Self Query Retriever
This retriever inspects the natural language query and writes a structured query to run on the underlying VectorStore.
Retrieval Augmented Generation (RAG) with LangChain connects your company data to the power of LLMs.
150+
Document Loaders
60+
Vector Stores
50+
Embedding Models
40+
Retrievers
Build best-in-class RAG systems with LangChain's comprehensive integrations, state-of-the-art techniques, and infinite composability.
LangChain offers an extensive library of off-the-shelf tools and an intuitive framework for customizing your own.
The LangChain Indexing API syncs your data from any source into a vector store, helping you save money and time.
Start by hosting a meetup, building a digital community, or creating educational content - and share it with us in our Community Slack!