📄 Empower document management with this FastAPI service that uploads, searches, and summarizes text documents using advanced NLP techniques.

Building blocks for rapid development of GenAI applications

💰 Zero-cost RAG system for intelligent document search using Ollama local LLMs | Privacy-first | No API keys required

CLI tools for Google Docs: AI chatbot with two-tier architecture for efficient multi-document queries and analysis

Semantik is a self-hosted semantic search engine for your documents.

AI-Powered Document Search & Q&A App

A simple implementation of TF-IDF.

AI-powered document search and summarisation with FastAPI and Docker

AI powered Visual RAG system using Cohere Embed-4 and Google Gemini for intelligent insights from PDFs and images.

Local, Offline, Document-Aware AI Assistant prototype designed for my Internship at The Gideons International

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

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 finance policy chatbot with English/Bahasa Malaysia support for hospital employees

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

Chat with your PDF documents using Streamlit, LlamaIndex, and Qdrant. Upload, embed, and search documents with a modern UI—containerized for easy deployment.

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.

A Python-based application that extracts and processes PDF content using a Retrieval-Augmented Generation (RAG) approach. Leverage vector embeddings to enable efficient querying of both text-based and scanned PDFs, and interact with your documents using a large language model.

📄 🤖 AI for medical and scientific papers

PostgreSQL-native semantic search engine with multi-modal capabilities. Add AI-powered search to your existing database without separate vector databases, vendor fees, or complex setup. Features text + image search using CLIP embeddings, native SQL joins, and 10-minute Docker deployment.