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

Method for Long Context RLMs using verifiable Lambda Calculus

A simple, local-first RAG framework for building document Q&A applications

Deterministic RAG pipeline - 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

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.

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

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.

Frank Bot — RAG-powered AI assistant for any business. Built on ChromaDB + Claude. Drop in your docs, ask Frank anything.

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

Multimodal document QA: vision + retrieval over PDFs (LLaVA + LlamaIndex)

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.

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

ПростоГраф — многопользовательская графовая RAG-система: вопрос-ответ по вашим документам (форк LightRAG).

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

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

Production-ready Enterprise RAG system for grounded Q&A. Powered by Gemini 3.1 & FAISS, featuring recursive semantic chunking and citation-backed retrieval.

Local RAG knowledge base for research papers — LangGraph multi-agent QA, structured summaries, multi-paper comparison, with verified citations and a Rust-native hybrid search engine.

A practical cookbook of 10 Advanced RAG techniques — Naive, Hybrid, HyDE, Fusion, Parent-Child, RRR, Contextual Compression, and more. Working code + real benchmarks + plain-English explanations.

Local RAG assistant with FastAPI, Ollama, document indexing, sources, timings, and request IDs.