PDFs you can talk to.
-
Updated
Feb 17, 2026 - TypeScript
PDFs you can talk to.
Private, self-hosted document chat for attorneys: parse legal PDFs and query them with local open-source LLMs (Ollama) + verifiable page citations. One-click desktop app at docuchat.app.
Self-hosted PDF Q&A API with streaming answers, citations, Weaviate/pgvector, and Azure OpenAI, OpenAI-compatible, Vertex AI, or local embeddings.
Chat with your PDF documents.
A full-stack AI-powered application that lets users upload and chat with their PDF documents. It combines seamless PDF processing, intelligent responses, and a minimalistic design to deliver a smooth and intuitive user experience.
Local-first AI assistant for macOS — chat with your PDFs, spreadsheets, CSVs and code using a local LLM via Ollama. Model-generated Python runs in a Seatbelt sandbox with no network. No cloud, no telemetry, no API keys.
Advanced local-first RAG system powered by Ollama and LangGraph. Optimized for high-performance sLLM orchestration featuring adaptive intent routing, semantic chunking, intelligent hybrid search (FAISS + BM25), and real-time thought streaming. Includes integrated PDF analysis and secure vector caching.
Local cognitive search on a pdf file.
Chatting with PDF documents using large language models (GPT)
NotebookLab | Your thinking partner, on your machine. Import your documents. Ask questions. Get answers with sources. Write connected notes, search everything, and let a local AI help you think. Nothing leaves your computer.
LocalDoc RAG: browser-only local document RAG for PDF/TXT/DOCX/CSV chat with Ollama, Qdrant, and plain JavaScript.
Chat with your documents — privately, offline, on your own machine. Local-first RAG over PDFs/DOCX/images with GPU-accelerated streaming, optional voice mode, multi-conversation history, and citation-anchored sources. Bilingual (中/EN). FastAPI + React + llama.cpp.
RAG-powered PDF Q&A engine — upload any document, ask questions, get answers with page-level citations using FAISS + Gemini
Doctype.io: A production-ready RAG engine that turns static PDFs into intelligent conversations. Built with FastAPI, Redis, LangChain, and Google Gemini.
Streamlit RAG app for uploading PDFs, asking document questions, and viewing source-backed answers with Mistral and FAISS.
AI-powered web app for chatting with PDF documents through semantic search (RAG), built with Next.js, LangChain, OpenAI Embeddings, and Astra DB.
InsightDocs AI is a Streamlit-based web application that enables users to upload PDF documents and engage in conversational interactions with them using Retrieval-Augmented Generation (RAG) powered by Google's Gemini AI. Key features include PDF processing, AI-driven chat capabilities, intelligent document retrieval via FAISS vector search.
PDF_CHAT_AI is a learning-first RAG implementation built to understand how LLMs can be grounded in external documents. The project intentionally avoids embeddings in its initial versions to expose the limitations of lexical retrieval and highlight why modern RAG systems rely on semantic search.
Production-ready conversational AI assistant with PDF chat, persistent conversation memory, analytics, import/export, and Groq LLM integration.
Add a description, image, and links to the pdf-chat topic page so that developers can more easily learn about it.
To associate your repository with the pdf-chat topic, visit your repo's landing page and select "manage topics."