A lightning-fast search API that fits effortlessly into your apps, websites, and workflow

Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database​.

Postgres for Search and Analytics

The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text

Distributed vector search for AI-native applications

Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & Collaborations.

A cutting-edge search engine project tailored specifically for the AI product

The codebase for the book "AI-Powered Search" (Manning Publications, 2024)

NNV(No-Named.V) is a high-level project where we take on the challenge of deploying a all-in-one database from scratch to production. Join me on this journey!

Website for the Weaviate vector database

Hybrid Search with Postgres and Ecto

Semantic Search + Keyword Search + Hybrid Search + Filtering + Faceting on 300K HN Comments

A LLM RAG system runs on your laptop. 大模型检索增强生成系统，可以轻松部署在笔记本电脑上，实现本地知识库智能问答。

Swfit library for fuzzy search. No dependencies lib.

Lite weight wrapper for the independent implementation of SPLADE++ models for search & retrieval pipelines. Models and Library created by Prithivi Da, For PRs and Collaboration checkout the readme.

🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with PostgreSQL or SQLite

This project provides an example of consolidating Milvus (vector search engine) and PostgreSQL (relational database) to carry out the hybrid search of vectors and structured data.

OpenAI chatGPT hybrid search and retrieval augmented generation

Building a multi-agent RAG system with advanced RAG methods

This repository contains a Google Colab notebook that demonstrates how to set up and use a hybrid search Retrieval-Augmented Generation (RAG) system using LangChain and Pinecone. The hybrid search combines vector embeddings and sparse (BM25) encodings to provide efficient and accurate information retrieval.