Sydney RunkleandGitHub
4eb124e83d
This PR does a few things:
1. Surfaces interrupts when `stream_mode='values'` (particularly
relevant for `invoke`, where this is the default behavior)
2. Adds an `interrupt_id` property to the `Interrupt` dataclass so that
interrupts can effectively be mapped to resumes
3. Minor docs updates to reflect the new pattern (no need for a special
section on interrupts with `invoke` and `ainvoke`)
* In a different PR (the one with the multiple resume values), as it's
more relevant there: add an `interrupts` property to `StateSnapshot` so
that `interrupts` can easily be iterated over if users are attempting to
map interrupts to resumes.
I **don't** recommend we release this until we have multi-resumes
working.
## Example
We have the following setup where we're sending multiple prompts to the
child graph, which uses `interrupt`:
```py
def child_graph(state):
human_input = interrupt(state["prompt"])
return {
"human_inputs": [human_input],
}
```
<img width="142" alt="Screenshot 2025-04-23 at 10 01 12 AM"
src="https://github.com/user-attachments/assets/c6238bf1-54ad-4e48-ab0b-60a0bfc18485"
/>
Old behavior:
```py
initial_input = {"prompts": ["a", "b"]}
print(parent_graph.invoke(input=initial_input,config=thread_config,stream_mode="values"))
#> {'prompts': ['a', 'b'], 'human_inputs': []}
print(parent_graph.invoke(Command(resume="hello 1"),config=thread_config,stream_mode="values"))
#> {'prompts': ['a', 'b'], 'human_inputs': ['hello 1']}
print(parent_graph.invoke(Command(resume="hello 2"),config=thread_config,stream_mode="values"))
#> {'prompts': ['a', 'b'], 'human_inputs': ['hello 1', 'hello 2']}
```
New behavior:
```py
initial_input = {"prompts": ["a", "b"]}
print(parent_graph.invoke(input=initial_input,config=thread_config,stream_mode="values"))
"""
{
"prompts": ["a", "b"],
"human_inputs": [],
"__interrupt__": [
Interrupt(
value="a",
resumable=True,
ns=["child_graph:38d43a18-a5e7-8ab2-ca83-9d80f6e9ca83"]
),
Interrupt(
value="b",
resumable=True,
ns=["child_graph:dad810e8-738e-9f90-41cd-30c0091eb79b"]
)
]
}
"""
print(parent_graph.invoke(Command(resume="hello 1"),config=thread_config,stream_mode="values"))
"""
{
"prompts": ["a", "b"],
"human_inputs": ["hello 1"],
"__interrupt__": [
Interrupt(
value="b",
resumable=True,
ns=["child_graph:dad810e8-738e-9f90-41cd-30c0091eb79b"]
)
]
}
"""
print(parent_graph.invoke(Command(resume="hello 2"),config=thread_config,stream_mode="values"))
#> {'prompts': ['a', 'b'], 'human_inputs': ['hello 1', 'hello 2']}
```
Setup
To setup requirements for building docs you can run:
poetry install --with test
Serving documentation locally
To run the documentation server locally you can run:
make serve-docs
This will start the documentation server on http://127.0.0.1:8000/langgraph/.
Execute notebooks
If you would like to automatically execute all of the notebooks, to mimic the "Run notebooks" GHA, you can run:
python _scripts/prepare_notebooks_for_ci.py
./_scripts/execute_notebooks.sh
Note: if you want to run the notebooks without %pip install cells, you can run:
python _scripts/prepare_notebooks_for_ci.py --comment-install-cells
./_scripts/execute_notebooks.sh
prepare_notebooks_for_ci.py script will add VCR cassette context manager for each cell in the notebook, so that:
- when the notebook is run for the first time, cells with network requests will be recorded to a VCR cassette file
- when the notebook is run subsequently, the cells with network requests will be replayed from the cassettes
Adding new notebooks
If you are adding a notebook with API requests, it's recommended to record network requests so that they can be subsequently replayed. If this is not done, the notebook runner will make API requests every time the notebook is run, which can be costly and slow.
To record network requests, please make sure to first run prepare_notebooks_for_ci.py script.
Then, run
jupyter execute <path_to_notebook>
Once the notebook is executed, you should see the new VCR cassettes recorded in cassettes directory and discard the updated notebook.
Updating existing notebooks
If you are updating an existing notebook, please make sure to remove any existing cassettes for the notebook in cassettes directory (each cassette is prefixed with the notebook name), and then run the steps from the "Adding new notebooks" section above.
To delete cassettes for a notebook, you can run:
rm cassettes/<notebook_name>*