Grounding LLM responses in chunks retrieved from an external corpus so the model reasons over real, citable sources instead of parametric memory alone.
Package-level reference for chromadb on PyPI — install variants, server/client split, embedding-function extras, and alternative vector stores.
Package-level reference for qdrant-client on PyPI — install variants, server version matching, gRPC vs HTTP, fastembed extras, and alternatives.
Package-level reference for the sentence-transformers library on PyPI — install, transformers/torch deps, model registry, and embedding alternatives.
Package-level reference for weaviate-client on PyPI — install variants, the v3 → v4 API split, gRPC, and alternative vector stores.
End-to-end checklist and code for building reliable Retrieval-Augmented Generation pipelines — chunking, embedding, vector DBs, retrieval, and evaluation.
Comprehensive reference for the sentence-transformers Python library — embeddings, similarity, clustering, retrieval, fine-tuning, and popular models (BGE, E5, GTE, Nomic, Jina).
Store and query vector embeddings locally or over a network with ChromaDB. Covers client types, collections, add, query, metadata filters, embedding functions, and LangChain/LlamaIndex integration.
Build RAG pipelines and LLM-powered data applications with LlamaIndex. Covers document loading, indexing, query engines, custom LLMs and embeddings, persistent storage, and agents.
Store and search vector embeddings with the Qdrant Python client. Covers collections, CRUD, filtered vector search, payload indexing, batch upsert, sparse/dense hybrid search, and integrations.
Store, search, and manage vector embeddings with the Weaviate Python client. Covers collections, CRUD, vector/hybrid/BM25 search, multi-tenancy, generative search, and batch import.
navigation
actions
cheat sheet pages