A pattern where an LLM is given relevant documents (retrieved from a vector or keyword index) at query time, so its response is grounded in real data rather than only what it memorised during training.
retrieval
Retrieval-Augmented Generation
Related terms
Tools that implement Retrieval-Augmented Generation
Chroma
RAG · Hosted vector DB (not an LLM)
8.1
Embedded, developer-friendly vector store for Python.
Freemium· Free open-source; Chroma Cloud paidprototypingembedded RAG
Pinecone
FeaturedRAG · Hosted vector DB (not an LLM)
8.8
Managed vector database for production-scale similarity search.
Freemium· Free starter; serverless pay-as-you-go from $0.33/1M readsmanaged vector DBproduction RAG
LangChain
RAG · BYO (any major LLM)
8.3
The broad LLM application framework — chains, agents, retrievers.
Freemium· Free open-source; LangSmith paidgeneral LLM appsRAG
Weaviate
RAG · Hosted vector DB (not an LLM)
8.4
Open-source vector DB with hybrid search and modules.
Freemium· Free open-source; cloud from $25/moself-hosted RAGhybrid search
LlamaIndex
FeaturedRAG · BYO (Claude / GPT / open)
8.7
Data framework for connecting LLMs to your data.
Freemium· Free open-source; LlamaCloud paidRAGdata ingestion