WEBDIENSTE/langgraph
1
0
Fork 0
mirror of https://github.com/langchain-ai/langgraph.git synced 2026-08-28 10:49:56 +02:00
Code Issues Packages Projects Releases Wiki Activity
6,455 Commits 323 Branches 572 Tags
6fe30ca652d8bb7e8c4342fa8fb00a8a2ca84c55
Commit Graph
6455 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Eugene YurtsevandGitHub dbceb3c2e6 docs: remove non directive to stop indexing output code blocks (it doesn't work) (#4461) 
This directive seems to have no effect on code blocks: `{
mkdocs-exclude-search }`. Removing it for now.
 2025-04-29 15:46:29 -04:00
Sydney Runkle 80dca9b9a5 removing remaining v1 logic 2025-04-29 15:11:37 -04:00
Vadym BardaandGitHub ea55c2d468 docs: simplify docstring / API reference for create_react_agent (#4457) 2025-04-29 18:52:43 +00:00
Eugene YurtsevandGitHub 8dd95a450b docs: strip ansi and exclude outputs from search (#4460) 
# Changes

* Strip ANSI codes from outputs
* Exclude outputs from search (relies on an insiders feature, so can't
test locally)

## ANSI Changes

Before


![image](https://github.com/user-attachments/assets/6ca626f3-143b-4f7a-ab4a-0866f0bbf52f)


After


![image](https://github.com/user-attachments/assets/3d2fdb4f-79a0-42d5-9956-e2aa44e3fea2)
 2025-04-29 14:50:07 -04:00
Sydney Runkle da0994b741 removing langchain-core pydantic utilities 2025-04-29 14:31:28 -04:00
Vadym BardaandGitHub 80a74a879c docs: expose supervisor, swarm & MCP in the API reference (#4446) 2025-04-29 17:59:42 +00:00
Eugene YurtsevandGitHub 7170a9f0f4 docs: apply boosts and tag a few things (#4455) 
Manual pass to apply a few heuristics:

* Boost conceptual pages
* Deboost (is that a word?) index pages that list all content
* Prefer Agents pages if search query contains the word "agent"
* Add tags for a few selected pages
 2025-04-29 13:56:57 -04:00
Sydney Runkle 64cfbb0d02 remove v1 test 2025-04-29 13:51:45 -04:00
langchain-infraandGitHub 11b472e876 chore: update eu ips for new cluster (#4454) 2025-04-29 10:54:48 -04:00
infra 5d831726a3 chore: update eu ips for new cluster 2025-04-29 10:50:31 -04:00
David DuongandGitHub 9ffa6371e0 feat(sdk-js): add onLangChainEvent and onDebugEvent to useStream (#4453) 0.4.0 2025-04-29 15:40:09 +02:00
David DuongandGitHub 4d1e5ab71f feat(sdk-js): pass the client instead of apiKey/apiUrl (#4452) 2025-04-29 15:38:47 +02:00
Sydney RunkleandGitHub c0d6524ec7 release: v0.4.0 (#4447) 2025-04-29 09:35:04 -04:00
Tat Dat Duong 8ad5331c89 feat(sdk-js): add onLangChainEvent and onDebugEvent to useStream 2025-04-29 15:34:03 +02:00
Tat Dat Duong cc62a9fa33 feat(sdk-js): pass the client instead of apiKey/apiUrl 2025-04-29 15:17:55 +02:00
David DuongandGitHub b7482a6f6a fix(docs): Studio troubleshooting docs (#4449) 2025-04-29 11:59:39 +02:00
Tat Dat Duong d4df2bd807 fix(docs): Studio troubleshooting docs 2025-04-29 11:58:52 +02:00
Sydney Runkle e99028cfc6 what would it look like to remove pydantic v1 support? 2025-04-28 21:44:17 -04:00
Sydney Runkle 6250b364f7 version bumps and locks 2025-04-28 17:39:20 -04:00
William FHandGitHub 062253fe48 Add examples of configurable headers (#4445) 2025-04-28 12:52:06 -07:00
Sydney RunkleandGitHub fc0d08328d langgraph: fix bug + add test for multi resume (#4444) 
Fine if command is "empty" as we don't add writes for mapped resumes.
 2025-04-28 15:48:33 -04:00
Sydney Runkle 2bf8e690b0 test + bug fix 2025-04-28 15:41:37 -04:00
Vadym BardaandGitHub 11c6a54de9 docs: small update in the manage message history how to (#4442) 2025-04-28 13:22:52 -04:00
Nuno CamposandGitHub 78581b80c2 Support multiple resume values with Command.resume (#4406) 
* Adding support for mapping interrupt ids -> resume values with the
`Command.resume_map` argument, like:

```py
resume_map = {
    i.interrupt_id: f"human input for prompt {i.value}" 
    for i in parent_graph.get_state(thread_config).interrupts 
}

parent_graph.invoke(Command(resume=resume_map), config=thread_config)
```

* Adds an `interrupts` attribute on `StateSnapshot` so that we can
access that directly rather than having to do
`get_state(thread_config).tasks` and then iterate over tasks to find
interrupts

* Deprecates undocumented feature where (if interrupting a graph from
the level of an interrupt), you could pass a dict mapping task ids ->
resume values. Now we recommend and endorse the `interrupt_id` approach
above.

I'll note, from an internal perspective, I would love if we didn't have
to pass around this map, but it seems like the best way right now to
make the necessary resume information necessary at different levels in a
graph with subgraphs.

Fix https://github.com/langchain-ai/langgraph/issues/4028

Slotted to be included in our v0.4.0 release early next week!
 2025-04-28 09:06:58 -07:00
vbarda 78f809bc52 update other tests 2025-04-28 12:02:23 -04:00
Sydney Runkle 5fee0d9d66 skip yielding interrupt if input was a map 2025-04-28 11:47:51 -04:00
William FHandGitHub 68e3d70967 Add section in how-to on exclusions (#4441) 2025-04-28 08:42:32 -07:00
William FHandGitHub dc9f2b1109 Add how-to on headers (#4440) 
and their configurability for configurability
 2025-04-28 15:31:48 +00:00
William FHandGitHub 67aeba6210 Add schema updates for the configurable headers (#4437) 2025-04-28 15:10:07 +00:00
vbarda 4b7ec256e9 prebuilt: switch to executing parallel tool calls via Send by default 2025-04-28 11:07:27 -04:00
Sydney Runkle dbf1c28ccd lint 2025-04-28 10:22:30 -04:00
Sydney Runkle cb25ef985d update loop to append mapped tasks to task specific values 2025-04-28 10:18:39 -04:00
Sydney RunkleandGitHub 2f49ebfd53 packaging: Remove Python Upper Bounds (#4416) 
A few notes:
* We shouldn't be using `tool.poetry.dependencies`, that's deprecated -
waiting for a future PR to address this big change though.
* We should remove upper bounds for all deps unless strictly necessary.
 2025-04-28 10:03:43 -04:00
David DuongandGitHub d9c781cc7d feat(js): add message-specific fallback UI components (#4430) 2025-04-28 12:17:07 +02:00
David DuongandGitHub 66af72acb3 fix(sdk-js): remove client-only bootstrapping warning (#4428) 2025-04-28 12:05:43 +02:00
Tat Dat Duong a44d822cd3 feat(js): add message-specific fallback UI components 2025-04-28 12:03:58 +02:00
Tat Dat Duong 28d884b37a fix(sdk-js): remove client-only bootstrapping warning 2025-04-28 11:52:26 +02:00
William FHandGitHub d7a0da8f06 checkpointer: Enter stack for blobs dict in InMemorySaver (#4419) checkpoint==2.0.25 2025-04-26 13:57:36 -07:00
Vadym BardaandGitHub 2d9347ec33 docs(cloud): update human-in-the-loop guides to use interrupt() (#4418) 2025-04-26 13:37:06 -04:00
Sydney Runkle 5e9bea5134 no upper bounds for python 2025-04-25 17:45:54 -07:00
Sydney RunkleandGitHub 5ddc24ba85 Merge branch 'main' into multi-resumes 2025-04-25 17:05:35 -07:00
Sydney Runkle 0362840d0b revert debugging note" 
"
 2025-04-25 17:00:26 -07:00
Sydney Runkle 44099d27c8 fixing tests 2025-04-25 16:53:37 -07:00
Nuno CamposandGitHub 8951d162f0 Improve logic for drawing virtual end node (#4409) 
- Don't draw unexpected edges to END node
- If a conditional edge has a custom label for END node then draw it
 2025-04-25 15:45:12 -07:00
Nuno Campos d90126b34e Fix 2025-04-25 15:38:41 -07:00
Nuno CamposandGitHub adc4569daf build(deps): bump h11 from 0.14.0 to 0.16.0 in /libs/checkpoint-sqlite (#4403) 
Bumps [h11](https://github.com/python-hyper/h11) from 0.14.0 to 0.16.0.
<details>
<summary>Commits</summary>
<ul>
<li><a
href="https://github.com/python-hyper/h11/commit/1c5b07581f058886c8bdd87adababd7d959dc7ca"><code>1c5b075</code></a>
this time for surer</li>
<li><a
href="https://github.com/python-hyper/h11/commit/d9c369935e853a7ee1aeb7e481f6dddf9b9c9b8a"><code>d9c3699</code></a>
this time for sure...</li>
<li><a
href="https://github.com/python-hyper/h11/commit/d91b9dd2290a25c8c3f5ec15feb57de5873e6e39"><code>d91b9dd</code></a>
blacken</li>
<li><a
href="https://github.com/python-hyper/h11/commit/5a4683ca466b59bbab9b19cfea20ee157b31cee0"><code>5a4683c</code></a>
Soothe mypy</li>
<li><a
href="https://github.com/python-hyper/h11/commit/9c9567f0a92d13a83a8d8ebdbc757c8c2d384536"><code>9c9567f</code></a>
Bump version to 0.16.0</li>
<li><a
href="https://github.com/python-hyper/h11/commit/114803a29ce50116dc47951c690ad4892b1a36ed"><code>114803a</code></a>
Merge commit from fork</li>
<li><a
href="https://github.com/python-hyper/h11/commit/9462006f6ce4941661888228cbd4ac1ea80689b0"><code>9462006</code></a>
Bump version to 0.15.0</li>
<li><a
href="https://github.com/python-hyper/h11/commit/70a96bea8e55403e5d92db14c111432c6d7a8685"><code>70a96be</code></a>
Merge pull request <a
href="https://redirect.github.com/python-hyper/h11/issues/181">#181</a>
from Julien00859/Julien00859/get_int_max_str_digits</li>
<li><a
href="https://github.com/python-hyper/h11/commit/60782ad107e538b9312aac7e1c119c8358bf797c"><code>60782ad</code></a>
Reject Content-Length longer 1 billion TB</li>
<li><a
href="https://github.com/python-hyper/h11/commit/dff7cc397a26ed4acdedd92d1bda6c8f18a6ed9f"><code>dff7cc3</code></a>
Validate Chunked-Encoding chunk footer</li>
<li>Additional commits viewable in <a
href="https://github.com/python-hyper/h11/compare/v0.14.0...v0.16.0">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=h11&package-manager=pip&previous-version=0.14.0&new-version=0.16.0)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)

Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
You can disable automated security fix PRs for this repo from the
[Security Alerts
page](https://github.com/langchain-ai/langgraph/network/alerts).

</details>
 2025-04-25 15:23:46 -07:00
Nuno Campos 6d70559618 Upgrade 2025-04-25 15:17:06 -07:00
Nuno Campos 70afd2dc2c Update all 2025-04-25 15:11:32 -07:00
ccurmeandGitHub 14e7215090 docs: use langchain-tavily in quickstart (#4412) 
We want to deprecate `TavilySearchResults` in langchain-community in
favor of `TavilySearch` in langchain-tavily.

Also update quickstart to use `init_chat_model`.
 2025-04-25 17:54:37 -04:00
Nuno Campos 460edde3a7 Lint 2025-04-25 14:37:53 -07:00