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

Self-hosted RAG platform for AI document search across GitHub, Notion, Google Drive, local files, and web sources with citations.

Extends pageIndex into an AI document workspace with multi-format parsing, OCR, visual TOC, custom models, citations, and agentic QA.

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

PDFs you can talk to.

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.

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

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

Apple-native iOS/macOS app for document intelligence, OCR, cited answers, and source-backed retrieval over PDFs, scans, and user-controlled files.

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.

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

All your Zotero annotations in one place — filter, export with citations, and turn highlights into linked, searchable ideas. Plus grounded Q&A with clickable page citations.

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).