e0ace8227c
The first cut of close()/aclose() unconditionally closed the SDK
client's underlying httpx pool. But both integrations back their
clients with a PROCESS-WIDE SHARED pool via @lru_cache
(`_get_default_*httpx_client`): every model with the same
base_url/timeout/proxy reuses one pool by design. Closing it from a
single model's teardown broke every other live model in the process —
observed in a long-lived worker as:
RuntimeError: Cannot send a request, as the client has been closed.
-> anthropic.APIConnectionError: Connection error.
Fix: close()/aclose() now release the underlying httpx client ONLY when
the model privately owns it; the shared cached pool and user-supplied
clients are left intact.
- anthropic: `ChatAnthropic` always wraps the shared cached pool (it has
no http_client field), so close()/aclose() are effectively no-ops for
the pool. An identity check against the lru-cache getter
(`_wraps_shared_httpx`) guards a hypothetical future private-client
path. `_http_client_params()` is factored out so the cached_property
builders and the identity check stay in sync.
- openai: ownership is computed in `validate_environment` and stored on
`_owns_sync_http_client` / `_owns_async_http_client`. A client is owned
iff the model built it privately — the unhashable-`httpx.Timeout`
fresh-client path or an `openai_proxy` transport — and the user did not
supply their own `http_client` / `http_async_client`. Default (shared
cache) and user-supplied clients are never closed.
Tests rewritten to pin the invariant: a regression test builds two
default models, closes one, and asserts the other's shared pool is still
open; plus owned-path and user-injected-not-closed cases.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The agent engineering platform.
LangChain is a framework for building agents and LLM-powered applications. It helps you chain together interoperable components and third-party integrations to simplify AI application development — all while future-proofing decisions as the underlying technology evolves.
Tip
Just getting started? Check out Deep Agents — a higher-level package built on LangChain for agents that have built-in capabilites for common usage patterns such as planning, subagents, file system usage, and more.
Quickstart
pip install langchain
# or
uv add langchain
from langchain.chat_models import init_chat_model
model = init_chat_model("openai:gpt-5.4")
result = model.invoke("Hello, world!")
If you're looking for more advanced customization or agent orchestration, check out LangGraph, our framework for building controllable agent workflows.
For an equivalent JS/TS library, check out LangChain.js.
Tip
For developing, debugging, and deploying AI agents and LLM applications, see LangSmith.
LangChain ecosystem
While the LangChain framework can be used standalone, it also integrates seamlessly with any LangChain product, giving developers a full suite of tools when building LLM applications.
- Deep Agents — Build agents that can plan, use subagents, and leverage file systems for complex tasks
- LangGraph — Build agents that can reliably handle complex tasks with our low-level agent orchestration framework
- Integrations — Chat & embedding models, tools & toolkits, and more
- LangSmith — Agent evals, observability, and debugging for LLM apps
- LangSmith Deployment — Deploy and scale agents with a purpose-built platform for long-running, stateful workflows
Why use LangChain?
LangChain helps developers build applications powered by LLMs through a standard interface for models, embeddings, vector stores, and more.
- Real-time data augmentation — Easily connect LLMs to diverse data sources and external/internal systems, drawing from LangChain's vast library of integrations with model providers, tools, vector stores, retrievers, and more
- Model interoperability — Swap models in and out as your engineering team experiments to find the best choice for your application's needs. As the industry frontier evolves, adapt quickly — LangChain's abstractions keep you moving without losing momentum
- Rapid prototyping — Quickly build and iterate on LLM applications with LangChain's modular, component-based architecture. Test different approaches and workflows without rebuilding from scratch, accelerating your development cycle
- Production-ready features — Deploy reliable applications with built-in support for monitoring, evaluation, and debugging through integrations like LangSmith. Scale with confidence using battle-tested patterns and best practices
- Vibrant community and ecosystem — Leverage a rich ecosystem of integrations, templates, and community-contributed components. Benefit from continuous improvements and stay up-to-date with the latest AI developments through an active open-source community
- Flexible abstraction layers — Work at the level of abstraction that suits your needs — from high-level chains for quick starts to low-level components for fine-grained control. LangChain grows with your application's complexity
Documentation
- docs.langchain.com – Comprehensive documentation, including conceptual overviews and guides
- reference.langchain.com/python – API reference docs for LangChain packages
- Chat LangChain – Chat with the LangChain documentation and get answers to your questions
Discussions: Visit the LangChain Forum to connect with the community and share all of your technical questions, ideas, and feedback.
Additional resources
- Contributing Guide – Learn how to contribute to LangChain projects and find good first issues.
- Code of Conduct – Our community guidelines and standards for participation.
- LangChain Academy – Comprehensive, free courses on LangChain libraries and products, made by the LangChain team.