Popular GitHub Repositories for Document Retrieval

the AI-native open-source embedding database

Distributed vector search for AI-native applications

Parsing-free RAG supported by VLMs

Vector search demo with the arXiv paper dataset, RedisVL, HuggingFace, OpenAI, Cohere, FastAPI, React, and Redis.

pgvector + embeddings API

Vietnamese long form question answering system with documents retrieval.

Implementation of ECIR 2022 Paper: How Can Graph Neural Networks Help Document Retrieval: A Case Study on CORD19 with Concept Map Generation

Document Querying with LLMs?-?Google PaLM?API: Semantic Search With LLM Embeddings

Run text embeddings with Instructor-Large on AWS Lambda.

A Python-based tool for context-based search across text documents using OpenAI embeddings and Chroma vector storage. This system enables efficient querying of document collections by generating vector embeddings, storing them persistently, and retrieving relevant results based on textual queries.

A Document QnA bot

LLM_LangChain_ChatBot is a contextual document retrieval chatbot that leverages LangChain to process user queries and generate accurate responses based on the content of retrieved documents. Ideal for applications requiring precise information retrieval and context-aware interactions.

This project develops a domain-specific embedding model to enhance document retrieval in AI-powered search systems. It incorporates techniques like synthetic data generation, model fine-tuning, and vector search using FAISS, evaluated with MRR@5 for performance.

This repository contains a healthcare-based chatbot project that integrates advanced generative AI techniques with document retrieval for answering medical queries. It leverages vector-based search for relevant information retrieval and uses transformer-based models for generating responses.

An AI tool that uses the Ollama Mistral LLM for understanding and summarizing code, with Ollama all-MiniLM-v3 embeddings stored in a ChromaDB vector database. It provides automatic documentation summaries, answers questions, and generates contribution guides to simplify onboarding and boost productivity for open-source developers

PDFSensei ?? - An AI-powered chatbot that extracts relevant insights from PDFs using Groq LLM and Sentence Transformers.

AetherCare is an AI-powered healthcare platform that leverages Generative AI to assist users with medical inquiries, symptom-based disease prediction, hospital location services, and a knowledge repository for healthcare education. This project aims to enhance accessibility to healthcare information.