Retrieval and search · MLD-1303
Vector database
A system storing vectors and associated data with indexing, filtering, and operational features.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Serve searchable document embeddings with metadata.
Original caveat
Products differ in consistency, filtering, and indexing semantics.
Context and aliases
Level: Intermediate. Stages: Data · Retrieval · Inference · Evaluation.
Tags: ML · NLP · SLM · LLM · IR.
Aliases: None recorded.
Related concepts
Concepts linking here
Technology connections
- Chroma — Embedding-oriented retrieval database and application tooling.
- Elasticsearch — Distributed search and analytics engine.
- FAISS — Library for dense-vector similarity search and clustering.
- hnswlib — Library implementing HNSW approximate nearest-neighbor indexes.
- LanceDB — Vector database built around the Lance columnar format.
- Milvus — Distributed vector database.
- OpenSearch — Open-source distributed search and analytics suite.
- pgvector — PostgreSQL extension for vector similarity search.
- Pinecone — Managed vector-database service.
- Qdrant — Vector database with payload filtering and retrieval APIs.
- Vespa — Search and recommendation serving engine with programmable ranking.
- Weaviate — Object and vector database with hybrid retrieval features.
Original references
- Faiss documentation ↗ · Reference link
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks ↗ · Consulted
- Sentence Transformers documentation ↗ · Reference link
- Original reference URL ↗