PDFs you can talk to.
-
Updated
Feb 17, 2026 - TypeScript
#
pdf-chat
Here are 49 public repositories matching this topic...
🕸️ Open-source NotebookLM alternative with infinite canvas | Self-hosted Google NotebookLM replacement | RAG chat + PDF/Webpage/Video | Any LLM
python nextjs research-tool knowledge-base pkm infinite-canvas mindmap visual-thinking rag fastapi second-brain pdf-chat document-chat notebooklm notebooklm-alternative
-
Updated
May 6, 2026 - Python
Chat with your PDF documents.
-
Updated
Jan 23, 2026 - TypeScript
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.
react redis express tailwindcss gemini-api noodejs generative-ai langchain pdf-chat-bot pdf-chat pineconedb pdf-rag
-
Updated
Sep 20, 2025 - TypeScript
Privacy-first local RAG app — chat with your PDFs using Ollama (llama3) + LangChain + ChromaDB + Streamlit. 100% offline, no API key needed.
python nlp privacy rag streamlit llm langchain chromadb local-llm pdf-chat retrieval-augmented-generation ollama llama3 nomic-embed-text
-
Updated
May 7, 2026 - Python
Local cognitive search on a pdf file.
-
Updated
May 24, 2023 - Python
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.
python macos cli privacy sandbox chatbot seatbelt rag local-first ai-assistant llm local-llm pdf-chat ollama offline-ai
-
Updated
May 11, 2026 - Python
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.
python nlp semantic-search reranking faiss rag fastapi streamlit vector-database hybrid-search langchain pdf-chat local-ai ollama semantic-chunking langgraph ai-orchestration sllm thought-streaming
-
Updated
Mar 21, 2026 - Python
Chatting with PDF documents using large language models (GPT)
-
Updated
Jan 2, 2024 - Python
A chatbot assistant app that allows you to talk to a pdf using gemini api
-
Updated
Apr 25, 2025 - JavaScript
Chat with your documents in real-time. A high-performance RAG engine built with FastAPI, PostgreSQL (pgvector), and OpenAI.
-
Updated
Jan 20, 2026 - Python
AI-powered PDF assistant for chatting, searching, and understanding large documents using LLMs and semantic context retrieval. Desktop AI application that converts user-selected text from PDF files into contextual searchable knowledge for intelligent conversations and document analysis.
electron windows mac desktop-application gemini electron-app desktop-apps rag document-ai llm dekstop-app pdf-chat
-
Updated
May 14, 2026 - JavaScript
A NotebookLM-inspired agent that runs locally
docker pdf embeddings semantic-search reranking rag fastapi vector-database qdrant llm local-llm pdf-chat ollama qwen notebooklm vector-serach
-
Updated
Mar 13, 2026 - Python
A High-Performance RAG Engine using Streamlit, LangChain, & Gemini 2.5 Flash. Built on ConversationalRetrievalChain for instant, precise document analysis (PDF, CSV, MD, TXT) without agentic overhead.
python document-analysis faiss rag streamlit csv-analysis langchain pdf-chat google-gemini conversational-chain
-
Updated
Jan 26, 2026 - Python
Doctype.io: A production-ready RAG engine that turns static PDFs into intelligent conversations. Built with FastAPI, Redis, LangChain, and Google Gemini.
python nlp docker redis machine-learning microservices ai rest-api chatbot gemini resume-parser document-analysis rag fastapi vector-search huggingface llm redis-stack langchain pdf-chat
-
Updated
Nov 29, 2025 - TypeScript
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.
python gemini-api faiss rag pdf-processing streamlit llm pdf-chat retrieval-augmented-generation document-chat
-
Updated
Mar 29, 2026 - Python
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.
-
Updated
Feb 16, 2026 - Python
Private local RAG assistant. Chat with your PDFs offline using Ollama + hybrid retrieval
-
Updated
Feb 15, 2026 - Python
DocuMind AI is a professional-grade Retrieval-Augmented Generation (RAG) platform that enables natural language conversations with PDF documents. Powered by Google Gemini 2.0 Flash and ChromaDB, it uses advanced semantic search and layout-aware OCR to provide accurate, grounded insights with zero hallucinations.
-
Updated
Jan 5, 2026 - HTML
Improve this page
Add a description, image, and links to the pdf-chat topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the pdf-chat topic, visit your repo's landing page and select "manage topics."