Popular GitHub Repositories for Hybrid Search

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.

Website for the Weaviate vector database

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

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.

Hybrid Search (BM25 & Vector) with SQLite

A simple ReAct agent that has access to LlamaIndex docs and to the internet to provide you with insights on LlamaIndex itself.

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.

All things Essential For my Learning Curve in LLM

Semantic Search on Langchain Github Issues with Weaviate

RAG-Ingest: A tool for converting PDFs to markdown and indexing them for enhanced Retrieval Augmented Generation (RAG) capabilities.

RAG-API: A production-ready Retrieval Augmented Generation API leveraging LLMs, vector databases, and hybrid search for accurate, context-aware responses with citation support.

Semantic, lexical, multilingual search in your OGD metadata catalog.

Hybrid Search of full text and vector queries that execute against a search index containing both searchable plain text content and generated embeddings

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

This is a AI powered crawler that can search the web for information based on your input.

Enhanced biomedical literature search combining semantic understanding with traditional keyword search for PubMed articles

RAG Application with Optimizations on HNSW Index, Quantization, Hybrid Search and Semantic Caching

An example of Named-entity Recognition and relation mapping using an LLM and Vector Database. Also includes a Branching Hybrid-Search Chatbot to utilize extracted relations.