Repository files navigation

LangChain is a framework for building LLM-powered applications. It helps you chaintogether interoperable components and third-party integrations to simplify AIapplication development — all while future-proofing decisions as the underlyingtechnology evolves.

pip install -U langchain

To learn more about LangChain, check outthe docs. If you’re looking for moreadvanced customization or agent orchestration, check outLangGraph, our framework for buildingcontrollable agent workflows.

LangChain helps developers build applications powered by LLMs through a standardinterface for models, embeddings, vector stores, and more.

Use LangChain for:

• Real-time data augmentation. Easily connect LLMs to diverse data sources andexternal / internal systems, drawing from LangChain’s vast library of integrations withmodel providers, tools, vector stores, retrievers, and more.
• Model interoperability. Swap models in and out as your engineering teamexperiments to find the best choice for your application’s needs. As the industryfrontier evolves, adapt quickly — LangChain’s abstractions keep you moving withoutlosing momentum.

While the LangChain framework can be used standalone, it also integrates seamlesslywith any LangChain product, giving developers a full suite of tools when building LLMapplications.

To improve your LLM application development, pair LangChain with:

• LangSmith - Helpful for agent evals andobservability. Debug poor-performing LLM app runs, evaluate agent trajectories, gainvisibility in production, and improve performance over time.
• LangGraph - Build agents that canreliably handle complex tasks with LangGraph, our low-level agent orchestrationframework. LangGraph offers customizable architecture, long-term memory, andhuman-in-the-loop workflows — and is trusted in production by companies like LinkedIn,Uber, Klarna, and GitLab.
• LangGraph Platform - Deployand scale agents effortlessly with a purpose-built deployment platform for longrunning, stateful workflows. Discover, reuse, configure, and share agents acrossteams — and iterate quickly with visual prototyping inLangGraph Studio.

• Tutorials: Simple walkthroughs withguided examples on getting started with LangChain.
• How-to Guides: Quick, actionable codesnippets for topics such as tool calling, RAG use cases, and more.
• Conceptual Guides: Explanations of keyconcepts behind the LangChain framework.
• LangChain Forum: Connect with the community and share all of your technical questions, ideas, and feedback.
• API Reference: Detailed reference onnavigating base packages and integrations for LangChain.