What problem does it solve?
LangChain streamlines building tool-using agents and retrieval-augmented generation (RAG) systems so developers can create chatbots, tool-calling workflows, and document-backed assistants without stitching together providers and vector stores manually.
Core Features & Use Cases
- Agent construction: Create ReAct and tool-calling agents that reason, call functions, and iterate until tasks complete.
- RAG pipelines: Load documents, split and embed text, build vector stores, and run retrieval-backed QA and conversational chains.
- Provider & integration flexibility: Swap LLM providers, connect Chroma/Pinecone/FAISS/Weaviate/Qdrant, and enable LangSmith tracing for observability.
- Use Case: Build a customer support chatbot that retrieves product docs, calls a pricing API, and returns structured answers with source citations.
Quick Start
Use LangChain to create an agent with a model and one retrieval or function tool to answer a user question.