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
WE
Weaviate
RAG · Hosted vector DB (not an LLM)
8.4
Open-source vector DB with hybrid search and modules.
Freemium· Free: $0 · Flex: $45 · Premium: $400self-hosted RAGhybrid search
CH
Chroma
RAG · Hosted vector DB (not an LLM)
8.1
Embedded, developer-friendly vector store for Python.
Freemium· Starter: $0 · Team: $250 · Enterprise: Customprototypingembedded RAG
PI
Pinecone
FeaturedRAG · Hosted vector DB (not an LLM)
8.8
Managed vector database for production-scale similarity search.
Freemium· Starter: Free · Builder: $20/month flat · Standard: $50/month min. usage · Enterprise: $500/month min. usagemanaged vector DBproduction RAG
LL
LlamaIndex
FeaturedRAG · BYO (Claude / GPT / open)
8.7
Data framework for connecting LLMs to your data.
Freemium· Free open-source; LlamaCloud paidRAGdata ingestion
LA
LangChain
RAG · BYO (any major LLM)
8.3
The broad LLM application framework — chains, agents, retrievers.
Freemium· Free open-source; LangSmith paidgeneral LLM appsRAG