Data, search & knowledge

Vector databases & semantic search

1,175 agents · most starred first

Vector databases & semantic search, page 11 of 12

swarmauri_doc2vec_vectorstore

A Doc2Vec based Vector Store and Doc2Vec Based Embedding Model.

swarmauri_embedding_doc2vec

A Doc2Vec based Embedding Model.

swarmauri_embedding_nmf

NMF Embedding for Swarmauri.

swarmauri_embedding_tfidf

Tfidf Embedding for Swarmauri

swarmauri_parser_bertembedding

Swarmauri Bert Embedding Parser

swarmauri_vectorstore_annoy

Swarmauri Annoy Vector Store

swarmauri_vectorstore_cloudweaviate

Swarmauri Weaviate Vector Store

swarmauri_vectorstore_doc2vec

A Doc2Vec based Vector Store and Doc2Vec Based Embedding Model.

swarmauri_vectorstore_duckdb

A DuckDB based Vector Store

swarmauri_vectorstore_fs

Swarmauri filesystem-aware BM25F vector store

swarmauri_vectorstore_git

Swarmauri Git Vector Store

swarmauri_vectorstore_mlm

Swarmauri MLM Vector Store

swarmauri_vectorstore_neo4j

Swarmauri Neo4j Vector Store

swarmauri_vectorstore_persistentchromadb

A Persistent ChromaDB based Vector Store

swarmauri_vectorstore_pinecone

Swarmauri Pinecone Vector Store

swarmauri_vectorstore_qdrant

Swarmauri Persistent Qdrant Vector Store

swarmauri_vectorstore_redis

Swarmauri Redis Vector Store

swarmauri_vectorstore_tfidf

A Tfidf based Vector Store and Tfidf Based Embedding Model.

tairHaystack

Tair vector database with Haystack

tensorage

Storing tensors in a supabase backend

turborag

Compressed vector and graph-augmented retrieval engine with adaptive two-stage search, implementing TurboQuant/QJL quantization from Google Research.

txtai

All-in-one open-source AI framework for semantic search, LLM orchestration and language model workflows

txtai-minimal

All-in-one open-source AI framework for semantic search, LLM orchestration and language model workflows

txtai-py

Python client for txtai

vecx-langchain

Encrypted Vector Database for Secure and Fast ANN Searches with LangChain

vecx-llamaindex

Encrypted Vector Database for Secure and Fast ANN Searches

vespa-haystack

Haystack integration for Vespa

vlite-storage

Super simple vector data storage based on vectorlite

voyage-embedders-haystack

Haystack component to embed strings and Documents using VoyageAI Embedding models.

weaviate-haystack

An integration of Weaviate vector database with Haystack

weaviate-txtai

An integration of the weaviate vector search engine with txtai

wordllama

WordLlama NLP Utility

z3c.optionstorage

Optional Storages -- Persistent, Managable Vocabularies

zc.FileStorage

New file-storage pack hack.

zc.beforestorage

View storage before a given time

zc.demostorage2

ZODB storage that stores changes relative to a base storage

zc.recipe.filestorage

ZC Buildout recipe for defining a file-storage

zc.zlibstorage

ZODB storage wrapper for zlib compression of database records

nanoindex-rag

Compressed vector index for RAG pipelines — 7-10x storage reduction, no training required

skeg-ollama

Ollama-based embedding + retrieval pipeline backed by skeg.

@turtlepusher/embeddings

V3 Embedding Service - OpenAI, Transformers.js, Agentic-Flow (ONNX), Mock providers with hyperbolic embeddings, normalization, and chunking

llama-index-cockroachdb

LlamaIndex vector store, reader, retriever, and KV/Doc/Index/Chat storage backends for CockroachDB

langchain-voxell

LangChain embeddings for Forge, Voxell's hosted text-embedding API (turbo, pro, ultra tiers). Voxell's Ingot-8B-R3 ranks #1 for English on the public MTEB leaderboard.

llama-index-embeddings-forge

LlamaIndex embeddings for Forge — Voxell's text-embedding API (turbo/pro/ultra; ultra = Qwen3-Embedding-8B, ~75+ avg MTEB, #4 English).

pixelrag-embed

Image tiles to vectors to FAISS index. Three independent CLI tools.

pixelrag-index

Build searchable FAISS indexes from any document source

pixelrag-serve

FAISS-based visual search API. Serves any pre-built index.

vision-agents-plugins-qdrant

Qdrant RAG integration for Vision Agents with hybrid search

@vektormemory/vex

Cross-standard vector DB migration tool — .vmig.jsonl interchange format for agent memory. Import Claude and ChatGPT conversations with LLM fact extraction. Migrate between Pinecone, Qdrant, Chroma, Weaviate, pgvector, Redis, Milvus, Neo4j, VEKTOR. Conver

@farukada/aws-langchain-s3-vector-ts

LangChain-compatible Amazon S3 Vectors store for TypeScript

arangodb-haystack

Haystack integration for arangodb

topk-haystack

TopK document store integration for Haystack with vector search, semantic search, keyword search, hybrid search and metadata retrievers

langchain-vectorpanda

LangChain VectorStore integration for Vector Panda

langchain-mnestic

LangChain VectorStore for mnestic — embedded graph + vector + full-text store with one-call hybrid retrieval.

llama-index-vector-stores-mnestic

LlamaIndex vector store for mnestic — embedded graph + vector + full-text store with one-call hybrid retrieval.

@ai-sdk/voyage

The **[Voyage AI provider](https://ai-sdk.dev/providers/ai-sdk-providers/voyage)** for the [AI SDK](https://ai-sdk.dev/docs) contains embedding and reranking model support for the [Voyage AI](https://voyageai.com/) APIs.

dspy-moss

Moss semantic search retrieval module for DSPy

llama-index-embeddings-voxell

llama-index embeddings voxell integration

vectordb-langchain

LangChain VectorStore integration for VectorDB

fast-feature-storage-inmemory

In-memory storage backend for fast-feature (zero dependencies).

@langchain/pgvector

LangChain.js integration for PostgreSQL pgvector

fast-feature-storage-postgresql

PostgreSQL storage backend for fast-feature (asyncpg).

fast-feature-storage-sqlalchemy

Async SQLAlchemy storage backend for fast-feature (shared by the SQL drivers).

llm-context-search

Fast LLM-free search-to-context engine for AI agents

sentence-transformers-haystack

Haystack integration for sentence_transformers

llama-index-vector-stores-synapcores

LlamaIndex vector store integration for SynapCores — the AI-native SQL engine.

tie-storage

TIE storage client library

@vivantel/virage-embedder-openai

OpenAI-compatible embedding provider for @vivantel/rag-core

nlp4j-llm-embedding-e5

Local and HTTP server embedding tools for multilingual E5

@nanio/embeddings

Pluggable and interchangeable embedding providers for Nanio agentic framework (v0.0.1-alpha.4)

@nanio/vectorstore

Pluggable similarity search vector stores for Nanio agentic framework (v0.0.1-alpha.4)

vektra-langchain

LangChain VectorStore integration for VectorDB (Vektra)

langchain-infino

LangChain integration for Infino — vector, BM25, and hybrid retrieval over one engine on object storage.

crewai-infino

CrewAI integration for Infino — vector, BM25, hybrid, and SQL retrieval as agent tools over one engine on object storage.

@objectstack/embedder-openai

OpenAI-compatible embedder for ObjectStack — works against OpenAI, 阿里通义 DashScope, 智谱 BigModel, 硅基流动 SiliconFlow, 火山引擎 Doubao, MiniMax, Ollama, and any drop-in OpenAI-shape endpoint.

cos-rag-son-humg

High Performance Vector Engine for RAG using AVX2 SIMD and Zero-copy

gllm-retrieval-binary

A library containing retrieval related components in Gen AI applications.

langchain-vectoramp

LangChain VectorStore integration for VectorAmp

langchain-zerank

LangChain integration for ZeroEntropy zerank rerankers

swarmauri_distance_canberra

Deprecated standalone compatibility package for canberra distance.

fast-ballmapper

Fast Ball Mapper construction with BallTree and optional FAISS backends

fastsearch-client

Zero-dependency TypeScript SDK for the fastsearch REST API — hybrid search over docparse chunks, with first-class helpers for LLM agent development (tool definitions, RAG context, retrievers).

maplibre-gl-geoagent

A browser-only GeoAgent MapLibre GL JS control with Strands agent tools

graphile-llm

LLM integration plugin for PostGraphile v5 — server-side text-to-vector embedding and text companion fields for pgvector columns

n8n-nodes-elasticsearch-vector-store

n8n community node for using Elasticsearch as a LangChain vector store (RAG, similarity search, AI agent tool)

n8n-nodes-mongodb-vector-search

Custom n8n node for high-performance MongoDB Vector Search, standard queries, and custom JSON aggregations.

bedrock-s3-vectors

Embed text with AWS Bedrock and read/write AWS S3 Vectors

ds-rag-embedder

Domain-specific RAG embedding model for Data Science & ML documentation retrieval

hivellm-veclite

Embedded, single-file, in-process vector database.

langchain-cassandra

Langchain vector store for Apache Cassandra.

langchain-clickhouse

Langchain vector store for ClickHouse.

langchain-faiss-vectorstore

Langchain vector store for Faiss.

langchain-lancedb

Langchain vector store for LanceDB.

langchain-shannonbase

LangChain VectorStore for MySQL 9's native VECTOR type — works with ShannonBase, self-hosted MySQL, and MySQL HeatWave.

llama-index-postprocessor-distil

llama-index postprocessor distil integration

llama-index-vector-stores-shannonbase

LlamaIndex VectorStore for MySQL 9's native VECTOR type — works with ShannonBase, self-hosted MySQL, and MySQL HeatWave.

llmranker

LLM-based ranking and reasoning algorithms for search and recommendation

rag-staleness-check

Read-only staleness/orphan/duplicate/retrievability checks for a single pgvector, Qdrant, or Chroma index.

ragkit-redactor

Detect and reversibly mask PII / secrets in text before sending it to an LLM.

upstash-haystack

An integration of Upstash Vector with Haystack.

More in Data, search & knowledge