Data, search & knowledge

Vector databases & semantic search

1,175 agents · most starred first

Vector databases & semantic search, page 12 of 12

haystack-azure-cosmosdb

Azure Cosmos DB for NoSQL integration for Haystack, including a document store and vector-search retriever.

langchain-opensolr

LangChain integration for Opensolr — managed Apache Solr with server-side embeddings and hybrid (BM25 + kNN) search

endee-langchain

Langchain integration with endee vector database.

citadeldb-haystack

Haystack document store backed by Citadel: encrypted at rest, with deletes that destroy the key

citadeldb-langchain

LangChain vector store and chat history backed by Citadel: encrypted at rest, with deletes that destroy the key

citadeldb-llamaindex

LlamaIndex vector storage backed by Citadel: encrypted at rest, with deletes that destroy the key

langchain-opensearch-py

Placeholder for the LangChain integration with OpenSearch (langchain-opensearch-py). Real integration is under active development.

llama-index-opensolr

LlamaIndex integration for Opensolr — managed Apache Solr vector store with server-side embeddings and hybrid BM25+kNN search

llama-index-vector-stores-polardbx

llama-index vector_stores PolarDB-X integration

mariadb-haystack

An integration of MariaDB 11.7+ (native VECTOR support) with Haystack

opensolr-haystack

Haystack integration for Opensolr — managed Apache Solr DocumentStore with server-side embeddings and hybrid BM25+kNN retrieval

@kybernesis/brain-embed-openai

OpenAI text-embedding provider for brain-core (inference-plane EmbeddingProvider)

vera-embed-openai

Official OpenAI embeddings provider for VERA

gatrag_server_rate_limiter

Per-IP semantic similarity rate limiter for GATRAG query endpoints

langchain-rostam

LangChain VectorStore integration for the Rostam vector database

langchain-serenedb

An integration package connecting SereneDB and LangChain

langchain-typesense

LangChain vector store integration for Typesense

llama-index-retrievers-alletra-x10000-retriever

llama-index retriever for AlletraMP X10000

llama-index-vector-stores-rostam

LlamaIndex vector store integration for the Rostam vector database

meridian-storage-oci

OCI Distribution object adapter for Meridian

meridian-storage-opensearch

OpenSearch adapter for Meridian V1 multilingual search projections

meridian-storage-valkey

Valkey adapter for Meridian V1 disposable key-value and cache semantics

mistralai-search-toolkit-plugins-postgres

PostgreSQL + pgvector backend for mistralai-search-toolkit

ragleap-vectorstores

Pluggable vector backends beyond ragleap-rag core's 6 (PgVector, FAISS, Pinecone, Weaviate, Qdrant, Milvus) - additional VectorBackend implementations as optional extras, no vendor lock-in, no bloated core dependency footprint.

singlestore-langchain-core

Shared SingleStore helpers for langchain-singlestore and langgraph-singlestore

solr-haystack

Haystack Document Store for Apache Solr

azure-documentdb-haystack

An integration of Azure DocumentDB with Haystack

openai-simple-vectorstore

可扩展的多向量数据库接入库(redis-search / milvus / milvus-lite / pgvector / elasticsearch / sqlite-vec / qdrant),集成 embeddings 与 rerank 模型,支持二阶段召回及插入、删除、刷新等管理功能。

@langchain/turbopuffer

LangChain.js integration for the turbopuffer vector database

@yukiharada1228/langchain-postgres

Unofficial LangChain.js port of langchain-postgres (Postgres/pgvector integrations for LangChain).

@mi8y/cap-agents-cds-vectorstore

CDS Plugin for building vector retrieval in LangGraph/LangChain/DeepAgents - Vector Store

agent-framework-azure-documentdb

Azure DocumentDB vector stores for Microsoft Agent Framework.

agent-framework-mongodb

MongoDB vector stores for Microsoft Agent Framework.

dynamodb-haystack

Haystack integration for dynamodb

langchain-aspected

LangChain integration for the Aspected vector database

langchain-hybit

Official Python SDK for the HyBit Vector Database

langchain-polign

LangChain vector store for polign_db

langchain-whoosh

A pure-Python BM25 (lexical) retriever for LangChain, powered by Whoosh.

llama-index-postprocessor-jev

Drop-in LlamaIndex reranker powered by TypeSafe Jev (typed 0–3 scores)

llama-index-retrievers-whoosh

A pure-Python BM25 (lexical) retriever for LlamaIndex, powered by Whoosh.

llama-index-vector-stores-infino

LlamaIndex integration for Infino — vector, BM25, hybrid (RRF), and SQL retrieval over one engine on object storage.

llama-index-vector-stores-polign

LlamaIndex vector store for polign_db

llamaindex-hybit

Official Python SDK for the HyBit Vector Database

manicule-ollama

Embedding backend for manicule that runs the model on an Ollama server.

mistralai-search-toolkit-plugins-qdrant

Qdrant plugin for Mistral Search Toolkit

rag-search-kit

A hybrid retrieval component for RAG pipelines.

@johpaz/hive-db

Motor de base de datos embebido, local-first y agent-native: event-log inmutable, proyecciones deterministas, búsqueda híbrida BM25+ANN y grafo de consentimiento.

agent-framework-duckdb

DuckDB vector stores for Microsoft Agent Framework.

agent-framework-oracle

Oracle AI Database native vector stores for Microsoft Agent Framework.

agent-framework-sql-server

SQL Server native vector integration for Microsoft Agent Framework.

agent-seed-brain

Compile any domain into an unbiased, incrementally-updatable seed index for AI agents. Zero dependencies.

circuit-rag

Exact, certified GPU vector search for RAG

jev-rag-retrieval

Jev-steered ingestion and retrieval for any vector database

langchain-amu

LangChain integration for amu-pgvector: a VectorStore and Retriever backed by lineage-gated Analytical Memory Units on PostgreSQL + pgvector.

langchain-cairn

LangChain vector store for Cairn, the hybrid search database where a deletion is final

langchain-chassisdb

LangChain vector store on Chassis: semantic search in one file, in your own process

langchain-cyborgdb

LangChain integration for CyborgDB: The Confidential Vector Database

langchain-infinispan

An integration package connecting Infinispan and LangChain

langchain-reranker

Add init_reranker to the LangChain ecosystem

llama-index-vector-stores-cairn

LlamaIndex vector store for Cairn, the hybrid search database where a deletion is final

vantadb-litellm

LiteLLM embedding gateway + VantaDB storage — unified embedding provider with local vector search

vantadb-ollama

Ollama local embedding API wrapper + VantaDB storage — generate embeddings via Ollama and store/search them in VantaDB

vantadb-openai

OpenAI embedding API wrapper + VantaDB storage — generate embeddings via OpenAI and store/search them in VantaDB

wexample-storage
zero-agent-core-embeddings

Zero Agent Core 的 Embedding Provider 扩展

@sap/hana-langchain

Integrates LangChain.js with SAP HANA Cloud to make use of vector search, knowledge graph, and further in-database capabilities as part of LLM-driven applications.

llama-index-vector-stores-ngt

LlamaIndex vector store integration for NGT (Neighborhood Graph and Tree)

langchain-houyidb

LangChain VectorStore adapter for HouyiDB

langchain-kjarni

LangChain integration for Kjarni: local embeddings in your own process, with no PyTorch, no ONNX Runtime and no server.

llama-index-embeddings-kjarni

LlamaIndex embeddings with Kjarni: local models in your own process, with no PyTorch, no ONNX Runtime and no server.

llama-index-vector-stores-houyidb

LlamaIndex VectorStore adapter for HouyiDB

gyrfalcon-rag

Fast hybrid retrieval for RAG: BM25 and dense search in one Rust engine, quick even on small CPUs.

fse-haystack

fse embeddings for haystack-ai

langchain-fse

fse embeddings for langchain-core

llama-index-embeddings-fse

fse embeddings for llama-index-core

More in Data, search & knowledge