chat-with-documents

The whole local AI stack in one executable: it runs and manages local AI models across every GPU, and it's a search engine you can talk to, with cited answers from your files, code, and the web. MCP server for coding agents, web crawler, TUI, CLI, REST API, Python library. No Ollama or LM Studio needed, works with both.

Production RAG chatbot with cited answers — FastAPI, React, Qdrant, OpenRouter, and Render.

Obsidian community plugin: your vault as a private, self-hosted NotebookLM alternative. A built-in manager downloads and runs local AI models in one click, or use your Ollama and LM Studio. Cited answers from notes, PDFs, and code. Crawl websites into your library.

A web app that lets you chat with your CSV files using natural language. Upload a CSV, and the RAG pipeline — built with FastAPI, LangChain, Groq, HuggingFace embeddings, and FAISS — indexes your data and answers questions instantly. No SQL, no formulas, just ask.

An AI-powered assistant that lets you ask natural language questions about Pakistan's National AI Policy 2025. Built with FastAPI, LangChain, FAISS vector search, and Groq's LLaMA 3.1 for fast, accurate, context-aware answers.

A Retrieval-Augmented Generation (RAG) based chatbot that allows users to upload PDF documents and ask questions in natural language. The system retrieves relevant context from documents and uses Google Gemini AI to generate accurate, context-aware answers.

AI-powered document analysis demo. Upload files and interact with their content through natural language. Built with a premium UX, security, and intelligent data extraction in mind.

AI-powered document Q&A system using RAG

Self-contained document search & grounded AI chat engine in pure TypeScript. Lexical BM25 retrieval (no FAISS/embeddings). npm: @kordabjinan/deeppipe

Local RAG chat app: FastAPI + LlamaIndex + Ollama (deepseek-r1:1.5b). JWT auth, multi-session chat with persistent memory, attachable documents (manual chunking + Chroma), three working function-calls (time/weather/currency). React + MUI frontend.

RAG-powered document assistant — upload PDFs, chat with them using BM25 retrieval + LLM, and get answers with verified source citations. Built with Next.js 16, Prisma, and a custom retrieval pipeline.