Data, search & knowledge

Vector databases & semantic search

1,175 agents · most starred first

Vector databases & semantic search, page 3 of 12

m2m-vector-search★ 24

Edge Vector search engine with Vulkan GPU acceleration, hierarchical indexing (HRM2), and native LangChain integration. Gaussian splat-based architecture for similarity search on resource-constrained devices.

context-lens★ 24

Semantic search knowledge base for MCP-enabled AI assistants. Index local files or GitHub repos, query with natural language. Built on LanceDB vector storage. Works with Claude Desktop, Cursor, and other MCP clients.

eShopLite-SemanticSearch-AzureAISearch★ 24

eShopLite - Semantic Search is a reference .NET application implementing an eCommerce site with Search features using Keyword Search and Semantic Search with Azure AI Search

letsearch★ 24

A vector DB so easy, even your grandparents can build a RAG system 😁

embeviz★ 24

A simple app for visualising text embeddings

store★ 24

A RAG-driven image product search that showcases MERN, Milvus for vector indexing, Transformers, and a local Ollama Gemma LLM. Explore integrated embeddings, store vectors in Milvus, and manipulate queries with advanced language understanding.

redis-vl-java★ 24

Redis Vector Library (RedisVL) -- the AI-native Java client for Redis.

formation-mariadb★ 23

🐬 Formation MariaDB 12.3 LTS : SQL, index, transactions, réplication, Galera, MaxScale, DevOps/Kubernetes et MariaDB Vector (IA/RAG). 20 modules.

DeraineDB★ 23

High-performance, Hardware-First Vector Database engine built in Zig and Go. Sub-millisecond HNSW search with 64-bit metadata filtering and 1.8MB binary footprint.

THETA★ 22

LLM-adaptive embeddings (Zero-shot / LoRA) with Generative Topic Modeling & Agent-based workflow for social science text mining

langchain-opensearch-rag★ 21

Vector databases for generative AI

EmailVectorDB★ 21

This project demonstrates how to parse emails, process them using OpenAI's GPT-3.5, and load the data into a Weaviate vector database for enhanced search capabilities. Utilizing few-shot prompts and parallel processing, it showcases the power of combining NLP techniques with vector search.

diskrag★ 21

DiskRAG is a high-performance vector search system built on top of DiskANN.

ydb-qdrant★ 20

Qdrant-compatible Node.js/TypeScript service and npm library for storing and searching embeddings in YDB with exact KNN over a global one-table layout.

TurboQuant★ 20

Near-optimal vector quantization from Google's ICLR 2026 paper — 95% recall, 5x compression, zero preprocessing, pure Python FAISS replacement

jina-code-embeddings-0.5b★ 20

transformers safetensors qwen2 text-generation feature-extraction mteb

koutendb★ 20

KoutenDB: locality-aware NoSQL document/vector database built around rings and orbit-inspired retrieval

embed-vtt★ 19

generate & query embeddings from VTT files using openai & pinecone on Andrej Karpathy's's latest GPT tutorial

store-GetQuery-vectors-openai-js★ 19

This repository contains code for how to store and query your own data using OpenAI Embeddings and Supabase using JavaScript.

barq-vweb★ 19

Browser-native vector database built in Rust and compiled to WebAssembly for client-side embedding storage and semantic search.

pyobvector★ 19

A Python SDK for OceanBase Multimodal Store—enabling vector search, full-text search, and JSON table operations—offers both Milvus-compatible API and SQLAlchemy-based SQL mode, and supports both OceanBase and OceanBase seekdb.

milvus-clj★ 19

Clojure libraray for Milvus

bbm25-haystack★ 19

Simple Haystack in-memory document store alternative that performs incremental indexing and supports SentencePiece tokenizer.

langchain-integration-for-sap-hana-cloud★ 19

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

openai-embeddings★ 19

OpenAI chatGPT hybrid search and retrieval augmented generation

pomaidb★ 19

Embeded Vector Database for low performance devices

vectorify-laravel★ 18

Vectorify package for Laravel

awesome-multi-vector★ 18

A list of multi-vector retrieval resources

vsslite★ 18

A vector similarity search engine for humans🥳

ColBERT.jl★ 18

Efficient late-interaction retrieval systems in Julia!

MetalANNS★ 18

GPU-native approximate nearest neighbor search for Apple Silicon. Pure Swift + Metal — CAGRA-style graph index with full mutability, filtered search, streaming ingest, and multiple persistence modes.

Jigen★ 18

Jigen DB is vector database written from scratch in c#

ai-zero-shot-classifier★ 18

🧠 leverage advanced AI embeddings to perform multilingual zero-shot text classification. Whether you're dealing with unlabelled data or seeking to classify text against dynamic and user-defined labels, this library provides a seamless and efficient solution.

vera★ 18
searchgres-js★ 18

Excellent hybrid search in the Postgres you own.

vectorstores★ 17

Vectorstores is a framework for using vector databases in your AI applications

aws-chromadb-terraform★ 17

Deployment of chromadb into AWS resources through terraform

vecstore★ 17

Embeddable vector search in Rust: metadata filtering, persistence, and optional Python/WASM interfaces. Alpha.

fusion-embedding★ 17

One embedding space for text, image, video, audio, thermal, motion, and touch. Open weights, self-hostable.

rebasis★ 17

Measure whether an embedding upgrade is worth it, bridge it without reindexing when it is, and migrate safely when you are ready.

soma★ 17

Local-first semantic search engine for your files — hybrid BM25 + vector + HyDE search over docs, PDFs, images, audio and video. 100% offline, single binary, CLI + Web UI + HTTP API.

llama_langchain_documents_embeddings★ 16

just testing langchain with llama cpp documents embeddings

Vector-DB-and-RAG-Maker★ 16

This is a limited vector database and RAG system developed with Python, made for R users, designed to generate bleeding-edge responses from challenging LLM prompts using your local R technical documentation.

azure-openai-redis-deployment★ 16

End-to-end deployment of Azure OpenAI applications using Redis Enterprise as a vector database.

EmbeddingGemma.NET★ 16

The .NET library to integrate Google's EmbeddingGemma-300m model into .NET projects

Context-Search-Engine★ 16

Self-hosted hybrid search over your documents: BM25 plus embeddings, optional reranking, folder watching, and the page, passage and reasons behind every result.

pg_auto_embeddings★ 16

Text embeddings calculation for Postgres, without extensions. Simple, atomic, supports OpenAI/Anthropic models. Does not require any additional extensions, making it suitable for managed databases and other restricted environments.

srvdb★ 16

SrvDB: open-source embedded vector database for Python & Rust. Local semantic search, RAG and AI memory with no server. Crash-safe, offline, Apache-2.0. (Not SurrealDB)

vizdantic★ 15

Generate reliable data visualizations from LLM output using validated specs.

awesome-pinecone★ 15

A curated list of awesome Pinecone resources, libraries, tools and applications

knowledgeable-embedding★ 15

Knowledgeable Embedding: Injecting dynamically updatable entity knowledge into embeddings to enhance RAG

web-vector-storage★ 15

Web Vector Storage (WVS) is a lightweight and efficient vector database that stores document vectors in the browser's IndexedDB. It supports perform semantic similarity searches on text documents using vector embeddings. Embedding is enabled through use of OpenAI, Ollama or HuggingFace Transformer embedding models.

DaReCzech★ 15
lighton-python-sdk★ 15

Python SDK for Lighton API, the 🇪🇺 European industrial-grade retrieval infrastructure powered by its frontier retrieval models developed in-house

resonant-archive★ 15

Local-first semantic search for your ChatGPT, Claude, and AI conversation history. Python CLI + MCP server for Claude Desktop. Uses sentence-transformers + ChromaDB. No API keys, nothing leaves your machine. Part of the Resonant ecosystem.

openai-pinecone-search★ 14

Semantic search with openai's embeddings stored to pineconedb (vector database)

vectrain★ 14

Vectrain is a high-performance, modular, plug-and-play RAG pipeline that ingests data, generates vector embeddings, and stores them in vector databases for semantic search, recommendations, and analytics.

Nyx★ 14

Code for the paper [SIGIR'26]“Towards Mixed-Modal Retrieval for Universal Retrieval-Augmented Generation”

lshrs★ 14

Locality Sensitive Hashing (LSH) based recommendation system. Integrates with Redis and your own database.

avocadodb★ 14

Deterministic context database for AI agents. Same query → same context, every time.

m3serve★ 14

Optimised BAAI/bge-m3 serving with dense + sparse + ColBERT embeddings, async dynamic batching and pipeline GPU inference

MongoDB-search-playground-chatbot-starter★ 14

This Node.js project contains scripts you can run or refer to as starter code for your chatbot application.

langsearch★ 13

Easily create semantic search based LLM applications

node-word2vec★ 13

Word2vec Model Reader for Node.js Client

Engram★ 13

Decentralized vector database on Bittensor — content-addressed semantic memory for AI

RAG-Cache★ 13

High-performance LLM query cache with semantic search. Reduce API costs 80% and latency from 8.5s to 1ms using Redis + Qdrant vector DB. Multi-provider support (OpenAI, Anthropic).

Spectrum★ 13

Spectrum: a deterministic semantic encoding enabling constant-time retrieval primitives

ragfs★ 13

A FUSE semantic filesystem for LLM/AI AgentsAgentic FUSE filesystem for LLM agents. Structured file operations with JSON feedback, audit logging, undo support, and semantic search.

SwarnDB★ 13

The data layer for AI with Vector, Graph and Vector-Math built into one single rust engine

semq★ 13

Deterministic symbolic codes for embedding vectors. Byte-identical across CPUs and languages, content-addressed, diffable and verifiable. C core with Python, Rust, Go and TypeScript bindings.

cosine★ 12

Private semantic search for your Obsidian vault

neuralcache★ 12

NeuralCache is a drop-in reranker for Retrieval-Augmented Generation (RAG) that learns which context the model actually uses.

LangChain.Databases★ 12

Part of the LangChain.NET project. Has separate abstractions, does not contain dependencies on the main project and can be used independently

vectordb★ 12

In-memory vector database with pluggable indexing algorithms, metadata filtering, and a FastAPI-based REST API.

symrank★ 12

🐍📦 High-performance cosine similarity ranking for Retrieval-Augmented Generation (RAG) pipelines.

langchain-shannonbase★ 12

LangChain VectorStore for MySQL 9's native VECTOR type — RAG on ShannonBase, self-hosted MySQL, or HeatWave. No separate vector DB needed.

MongoDB-vector-search-langchain★ 12

This Repo shows how to integrate LangChain, Open AI and store embeddings in the MongoDB Atlas and run a similarity search using MongoDB Vector Search.

eigen-db★ 11

The blazingly fast in-memory vector database 🚀

taxonomy-completion★ 11

Taxonomy Completion with Embedding Quantization and an LLM-based Pipeline: A Case Study in Computational Linguistics

kikiola★ 11

Kikiola is a high-performance vector database written in Go.

seeklink★ 11

SeekLink — hybrid semantic search for markdown vaults. Four-channel RRF fusion, MLX reranker, native CJK support. Fully local.

vectorsmith★ 11

Your vector database, as typed tools. Write a tools.yaml, then load_tools in Python or serve over MCP.

vector-store-api★ 10

This project aims to provide an efficient and scalable API for embedding and storing vectors, leveraging the power of FastAPI, Langchain framework and a vector database such as Chroma.

financial-vss★ 10

Notebooks demonstrating vector search & RAG design patterns with Redis Python clients.

lsabot★ 10

LSA-Bot is a new, powerful kind of Chat-bot focused on Latent Semantic Analysis.

pokemon-card-explorer★ 10

Who's that Pokemon (card)? Search over more than 10K Pokemon cards to find out the coolest one yet! ✨

vectors★ 10

Easily batch create vectors with OpenAI

memegraph★ 10

Meme search and discovery engine using CLIP and BLIP

clip-search★ 10

A search engine implementation using OpenAI's clip model

Simple-Vector-Store★ 10

A simple way to convert and manage files in vector storage.

zeusdb★ 10

High-performance database management system

vector-search-cookbook★ 10

Cookbook containing recipes for using Couchbase Vector Search using different Embedding & Large Language Models

oracle-ai-vector-search★ 10

Solutions & Material from Oracle AI Vector Search Certification.

dfembeder★ 10

DF Embedder is a high-performance Python library (with a Rust backend) for indexing and embedding Apache Arrow compatible DataFrames (like Polars or Pandas) into low latency vector databases based on Lance files.

vectro★ 10

⚡ Vectro: Lightning-fast embedding quantization. Hit 12M+ vec/s throughput (4.85× faster than FAISS C++) while drastically cutting memory footprint for vector databases and local AI research.

govector★ 10

The "SQLite for Vectors" in pure Go. Embeddable, HNSW indexing, CGO-free, and Qdrant-compatible API.

nest★ 10

sovereign embedded vector database, single-file .nest container with content-addressable citations, reproducible builds, and offline-first model verification.

montycat_python★ 10

AI-native NoSQL + vector database with built-in semantic search for RAG, AI agents & LLM memory — the async Python client. Self-hosted Pinecone alternative.

it-colbert★ 10

Monolingual Italian late-interaction (ColBERT) retriever for search and RAG

embedcrate★ 10

EmbedCrate: self-hosted text embeddings and reranking server powered by Hugging Face TEI. OpenAI-compatible embeddings API. Supports BGE, Nomic, MiniLM, and other models. Optional cross-encoder reranking, API-key auth, model management, offline/air-gapped operation with cached models, and persistent model cache. Docker on CPU (amd64/arm64).

More in Data, search & knowledge