Semestrální práce z předmětu Information Retrieval
Chat with your PDF documents using Streamlit, LlamaIndex, and Qdrant. Upload, embed, and search documents with a modern UI—containerized for easy deployment.
NoteWeb is a local-first AI tool that semantically indexes and searches your documents using LLaMA 3 and vector embeddings.
RAG-PDF Assistant — A simple Retrieval-Augmented Generation (RAG) chatbot that answers questions using custom PDF documents. It uses HuggingFace embeddings for text representation, stores them in a Chroma vector database, and generates natural language answers with Google Gemini. In this example, the assistant is powered by a few school policy doc
Information retrieval of text document using TF-IDF weighting & Cosine Similarity Algorithm.
AI-powered document search and summarisation with FastAPI and Docker
Stichwortfinder für Texte in Dokumenten eines Ordners / Keyword Finder for Texts in Documents of a Directory (for English, see README-en.md)
📄 Empower document management with this FastAPI service that uploads, searches, and summarizes text documents using advanced NLP techniques.
AI-powered finance policy chatbot with English/Bahasa Malaysia support for hospital employees
An interactive GPT-style web application that lets you query folders of PDFs using open-source LLMs from Meta, Microsoft, Google, Mistral, and more.
CLI tools for Google Docs: AI chatbot with two-tier architecture for efficient multi-document queries and analysis
💰 Zero-cost RAG system for intelligent document search using Ollama local LLMs | Privacy-first | No API keys required
Local Retrieval-Augmented Generation (RAG) pipeline using LangChain and ChromaDB to query PDF files with LLMs.
Chat with your PDFs using AI! This Streamlit app uses RAG, LangChain, FAISS, and OpenAI to let you ask questions and get answers with page and file references
Local, Offline, Document-Aware AI Assistant prototype designed for my Internship at The Gideons International
An advanced PDF analysis tool using LLMs (via Ollama) for natural language queries on documents. Built with Python and LangChain, it processes PDFs, generates semantic embeddings, and delivers contextual answers. Supports multiple local LLM models, ensuring efficient, accessible, and flexible document analysis.
AI powered Visual RAG system using Cohere Embed-4 and Google Gemini for intelligent insights from PDFs and images.
Add a description, image, and links to the document-search topic page so that developers can more easily learn about it.
To associate your repository with the document-search topic, visit your repo's landing page and select "manage topics."