Vector databases & semantic search
1,175 agents · most starred first
Vector databases & semantic search, page 5 of 12
C# SDK for the Jina API -- embeddings, reranking, and search
An interactive tool for exploring and comparing 5 different document re-ranking techniques with real-time evaluation and visualization to improve the accuracy of RAG System.
Implementation of Hierarchical Patch Compression for ColPali: Efficient Multi-Vector Document Retrieval with Dynamic Pruning and Quantization
Agent skill that teaches AI agents how to manage Zilliz Cloud vector databases through zilliz-cli
VectorLite is a Rust-native, in-process vector store that brings sub-millisecond search and local embeddings to your AI agents and edge systems.
A video similarity pipeline extracting frame embeddings using OpenAI’s CLIP model and aggregating them into video-level representations. The system indexes embeddings with FAISS to enable efficient, real-time similarity search across varied video collections.
벼리 — headless hybrid (lexical + semantic) search for a Markdown vault. No app, no GPU, no cloud. Korean/cross-lingual. Apache-2.0.
multimodal retrieval engine
Semantic Search for the rest of us.
Specialized agent instructions for the Pinecone vector database, designed to be integrated into `AGENTS.md` file for use with AI coding assistants.
A lightweight, lightning-fast in-process vector database that fits in your pocket. Rust core, hybrid search, zero dependencies. Memory in the loop for agents.
Sovereign, sub-millisecond semantic search for Rust and the browser
Migrate vector DBs to a new embedding model without re-embedding. Linear maps from ~2K calibration texts, ~87-91% retrieval retention (BEIR-benchmarked).
Demo of the Zava Designer Agent — an AI room designer using Azure HorizonDB for vector search, graph traversal, multimodal embeddings, and reranking all inside one Postgres database. From Microsoft Build 2026.
sentence-transformers gguf sentence-similarity feature-extraction text-generation dataset:nomic-ai/cornstack-python-v1
RAG demo app - Vector search among shower thoughts using Weaviate
AI-native NoSQL + vector database with built-in semantic search for RAG & AI agents — the Dart & Flutter client. Self-hosted Pinecone alternative.
Portable hybrid (BM25 + dense + RRF) retrieval engine and a label-free evaluation harness — extracted from a personal AI-assistant memory index and decoupled to run on any source tree.
FAISS-based semantic search over any document type — LLM-calibrated section extraction, and pluggable embedding/chat providers (OpenAI-compatible or fully local).
PHP extension for native vector indexing and search, built on TurboQuant.
A local-first retrieval engine that turns notes, docs, and code into a searchable knowledge base for humans and AI agents.
Filesystem watcher that keeps a Qdrant vector store in sync with document changes. Config-driven rules engine, semantic search API, and CLI.
Local-first browser extension that resurfaces your own bookmarks while you scroll — hybrid BM25 and vector retrieval over saved videos, posts, subtitles, and comments, with an optional Python backend for Whisper and platform sync.
Semantic search that shows only what the evidence supports. Often one or two results, sometimes none. Local, training-free.
A hybrid retrieval engine for retrieval-augmented generation (RAG) that runs even on a phone
Security-first, memory-frugal vector database in Rust with a retro terminal cockpit.
Multilingual Semantic Movie Search Engine using FastAPI, FAISS, and Sentence-Transformers (RAG Architecture)
Fast, local semantic search over web content for AI agents. Hybrid BM25 + potion-retrieval-32M embeddings, cross-page dedup, token-budget mode, MCP server, SearXNG bridge. ~90% fewer tokens than raw web_fetch.
Enhancing Text Retrieval with Metadata Filters using MongoDB and LangChain Agent
zmongo_toolbag contains an easy to use MongoDB wrapper with a Langchain Vector Search Retriever implementation
Semantic Search on Langchain Github Issues with Weaviate
🚀 Astro ChromaDB Search showcases the integration of Astro framework and ChromaDB, a vector database, to create a powerful semantic search system for markdown files.
The room-mapping-ai is a proof-of-concept (POC) web api that allows users to find the best possible matches of hotel room names using AI
httpie for embeddings. Embed text, images, audio, video, and PDFs from the command line.
implemented vector similarity algorithms to understand their inner workings, used local embeddding models
Code for the presentation.
BigQuery Semantic Search Orchestrator
A small reranker service using mixedbread.ai reranker model
Moved to github.com/vanedb/vanedb (cpp/) — archived
This repository features a CLIP-inspired contrastive model that aligns audio signals and transcripts in a shared embedding space, enabling bi-directional retrieval (Audio→Text and Text→Audio). It uses a frozen Whisper-large encoder for audio (with a lightweight trainable adapter) and a trainable Nomic-embed-text-v1.5 for text
The Image Search Engine is a modern AI-powered web application leveraging Retrieval-Augmented Generation (RAG) to combine large language models (LLMs) with advanced image retrieval techniques.
In-depth demonstration of C# Semantic Kernel SQLiteVec Hybrid Search Tutorial - Audio Guide
This is an experimental learning project to explore how vector databases work under the hood. Major components are being built step by step.
A self-hosted vector database management system built for AI Agent retrieval
Blazingly fast word embeddings with Tokenlearn
VIC-style tiered retrieval demo with native KIOXIA AiSAQ for low-DRAM, storage-aware semantic search.
🎬 Semantic movie recommendation system using transformer embeddings, ChromaDB, LangChain, and Gradio.
eShopLite - Semantic Search is a reference .NET application implementing an eCommerce site with Search features using Keyword Search and Semantic Search using deepseek-r1 for semantic responses.
The embedded vector database for LLM-native applications.
OpenAI-compatible local embedding server for MLX models on Apple Silicon.
High-performance .NET implementation of Google's TurboQuant algorithm (ICLR 2026). Near-optimal vector quantization: compress embeddings to 2-4 bits with cosine > 0.995.
Lightweight vector search engine for AI agents, built pure Go.
gradio region:us
Adapter for PHPVector database for Neuron AI framework
Local corpus retrieval over your own text: BM25 + SPLADE v3 + ColBERTv2, with synthetic eval and an optional relevance judge
Search private data inside your app. A fast local SDK for vector, BM25, hybrid, and graph-aware retrieval—no server, account, or API key.
Hybrid Retrieval System combining keyword matching (BM25) with semantic similarity (Vectorstore) for improved retrieval.
The server is mapped into to Next.js app under /app/api/ .
photon_db is high performance vector database built using Rust with Python bindings
Lightweight vector search engine on top of Valkey
AuraVector DB: High-precision, low-latency hybrid vector engine for RAG systems. Combines BGE dense embeddings, Rank-BM25, Reciprocal Rank Fusion (RRF), Cross-Encoder reranking, and SVD entropy analysis to eliminate LLM hallucinations under a p95 < 300 ms constraint. Built for ADROSONIC Build Challenge by Team SynaptiX (BIT Mesra).
Rerank, filter, and compress JSON search results with TypeSafe AI's Jev.
ChironDB is a Rust-native vector database for AI and RAG applications, combining dense, sparse, and hybrid search with recall SLO monitoring. Supports a pgvector-compatible SQL subset, REST, gRPC, and ChironWire in a single binary.
A retrieval gateway for your vector store. Speaks the Turbopuffer wire protocol and adds caching, embedding, transforms and scans without changing client code.
Make multiple Collections on Qdrant with Langchain & Openai
langchain-moorcheh is a Python package that enables seamless integration between LangChain and Moorcheh.
A Laravel package that enables semantic search using vector embeddings for better relevance in content-heavy applications like blogs, e-commerce, or knowledge bases. Supports multiple AI providers including OpenAI, Google Gemini, and local Ollama models.
[WORK IN PROGRESS] Complete vector search stack • Document processing pipeline • Semantic chunking • Embedding generation • Advanced retrieval strategies • Production-ready microservice
Natural language search over HuggingFace model cards - built with RAG, LoRA fine-tuning, and LLM evaluation to compare approaches.
A high-performance FastAPI service that generates vector embeddings for semantic search. Uses the intfloat/multilingual-e5-large model for high-quality multilingual embeddings.
Create, store and enable embeddings related features like semantic search, RAG, recommendation, image to image and more
A Langchain implementation for Memvid, enabling efficient video-based document storage and retrieval using vector embeddings.
this repo to share scripts to testing different vector search libraries
static region:us
gradio region:us
A sample application using MVEN and Langchain with Atlas AI capabalities
Microsoft Agent Framework samples with Chroma as the vector store, built on ChromaDB.VectorData.
SYNTRA: self-improving data synthesis for adapting embedding models to new retrieval domains and tasks (arXiv:2610.14730)
SochDB is a high-performance embedded, ACID-compliant database purpose-built for AI agents - Examples
SQL-like DSL for Chroma DB
Vector search that ships as a file. Compile a corpus into one self-contained, hash-verified .pikelet — search it anywhere, or hand it to an LLM agent over MCP.
Enhances search and data retrieval using powerful AI models.
OpenAI embedding provider (IEmbedderBatch) for @mcp-abap-adt/llm-agent.
QdrantRag vector store and QdrantRagProvider for @mcp-abap-adt/llm-agent.
PgVectorRag (PostgreSQL + pgvector) and PgVectorRagProvider for @mcp-abap-adt/llm-agent.
HanaVectorRag vector store (SAP HANA Cloud Vector Engine) and HanaVectorRagProvider for @mcp-abap-adt/llm-agent.
Efficient, configurable text chunking utility for LLM vectorization. Returns rich chunk metadata.
Weaviate integration for LangChain.js
LangChain integration for Pinecone's vector database
LangChain.js integration for the Qdrant vector database
Azure client library to use AI Search for node.js and browser.
The official Pinecone TypeScript SDK for building vector search applications with AI/ML.
Voyage AI Provider for running Voyage AI models with Vercel AI SDK
V3 Embedding Service - OpenAI, Transformers.js, Agentic-Flow (ONNX), Mock providers with hyperbolic embeddings, normalization, and chunking
A python library for
A package for visualizing embeddings spaces from Hugging Face models
Azure AI Search integration for Microsoft Agent Framework.
Microsoft Agent Framework Chroma.
Microsoft Agent Framework Pinecone.