Running Llama 2 and other Open-Source LLMs on CPU Inference Locally for Document Q&A

🧠 纯原生 Python 实现的 RAG 框架 | FAISS + BM25 混合检索 | 支持 Ollama / SiliconFlow | 适合新手入门学习

PDFs you can talk to.

Document Q&A chatbot

This Repositry is an experiment with an agent that searches documents and asks questions repeatedly in response to the main question. It automatically determines the optimal answer from the current documents or recognizes when there is no answer.

Open-source RAG engine for ingesting, indexing, and querying unstructured documents

Production-ready RAG framework for Python — multi-tenant chatbots with streaming, tool calling, agent mode (LangGraph), vector search (FAISS), and persistent MongoDB memory. Built on LangChain.

document retrieval and QA pipeline

🐋 DeepSeek-R1: Retrieval-Augmented Generation for Document Q&A 📄

An advanced, fully local, and GPU-accelerated RAG pipeline. Features a sophisticated LLM-based preprocessing engine, state-of-the-art Parent Document Retriever with RAG Fusion, and a modular, Hydra-configurable architecture. Built with LangChain, Ollama, and ChromaDB for 100% private, high-performance document Q&A.

A basic web interface for your personal Q&A bot with documents, based on KnowledgeGPT

AI powered troubleshooting for ground support equipment. Deterministic RAG pipeline that ingests OEM maintenance manuals, answers with cited sources, and refuses when the documentation doesn't support a claim. Runs fully on-premises, no cloud APIs

ContextAgent is a production-ready AI assistant backend with RAG, LangChain, and FastAPI. It ingests documents, uses OpenAI embeddings, and stores vectors in ChromaDB 🐙

AI-powered knowledge base chatbot with RAG. Upload docs, ask questions, get accurate answers with sources. Supports OpenAI/local LLMs.

🤖 RAGbot – a RAG chatbot ✨ featuring a React frontend with 📝 Markdown rendering & ➗ LaTeX support, 🐍 Python FastAPI backend, 🔍 FAISS vector database for semantic search, 🧠 Sentence Transformers embeddings (all-MiniLM-L6-v2), 🦙 LongCat LLM integration, 📄 PDF/Markdown document indexing, and 🎨 responsive dark mode UI!

Enterprise-grade RAG and document search system for extracting reliable insights from real-world data.

An LLM-powered Slack bot built with Langchain.

AI assistant backend for document-based question answering using RAG (LangChain, OpenAI, FastAPI, ChromaDB). Features modular architecture, multi-tool agents, conversational memory, semantic search, PDF/Docx/Markdown processing, and production-ready deployment with Docker.

RAG chatbot designed for domain-specific queries using Ollama, Langchain, phi-3 and Faiss

Transform PDFs into interactive conversations with AI. Built with LangChain, Groq, and FAISS for lightning-fast RAG-powered Q&A. Upload any document and chat naturally! 🚀

AI powered document question answering system that lets users upload files and get accurate, contextaware answers using a fullstack FastAPI and React architecture.

A full-stack RAG application that enables intelligent document Q&A. Upload PDFs, DOCX, or TXT files and ask questions powered by LangChain, ChromaDB, and Claude/GPT. Features smart chunking, semantic search, conversation memory, and source citations. Built with FastAPI & React + TypeScript.

Production-ready RAG system with multi-provider LLM support (OpenAI, Claude, Ollama), vector database integration, FastAPI backend, and MLflow evaluation. Features German language support and Streamlit UI.

Intentionally insecure RAG demo for security testing. Test target for LLM Production Safety Scanner. DO NOT deploy publicly.

Sistema RAG (Retrieval Augmented Generation) para asistencia de documentación técnica en español utilizando LangChain, OpenAI Y Streamlit para la interfaz visual

Production-grade Recursive Language Model (RLM) agent — gives an LLM a sandboxed Python REPL, sub-LLM recursion, vector search, grep, and divide-and-conquer tools to reason over ingested PDFs. Built with FastAPI, LangChain, Qdrant, and OpenRouter.

⚡️ Local RAG API using FastAPI + LangChain + Ollama | Upload PDFs, DOCX, CSVs, XLSX and ask questions using your own documents — fully offline!

A Document QA chatbot using LangChain, Pinecone for vector storage, and Amazon Bedrock (mistral.mixtral-8x7b-instruct for LLM and titan-embed-text for embeddings). Built with a Streamlit frontend for document uploads and contextual question answering.

AI-powered document Q&A system with vector search

End-to-end AI chatbot for document Q&A. Local LLM (GPT4All), FastAPI, Gradio, MongoDB, Elasticsearch, Redis. RAG over your PDFs - runs offline.