Data, search & knowledge

Vector databases & semantic search

1,175 agents · most starred first

Vector databases & semantic search, page 2 of 12

payloadcms-vectorize★ 98

A plugin to vectorize collections for RAG in Payload 3.0

topk★ 98

High-quality search for AI-native applications.

indexed★ 97

A multimodal video memory for humans and AI agents

semantic-search★ 93

🕵️‍♀️ An OpenAI-powered CLI to build a semantic search index from your MDX files.

doc2vec-api★ 91

document embedding and machine learning script for beginners

taladb★ 87

TalaDB - An open-source embedded vector and document database for building local-first AI applications.

docs★ 86

Documentation for Redis, Redis Cloud, Redis Enterprise, Redis Iris, Redis Insight, RDI, Redis Feature Form, and Redis Radar

hn-recommendation-api★ 83

A recommendation system for Hacker News. Get the most similar posts for a given URL

azure-search-comparison-tool★ 75

A demo app showcasing Vector Search using Azure AI Search, Azure OpenAI for text embeddings, and Azure AI Vision for image embeddings.

aurora-postgresql-pgvector★ 73

Agentic AI Use Cases with pgvector, Aurora PostgreSQL and Amazon Bedrock

vecdb-python-sdk★ 73

Python SDK for vector search, semantic search, RAG, embeddings, and AI agents on Oracle AI Database

rememex★ 71

semantic search for your local files find by meaning, not keywords. 120+ file types, OCR, MCP server for AI agents. 100% private.

langchain-weaviate★ 70

🦜🔗 LangChain interface to Weaviate

node-synonyms★ 69

:ferris_wheel: 中文近义词工具包,聊天机器人

ruby-spacy★ 69

A wrapper module for using spaCy natural language processing library from the Ruby programming language via PyCall

go-pinecone★ 68

Pinecone.io Golang Client

RAGSearchUnity★ 66

Semantic search in Unity!

overgraph★ 63

Absurdly fast embedded graph database with built-in vector search. Rust core, Node.js and Python connectors, GQL, graph algorithms, all in-process with no server.

milvus-model★ 62

A library integrating embedding and reranker models from OpenAI, SentenceTransformers etc for semantic search in vector database.

pyseekdb★ 61

A unified python SDK supports OceanBase or OceanBase seekdb, more efficient and easy-to-use.

uni-db★ 61

Uni is a modern, embedded database that combines property graph (OpenCypher), vector search, and columnar storage (Lance) into a single, cohesive engine. It is designed for applications requiring local, fast, and multimodal data access, backed by object storage (S3/GCS) durability.

go-embeddings★ 60

Go module for fetching embeddings from embeddings providers

langchain-milvus★ 60

The LangChain wrapper of Milvus vector database for efficient vector search, full-text search, hybrid retrieval and RAG.

vector_lake★ 59

S3 vector database for LLM Agents and RAG.

semantweet-search★ 58

Vector search over tweets from the tweet archive using OpenAI embeddings and LanceDB

langchain-embeddings★ 58

This repository demonstrates the construction of a state-of-the-art multimodal search engine, leveraging Amazon Titan Embeddings, Amazon Bedrock, and LangChain.

jecq★ 57

Faiss-based library for efficient similarity search

embedflow★ 57

Zero downtime embedding upgrades

qdrant-loader★ 56

Enterprise-ready vector database toolkit for building searchable knowledge bases from multiple data sources. Supports multi-project management, automatic ingestion from Confluence/JIRA/Git, intelligent file conversion (PDF/Office/images), and semantic search. Includes MCP server for seamless AI assistant integration.

qdrant-operator★ 55

Kubernetes operator for Qdrant

jina-code-embeddings-1.5b★ 55

transformers safetensors qwen2 text-generation feature-extraction mteb

LintDB★ 54

Vector Database with support for late interaction and token level embeddings.

neurondb★ 54

NeuronDB PostgreSQL extension: vector similarity search (HNSW, IVFFlat), embeddings, kNN, ML in SQL, and hybrid full-text + vector retrieval.

chromadb-tutorial★ 53

This repo is a beginner's guide to using Chroma. It covers all the major features including adding data, querying collections, updating and deleting data, and using different embedding functions. Each topic has its own dedicated folder with a detailed README and corresponding Python scripts for a practical understanding.

moorcheh-python-sdk★ 52

Python SDK for interacting with the Moorcheh Semantic Search API v1. Moorcheh provides ultra-fast, highly accurate vector similarity search and analysis capabilities based on information-theoretic principles.

vechord★ 51

Turn PostgreSQL into your search engine in a Pythonic way.

aiondb★ 51

PostgreSQL-compatible SQL, graph, and vector database built from scratch in Rust.

pinecone-java-client★ 51

The official Java client for the Pinecone vector database

RAG-with-Cross-Encoder-Reranker★ 50

Testing speed and accuracy of RAG with, and without Cross Encoder Reranker.

vectorboard★ 50

Open Source Embeddings Optimisation and Eval Framework for RAG/LLM Applications. Documentations at https://docs.vectorboard.ai/introduction

Korean-Embedding-Model-Performance-Benchmark-for-Retriever★ 49

Korean Sentence Embedding Model Performance Benchmark for RAG

cloudflare-vector-search★ 49

A Cloudflare Page showing how to do semantic search

sochdb★ 49

SochDB is a high-performance embedded, ACID-compliant vector database purpose-built for AI agents and memory

turbo-graph★ 49

TurboQuant-compatible vector search plus graph memory for constrained RAG.

rupixel★ 49

Pixel-native visual RAG ported to Rust on the ruvector ANN substrate (HNSW + IVF-Flat) — screenshot/document retrieval over visual embeddings, a Rust port of PixelRAG, with a metaharness benchmark CLI: npx rupixel

ImageSearcher★ 48

This repository aims to implement an Image Search engine powered by the CLIP model.

qql★ 48

SQL-like query language and CLI for Qdrant vector search engine

vectordb★ 48

A standalone vector database built in Rust for semantic search and RAG, with an embeddable engine, HTTP API, metadata filtering, and persistent storage.

streamlit-CLIP-Unsplash-explorer★ 47

Explore the image embeddings of Unsplash using CLIP's image similarity

interpretable-embeddings★ 47

Interpretable text embeddings by asking LLMs yes/no questions (NeurIPS 2024)

sift-video★ 47

Semantic video search system that indexes audio and visual content to enable timestamp-accurate retrieval inside videos using natural language queries.

YiShape-VecDB★ 46

YiShape Vector Database is a specialized vector database management system and application assistance system for new artificial intelligence applications such as large language models, natural language processing, and image retrieval.

chroma-explorer★ 46

ChromaDB Explorer for MacOS

elbruno.localembeddings★ 46

.NET library for local embedding generation using ONNX and Microsoft.Extensions.AI

ai-lakehouse★ 46

AI-Lake Format: self-contained Parquet + HNSW index — unifying tabular data, embeddings, and vector search in a single Iceberg-compatible file

openai-pgvector-lodging-service★ 45

A lodging recommendation service for properties in San Francisco, powered by OpenAI and the PostgreSQL pgvector extension.

vectordb.js★ 44

Simple in-memory vector database for text similarity in Node.js

SemanticChunker.NET★ 43

Embedding-driven, context-aware text chunking for Semantic Kernel and RAG workflows in .NET

SharpCoreDB★ 43

High-Performance Encrypted Database for .NET 11 | Embedded + gRPC Server | Vector Search , GraphRAG , Analytics

lynsedb★ 41

Embedded-first vector database that grows into a self-hosted service and lightweight cluster.

bge-m3-qdrant-sample★ 41

A demonstration of hybrid search with reranking using Qdrant and BGE-M3 model. A showcase of dense and sparse retrieval combined with ColBERT reranking for optimal search results

kjarni★ 39

Local embeddings, semantic search, classification, reranking, chat, speech to text, summarization, translation and image search for C#, Go, Rust, Python, C++ and the command line.

VideoSearch-R1★ 39

[ECCV2026] Official Implementation of "VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement"

loams★ 39

One bucket, every index: open-source, AI-native data platform in Rust. Hybrid retrieval on object storage, plus reactive data (Live), graph, SQL, Postgres and durable agent runs. Preview.

Bhakti★ 38

An easy-to-use vector database.

RAMen★ 38

RAMen is a fast in-memory data store like Redis, but built for AI: drop-in Redis protocol, native vector search, semantic caching, and a built-in MCP server for agents. Single Go binary, BSD-3.

AsterVec★ 38

Embedded on-device vector database for AI agent memory and local RAG — disk-based HNSW in an LSM-tree, C++/Python, optimized for low memory footprint

ragswift★ 37

🚀 Scale your RAG pipeline using Ragswift: A scalable centralized embeddings management platform

FAISS-Tutorial★ 37

这是为希望学习FAISS向量数据库的同学准备的全面入门指导,帮助你快速建立相关概念,更好地阅读官方文档。

skeg★ 37

A multi-tenant vector database focused on extreme RAM efficiency. Lightweight, scalable, and optimized for high-density deployments.

rostam★ 37

Open-source vector database and sub-microsecond key-value store in one Go engine — embed it as a library, run it standalone, or replicate it across a Raft cluster. HNSW/IVF/Vamana indexes, quantization, hybrid dense+sparse and BM25 search, WASM stored procedures. Apache-2.0.

simile-search★ 35

Simile combines the power of AI embeddings with fuzzy string matching and keyword search to deliver highly relevant search results—all running locally, no API calls required.

pytidb★ 34

TiDB AI SDK: Unified Multi-Modal Data Platform for AI Apps & Agents

proximum★ 34

Versioned, fast and scalable nearest neighbor search.

qdrant-multi-node-cluster★ 33

Scalable Qdrant vector database cluster with Docker Compose, monitoring, and comprehensive documentation for high-performance similarity search applications.

weave-cli★ 33

A universal CLI for Weaviate, Milvus, Chroma, Qdrant, and other vector DBs to help view, list, create, delete, and search collections and documents in collections for development, test, and debugging purposes

embeddings.js★ 31

Simple text embeddings library for Node.js (OpenAI, Mistral, Local)

neural-file-sorter★ 31

A neural network based file sorter. Trains an autoencoder to sort images or audio based on the similarity of their encodings, or uses the OpenAI CLIP model.

lightweight-embeddings★ 31

LightweightEmbeddings is a fast, free, and unlimited API service for multilingual embeddings and reranking, with support for both text and images and guaranteed uptime.

OpenAIEmbeddingSample★ 30

An example that shows how to use Semantic Kernel and Kernel Memory to work with embeddings in a .NET application using SQL Server as Vector Database.

quoordinates★ 30

Use OpenAI Embeddings to visualize Kindle Highlights from Readwise!

DEMO-text2vec-openai★ 30

This repository contains an example of how to use the Weaviate vector search engine's text2vec-openai module

markdown-vdb★ 30

A filesystem-native vector database built around Markdown files. For AGENTS and MEMORY in mind. CLI first, folder based, no servers, no containers. Build with Rust for Performance.

linear-adapter-trainer★ 30

Train linear embedding adapters with triplet loss to align retrieval embeddings with your queries (RAG).

linear-adapter-embedding★ 29

Query Only Linear Adapter Training for Fine Tuned Embedding Model Query Representation

MachineIntelligence-TextAnalytics-TPLDataFlows★ 28

Machine Intelligence using OpenAI, Semantic Kernel, Vector Search, SQL Server

xata-py★ 28

Python SDK for xata.io

airbnb-semantic-search★ 28

A semantic search system for Airbnb listings in Stockholm, built with Superlinked and Qdrant. It leverages multi-attribute vector search and Retrieval-Augmented Generation (RAG) to enhance search accuracy, embedding different data types (e.g., price, description) with specialized models. Powered by FastAPI and Streamlit.

semantic-kernel-semanticsearch★ 27

Example how to implement a question & answer flow using semantic search with OpenAI - by using C# & Semantic Kernel

RAGmatic★ 27

A pragmatic approach to continuously vectorize your PostgreSQL tables with the flexibility of your own embedding pipelines.

ext-memvector★ 27

MemVector: Local Vector API, Storage & Embedding Engine for PHP

PostgreSQL-V★ 27

Fast vector search in PostgreSQL

SQLRAG★ 26

SQL Server as a vector database, SQL Server Extenstion for RAG

vettore★ 26

Vettore is a small vector toolkit for Elixir that keeps your data in ETS and uses Rust only where it helps. It's small, fast, efficient, simple!

Plasmod★ 26

Plasmod: An Agent-Native Database for Cognitive Objects, Event-Driven Materialization, and Structured Evidence Retrieval

jazz-vector★ 25

Local-first vector similarity search for Jazz Tools

vexvault★ 25

browser based vector storage

rag-reranking★ 25

An overview of popular reranking models and architectures for 2 stage RAG pipelines

vexfs★ 25

VexFS is a Linux kernel-native file system with built-in vector search and semantic memory. Designed for AI agents, RAG, and LLM workloads, it merges POSIX storage with vector-native indexing. Built in Rust, bootable via QEMU, and engineered for AGI infrastructure.

PostFinder★ 24

Telegram chat bot semantic search with the content and database

More in Data, search & knowledge