dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>Eugene Yurtsev
7c6dbb3972 chore(deps): bump astral-sh/setup-uv from 6 to 7 (#6273)
Bumps [astral-sh/setup-uv](https://github.com/astral-sh/setup-uv) from 6
to 7.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/astral-sh/setup-uv/releases">astral-sh/setup-uv's
releases</a>.</em></p>
<blockquote>
<h2>v7.0.0 🌈 node24 and a lot of bugfixes</h2>
<h2>Changes</h2>
<p>This release comes with a load of bug fixes and a speed up. Because
of switching from node20 to node24 it is also a breaking change. If you
are running on GitHub hosted runners this will just work, if you are
using self-hosted runners make sure, that your runners are up to date.
If you followed the normal installation instructions your self-hosted
runner will keep itself updated.</p>
<p>This release also removes the deprecated input
<code>server-url</code> which was used to download uv releases from a
different server.
The <a
href="https://github.com/astral-sh/setup-uv?tab=readme-ov-file#manifest-file">manifest-file</a>
input supersedes that functionality by adding a flexible way to define
available versions and where they should be downloaded from.</p>
<h3>Fixes</h3>
<ul>
<li>The action now respects when the environment variable
<code>UV_CACHE_DIR</code> is already set and does not overwrite it. It
now also finds <a
href="https://docs.astral.sh/uv/reference/settings/#cache-dir">cache-dir</a>
settings in config files if you set them.</li>
<li>Some users encountered problems that <a
href="https://github.com/astral-sh/setup-uv?tab=readme-ov-file#disable-cache-pruning">cache
pruning</a> took forever because they had some <code>uv</code> processes
running in the background. Starting with uv version <code>0.8.24</code>
this action uses <code>uv cache prune --ci --force</code> to ignore the
running processes</li>
<li>If you just want to install uv but not have it available in path,
this action now respects <code>UV_NO_MODIFY_PATH</code></li>
<li>Some other actions also set the env var <code>UV_CACHE_DIR</code>.
This action can now deal with that but as this could lead to unwanted
behavior in some edgecases a warning is now displayed.</li>
</ul>
<h3>Improvements</h3>
<p>If you are using minimum version specifiers for the version of uv to
install for example</p>
<pre lang="toml"><code>[tool.uv]
required-version = &quot;&gt;=0.8.17&quot;
</code></pre>
<p>This action now detects that and directly uses the latest version.
Previously it would download all available releases from the uv repo
to determine the highest matching candidate for the version specifier,
which took much more time.</p>
<p>If you are using other specifiers like <code>0.8.x</code> this action
still needs to download all available releases because the specifier
defines an upper bound (not 0.9.0 or later) and &quot;latest&quot; would
possibly not satisfy that.</p>
<h2>🚨 Breaking changes</h2>
<ul>
<li>Use node24 instead of node20 <a
href="https://github.com/eifinger"><code>@​eifinger</code></a> (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/608">#608</a>)</li>
<li>Remove deprecated input server-url <a
href="https://github.com/eifinger"><code>@​eifinger</code></a> (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/607">#607</a>)</li>
</ul>
<h2>🐛 Bug fixes</h2>
<ul>
<li>Respect UV_CACHE_DIR and cache-dir <a
href="https://github.com/eifinger"><code>@​eifinger</code></a> (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/612">#612</a>)</li>
<li>Use --force when pruning cache <a
href="https://github.com/eifinger"><code>@​eifinger</code></a> (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/611">#611</a>)</li>
<li>Respect UV_NO_MODIFY_PATH <a
href="https://github.com/eifinger"><code>@​eifinger</code></a> (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/603">#603</a>)</li>
<li>Warn when <code>UV_CACHE_DIR</code> has changed <a
href="https://github.com/jamesbraza"><code>@​jamesbraza</code></a> (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/601">#601</a>)</li>
</ul>
<h2>🚀 Enhancements</h2>
<ul>
<li>Shortcut to latest version for minimum version specifier <a
href="https://github.com/eifinger"><code>@​eifinger</code></a> (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/598">#598</a>)</li>
</ul>
<h2>🧰 Maintenance</h2>
<ul>
<li>Bump dependencies <a
href="https://github.com/eifinger"><code>@​eifinger</code></a> (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/613">#613</a>)</li>
<li>Fix test-uv-no-modify-path <a
href="https://github.com/eifinger"><code>@​eifinger</code></a> (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/604">#604</a>)</li>
</ul>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="https://github.com/astral-sh/setup-uv/commit/3259c6206f993105e3a61b142c2d97bf4b9ef83d"><code>3259c62</code></a>
Bump deps (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/633">#633</a>)</li>
<li><a
href="https://github.com/astral-sh/setup-uv/commit/bf8e8ed895b7f686f85839659243f31a7df4a977"><code>bf8e8ed</code></a>
Split up documentation (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/632">#632</a>)</li>
<li><a
href="https://github.com/astral-sh/setup-uv/commit/9c6b5e9fb575cac8e82bb437dd7fc25a094bd85d"><code>9c6b5e9</code></a>
Add resolution-strategy input to support oldest compatible version
selection ...</li>
<li><a
href="https://github.com/astral-sh/setup-uv/commit/a5129e99f44f5d2ba22cdc54770745bd6f0d9c33"><code>a5129e9</code></a>
Add copilot-instructions.md (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/630">#630</a>)</li>
<li><a
href="https://github.com/astral-sh/setup-uv/commit/d18bcc753ac29c1ed721aa4a812a90eb937852d6"><code>d18bcc7</code></a>
Add value of UV_PYTHON_INSTALL_DIR to path (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/628">#628</a>)</li>
<li><a
href="https://github.com/astral-sh/setup-uv/commit/bd1f875aba1ebb6d38211b773b094ad1dcca58df"><code>bd1f875</code></a>
Set output venv when activate-environment is used (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/627">#627</a>)</li>
<li><a
href="https://github.com/astral-sh/setup-uv/commit/1a91c3851df47749b241e3c5c696350957c93ff0"><code>1a91c38</code></a>
chore: update known checksums for 0.9.2 (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/626">#626</a>)</li>
<li><a
href="https://github.com/astral-sh/setup-uv/commit/c79f606987cb4a0f3d1a95a3e44bcebfb0a9b303"><code>c79f606</code></a>
chore: update known checksums for 0.9.1 (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/625">#625</a>)</li>
<li><a
href="https://github.com/astral-sh/setup-uv/commit/e0249f159931b41f44fc8208c9b4cff085288cc9"><code>e0249f1</code></a>
Fall back to PR for updating known versions (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/623">#623</a>)</li>
<li><a
href="https://github.com/astral-sh/setup-uv/commit/6d2eb15b4979924f7be71aa06908c6211f80ac88"><code>6d2eb15</code></a>
Cache python installs (<a
href="https://redirect.github.com/astral-sh/setup-uv/issues/621">#621</a>)</li>
<li>Additional commits viewable in <a
href="https://github.com/astral-sh/setup-uv/compare/v6...v7">compare
view</a></li>
</ul>
</details>
<br />


[![Dependabot compatibility
score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=astral-sh/setup-uv&package-manager=github_actions&previous-version=6&new-version=7)](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)


</details>

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
2025-10-14 10:55:27 -04:00
2025-06-10 10:06:08 -07:00
2025-09-09 14:22:19 +00:00
2024-03-15 14:31:59 -07:00

LangGraph Logo

Version Downloads Open Issues Docs

Trusted by companies shaping the future of agents including Klarna, Replit, Elastic, and more LangGraph is a low-level orchestration framework for building, managing, and deploying long-running, stateful agents.

Get started

Install LangGraph:

pip install -U langgraph

Then, create an agent using prebuilt components:

# pip install -qU "langchain[anthropic]" to call the model

from langgraph.prebuilt import create_react_agent

def get_weather(city: str) -> str:
    """Get weather for a given city."""
    return f"It's always sunny in {city}!"

agent = create_react_agent(
    model="anthropic:claude-3-7-sonnet-latest",
    tools=[get_weather],
    prompt="You are a helpful assistant"
)

# Run the agent
agent.invoke(
    {"messages": [{"role": "user", "content": "what is the weather in sf"}]}
)

For more information, see the Quickstart. Or, to learn how to build an agent workflow with a customizable architecture, long-term memory, and other complex task handling, see the LangGraph basics tutorials.

Core benefits

LangGraph provides low-level supporting infrastructure for any long-running, stateful workflow or agent. LangGraph does not abstract prompts or architecture, and provides the following central benefits:

  • Durable execution: Build agents that persist through failures and can run for extended periods, automatically resuming from exactly where they left off.
  • Human-in-the-loop: Seamlessly incorporate human oversight by inspecting and modifying agent state at any point during execution.
  • Comprehensive memory: Create truly stateful agents with both short-term working memory for ongoing reasoning and long-term persistent memory across sessions.
  • Debugging with LangSmith: Gain deep visibility into complex agent behavior with visualization tools that trace execution paths, capture state transitions, and provide detailed runtime metrics.
  • Production-ready deployment: Deploy sophisticated agent systems confidently with scalable infrastructure designed to handle the unique challenges of stateful, long-running workflows.

LangGraphs ecosystem

While LangGraph can be used standalone, it also integrates seamlessly with any LangChain product, giving developers a full suite of tools for building agents. To improve your LLM application development, pair LangGraph with:

  • LangSmith — Helpful for agent evals and observability. Debug poor-performing LLM app runs, evaluate agent trajectories, gain visibility in production, and improve performance over time.
  • LangGraph Platform — Deploy and scale agents effortlessly with a purpose-built deployment platform for long running, stateful workflows. Discover, reuse, configure, and share agents across teams — and iterate quickly with visual prototyping in LangGraph Studio.
  • LangChain Provides integrations and composable components to streamline LLM application development.

Note

Looking for the JS version of LangGraph? See the JS repo and the JS docs.

Additional resources

  • Guides: Quick, actionable code snippets for topics such as streaming, adding memory & persistence, and design patterns (e.g. branching, subgraphs, etc.).
  • Reference: Detailed reference on core classes, methods, how to use the graph and checkpointing APIs, and higher-level prebuilt components.
  • Examples: Guided examples on getting started with LangGraph.
  • LangChain Forum: Connect with the community and share all of your technical questions, ideas, and feedback.
  • LangChain Academy: Learn the basics of LangGraph in our free, structured course.
  • Templates: Pre-built reference apps for common agentic workflows (e.g. ReAct agent, memory, retrieval etc.) that can be cloned and adapted.
  • Case studies: Hear how industry leaders use LangGraph to ship AI applications at scale.

Acknowledgements

LangGraph is inspired by Pregel and Apache Beam. The public interface draws inspiration from NetworkX. LangGraph is built by LangChain Inc, the creators of LangChain, but can be used without LangChain.

Languages
Python 99.6%
Makefile 0.2%
TypeScript 0.1%