternative decision making paths.
|
||||
|
||||
Collectively, we call these debugging concepts `time-travel` and they are composed of `replaying` and `forking`.
|
||||
|
||||
#### Replaying
|
||||
|
||||

|
||||
|
||||
Sometimes we want to simply replay past actions of an agent.
|
||||
|
||||
Above, we showed the case of executing an agent from the current state (or checkpoint) of the graph.
|
||||
|
||||
We by simply passing in `None` for the input with a `thread`.
|
||||
|
||||
```
|
||||
thread = {"configurable": {"thread_id": "1"}}
|
||||
for event in graph.stream(None, thread, stream_mode="values"):
|
||||
print(event)
|
||||
```
|
||||
|
||||
Now, we can modify this to replay past actions from a *specific* checkpoint by passing in the checkpoint ID.
|
||||
|
||||
To get a specific checkpoint ID, we can easily get all of the checkpoints in the thread and filter to the one we want.
|
||||
|
||||
```python
|
||||
all_checkpoints = []
|
||||
for state in app.get_state_history(thread):
|
||||
all_checkpoints.append(state)
|
||||
```
|
||||
|
||||
Each checkpoint has a unique ID, which we can use to replay from a specific checkpoint.
|
||||
|
||||
Assume from reviewing the checkpoints that we want to replay from one, `xxx`.
|
||||
|
||||
We just pass in the checkpoint ID when we run the graph.
|
||||
|
||||
```python
|
||||
config = {'configurable': {'thread_id': '1', 'checkpoint_id': 'xxx'}}
|
||||
for event in graph.stream(None, config, stream_mode="values"):
|
||||
print(event)
|
||||
```
|
||||
|
||||
Importantly, the graph knows which checkpoints have been previously executed.
|
||||
|
||||
So, it will re-play any previously executed nodes rather than re-executing them.
|
||||
|
||||
See [this additional conceptual guide](https://langchain-ai.github.io/langgraph/concepts/persistence/#replay) for related context on replaying.
|
||||
|
||||
See see [this guide](../how-tos/human_in_the_loop/time-travel.ipynb) for a detailed how-to on doing time-travel!
|
||||
|
||||
#### Forking
|
||||
|
||||

|
||||
|
||||
Sometimes we want to fork past actions of an agent, and explore different paths through the graph.
|
||||
|
||||
`Editing`, as discussed above, is *exactly* how we do this for the *current* state of the graph!
|
||||
|
||||
But, what if we want to fork *past* states of the graph?
|
||||
|
||||
For example, let's say we want to edit a particular checkpoint, `xxx`.
|
||||
|
||||
We pass this `checkpoint_id` when we update the state of the graph.
|
||||
|
||||
```python
|
||||
config = {"configurable": {"thread_id": "1", "checkpoint_id": "xxx"}}
|
||||
graph.update_state(config, {"state": "updated state"}, )
|
||||
```
|
||||
|
||||
This creates a new forked checkpoint, `xxx-fork`, which we can then run the graph from.
|
||||
|
||||
```python
|
||||
config = {'configurable': {'thread_id': '1', 'checkpoint_id': 'xxx-fork'}}
|
||||
for event in graph.stream(None, config, stream_mode="values"):
|
||||
print(event)
|
||||
```
|
||||
|
||||
See [this additional conceptual guide](https://langchain-ai.github.io/langgraph/concepts/persistence/#update-state) for related context on forking.
|
||||
|
||||
See [this guide](../how-tos/human_in_the_loop/time-travel.ipynb) for a detailed how-to on doing time-travel!
|
||||
@@ -1,259 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "d33ecddc-6818-41a3-9d0d-b1b1cbcd286d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# How to combine control flow and state updates with Command"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "7c0a8d03-80b4-47fd-9b17-e26aa9b081f3",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"!!! info \"Prerequisites\"\n",
|
||||
" This guide assumes familiarity with the following:\n",
|
||||
" \n",
|
||||
" - [State](../../concepts/low_level/#state)\n",
|
||||
" - [Nodes](../../concepts/low_level/#nodes)\n",
|
||||
" - [Edges](../../concepts/low_level/#edges)\n",
|
||||
" - [Command](../../concepts/low_level/#command)\n",
|
||||
"\n",
|
||||
"It can be useful to combine control flow (edges) and state updates (nodes). For example, you might want to BOTH perform state updates AND decide which node to go to next in the SAME node. LangGraph provides a way to do so by returning a `Command` object from node functions:\n",
|
||||
"\n",
|
||||
"```python\n",
|
||||
"def my_node(state: State) -> Command[Literal[\"my_other_node\"]]:\n",
|
||||
" return Command(\n",
|
||||
" # state update\n",
|
||||
" update={\"foo\": \"bar\"},\n",
|
||||
" # control flow\n",
|
||||
" goto=\"my_other_node\"\n",
|
||||
" )\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"This guide shows how you can do use `Command` to add dynamic control flow in your LangGraph app."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "d1c3f866-8c20-40c7-a201-35f6c9f4b680",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Setup\n",
|
||||
"\n",
|
||||
"First, let's install the required packages"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "6999c7fe-31bb-4c19-946a-85c2edc57da7",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%capture --no-stderr\n",
|
||||
"%pip install -U langgraph"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "0f131c92-4744-431c-a89c-7c382a15b79f",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<div class=\"admonition tip\">\n",
|
||||
" <p class=\"admonition-title\">Set up <a href=\"https://smith.langchain.com\">LangSmith</a> for LangGraph development</p>\n",
|
||||
" <p style=\"padding-top: 5px;\">\n",
|
||||
" Sign up for LangSmith to quickly spot issues and improve the performance of your LangGraph projects. LangSmith lets you use trace data to debug, test, and monitor your LLM apps built with LangGraph — read more about how to get started <a href=\"https://docs.smith.langchain.com\">here</a>. \n",
|
||||
" </p>\n",
|
||||
"</div>"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "f22c228f-6882-4757-8e7e-1ca51328af4a",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Let's create a simple graph with 3 nodes: A, B and C. We will first execute node A, and then decide whether to go to Node B or Node C next based on the output of node A."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "6a08d957-b3d2-4538-bf4a-68ef90a51b98",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Define graph"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "4539b81b-09e9-4660-ac55-1b1775e13892",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import random\n",
|
||||
"from typing_extensions import TypedDict, Literal\n",
|
||||
"\n",
|
||||
"from langgraph.graph import StateGraph, START\n",
|
||||
"from langgraph.types import Command\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"# Define graph state\n",
|
||||
"class State(TypedDict):\n",
|
||||
" foo: str\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"# Define the nodes\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def node_a(state: State) -> Command[Literal[\"node_b\", \"node_c\"]]:\n",
|
||||
" print(\"Called A\")\n",
|
||||
" value = random.choice([\"a\", \"b\"])\n",
|
||||
" # this is a replacement for a conditional edge function\n",
|
||||
" if value == \"a\":\n",
|
||||
" goto = \"node_b\"\n",
|
||||
" else:\n",
|
||||
" goto = \"node_c\"\n",
|
||||
"\n",
|
||||
" # note how Command allows you to BOTH update the graph state AND route to the next node\n",
|
||||
" return Command(\n",
|
||||
" # this is the state update\n",
|
||||
" update={\"foo\": value},\n",
|
||||
" # this is a replacement for an edge\n",
|
||||
" goto=goto,\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"# Nodes B and C are unchanged\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def node_b(state: State):\n",
|
||||
" print(\"Called B\")\n",
|
||||
" return {\"foo\": state[\"foo\"] + \"b\"}\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def node_c(state: State):\n",
|
||||
" print(\"Called C\")\n",
|
||||
" return {\"foo\": state[\"foo\"] + \"c\"}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "badc25eb-4876-482e-bb10-d763023cdaad",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We can now create the `StateGraph` with the above nodes. Notice that the graph doesn't have [conditional edges](../../concepts/low_level#conditional-edges) for routing! This is because control flow is defined with `Command` inside `node_a`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "d6711650-4380-4551-a007-2805f49ab2d8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"builder = StateGraph(State)\n",
|
||||
"builder.add_edge(START, \"node_a\")\n",
|
||||
"builder.add_node(node_a)\n",
|
||||
"builder.add_node(node_b)\n",
|
||||
"builder.add_node(node_c)\n",
|
||||
"# NOTE: there are no edges between nodes A, B and C!\n",
|
||||
"\n",
|
||||
"graph = builder.compile()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "0ab344c5-d634-4d7d-b3b4-edf4fa875311",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"!!! important\n",
|
||||
"\n",
|
||||
" You might have noticed that we used `Command` as a return type annotation, e.g. `Command[Literal[\"node_b\", \"node_c\"]]`. This is necessary for the graph rendering and tells LangGraph that `node_a` can navigate to `node_b` and `node_c`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "eeb810e5-8822-4c09-8d53-c55cd0f5d42e",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"image/jpeg": "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 truncated
|
||||
"text/plain": [
|
||||
"<IPython.core.display.Image object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from IPython.display import display, Image\n",
|
||||
"\n",
|
||||
"display(Image(graph.get_graph().draw_mermaid_png()))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "58fb6c32-e6fb-4c94-8182-e351ed52a45d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"If we run the graph multiple times, we'd see it take different paths (A -> B or A -> C) based on the random choice in node A."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "d88a5d9b-ee08-4ed4-9c65-6e868210bfac",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Called A\n",
|
||||
"Called C\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'foo': 'bc'}"
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"graph.invoke({\"foo\": \"\"})"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.12.3"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -41,9 +41,6 @@
|
||||
" <p>\n",
|
||||
" Support for the <code><a href=\"https://langchain-ai.github.io/langgraph/reference/store/#langgraph.store.base.BaseStore\">Store</a></code> API that is used in this guide was added in LangGraph <code>v0.2.32</code>.\n",
|
||||
" </p>\n",
|
||||
" <p>\n",
|
||||
" Support for <b>index</b> and <b>query</b> arguments of the <code><a href=\"https://langchain-ai.github.io/langgraph/reference/store/#langgraph.store.base.BaseStore\">Store</a></code> API that is used in this guide was added in LangGraph <code>v0.2.54</code>.\n",
|
||||
" </p>\n",
|
||||
"</div>\n",
|
||||
"\n",
|
||||
"## Setup\n",
|
||||
@@ -117,7 +114,7 @@
|
||||
"\n",
|
||||
"Importantly, to determine the user, we will be passing `user_id` via the config keyword argument of the node function.\n",
|
||||
"\n",
|
||||
"Let's first define an `InMemoryStore` already populated with some memories about the users."
|
||||
"Let's first define an `InMemoryStore` which is already populated with some memories about the users."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -128,14 +125,8 @@
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langgraph.store.memory import InMemoryStore\n",
|
||||
"from langchain_openai import OpenAIEmbeddings\n",
|
||||
"\n",
|
||||
"in_memory_store = InMemoryStore(\n",
|
||||
" index={\n",
|
||||
" \"embed\": OpenAIEmbeddings(model=\"text-embedding-3-small\"),\n",
|
||||
" \"dims\": 1536,\n",
|
||||
" }\n",
|
||||
")"
|
||||
"in_memory_store = InMemoryStore()"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -172,7 +163,7 @@
|
||||
"def call_model(state: MessagesState, config: RunnableConfig, *, store: BaseStore):\n",
|
||||
" user_id = config[\"configurable\"][\"user_id\"]\n",
|
||||
" namespace = (\"memories\", user_id)\n",
|
||||
" memories = store.search(namespace, query=str(state[\"messages\"][-1].content))\n",
|
||||
" memories = store.search(namespace)\n",
|
||||
" info = \"\\n\".join([d.value[\"data\"] for d in memories])\n",
|
||||
" system_msg = f\"You are a helpful assistant talking to the user. User info: {info}\"\n",
|
||||
"\n",
|
||||
|
||||
@@ -17,10 +17,6 @@ You will need to do the following:
|
||||
2. Build a docker image with the [LangGraph Server](../concepts/langgraph_server.md) using the [LangGraph CLI](../concepts/langgraph_cli.md).
|
||||
3. Deploy a web server that will run the docker image and pass in the necessary environment variables.
|
||||
|
||||
## Helm Chart
|
||||
|
||||
If you would like to deploy LangGraph Cloud on Kubernetes, you can use this [Helm chart](https://github.com/langchain-ai/helm/blob/main/charts/langgraph-cloud/README.md).
|
||||
|
||||
## Environment Variables
|
||||
|
||||
You will eventually need to pass in the following environment variables to the LangGraph Deploy server:
|
||||
|
||||
@@ -12,14 +12,6 @@
|
||||
"source": [
|
||||
"# How to add breakpoints\n",
|
||||
"\n",
|
||||
"!!! tip \"Prerequisites\"\n",
|
||||
"\n",
|
||||
" This guide assumes familiarity with the following concepts:\n",
|
||||
"\n",
|
||||
" * [Breakpoints](../../../concepts/breakpoints)\n",
|
||||
" * [LangGraph Glossary](../../../concepts/low_level)\n",
|
||||
" \n",
|
||||
"\n",
|
||||
"Human-in-the-loop (HIL) interactions are crucial for [agentic systems](https://langchain-ai.github.io/langgraph/concepts/agentic_concepts/#human-in-the-loop). [Breakpoints](https://langchain-ai.github.io/langgraph/concepts/low_level/#breakpoints) are a common HIL interaction pattern, allowing the graph to stop at specific steps and seek human approval before proceeding (e.g., for sensitive actions). \n",
|
||||
"\n",
|
||||
"Breakpoints are built on top of LangGraph [checkpoints](https://langchain-ai.github.io/langgraph/concepts/low_level/#checkpointer), which save the graph's state after each node execution. Checkpoints are saved in [threads](https://langchain-ai.github.io/langgraph/concepts/low_level/#threads) that preserve graph state and can be accessed after a graph has finished execution. This allows for graph execution to pause at specific points, await human approval, and then resume execution from the last checkpoint.\n",
|
||||
@@ -475,7 +467,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.4"
|
||||
"version": "3.11.8"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
@@ -1,32 +1,24 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "b7d5f6a5-9e59-43e4-a4b6-8ada6dace691",
|
||||
"id": "ee54cde3-7e4d-43f4-b921-e7141ea0f19e",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# How to add dynamic breakpoints"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "607849c6-4b8c-4e06-ad9c-758bb5a08e86",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# How to add dynamic breakpoints with `NodeInterrupt`\n",
|
||||
"\n",
|
||||
"!!! note\n",
|
||||
"\n",
|
||||
" For **human-in-the-loop** workflows use the new [`interrupt()`](../../../reference/types/#langgraph.types.interrupt) function for **human-in-the-loop** workflows. Please review the [Human-in-the-loop conceptual guide](../../../concepts/human_in_the_loop) for more information about design patterns with `interrupt`.\n",
|
||||
"\n",
|
||||
"!!! tip \"Prerequisites\"\n",
|
||||
"\n",
|
||||
" This guide assumes familiarity with the following concepts:\n",
|
||||
"\n",
|
||||
" * [Breakpoints](../../../concepts/breakpoints)\n",
|
||||
" * [LangGraph Glossary](../../../concepts/low_level)\n",
|
||||
" \n",
|
||||
"\n",
|
||||
"Human-in-the-loop (HIL) interactions are crucial for [agentic systems](https://langchain-ai.github.io/langgraph/concepts/agentic_concepts/#human-in-the-loop). [Breakpoints](https://langchain-ai.github.io/langgraph/concepts/low_level/#breakpoints) are a common HIL interaction pattern, allowing the graph to stop at specific steps and seek human approval before proceeding (e.g., for sensitive actions).\n",
|
||||
"\n",
|
||||
"In LangGraph you can add breakpoints before / after a node is executed. But oftentimes it may be helpful to **dynamically** interrupt the graph from inside a given node based on some condition. When doing so, it may also be helpful to include information about **why** that interrupt was raised.\n",
|
||||
"\n",
|
||||
"This guide shows how you can dynamically interrupt the graph using `NodeInterrupt` -- a special exception that can be raised from inside a node. Let's see it in action!\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"## Setup\n",
|
||||
"\n",
|
||||
"First, let's install the required packages"
|
||||
@@ -438,7 +430,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.4"
|
||||
"version": "3.11.9"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
@@ -12,12 +12,6 @@
|
||||
"source": [
|
||||
"# How to edit graph state\n",
|
||||
"\n",
|
||||
"!!! tip \"Prerequisites\"\n",
|
||||
"\n",
|
||||
" * [Human-in-the-loop](../../../concepts/human_in_the_loop)\n",
|
||||
" * [Breakpoints](../../../concepts/breakpoints)\n",
|
||||
" * [LangGraph Glossary](../../../concepts/low_level)\n",
|
||||
"\n",
|
||||
"Human-in-the-loop (HIL) interactions are crucial for [agentic systems](https://langchain-ai.github.io/langgraph/concepts/agentic_concepts/#human-in-the-loop). Manually updating the graph state a common HIL interaction pattern, allowing the human to edit actions (e.g., what tool is being called or how it is being called).\n",
|
||||
"\n",
|
||||
"We can implement this in LangGraph using a [breakpoint](https://langchain-ai.github.io/langgraph/how-tos/human_in_the_loop/breakpoints/): breakpoints allow us to interrupt graph execution before a specific step. At this breakpoint, we can manually update the graph state and then resume from that spot to continue. \n",
|
||||
@@ -560,7 +554,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.4"
|
||||
"version": "3.11.8"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
@@ -8,15 +8,7 @@
|
||||
"source": [
|
||||
"# How to Review Tool Calls\n",
|
||||
"\n",
|
||||
"!!! tip \"Prerequisites\"\n",
|
||||
"\n",
|
||||
" This guide assumes familiarity with the following concepts:\n",
|
||||
"\n",
|
||||
" * [Tool calling](https://python.langchain.com/docs/concepts/tool_calling/)\n",
|
||||
" * [Human-in-the-loop](../../../concepts/human_in_the_loop)\n",
|
||||
" * [LangGraph Glossary](../../../concepts/low_level) \n",
|
||||
"\n",
|
||||
"Human-in-the-loop (HIL) interactions are crucial for [agentic systems](../../../concepts/agentic_concepts). A common pattern is to add some human in the loop step after certain tool calls. These tool calls often lead to either a function call or saving of some information. Examples include:\n",
|
||||
"Human-in-the-loop (HIL) interactions are crucial for [agentic systems](https://langchain-ai.github.io/langgraph/concepts/agentic_concepts/#human-in-the-loop). A common pattern is to add some human in the loop step after certain tool calls. These tool calls often lead to either a function call or saving of some information. Examples include:\n",
|
||||
"\n",
|
||||
"- A tool call to execute SQL, which will then be run by the tool\n",
|
||||
"- A tool call to generate a summary, which will then be saved to the State of the graph\n",
|
||||
@@ -27,42 +19,9 @@
|
||||
"\n",
|
||||
"1. Approve the tool call and continue\n",
|
||||
"2. Modify the tool call manually and then continue\n",
|
||||
"3. Give natural language feedback, and then pass that back to the agent\n",
|
||||
"3. Give natural language feedback, and then pass that back to the agent instead of continuing\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"We can implement these in LangGraph using the [`interrupt()`][langgraph.types.interrupt] function. `interrupt` allows us to stop graph execution to collect input from a user and continue execution with collected input:\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"```python\n",
|
||||
"def human_review_node(state) -> Command[Literal[\"call_llm\", \"run_tool\"]]:\n",
|
||||
" # this is the value we'll be providing via Command(resume=<human_review>)\n",
|
||||
" human_review = interrupt(\n",
|
||||
" {\n",
|
||||
" \"question\": \"Is this correct?\",\n",
|
||||
" # Surface tool calls for review\n",
|
||||
" \"tool_call\": tool_call\n",
|
||||
" }\n",
|
||||
" )\n",
|
||||
" \n",
|
||||
" review_action, review_data = human_review\n",
|
||||
" \n",
|
||||
" # Approve the tool call and continue\n",
|
||||
" if review_action == \"continue\":\n",
|
||||
" return Command(goto=\"run_tool\")\n",
|
||||
" \n",
|
||||
" # Modify the tool call manually and then continue\n",
|
||||
" elif review_action == \"update\":\n",
|
||||
" ...\n",
|
||||
" updated_msg = get_updated_msg(review_data)\n",
|
||||
" return Command(goto=\"run_tool\", update={\"messages\": [updated_message]})\n",
|
||||
"\n",
|
||||
" # Give natural language feedback, and then pass that back to the agent\n",
|
||||
" elif review_action == \"feedback\":\n",
|
||||
" ...\n",
|
||||
" feedback_msg = get_feedback_msg(review_data)\n",
|
||||
" return Command(goto=\"call_llm\", update={\"messages\": [feedback_msg]})\n",
|
||||
"\n",
|
||||
"```"
|
||||
"We can implement this in LangGraph using a [breakpoint](https://langchain-ai.github.io/langgraph/how-tos/human_in_the_loop/breakpoints/): breakpoints allow us to interrupt graph execution before a specific step. At this breakpoint, we can manually update the graph state taking one of the three options above"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -99,15 +58,7 @@
|
||||
"execution_count": 2,
|
||||
"id": "c903a1cf-2977-4e2d-ad7d-8b3946821d89",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"ANTHROPIC_API_KEY: ········\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import getpass\n",
|
||||
"import os\n",
|
||||
@@ -151,13 +102,13 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"execution_count": 1,
|
||||
"id": "85e452f8-f33a-4ead-bb4d-7386cdba8edc",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"image/png": "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 truncated
|
||||
"image/jpeg": "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 truncated
|
||||
"text/plain": [
|
||||
"<IPython.core.display.Image object>"
|
||||
]
|
||||
@@ -170,7 +121,6 @@
|
||||
"from typing_extensions import TypedDict, Literal\n",
|
||||
"from langgraph.graph import StateGraph, START, END, MessagesState\n",
|
||||
"from langgraph.checkpoint.memory import MemorySaver\n",
|
||||
"from langgraph.types import Command, interrupt\n",
|
||||
"from langchain_anthropic import ChatAnthropic\n",
|
||||
"from langchain_core.tools import tool\n",
|
||||
"from langchain_core.messages import AIMessage\n",
|
||||
@@ -186,7 +136,7 @@
|
||||
" return \"Sunny!\"\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"model = ChatAnthropic(model_name=\"claude-3-5-sonnet-latest\").bind_tools(\n",
|
||||
"model = ChatAnthropic(model_name=\"claude-3-5-sonnet-20240620\").bind_tools(\n",
|
||||
" [weather_search]\n",
|
||||
")\n",
|
||||
"\n",
|
||||
@@ -199,58 +149,8 @@
|
||||
" return {\"messages\": [model.invoke(state[\"messages\"])]}\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def human_review_node(state) -> Command[Literal[\"call_llm\", \"run_tool\"]]:\n",
|
||||
" last_message = state[\"messages\"][-1]\n",
|
||||
" tool_call = last_message.tool_calls[-1]\n",
|
||||
"\n",
|
||||
" # this is the value we'll be providing via Command(resume=<human_review>)\n",
|
||||
" human_review = interrupt(\n",
|
||||
" {\n",
|
||||
" \"question\": \"Is this correct?\",\n",
|
||||
" # Surface tool calls for review\n",
|
||||
" \"tool_call\": tool_call,\n",
|
||||
" }\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" review_action = human_review[\"action\"]\n",
|
||||
" review_data = human_review.get(\"data\")\n",
|
||||
"\n",
|
||||
" # if approved, call the tool\n",
|
||||
" if review_action == \"continue\":\n",
|
||||
" return Command(goto=\"run_tool\")\n",
|
||||
"\n",
|
||||
" # update the AI message AND call tools\n",
|
||||
" elif review_action == \"update\":\n",
|
||||
" updated_message = {\n",
|
||||
" \"role\": \"ai\",\n",
|
||||
" \"content\": last_message.content,\n",
|
||||
" \"tool_calls\": [\n",
|
||||
" {\n",
|
||||
" \"id\": tool_call[\"id\"],\n",
|
||||
" \"name\": tool_call[\"name\"],\n",
|
||||
" # This the update provided by the human\n",
|
||||
" \"args\": review_data,\n",
|
||||
" }\n",
|
||||
" ],\n",
|
||||
" # This is important - this needs to be the same as the message you replacing!\n",
|
||||
" # Otherwise, it will show up as a separate message\n",
|
||||
" \"id\": last_message.id,\n",
|
||||
" }\n",
|
||||
" return Command(goto=\"run_tool\", update={\"messages\": [updated_message]})\n",
|
||||
"\n",
|
||||
" # provide feedback to LLM\n",
|
||||
" elif review_action == \"feedback\":\n",
|
||||
" # NOTE: we're adding feedback message as a ToolMessage\n",
|
||||
" # to preserve the correct order in the message history\n",
|
||||
" # (AI messages with tool calls need to be followed by tool call messages)\n",
|
||||
" tool_message = {\n",
|
||||
" \"role\": \"tool\",\n",
|
||||
" # This is our natural language feedback\n",
|
||||
" \"content\": review_data,\n",
|
||||
" \"name\": tool_call[\"name\"],\n",
|
||||
" \"tool_call_id\": tool_call[\"id\"],\n",
|
||||
" }\n",
|
||||
" return Command(goto=\"call_llm\", update={\"messages\": [tool_message]})\n",
|
||||
"def human_review_node(state):\n",
|
||||
" pass\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def run_tool(state):\n",
|
||||
@@ -278,19 +178,27 @@
|
||||
" return \"human_review_node\"\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def route_after_human(state) -> Literal[\"run_tool\", \"call_llm\"]:\n",
|
||||
" if isinstance(state[\"messages\"][-1], AIMessage):\n",
|
||||
" return \"run_tool\"\n",
|
||||
" else:\n",
|
||||
" return \"call_llm\"\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"builder = StateGraph(State)\n",
|
||||
"builder.add_node(call_llm)\n",
|
||||
"builder.add_node(run_tool)\n",
|
||||
"builder.add_node(human_review_node)\n",
|
||||
"builder.add_edge(START, \"call_llm\")\n",
|
||||
"builder.add_conditional_edges(\"call_llm\", route_after_llm)\n",
|
||||
"builder.add_conditional_edges(\"human_review_node\", route_after_human)\n",
|
||||
"builder.add_edge(\"run_tool\", \"call_llm\")\n",
|
||||
"\n",
|
||||
"# Set up memory\n",
|
||||
"memory = MemorySaver()\n",
|
||||
"\n",
|
||||
"# Add\n",
|
||||
"graph = builder.compile(checkpointer=memory)\n",
|
||||
"graph = builder.compile(checkpointer=memory, interrupt_before=[\"human_review_node\"])\n",
|
||||
"\n",
|
||||
"# View\n",
|
||||
"display(Image(graph.get_graph().draw_mermaid_png()))"
|
||||
@@ -308,7 +216,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"execution_count": 2,
|
||||
"id": "1b3aa6fc-c7fb-4819-8d7f-ba6057cc4edf",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@@ -316,9 +224,8 @@
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"{'call_llm': {'messages': [AIMessage(content=\"Hello! I'm here to help you. I can assist you with checking the weather in different cities using the weather search tool. Would you like to know the weather for a specific city? Just let me know which city you're interested in!\", additional_kwargs={}, response_metadata={'id': 'msg_01XHvA3ZWpsq4PdyiruWFLBs', 'model': 'claude-3-5-sonnet-20241022', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 374, 'output_tokens': 52}}, id='run-c3ff5fea-0135-4d66-8ec1-f8ed6a88356b-0', usage_metadata={'input_tokens': 374, 'output_tokens': 52, 'total_tokens': 426, 'input_token_details': {}})]}}\n",
|
||||
"\n",
|
||||
"\n"
|
||||
"{'messages': [HumanMessage(content='hi!', id='393fa21d-4bfb-445b-8faa-78e22b92e346')]}\n",
|
||||
"{'messages': [HumanMessage(content='hi!', id='393fa21d-4bfb-445b-8faa-78e22b92e346'), AIMessage(content=\"Hello! Welcome to our conversation. How can I assist you today? Is there anything specific you'd like to know or discuss?\", response_metadata={'id': 'msg_017S671xYvZm1mi9EcsKvPzF', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 355, 'output_tokens': 29}}, id='run-8ec507a1-5caf-47d6-89eb-1a2e8f38423c-0', usage_metadata={'input_tokens': 355, 'output_tokens': 29, 'total_tokens': 384})]}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@@ -330,9 +237,8 @@
|
||||
"thread = {\"configurable\": {\"thread_id\": \"1\"}}\n",
|
||||
"\n",
|
||||
"# Run the graph until the first interruption\n",
|
||||
"for event in graph.stream(initial_input, thread, stream_mode=\"updates\"):\n",
|
||||
" print(event)\n",
|
||||
" print(\"\\n\")"
|
||||
"for event in graph.stream(initial_input, thread, stream_mode=\"values\"):\n",
|
||||
" print(event)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -343,6 +249,26 @@
|
||||
"If we check the state, we can see that it is finished"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "213323cc-0320-4313-ab11-19042e28b495",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Pending Executions!\n",
|
||||
"()\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(\"Pending Executions!\")\n",
|
||||
"print(graph.get_state(thread).next)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5c1985f7-54f1-420f-a2b6-5e6154909966",
|
||||
@@ -355,7 +281,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"execution_count": 4,
|
||||
"id": "2561a38f-edb5-4b44-b2d7-6a7b70d2e6b7",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@@ -363,12 +289,8 @@
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"{'call_llm': {'messages': [AIMessage(content=[{'text': \"I'll help you check the weather in San Francisco.\", 'type': 'text'}, {'id': 'toolu_01Kn67GmQAA3BEF1cfYdNW3c', 'input': {'city': 'sf'}, 'name': 'weather_search', 'type': 'tool_use'}], additional_kwargs={}, response_metadata={'id': 'msg_013eJXUAEA2ANvYLkDUQFRPo', 'model': 'claude-3-5-sonnet-20241022', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 379, 'output_tokens': 65}}, id='run-e8174b94-f681-4688-967f-a32295412f91-0', tool_calls=[{'name': 'weather_search', 'args': {'city': 'sf'}, 'id': 'toolu_01Kn67GmQAA3BEF1cfYdNW3c', 'type': 'tool_call'}], usage_metadata={'input_tokens': 379, 'output_tokens': 65, 'total_tokens': 444, 'input_token_details': {}})]}}\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"{'__interrupt__': (Interrupt(value={'question': 'Is this correct?', 'tool_call': {'name': 'weather_search', 'args': {'city': 'sf'}, 'id': 'toolu_01Kn67GmQAA3BEF1cfYdNW3c', 'type': 'tool_call'}}, resumable=True, ns=['human_review_node:be252162-5b29-0a98-1ed2-c807c1fc64c6'], when='during'),)}\n",
|
||||
"\n",
|
||||
"\n"
|
||||
"{'messages': [HumanMessage(content=\"what's the weather in sf?\", id='8bda37cc-4bd3-4a14-bca5-b992934e710b')]}\n",
|
||||
"{'messages': [HumanMessage(content=\"what's the weather in sf?\", id='8bda37cc-4bd3-4a14-bca5-b992934e710b'), AIMessage(content=[{'text': 'To get the weather information for San Francisco, I can use the weather_search function. Let me do that for you.', 'type': 'text'}, {'id': 'toolu_01MW3ETLpq4b8s6VaAMgDBZP', 'input': {'city': 'San Francisco'}, 'name': 'weather_search', 'type': 'tool_use'}], response_metadata={'id': 'msg_019FjC1prjVv8BuQX7DmF65F', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 360, 'output_tokens': 80}}, id='run-1b580410-173c-4fe0-a149-22e8f516b259-0', tool_calls=[{'name': 'weather_search', 'args': {'city': 'San Francisco'}, 'id': 'toolu_01MW3ETLpq4b8s6VaAMgDBZP', 'type': 'tool_call'}], usage_metadata={'input_tokens': 360, 'output_tokens': 80, 'total_tokens': 440})]}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@@ -380,9 +302,8 @@
|
||||
"thread = {\"configurable\": {\"thread_id\": \"2\"}}\n",
|
||||
"\n",
|
||||
"# Run the graph until the first interruption\n",
|
||||
"for event in graph.stream(initial_input, thread, stream_mode=\"updates\"):\n",
|
||||
" print(event)\n",
|
||||
" print(\"\\n\")"
|
||||
"for event in graph.stream(initial_input, thread, stream_mode=\"values\"):\n",
|
||||
" print(event)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -395,7 +316,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"execution_count": 5,
|
||||
"id": "33d68f0f-d435-4dd1-8013-6a59186dc9f5",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@@ -418,12 +339,12 @@
|
||||
"id": "14c99fdd-4204-4c2d-b1af-02f38ab6ad57",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"To approve the tool call, we can just continue the thread with no edits. To do so, we need to let `human_review_node` know what value to use for the `human_review` variable we defined inside the node. We can provide this value by invoking the graph with a `Command(resume=<human_review>)` input. Since we're approving the tool call, we'll provide `resume` value of `{\"action\": \"continue\"}` to navigate to `run_tool` node:"
|
||||
"To approve the tool call, we can just continue the thread with no edits. To do this, we just create a new run with no inputs."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"execution_count": 6,
|
||||
"id": "f9a0d5d4-52ff-49e0-a6f4-41f9a0e844d8",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@@ -431,30 +352,17 @@
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"{'human_review_node': None}\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"----\n",
|
||||
"Searching for: sf\n",
|
||||
"Searching for: San Francisco\n",
|
||||
"----\n",
|
||||
"{'run_tool': {'messages': [{'role': 'tool', 'name': 'weather_search', 'content': 'Sunny!', 'tool_call_id': 'toolu_01Kn67GmQAA3BEF1cfYdNW3c'}]}}\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"{'call_llm': {'messages': [AIMessage(content=\"According to the search, it's sunny in San Francisco today!\", additional_kwargs={}, response_metadata={'id': 'msg_01FJTbC8oK5fkD73rUBmAtUx', 'model': 'claude-3-5-sonnet-20241022', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 457, 'output_tokens': 17}}, id='run-c21af72d-3cc5-4b74-bb7c-fbeb8f88bd6d-0', usage_metadata={'input_tokens': 457, 'output_tokens': 17, 'total_tokens': 474, 'input_token_details': {}})]}}\n",
|
||||
"\n",
|
||||
"\n"
|
||||
"{'messages': [HumanMessage(content=\"what's the weather in sf?\", id='8bda37cc-4bd3-4a14-bca5-b992934e710b'), AIMessage(content=[{'text': 'To get the weather information for San Francisco, I can use the weather_search function. Let me do that for you.', 'type': 'text'}, {'id': 'toolu_01MW3ETLpq4b8s6VaAMgDBZP', 'input': {'city': 'San Francisco'}, 'name': 'weather_search', 'type': 'tool_use'}], response_metadata={'id': 'msg_019FjC1prjVv8BuQX7DmF65F', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 360, 'output_tokens': 80}}, id='run-1b580410-173c-4fe0-a149-22e8f516b259-0', tool_calls=[{'name': 'weather_search', 'args': {'city': 'San Francisco'}, 'id': 'toolu_01MW3ETLpq4b8s6VaAMgDBZP', 'type': 'tool_call'}], usage_metadata={'input_tokens': 360, 'output_tokens': 80, 'total_tokens': 440}), ToolMessage(content='Sunny!', name='weather_search', id='835b0fe3-8aa0-45d5-ac29-03bbe57cc767', tool_call_id='toolu_01MW3ETLpq4b8s6VaAMgDBZP')]}\n",
|
||||
"{'messages': [HumanMessage(content=\"what's the weather in sf?\", id='8bda37cc-4bd3-4a14-bca5-b992934e710b'), AIMessage(content=[{'text': 'To get the weather information for San Francisco, I can use the weather_search function. Let me do that for you.', 'type': 'text'}, {'id': 'toolu_01MW3ETLpq4b8s6VaAMgDBZP', 'input': {'city': 'San Francisco'}, 'name': 'weather_search', 'type': 'tool_use'}], response_metadata={'id': 'msg_019FjC1prjVv8BuQX7DmF65F', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 360, 'output_tokens': 80}}, id='run-1b580410-173c-4fe0-a149-22e8f516b259-0', tool_calls=[{'name': 'weather_search', 'args': {'city': 'San Francisco'}, 'id': 'toolu_01MW3ETLpq4b8s6VaAMgDBZP', 'type': 'tool_call'}], usage_metadata={'input_tokens': 360, 'output_tokens': 80, 'total_tokens': 440}), ToolMessage(content='Sunny!', name='weather_search', id='835b0fe3-8aa0-45d5-ac29-03bbe57cc767', tool_call_id='toolu_01MW3ETLpq4b8s6VaAMgDBZP'), AIMessage(content=\"Based on the search results, the weather in San Francisco is sunny! It's a beautiful day in the city. Is there anything else you'd like to know about the weather or any other information I can help you with?\", response_metadata={'id': 'msg_01UY2d6RCzvwagwMb1J5etek', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 453, 'output_tokens': 49}}, id='run-7137f52c-abe6-4dc1-b536-92dd1d9187b0-0', usage_metadata={'input_tokens': 453, 'output_tokens': 49, 'total_tokens': 502})]}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"for event in graph.stream(\n",
|
||||
" # provide value\n",
|
||||
" Command(resume={\"action\": \"continue\"}),\n",
|
||||
" thread,\n",
|
||||
" stream_mode=\"updates\",\n",
|
||||
"):\n",
|
||||
" print(event)\n",
|
||||
" print(\"\\n\")"
|
||||
"for event in graph.stream(None, thread, stream_mode=\"values\"):\n",
|
||||
" print(event)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -469,7 +377,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"execution_count": 7,
|
||||
"id": "ec77831c-e6b8-4903-9146-e098a4b2fda1",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@@ -477,12 +385,8 @@
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"{'call_llm': {'messages': [AIMessage(content=[{'text': \"I'll help you check the weather in San Francisco.\", 'type': 'text'}, {'id': 'toolu_013eUXow3jwM6eekcDJdrjDa', 'input': {'city': 'sf'}, 'name': 'weather_search', 'type': 'tool_use'}], additional_kwargs={}, response_metadata={'id': 'msg_013ruFpCRNZKX3cDeBAH8rEb', 'model': 'claude-3-5-sonnet-20241022', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 379, 'output_tokens': 65}}, id='run-13df3982-ce6d-4fe2-9e5c-ea6ce30a63e4-0', tool_calls=[{'name': 'weather_search', 'args': {'city': 'sf'}, 'id': 'toolu_013eUXow3jwM6eekcDJdrjDa', 'type': 'tool_call'}], usage_metadata={'input_tokens': 379, 'output_tokens': 65, 'total_tokens': 444, 'input_token_details': {}})]}}\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"{'__interrupt__': (Interrupt(value={'question': 'Is this correct?', 'tool_call': {'name': 'weather_search', 'args': {'city': 'sf'}, 'id': 'toolu_013eUXow3jwM6eekcDJdrjDa', 'type': 'tool_call'}}, resumable=True, ns=['human_review_node:da717c23-60a0-2a1a-45de-cac5cff308bb'], when='during'),)}\n",
|
||||
"\n",
|
||||
"\n"
|
||||
"{'messages': [HumanMessage(content=\"what's the weather in sf?\", id='0c488edd-7b9c-4416-ba02-8a2d7e9f2597')]}\n",
|
||||
"{'messages': [HumanMessage(content=\"what's the weather in sf?\", id='0c488edd-7b9c-4416-ba02-8a2d7e9f2597'), AIMessage(content=[{'text': \"Certainly! I can help you check the weather in San Francisco. To get this information, I'll use the weather search tool. Let me fetch that for you.\", 'type': 'text'}, {'id': 'toolu_01CpbVmprQnjxpQzx8MzE1g8', 'input': {'city': 'San Francisco'}, 'name': 'weather_search', 'type': 'tool_use'}], response_metadata={'id': 'msg_01Mv7iqdtPgZEX2LiBBqWDuY', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 360, 'output_tokens': 88}}, id='run-52a09799-efb5-4fff-82c3-884e20119ad3-0', tool_calls=[{'name': 'weather_search', 'args': {'city': 'San Francisco'}, 'id': 'toolu_01CpbVmprQnjxpQzx8MzE1g8', 'type': 'tool_call'}], usage_metadata={'input_tokens': 360, 'output_tokens': 88, 'total_tokens': 448})]}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@@ -491,17 +395,16 @@
|
||||
"initial_input = {\"messages\": [{\"role\": \"user\", \"content\": \"what's the weather in sf?\"}]}\n",
|
||||
"\n",
|
||||
"# Thread\n",
|
||||
"thread = {\"configurable\": {\"thread_id\": \"3\"}}\n",
|
||||
"thread = {\"configurable\": {\"thread_id\": \"5\"}}\n",
|
||||
"\n",
|
||||
"# Run the graph until the first interruption\n",
|
||||
"for event in graph.stream(initial_input, thread, stream_mode=\"updates\"):\n",
|
||||
" print(event)\n",
|
||||
" print(\"\\n\")"
|
||||
"for event in graph.stream(initial_input, thread, stream_mode=\"values\"):\n",
|
||||
" print(event)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"execution_count": 8,
|
||||
"id": "edcffbd7-829b-4d0c-88bf-cd531bc0e6b2",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@@ -524,46 +427,72 @@
|
||||
"id": "87358aca-9b8f-48c7-98d4-3d755f6b0104",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"To do this, we will use `Command` with a different resume value of `{\"action\": \"update\", \"data\": <tool call args>}`. This will do the following:\n",
|
||||
"\n",
|
||||
"* combine existing tool call with user-provided tool call arguments and update the existing AI message with the new tool call\n",
|
||||
"* navigate to `run_tool` node with the updated AI message and continue execution"
|
||||
"To do this, we first need to update the state. We can do this by passing a message in with the **same** id of the message we want to overwrite. This will have the effect of **replacing** that old message. Note that this is only possible because of the **reducer** we are using that replaces messages with the same ID - read more about that [here](https://langchain-ai.github.io/langgraph/concepts/low_level/#working-with-messages-in-graph-state)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "b2f73998-baae-4c00-8a90-f4153e924941",
|
||||
"execution_count": 9,
|
||||
"id": "df4a9900-d953-4465-b8af-bd2858cb63ea",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"{'human_review_node': {'messages': [{'role': 'ai', 'content': [{'text': \"I'll help you check the weather in San Francisco.\", 'type': 'text'}, {'id': 'toolu_013eUXow3jwM6eekcDJdrjDa', 'input': {'city': 'sf'}, 'name': 'weather_search', 'type': 'tool_use'}], 'tool_calls': [{'id': 'toolu_013eUXow3jwM6eekcDJdrjDa', 'name': 'weather_search', 'args': {'city': 'San Francisco, USA'}}], 'id': 'run-13df3982-ce6d-4fe2-9e5c-ea6ce30a63e4-0'}]}}\n",
|
||||
"\n",
|
||||
"Current State:\n",
|
||||
"{'messages': [HumanMessage(content=\"what's the weather in sf?\", id='0c488edd-7b9c-4416-ba02-8a2d7e9f2597'), AIMessage(content=[{'text': \"Certainly! I can help you check the weather in San Francisco. To get this information, I'll use the weather search tool. Let me fetch that for you.\", 'type': 'text'}, {'id': 'toolu_01CpbVmprQnjxpQzx8MzE1g8', 'input': {'city': 'San Francisco'}, 'name': 'weather_search', 'type': 'tool_use'}], response_metadata={'id': 'msg_01Mv7iqdtPgZEX2LiBBqWDuY', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 360, 'output_tokens': 88}}, id='run-52a09799-efb5-4fff-82c3-884e20119ad3-0', tool_calls=[{'name': 'weather_search', 'args': {'city': 'San Francisco'}, 'id': 'toolu_01CpbVmprQnjxpQzx8MzE1g8', 'type': 'tool_call'}], usage_metadata={'input_tokens': 360, 'output_tokens': 88, 'total_tokens': 448})]}\n",
|
||||
"\n",
|
||||
"Current Tool Call ID:\n",
|
||||
"toolu_01CpbVmprQnjxpQzx8MzE1g8\n",
|
||||
"----\n",
|
||||
"Searching for: San Francisco, USA\n",
|
||||
"----\n",
|
||||
"{'run_tool': {'messages': [{'role': 'tool', 'name': 'weather_search', 'content': 'Sunny!', 'tool_call_id': 'toolu_013eUXow3jwM6eekcDJdrjDa'}]}}\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"{'call_llm': {'messages': [AIMessage(content=\"According to the search, it's sunny in San Francisco right now!\", additional_kwargs={}, response_metadata={'id': 'msg_01QssVtxXPqr8NWjYjTaiHqN', 'model': 'claude-3-5-sonnet-20241022', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 460, 'output_tokens': 18}}, id='run-8ab865c8-cc9e-4300-8e1d-9eb673e8445c-0', usage_metadata={'input_tokens': 460, 'output_tokens': 18, 'total_tokens': 478, 'input_token_details': {}})]}}\n",
|
||||
"\n",
|
||||
"\n"
|
||||
"{'messages': [HumanMessage(content=\"what's the weather in sf?\", id='0c488edd-7b9c-4416-ba02-8a2d7e9f2597'), AIMessage(content=[{'text': \"Certainly! I can help you check the weather in San Francisco. To get this information, I'll use the weather search tool. Let me fetch that for you.\", 'type': 'text'}, {'id': 'toolu_01CpbVmprQnjxpQzx8MzE1g8', 'input': {'city': 'San Francisco'}, 'name': 'weather_search', 'type': 'tool_use'}], id='run-52a09799-efb5-4fff-82c3-884e20119ad3-0', tool_calls=[{'name': 'weather_search', 'args': {'city': 'San Francisco, USA'}, 'id': 'toolu_01CpbVmprQnjxpQzx8MzE1g8', 'type': 'tool_call'}]), ToolMessage(content='Sunny!', name='weather_search', id='ff968b9f-9b87-4893-9f32-dfb88dbe0536', tool_call_id='toolu_01CpbVmprQnjxpQzx8MzE1g8')]}\n",
|
||||
"{'messages': [HumanMessage(content=\"what's the weather in sf?\", id='0c488edd-7b9c-4416-ba02-8a2d7e9f2597'), AIMessage(content=[{'text': \"Certainly! I can help you check the weather in San Francisco. To get this information, I'll use the weather search tool. Let me fetch that for you.\", 'type': 'text'}, {'id': 'toolu_01CpbVmprQnjxpQzx8MzE1g8', 'input': {'city': 'San Francisco'}, 'name': 'weather_search', 'type': 'tool_use'}], id='run-52a09799-efb5-4fff-82c3-884e20119ad3-0', tool_calls=[{'name': 'weather_search', 'args': {'city': 'San Francisco, USA'}, 'id': 'toolu_01CpbVmprQnjxpQzx8MzE1g8', 'type': 'tool_call'}]), ToolMessage(content='Sunny!', name='weather_search', id='ff968b9f-9b87-4893-9f32-dfb88dbe0536', tool_call_id='toolu_01CpbVmprQnjxpQzx8MzE1g8'), AIMessage(content=\"Great news! The weather in San Francisco is currently sunny. It's a beautiful day in the city by the bay. Is there anything else you'd like to know about the weather or any other information I can help you with?\", response_metadata={'id': 'msg_01PhwUeRWkSJB6kzHZS361XZ', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 464, 'output_tokens': 50}}, id='run-5aebcf37-626e-4675-b225-476bc99bdbb8-0', usage_metadata={'input_tokens': 464, 'output_tokens': 50, 'total_tokens': 514})]}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Let's now continue executing from here\n",
|
||||
"for event in graph.stream(\n",
|
||||
" Command(resume={\"action\": \"update\", \"data\": {\"city\": \"San Francisco, USA\"}}),\n",
|
||||
"# To get the ID of the message we want to replace, we need to fetch the current state and find it there.\n",
|
||||
"state = graph.get_state(thread)\n",
|
||||
"print(\"Current State:\")\n",
|
||||
"print(state.values)\n",
|
||||
"print(\"\\nCurrent Tool Call ID:\")\n",
|
||||
"current_content = state.values[\"messages\"][-1].content\n",
|
||||
"current_id = state.values[\"messages\"][-1].id\n",
|
||||
"tool_call_id = state.values[\"messages\"][-1].tool_calls[0][\"id\"]\n",
|
||||
"print(tool_call_id)\n",
|
||||
"\n",
|
||||
"# We now need to construct a replacement tool call.\n",
|
||||
"# We will change the argument to be `San Francisco, USA`\n",
|
||||
"# Note that we could change any number of arguments or tool names - it just has to be a valid one\n",
|
||||
"new_message = {\n",
|
||||
" \"role\": \"assistant\",\n",
|
||||
" \"content\": current_content,\n",
|
||||
" \"tool_calls\": [\n",
|
||||
" {\n",
|
||||
" \"id\": tool_call_id,\n",
|
||||
" \"name\": \"weather_search\",\n",
|
||||
" \"args\": {\"city\": \"San Francisco, USA\"},\n",
|
||||
" }\n",
|
||||
" ],\n",
|
||||
" # This is important - this needs to be the same as the message you replacing!\n",
|
||||
" # Otherwise, it will show up as a separate message\n",
|
||||
" \"id\": current_id,\n",
|
||||
"}\n",
|
||||
"graph.update_state(\n",
|
||||
" # This is the config which represents this thread\n",
|
||||
" thread,\n",
|
||||
" stream_mode=\"updates\",\n",
|
||||
"):\n",
|
||||
" print(event)\n",
|
||||
" print(\"\\n\")"
|
||||
" # This is the updated value we want to push\n",
|
||||
" {\"messages\": [new_message]},\n",
|
||||
" # We push this update acting as our human_review_node\n",
|
||||
" as_node=\"human_review_node\",\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# Let's now continue executing from here\n",
|
||||
"for event in graph.stream(None, thread, stream_mode=\"values\"):\n",
|
||||
" print(event)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -573,21 +502,21 @@
|
||||
"source": [
|
||||
"## Give feedback to a tool call\n",
|
||||
"\n",
|
||||
"Sometimes, you may not want to execute a tool call, but you also may not want to ask the user to manually modify the tool call. In that case it may be better to get natural language feedback from the user. You can then insert this feedback as a mock **RESULT** of the tool call.\n",
|
||||
"Sometimes, you may not want to execute a tool call, but you also may not want to ask the user to manually modify the tool call. In that case it may be better to get natural language feedback from the user. You can then insert these feedback as a mock **RESULT** of the tool call.\n",
|
||||
"\n",
|
||||
"There are multiple ways to do this:\n",
|
||||
"\n",
|
||||
"1. You could add a new message to the state (representing the \"result\" of a tool call)\n",
|
||||
"2. You could add TWO new messages to the state - one representing an \"error\" from the tool call, other HumanMessage representing the feedback\n",
|
||||
"\n",
|
||||
"Both are similar in that they involve adding messages to the state. The main difference lies in the logic AFTER the `human_review_node` and how it handles different types of messages.\n",
|
||||
"Both are similar in that they involve adding messages to the state. The main difference lies in the logic AFTER the `human_node` and how it handles different types of messages.\n",
|
||||
"\n",
|
||||
"For this example we will just add a single tool call representing the feedback (see `human_review_node` implementation). Let's see this in action!"
|
||||
"For this example we will just add a single tool call representing the feedback. Let's see this in action!"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"execution_count": 10,
|
||||
"id": "d57d5131-7912-4216-aa87-b7272507fa51",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@@ -595,12 +524,8 @@
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"{'call_llm': {'messages': [AIMessage(content=[{'text': \"I'll help you check the weather in San Francisco.\", 'type': 'text'}, {'id': 'toolu_01QxXNTCasnNLQCGAiVoNUBe', 'input': {'city': 'sf'}, 'name': 'weather_search', 'type': 'tool_use'}], additional_kwargs={}, response_metadata={'id': 'msg_01DjwkVxgfqT2K329rGkycx6', 'model': 'claude-3-5-sonnet-20241022', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 379, 'output_tokens': 65}}, id='run-c57bee36-9f5f-4d2e-85df-758b56d3cc05-0', tool_calls=[{'name': 'weather_search', 'args': {'city': 'sf'}, 'id': 'toolu_01QxXNTCasnNLQCGAiVoNUBe', 'type': 'tool_call'}], usage_metadata={'input_tokens': 379, 'output_tokens': 65, 'total_tokens': 444, 'input_token_details': {}})]}}\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"{'__interrupt__': (Interrupt(value={'question': 'Is this correct?', 'tool_call': {'name': 'weather_search', 'args': {'city': 'sf'}, 'id': 'toolu_01QxXNTCasnNLQCGAiVoNUBe', 'type': 'tool_call'}}, resumable=True, ns=['human_review_node:47a3f541-b630-5f8a-32d7-5a44826d99da'], when='during'),)}\n",
|
||||
"\n",
|
||||
"\n"
|
||||
"{'messages': [HumanMessage(content=\"what's the weather in sf?\", id='601c4c75-f506-4d91-896d-5e382123de24')]}\n",
|
||||
"{'messages': [HumanMessage(content=\"what's the weather in sf?\", id='601c4c75-f506-4d91-896d-5e382123de24'), AIMessage(content=[{'text': \"Certainly! I can help you check the weather in San Francisco. To get the most accurate and up-to-date information, I'll use the weather search tool. Let me fetch that for you right away.\", 'type': 'text'}, {'id': 'toolu_014UTKh5uqfc885Fj4RRqGdg', 'input': {'city': 'San Francisco'}, 'name': 'weather_search', 'type': 'tool_use'}], response_metadata={'id': 'msg_013nHyPYxNXFSoXeS6q4oWua', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 360, 'output_tokens': 98}}, id='run-0537e15e-86a4-4c6f-8dfb-6e4c160812c4-0', tool_calls=[{'name': 'weather_search', 'args': {'city': 'San Francisco'}, 'id': 'toolu_014UTKh5uqfc885Fj4RRqGdg', 'type': 'tool_call'}], usage_metadata={'input_tokens': 360, 'output_tokens': 98, 'total_tokens': 458})]}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@@ -609,17 +534,16 @@
|
||||
"initial_input = {\"messages\": [{\"role\": \"user\", \"content\": \"what's the weather in sf?\"}]}\n",
|
||||
"\n",
|
||||
"# Thread\n",
|
||||
"thread = {\"configurable\": {\"thread_id\": \"4\"}}\n",
|
||||
"thread = {\"configurable\": {\"thread_id\": \"6\"}}\n",
|
||||
"\n",
|
||||
"# Run the graph until the first interruption\n",
|
||||
"for event in graph.stream(initial_input, thread, stream_mode=\"updates\"):\n",
|
||||
" print(event)\n",
|
||||
" print(\"\\n\")"
|
||||
"for event in graph.stream(initial_input, thread, stream_mode=\"values\"):\n",
|
||||
" print(event)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"execution_count": 11,
|
||||
"id": "e33ad664-0307-43c5-b85a-1e02eebceb5c",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@@ -642,15 +566,12 @@
|
||||
"id": "483d9455-8625-4c6a-9b98-f731403b2ed3",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"To do this, we will use `Command` with a different resume value of `{\"action\": \"feedback\", \"data\": <feedback string>}`. This will do the following:\n",
|
||||
"\n",
|
||||
"* create a new tool message that combines existing tool call from LLM with the with user-provided feedback as content\n",
|
||||
"* navigate to `call_llm` node with the updated tool message and continue execution"
|
||||
"To do this, we first need to update the state. We can do this by passing a message in with the same **tool call id** of the tool call we want to respond to. Note that this is a **different** ID from above."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"execution_count": 12,
|
||||
"id": "3f05f8b6-6128-4de5-8884-862fc93f1227",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@@ -658,33 +579,46 @@
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"{'human_review_node': {'messages': [{'role': 'tool', 'content': 'User requested changes: use <city, country> format for location', 'name': 'weather_search', 'tool_call_id': 'toolu_01QxXNTCasnNLQCGAiVoNUBe'}]}}\n",
|
||||
"Current State:\n",
|
||||
"{'messages': [HumanMessage(content=\"what's the weather in sf?\", id='601c4c75-f506-4d91-896d-5e382123de24'), AIMessage(content=[{'text': \"Certainly! I can help you check the weather in San Francisco. To get the most accurate and up-to-date information, I'll use the weather search tool. Let me fetch that for you right away.\", 'type': 'text'}, {'id': 'toolu_014UTKh5uqfc885Fj4RRqGdg', 'input': {'city': 'San Francisco'}, 'name': 'weather_search', 'type': 'tool_use'}], response_metadata={'id': 'msg_013nHyPYxNXFSoXeS6q4oWua', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 360, 'output_tokens': 98}}, id='run-0537e15e-86a4-4c6f-8dfb-6e4c160812c4-0', tool_calls=[{'name': 'weather_search', 'args': {'city': 'San Francisco'}, 'id': 'toolu_014UTKh5uqfc885Fj4RRqGdg', 'type': 'tool_call'}], usage_metadata={'input_tokens': 360, 'output_tokens': 98, 'total_tokens': 458})]}\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"{'call_llm': {'messages': [AIMessage(content=[{'text': 'Let me try again with the full city name.', 'type': 'text'}, {'id': 'toolu_01WBGTKBWusaPNZYJi5LKmeQ', 'input': {'city': 'San Francisco, USA'}, 'name': 'weather_search', 'type': 'tool_use'}], additional_kwargs={}, response_metadata={'id': 'msg_0141KCdx6KhJmWXyYwAYGvmj', 'model': 'claude-3-5-sonnet-20241022', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 468, 'output_tokens': 68}}, id='run-60c8267a-52c7-4b6e-87ca-16aa3bd6266b-0', tool_calls=[{'name': 'weather_search', 'args': {'city': 'San Francisco, USA'}, 'id': 'toolu_01WBGTKBWusaPNZYJi5LKmeQ', 'type': 'tool_call'}], usage_metadata={'input_tokens': 468, 'output_tokens': 68, 'total_tokens': 536, 'input_token_details': {}})]}}\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"{'__interrupt__': (Interrupt(value={'question': 'Is this correct?', 'tool_call': {'name': 'weather_search', 'args': {'city': 'San Francisco, USA'}, 'id': 'toolu_01WBGTKBWusaPNZYJi5LKmeQ', 'type': 'tool_call'}}, resumable=True, ns=['human_review_node:621fc4a9-bbf1-9a99-f50b-3bf91675234e'], when='during'),)}\n",
|
||||
"\n",
|
||||
"\n"
|
||||
"Current Tool Call ID:\n",
|
||||
"toolu_014UTKh5uqfc885Fj4RRqGdg\n",
|
||||
"{'messages': [HumanMessage(content=\"what's the weather in sf?\", id='601c4c75-f506-4d91-896d-5e382123de24'), AIMessage(content=[{'text': \"Certainly! I can help you check the weather in San Francisco. To get the most accurate and up-to-date information, I'll use the weather search tool. Let me fetch that for you right away.\", 'type': 'text'}, {'id': 'toolu_014UTKh5uqfc885Fj4RRqGdg', 'input': {'city': 'San Francisco'}, 'name': 'weather_search', 'type': 'tool_use'}], response_metadata={'id': 'msg_013nHyPYxNXFSoXeS6q4oWua', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 360, 'output_tokens': 98}}, id='run-0537e15e-86a4-4c6f-8dfb-6e4c160812c4-0', tool_calls=[{'name': 'weather_search', 'args': {'city': 'San Francisco'}, 'id': 'toolu_014UTKh5uqfc885Fj4RRqGdg', 'type': 'tool_call'}], usage_metadata={'input_tokens': 360, 'output_tokens': 98, 'total_tokens': 458}), ToolMessage(content='User requested changes: pass in the country as well', name='weather_search', id='e20ceddc-a0d3-469d-b31e-512f3042a07e', tool_call_id='toolu_014UTKh5uqfc885Fj4RRqGdg'), AIMessage(content=[{'text': \"I apologize for the oversight. It seems that the weather search function requires more specific information. Let's try again with a more detailed search, including the country. Since San Francisco is commonly associated with the one in California, USA, I'll use that. Here's the updated search:\", 'type': 'text'}, {'id': 'toolu_01AaipBbWDLjHnPcoApx8wRq', 'input': {'city': 'San Francisco, USA'}, 'name': 'weather_search', 'type': 'tool_use'}], response_metadata={'id': 'msg_018rErqC2cLe2VVhebdJf81e', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 480, 'output_tokens': 116}}, id='run-fcba65ed-400a-4783-9ecd-e22051682399-0', tool_calls=[{'name': 'weather_search', 'args': {'city': 'San Francisco, USA'}, 'id': 'toolu_01AaipBbWDLjHnPcoApx8wRq', 'type': 'tool_call'}], usage_metadata={'input_tokens': 480, 'output_tokens': 116, 'total_tokens': 596})]}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Let's now continue executing from here\n",
|
||||
"for event in graph.stream(\n",
|
||||
" # provide our natural language feedback!\n",
|
||||
" Command(\n",
|
||||
" resume={\n",
|
||||
" \"action\": \"feedback\",\n",
|
||||
" \"data\": \"User requested changes: use <city, country> format for location\",\n",
|
||||
" }\n",
|
||||
" ),\n",
|
||||
"# To get the ID of the message we want to replace, we need to fetch the current state and find it there.\n",
|
||||
"state = graph.get_state(thread)\n",
|
||||
"print(\"Current State:\")\n",
|
||||
"print(state.values)\n",
|
||||
"print(\"\\nCurrent Tool Call ID:\")\n",
|
||||
"tool_call_id = state.values[\"messages\"][-1].tool_calls[0][\"id\"]\n",
|
||||
"print(tool_call_id)\n",
|
||||
"\n",
|
||||
"# We now need to construct a replacement tool call.\n",
|
||||
"# We will change the argument to be `San Francisco, USA`\n",
|
||||
"# Note that we could change any number of arguments or tool names - it just has to be a valid one\n",
|
||||
"new_message = {\n",
|
||||
" \"role\": \"tool\",\n",
|
||||
" # This is our natural language feedback\n",
|
||||
" \"content\": \"User requested changes: pass in the country as well\",\n",
|
||||
" \"name\": \"weather_search\",\n",
|
||||
" \"tool_call_id\": tool_call_id,\n",
|
||||
"}\n",
|
||||
"graph.update_state(\n",
|
||||
" # This is the config which represents this thread\n",
|
||||
" thread,\n",
|
||||
" stream_mode=\"updates\",\n",
|
||||
"):\n",
|
||||
" print(event)\n",
|
||||
" print(\"\\n\")"
|
||||
" # This is the updated value we want to push\n",
|
||||
" {\"messages\": [new_message]},\n",
|
||||
" # We push this update acting as our human_review_node\n",
|
||||
" as_node=\"human_review_node\",\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# Let's now continue executing from here\n",
|
||||
"for event in graph.stream(None, thread, stream_mode=\"values\"):\n",
|
||||
" print(event)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -692,32 +626,12 @@
|
||||
"id": "2d2e79ab-7cdb-42ce-b2ca-2932f8782c90",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We can see that we now get to another interrupt - because it went back to the model and got an entirely new prediction of what to call. Let's now approve this one and continue."
|
||||
"We can see that we now get to another breakpoint - because it went back to the model and got an entirely new prediction of what to call. Let's now approve this one and continue."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"id": "ca558915-f4d9-4ff2-95b7-cdaf0c6db485",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Pending Executions!\n",
|
||||
"('human_review_node',)\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(\"Pending Executions!\")\n",
|
||||
"print(graph.get_state(thread).next)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 15,
|
||||
"execution_count": 13,
|
||||
"id": "a30d40ad-611d-4ec3-84be-869ea05acb89",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@@ -725,27 +639,22 @@
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"{'human_review_node': None}\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"Pending Executions!\n",
|
||||
"('human_review_node',)\n",
|
||||
"----\n",
|
||||
"Searching for: San Francisco, USA\n",
|
||||
"----\n",
|
||||
"{'run_tool': {'messages': [{'role': 'tool', 'name': 'weather_search', 'content': 'Sunny!', 'tool_call_id': 'toolu_01WBGTKBWusaPNZYJi5LKmeQ'}]}}\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"{'call_llm': {'messages': [AIMessage(content='The weather in San Francisco is sunny!', additional_kwargs={}, response_metadata={'id': 'msg_01JrfZd8SYyH51Q8rhZuaC3W', 'model': 'claude-3-5-sonnet-20241022', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 549, 'output_tokens': 12}}, id='run-09a198b2-79fa-484d-9d9d-f12432978488-0', usage_metadata={'input_tokens': 549, 'output_tokens': 12, 'total_tokens': 561, 'input_token_details': {}})]}}\n",
|
||||
"\n",
|
||||
"\n"
|
||||
"{'messages': [HumanMessage(content=\"what's the weather in sf?\", id='601c4c75-f506-4d91-896d-5e382123de24'), AIMessage(content=[{'text': \"Certainly! I can help you check the weather in San Francisco. To get the most accurate and up-to-date information, I'll use the weather search tool. Let me fetch that for you right away.\", 'type': 'text'}, {'id': 'toolu_014UTKh5uqfc885Fj4RRqGdg', 'input': {'city': 'San Francisco'}, 'name': 'weather_search', 'type': 'tool_use'}], response_metadata={'id': 'msg_013nHyPYxNXFSoXeS6q4oWua', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 360, 'output_tokens': 98}}, id='run-0537e15e-86a4-4c6f-8dfb-6e4c160812c4-0', tool_calls=[{'name': 'weather_search', 'args': {'city': 'San Francisco'}, 'id': 'toolu_014UTKh5uqfc885Fj4RRqGdg', 'type': 'tool_call'}], usage_metadata={'input_tokens': 360, 'output_tokens': 98, 'total_tokens': 458}), ToolMessage(content='User requested changes: pass in the country as well', name='weather_search', id='e20ceddc-a0d3-469d-b31e-512f3042a07e', tool_call_id='toolu_014UTKh5uqfc885Fj4RRqGdg'), AIMessage(content=[{'text': \"I apologize for the oversight. It seems that the weather search function requires more specific information. Let's try again with a more detailed search, including the country. Since San Francisco is commonly associated with the one in California, USA, I'll use that. Here's the updated search:\", 'type': 'text'}, {'id': 'toolu_01AaipBbWDLjHnPcoApx8wRq', 'input': {'city': 'San Francisco, USA'}, 'name': 'weather_search', 'type': 'tool_use'}], response_metadata={'id': 'msg_018rErqC2cLe2VVhebdJf81e', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 480, 'output_tokens': 116}}, id='run-fcba65ed-400a-4783-9ecd-e22051682399-0', tool_calls=[{'name': 'weather_search', 'args': {'city': 'San Francisco, USA'}, 'id': 'toolu_01AaipBbWDLjHnPcoApx8wRq', 'type': 'tool_call'}], usage_metadata={'input_tokens': 480, 'output_tokens': 116, 'total_tokens': 596}), ToolMessage(content='Sunny!', name='weather_search', id='3f3ee262-70f5-422c-8e3f-6a9af758514d', tool_call_id='toolu_01AaipBbWDLjHnPcoApx8wRq')]}\n",
|
||||
"{'messages': [HumanMessage(content=\"what's the weather in sf?\", id='601c4c75-f506-4d91-896d-5e382123de24'), AIMessage(content=[{'text': \"Certainly! I can help you check the weather in San Francisco. To get the most accurate and up-to-date information, I'll use the weather search tool. Let me fetch that for you right away.\", 'type': 'text'}, {'id': 'toolu_014UTKh5uqfc885Fj4RRqGdg', 'input': {'city': 'San Francisco'}, 'name': 'weather_search', 'type': 'tool_use'}], response_metadata={'id': 'msg_013nHyPYxNXFSoXeS6q4oWua', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 360, 'output_tokens': 98}}, id='run-0537e15e-86a4-4c6f-8dfb-6e4c160812c4-0', tool_calls=[{'name': 'weather_search', 'args': {'city': 'San Francisco'}, 'id': 'toolu_014UTKh5uqfc885Fj4RRqGdg', 'type': 'tool_call'}], usage_metadata={'input_tokens': 360, 'output_tokens': 98, 'total_tokens': 458}), ToolMessage(content='User requested changes: pass in the country as well', name='weather_search', id='e20ceddc-a0d3-469d-b31e-512f3042a07e', tool_call_id='toolu_014UTKh5uqfc885Fj4RRqGdg'), AIMessage(content=[{'text': \"I apologize for the oversight. It seems that the weather search function requires more specific information. Let's try again with a more detailed search, including the country. Since San Francisco is commonly associated with the one in California, USA, I'll use that. Here's the updated search:\", 'type': 'text'}, {'id': 'toolu_01AaipBbWDLjHnPcoApx8wRq', 'input': {'city': 'San Francisco, USA'}, 'name': 'weather_search', 'type': 'tool_use'}], response_metadata={'id': 'msg_018rErqC2cLe2VVhebdJf81e', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 480, 'output_tokens': 116}}, id='run-fcba65ed-400a-4783-9ecd-e22051682399-0', tool_calls=[{'name': 'weather_search', 'args': {'city': 'San Francisco, USA'}, 'id': 'toolu_01AaipBbWDLjHnPcoApx8wRq', 'type': 'tool_call'}], usage_metadata={'input_tokens': 480, 'output_tokens': 116, 'total_tokens': 596}), ToolMessage(content='Sunny!', name='weather_search', id='3f3ee262-70f5-422c-8e3f-6a9af758514d', tool_call_id='toolu_01AaipBbWDLjHnPcoApx8wRq'), AIMessage(content=\"Great news! The weather in San Francisco, USA is currently sunny. \\n\\nHere's a summary of the weather information:\\n- Location: San Francisco, USA\\n- Current conditions: Sunny\\n\\nIt's a beautiful day in San Francisco! The sunny weather is perfect for outdoor activities or simply enjoying the city. Remember to wear sunscreen and stay hydrated if you plan to spend time outside. \\n\\nIs there anything else you'd like to know about the weather in San Francisco or any other location?\", response_metadata={'id': 'msg_017Pnjyte2ZXAREgUvEqbUVt', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 609, 'output_tokens': 107}}, id='run-30c0d0ef-09a3-40ad-b410-80019b284983-0', usage_metadata={'input_tokens': 609, 'output_tokens': 107, 'total_tokens': 716})]}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"for event in graph.stream(\n",
|
||||
" Command(resume={\"action\": \"continue\"}), thread, stream_mode=\"updates\"\n",
|
||||
"):\n",
|
||||
" print(event)\n",
|
||||
" print(\"\\n\")"
|
||||
"print(\"Pending Executions!\")\n",
|
||||
"print(graph.get_state(thread).next)\n",
|
||||
"\n",
|
||||
"for event in graph.stream(None, thread, stream_mode=\"values\"):\n",
|
||||
" print(event)"
|
||||
]
|
||||
}
|
||||
],
|
||||
@@ -765,7 +674,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.4"
|
||||
"version": "3.11.9"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
@@ -7,15 +7,6 @@
|
||||
"source": [
|
||||
"# How to view and update past graph state\n",
|
||||
"\n",
|
||||
"!!! tip \"Prerequisites\"\n",
|
||||
"\n",
|
||||
" This guide assumes familiarity with the following concepts:\n",
|
||||
"\n",
|
||||
" * [Time Travel](../../../concepts/time-travel)\n",
|
||||
" * [Breakpoints](../../../concepts/breakpoints)\n",
|
||||
" * [LangGraph Glossary](../../../concepts/low_level)\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"Once you start [checkpointing](../../persistence) your graphs, you can easily **get** or **update** the state of the agent at any point in time. This permits a few things:\n",
|
||||
"\n",
|
||||
"1. You can surface a state during an interrupt to a user to let them accept an action.\n",
|
||||
@@ -598,7 +589,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.4"
|
||||
"version": "3.11.9"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
@@ -1,25 +1,22 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"attachments": {
|
||||
"f6c5e4f7-4e60-4085-95ad-6edeaeb902e0.png": {
|
||||
"image/png": "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 truncated
|
||||
}
|
||||
},
|
||||
"cell_type": "markdown",
|
||||
"id": "51466c8d-8ce4-4b3d-be4e-18fdbeda5f53",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# How to wait for user input using `interrupt`\n",
|
||||
"# How to wait for user input\n",
|
||||
"\n",
|
||||
"!!! tip \"Prerequisites\"\n",
|
||||
"Human-in-the-loop (HIL) interactions are crucial for [agentic systems](https://langchain-ai.github.io/langgraph/concepts/agentic_concepts/#human-in-the-loop). Waiting for human input is a common HIL interaction pattern, allowing the agent to ask the user clarifying questions and await input before proceeding. \n",
|
||||
"\n",
|
||||
" This guide assumes familiarity with the following concepts:\n",
|
||||
"We can implement this in LangGraph using a [breakpoint](https://langchain-ai.github.io/langgraph/how-tos/human_in_the_loop/breakpoints/): breakpoints allow us to stop graph execution at a specific step. At this breakpoint, we can wait for human input. Once we have input from the user, we can add it to the graph state and proceed.\n",
|
||||
"\n",
|
||||
" * [Human-in-the-loop](../../../concepts/human_in_the_loop)\n",
|
||||
" * [Breakpoints](../../../concepts/breakpoints)\n",
|
||||
" * [LangGraph Glossary](../../../concepts/low_level)\n",
|
||||
" \n",
|
||||
"\n",
|
||||
"**Human-in-the-loop (HIL)** interactions are crucial for [agentic systems](https://langchain-ai.github.io/langgraph/concepts/agentic_concepts/#human-in-the-loop). Waiting for human input is a common HIL interaction pattern, allowing the agent to ask the user clarifying questions and await input before proceeding. \n",
|
||||
"\n",
|
||||
"We can implement this in LangGraph using the [`interrupt()`][langgraph.types.interrupt] function. `interrupt` allows us to stop graph execution to collect input from a user and continue execution with collected input."
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -40,7 +37,7 @@
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%capture --no-stderr\n",
|
||||
"%pip install --quiet -U langgraph langchain_anthropic"
|
||||
"%pip install --quiet -U langgraph langchain_anthropic langchain_openai"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -53,18 +50,10 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"execution_count": null,
|
||||
"id": "c903a1cf-2977-4e2d-ad7d-8b3946821d89",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"ANTHROPIC_API_KEY: ········\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import getpass\n",
|
||||
"import os\n",
|
||||
@@ -75,6 +64,7 @@
|
||||
" os.environ[var] = getpass.getpass(f\"{var}: \")\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"_set_env(\"OPENAI_API_KEY\")\n",
|
||||
"_set_env(\"ANTHROPIC_API_KEY\")"
|
||||
]
|
||||
},
|
||||
@@ -98,24 +88,27 @@
|
||||
"source": [
|
||||
"## Simple Usage\n",
|
||||
"\n",
|
||||
"Let's explore a basic example of using human feedback. A straightforward approach is to create a node, **`human_feedback`**, designed specifically to collect user input. This allows us to gather feedback at a specific, chosen point in our graph.\n",
|
||||
"Let's look at very basic usage of this. One intuitive approach is simply to create a node, `human_feedback`, that will get user feedback. This allows us to place our feedback gathering at a specific, chosen point in our graph.\n",
|
||||
" \n",
|
||||
"1) We specify the [breakpoint](https://langchain-ai.github.io/langgraph/concepts/low_level/#breakpoints) using `interrupt_before` our `human_feedback` node.\n",
|
||||
"\n",
|
||||
"Steps:\n",
|
||||
"2) We set up a [checkpointer](https://langchain-ai.github.io/langgraph/concepts/low_level/#checkpointer) to save the state of the graph up until this node.\n",
|
||||
"\n",
|
||||
"1. **Call `interrupt()`** inside the **`human_feedback`** node. \n",
|
||||
"2. **Set up a [checkpointer](https://langchain-ai.github.io/langgraph/concepts/low_level/#checkpointer)** to save the graph's state up to this node. \n",
|
||||
"3. **Use `Command(resume=...)`** to provide the requested value to the **`human_feedback`** node and resume execution."
|
||||
"3) We use `.update_state` to update the state of the graph with the human response we get.\n",
|
||||
"\n",
|
||||
"* We [use the `as_node` parameter](https://langchain-ai.github.io/langgraph/concepts/low_level/#update-state) to apply this state update as the specified node, `human_feedback`.\n",
|
||||
"* The graph will then resume execution as if the `human_feedback` node just acted."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"execution_count": 5,
|
||||
"id": "58eae42d-be32-48da-8d0a-ab64471657d9",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"image/png": "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 truncated
|
||||
"image/jpeg": "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 truncated
|
||||
"text/plain": [
|
||||
"<IPython.core.display.Image object>"
|
||||
]
|
||||
@@ -127,7 +120,6 @@
|
||||
"source": [
|
||||
"from typing_extensions import TypedDict\n",
|
||||
"from langgraph.graph import StateGraph, START, END\n",
|
||||
"from langgraph.types import Command, interrupt\n",
|
||||
"from langgraph.checkpoint.memory import MemorySaver\n",
|
||||
"from IPython.display import Image, display\n",
|
||||
"\n",
|
||||
@@ -144,8 +136,7 @@
|
||||
"\n",
|
||||
"def human_feedback(state):\n",
|
||||
" print(\"---human_feedback---\")\n",
|
||||
" feedback = interrupt(\"Please provide feedback:\")\n",
|
||||
" return {\"user_feedback\": feedback}\n",
|
||||
" pass\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def step_3(state):\n",
|
||||
@@ -166,7 +157,7 @@
|
||||
"memory = MemorySaver()\n",
|
||||
"\n",
|
||||
"# Add\n",
|
||||
"graph = builder.compile(checkpointer=memory)\n",
|
||||
"graph = builder.compile(checkpointer=memory, interrupt_before=[\"human_feedback\"])\n",
|
||||
"\n",
|
||||
"# View\n",
|
||||
"display(Image(graph.get_graph().draw_mermaid_png()))"
|
||||
@@ -177,12 +168,12 @@
|
||||
"id": "ce0fe2bc-86fc-465f-956c-729805d50404",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Run until our breakpoint at `human_feedback`:"
|
||||
"Run until our breakpoint at `human_feedback` - "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"execution_count": 6,
|
||||
"id": "eb8e7d47-e7c9-4217-b72c-08394a2c4d3e",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@@ -190,14 +181,8 @@
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"---Step 1---\n",
|
||||
"{'step_1': None}\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"---human_feedback---\n",
|
||||
"{'__interrupt__': (Interrupt(value='Please provide feedback:', resumable=True, ns=['human_feedback:e9a51d27-22ed-8c01-3f17-0ed33209b554'], when='during'),)}\n",
|
||||
"\n",
|
||||
"\n"
|
||||
"{'input': 'hello world'}\n",
|
||||
"---Step 1---\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@@ -209,9 +194,8 @@
|
||||
"thread = {\"configurable\": {\"thread_id\": \"1\"}}\n",
|
||||
"\n",
|
||||
"# Run the graph until the first interruption\n",
|
||||
"for event in graph.stream(initial_input, thread, stream_mode=\"updates\"):\n",
|
||||
" print(event)\n",
|
||||
" print(\"\\n\")"
|
||||
"for event in graph.stream(initial_input, thread, stream_mode=\"values\"):\n",
|
||||
" print(event)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -219,12 +203,63 @@
|
||||
"id": "28a7d545-ab19-4800-985b-62837d060809",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Now, we can manually update our graph state with the user input:"
|
||||
"Now, we can just manually update our graph state with with the user input - "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"execution_count": 7,
|
||||
"id": "2165a1bc-1c5b-411f-9e9c-a2b9627e5d56",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"--State after update--\n",
|
||||
"StateSnapshot(values={'input': 'hello world', 'user_feedback': 'go to step 3!'}, next=('step_3',), config={'configurable': {'thread_id': '1', 'checkpoint_ns': '', 'checkpoint_id': '1ef7830e-b807-6142-8002-1b511e4caf96'}}, metadata={'source': 'update', 'step': 2, 'writes': {'human_feedback': {'user_feedback': 'go to step 3!'}}, 'parents': {}}, created_at='2024-09-21T15:48:17.660131+00:00', parent_config={'configurable': {'thread_id': '1', 'checkpoint_ns': '', 'checkpoint_id': '1ef7830e-36d1-6f1e-8001-4d4c913ae8a8'}}, tasks=(PregelTask(id='6b5486bf-eb6c-0e27-4784-cad2a69b86a2', name='step_3', path=('__pregel_pull', 'step_3'), error=None, interrupts=(), state=None),))\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"('step_3',)"
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Get user input\n",
|
||||
"try:\n",
|
||||
" user_input = input(\"Tell me how you want to update the state: \")\n",
|
||||
"except:\n",
|
||||
" user_input = \"go to step 3!\"\n",
|
||||
"\n",
|
||||
"# We now update the state as if we are the human_feedback node\n",
|
||||
"graph.update_state(thread, {\"user_feedback\": user_input}, as_node=\"human_feedback\")\n",
|
||||
"\n",
|
||||
"# We can check the state\n",
|
||||
"print(\"--State after update--\")\n",
|
||||
"print(graph.get_state(thread))\n",
|
||||
"\n",
|
||||
"# We can check the next node, showing that it is node 3 (which follows human_feedback)\n",
|
||||
"graph.get_state(thread).next"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "ccc4a84a-02f2-4b79-a5a5-22173645526d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We can proceed after our breakpoint - "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 64,
|
||||
"id": "3cca588f-e8d8-416b-aba7-0f3ae5e51598",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@@ -232,24 +267,14 @@
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"---human_feedback---\n",
|
||||
"{'human_feedback': {'user_feedback': 'go to step 3!'}}\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"---Step 3---\n",
|
||||
"{'step_3': None}\n",
|
||||
"\n",
|
||||
"\n"
|
||||
"---Step 3---\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Continue the graph execution\n",
|
||||
"for event in graph.stream(\n",
|
||||
" Command(resume=\"go to step 3!\"), thread, stream_mode=\"updates\"\n",
|
||||
"):\n",
|
||||
" print(event)\n",
|
||||
" print(\"\\n\")"
|
||||
"for event in graph.stream(None, thread, stream_mode=\"values\"):\n",
|
||||
" print(event)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -262,7 +287,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"execution_count": 66,
|
||||
"id": "2b83e5ca-8497-43ca-bff7-7203e654c4d3",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@@ -272,7 +297,7 @@
|
||||
"{'input': 'hello world', 'user_feedback': 'go to step 3!'}"
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"execution_count": 66,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@@ -283,19 +308,21 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "b22b9598-7ce4-4d16-b932-bba2bc2803ec",
|
||||
"id": "e36f89e5",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Agent\n",
|
||||
"\n",
|
||||
"In the context of [agents](../../../concepts/agentic_concepts), waiting for user feedback is especially useful for asking clarifying questions. To illustrate this, we’ll create a simple [ReAct-style agent](../../../concepts/agentic_concepts#react-implementation) capable of [tool calling](https://python.langchain.com/docs/concepts/tool_calling/). \n",
|
||||
"In the context of agents, waiting for user feedback is useful to ask clarifying questions.\n",
|
||||
" \n",
|
||||
"To show this, we will build a relatively simple ReAct-style agent that does tool calling. \n",
|
||||
"\n",
|
||||
"For this example, we’ll use Anthropic's chat model along with a **mock tool** (purely for demonstration purposes)."
|
||||
"We will use OpenAI and / or Anthropic's models and a fake tool (just for demo purposes)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "01789855-b769-426d-a329-3cdb29684df8",
|
||||
"id": "b3b8b7e5",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<div class=\"admonition note\">\n",
|
||||
@@ -308,13 +335,13 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"execution_count": 2,
|
||||
"id": "f5319e01",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"image/png": "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 truncated
|
||||
"image/jpeg": "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 truncated
|
||||
"text/plain": [
|
||||
"<IPython.core.display.Image object>"
|
||||
]
|
||||
@@ -348,8 +375,10 @@
|
||||
"\n",
|
||||
"# Set up the model\n",
|
||||
"from langchain_anthropic import ChatAnthropic\n",
|
||||
"from langchain_openai import ChatOpenAI\n",
|
||||
"\n",
|
||||
"model = ChatAnthropic(model=\"claude-3-5-sonnet-latest\")\n",
|
||||
"model = ChatAnthropic(model=\"claude-3-5-sonnet-20240620\")\n",
|
||||
"model = ChatOpenAI(model=\"gpt-4o\")\n",
|
||||
"\n",
|
||||
"from pydantic import BaseModel\n",
|
||||
"\n",
|
||||
@@ -375,7 +404,7 @@
|
||||
" last_message = messages[-1]\n",
|
||||
" # If there is no function call, then we finish\n",
|
||||
" if not last_message.tool_calls:\n",
|
||||
" return END\n",
|
||||
" return \"end\"\n",
|
||||
" # If tool call is asking Human, we return that node\n",
|
||||
" # You could also add logic here to let some system know that there's something that requires Human input\n",
|
||||
" # For example, send a slack message, etc\n",
|
||||
@@ -383,7 +412,7 @@
|
||||
" return \"ask_human\"\n",
|
||||
" # Otherwise if there is, we continue\n",
|
||||
" else:\n",
|
||||
" return \"action\"\n",
|
||||
" return \"continue\"\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"# Define the function that calls the model\n",
|
||||
@@ -396,10 +425,7 @@
|
||||
"\n",
|
||||
"# We define a fake node to ask the human\n",
|
||||
"def ask_human(state):\n",
|
||||
" tool_call_id = state[\"messages\"][-1].tool_calls[0][\"id\"]\n",
|
||||
" location = interrupt(\"Please provide your location:\")\n",
|
||||
" tool_message = [{\"tool_call_id\": tool_call_id, \"type\": \"tool\", \"content\": location}]\n",
|
||||
" return {\"messages\": tool_message}\n",
|
||||
" pass\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"# Build the graph\n",
|
||||
@@ -425,6 +451,20 @@
|
||||
" \"agent\",\n",
|
||||
" # Next, we pass in the function that will determine which node is called next.\n",
|
||||
" should_continue,\n",
|
||||
" # Finally we pass in a mapping.\n",
|
||||
" # The keys are strings, and the values are other nodes.\n",
|
||||
" # END is a special node marking that the graph should finish.\n",
|
||||
" # What will happen is we will call `should_continue`, and then the output of that\n",
|
||||
" # will be matched against the keys in this mapping.\n",
|
||||
" # Based on which one it matches, that node will then be called.\n",
|
||||
" {\n",
|
||||
" # If `tools`, then we call the tool node.\n",
|
||||
" \"continue\": \"action\",\n",
|
||||
" # We may ask the human\n",
|
||||
" \"ask_human\": \"ask_human\",\n",
|
||||
" # Otherwise we finish.\n",
|
||||
" \"end\": END,\n",
|
||||
" },\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# We now add a normal edge from `tools` to `agent`.\n",
|
||||
@@ -443,7 +483,7 @@
|
||||
"# This compiles it into a LangChain Runnable,\n",
|
||||
"# meaning you can use it as you would any other runnable\n",
|
||||
"# We add a breakpoint BEFORE the `ask_human` node so it never executes\n",
|
||||
"app = workflow.compile(checkpointer=memory)\n",
|
||||
"app = workflow.compile(checkpointer=memory, interrupt_before=[\"ask_human\"])\n",
|
||||
"\n",
|
||||
"display(Image(app.get_graph().draw_mermaid_png()))"
|
||||
]
|
||||
@@ -462,7 +502,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"execution_count": 48,
|
||||
"id": "cfd140f0-a5a6-4697-8115-322242f197b5",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@@ -474,51 +514,75 @@
|
||||
"\n",
|
||||
"Use the search tool to ask the user where they are, then look up the weather there\n",
|
||||
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
|
||||
"\n",
|
||||
"[{'text': \"I'll help you with that. Let me first ask the user about their location.\", 'type': 'text'}, {'id': 'toolu_01KNvb7RCVu8yKYUuQQSKN1x', 'input': {'question': 'Where are you located?'}, 'name': 'AskHuman', 'type': 'tool_use'}]\n",
|
||||
"Tool Calls:\n",
|
||||
" AskHuman (toolu_01KNvb7RCVu8yKYUuQQSKN1x)\n",
|
||||
" Call ID: toolu_01KNvb7RCVu8yKYUuQQSKN1x\n",
|
||||
" AskHuman (call_LDo62KBPQKZWxPI5IHxPBF0w)\n",
|
||||
" Call ID: call_LDo62KBPQKZWxPI5IHxPBF0w\n",
|
||||
" Args:\n",
|
||||
" question: Where are you located?\n"
|
||||
" question: Can you tell me where you are located?\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain_core.messages import HumanMessage\n",
|
||||
"\n",
|
||||
"config = {\"configurable\": {\"thread_id\": \"2\"}}\n",
|
||||
"for event in app.stream(\n",
|
||||
" {\n",
|
||||
" \"messages\": [\n",
|
||||
" (\n",
|
||||
" \"user\",\n",
|
||||
" \"Use the search tool to ask the user where they are, then look up the weather there\",\n",
|
||||
" )\n",
|
||||
" ]\n",
|
||||
" },\n",
|
||||
" config,\n",
|
||||
" stream_mode=\"values\",\n",
|
||||
"):\n",
|
||||
"input_message = HumanMessage(\n",
|
||||
" content=\"Use the search tool to ask the user where they are, then look up the weather there\"\n",
|
||||
")\n",
|
||||
"for event in app.stream({\"messages\": [input_message]}, config, stream_mode=\"values\"):\n",
|
||||
" event[\"messages\"][-1].pretty_print()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "cc168c90-a374-4280-a9a6-8bc232dbb006",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We now want to update this thread with a response from the user. We then can kick off another run. \n",
|
||||
"\n",
|
||||
"Because we are treating this as a tool call, we will need to update the state as if it is a response from a tool call. In order to do this, we will need to check the state to get the ID of the tool call."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "924a30ea-94c0-468e-90fe-47eb9c08584d",
|
||||
"execution_count": 50,
|
||||
"id": "63598092-d565-4170-9773-e092d345f8c1",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"('ask_human',)"
|
||||
"('agent',)"
|
||||
]
|
||||
},
|
||||
"execution_count": 9,
|
||||
"execution_count": 50,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"tool_call_id = app.get_state(config).values[\"messages\"][-1].tool_calls[0][\"id\"]\n",
|
||||
"\n",
|
||||
"# We now create the tool call with the id and the response we want\n",
|
||||
"tool_message = [\n",
|
||||
" {\"tool_call_id\": tool_call_id, \"type\": \"tool\", \"content\": \"san francisco\"}\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"# # This is equivalent to the below, either one works\n",
|
||||
"# from langchain_core.messages import ToolMessage\n",
|
||||
"# tool_message = [ToolMessage(tool_call_id=tool_call_id, content=\"san francisco\")]\n",
|
||||
"\n",
|
||||
"# We now update the state\n",
|
||||
"# Notice that we are also specifying `as_node=\"ask_human\"`\n",
|
||||
"# This will apply this update as this node,\n",
|
||||
"# which will make it so that afterwards it continues as normal\n",
|
||||
"app.update_state(config, {\"messages\": tool_message}, as_node=\"ask_human\")\n",
|
||||
"\n",
|
||||
"# We can check the state\n",
|
||||
"# We can see that the state currently has the `agent` node next\n",
|
||||
"# This is based on how we define our graph,\n",
|
||||
"# where after the `ask_human` node goes (which we just triggered)\n",
|
||||
"# there is an edge to the `agent` node\n",
|
||||
"app.get_state(config).next"
|
||||
]
|
||||
},
|
||||
@@ -527,12 +591,12 @@
|
||||
"id": "6a30c9fb-2a40-45cc-87ba-406c11c9f0cf",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"You can see that our graph got interrupted inside the `ask_human` node, which is now waiting for a `location` to be provided. We can provide this value by invoking the graph with a `Command(resume=\"<location>\")` input:"
|
||||
"We can now tell the agent to continue. We can just pass in `None` as the input to the graph, since no additional input is needed"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"execution_count": 51,
|
||||
"id": "a9f599b5-1a55-406b-a76b-f52b3ca06975",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@@ -541,36 +605,23 @@
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
|
||||
"\n",
|
||||
"[{'text': \"I'll help you with that. Let me first ask the user about their location.\", 'type': 'text'}, {'id': 'toolu_01KNvb7RCVu8yKYUuQQSKN1x', 'input': {'question': 'Where are you located?'}, 'name': 'AskHuman', 'type': 'tool_use'}]\n",
|
||||
"Tool Calls:\n",
|
||||
" AskHuman (toolu_01KNvb7RCVu8yKYUuQQSKN1x)\n",
|
||||
" Call ID: toolu_01KNvb7RCVu8yKYUuQQSKN1x\n",
|
||||
" search (call_LJlkCFfHvAS2taKHTaMmORE5)\n",
|
||||
" Call ID: call_LJlkCFfHvAS2taKHTaMmORE5\n",
|
||||
" Args:\n",
|
||||
" question: Where are you located?\n",
|
||||
"=================================\u001b[1m Tool Message \u001b[0m=================================\n",
|
||||
"\n",
|
||||
"san francisco\n",
|
||||
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
|
||||
"\n",
|
||||
"[{'text': \"Now I'll search for the weather in San Francisco.\", 'type': 'text'}, {'id': 'toolu_01Y5C4rU9WcxBqFLYSMGjV1F', 'input': {'query': 'current weather in san francisco'}, 'name': 'search', 'type': 'tool_use'}]\n",
|
||||
"Tool Calls:\n",
|
||||
" search (toolu_01Y5C4rU9WcxBqFLYSMGjV1F)\n",
|
||||
" Call ID: toolu_01Y5C4rU9WcxBqFLYSMGjV1F\n",
|
||||
" Args:\n",
|
||||
" query: current weather in san francisco\n",
|
||||
" query: current weather in San Francisco\n",
|
||||
"=================================\u001b[1m Tool Message \u001b[0m=================================\n",
|
||||
"Name: search\n",
|
||||
"\n",
|
||||
"I looked up: current weather in san francisco. Result: It's sunny in San Francisco, but you better look out if you're a Gemini 😈.\n",
|
||||
"[\"I looked up: current weather in San Francisco. Result: It's sunny in San Francisco, but you better look out if you're a Gemini \\ud83d\\ude08.\"]\n",
|
||||
"==================================\u001b[1m Ai Message \u001b[0m==================================\n",
|
||||
"\n",
|
||||
"Based on the search results, it's currently sunny in San Francisco. Note that this is the current weather at the time of our conversation, and conditions can change throughout the day.\n"
|
||||
"The current weather in San Francisco is sunny. Enjoy the good weather! 🌞\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"for event in app.stream(Command(resume=\"san francisco\"), config, stream_mode=\"values\"):\n",
|
||||
"for event in app.stream(None, config, stream_mode=\"values\"):\n",
|
||||
" event[\"messages\"][-1].pretty_print()"
|
||||
]
|
||||
}
|
||||
@@ -591,7 +642,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.4"
|
||||
"version": "3.11.8"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||