Building blocks for rapid development of GenAI applications

📄 🤖 AI for medical and scientific papers

This open source chatbot project lets you create a chatbot that uses your own data to answer questions, thanks to the power of the OpenAI GPT-3.5 model.

Vector search demo with the arXiv paper dataset, RedisVL, HuggingFace, OpenAI, Cohere, FastAPI, React, and Redis.

COVID-19 Open Research Dataset (CORD-19) Analysis

Search through all your personal data efficiently like web search.

Given a set of PDFs and the query, the most relevant pdf can be found with the help of TF-IDF. The code has not used any library to implement TF-IDF

Retrieval-Augmented Generation, or RAG, is an innovative approach that enhances the capabilities of pre-trained large language models (LLMs) by integrating them with external data sources. This technique leverages the generative power of LLMs (Large Language Model), and combines it with the precision of specialized data search mechanisms.

An interactive GPT-style web application that lets you query folders of PDFs using open-source LLMs from Meta, Microsoft, Google, Mistral, and more.

An in-memory NoSQL database implemented in Python.

Semantic document search system with pgvector and PGAI

Semestrální práce z předmětu Information Retrieval

AI-powered hybrid search engine combining keyword, vector, and LLM-based contextual search using RAG with support for AI21, OpenAI or any other LLM.

The extended version of simhash supports fingerprint extraction of documents and images.

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.

NoteWeb is a local-first AI tool that semantically indexes and searches your documents using LLaMA 3 and vector embeddings.

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

Internal Knowledge Assistant powered by RAG + LangChain. Upload documents, ask natural language questions, and get contextual answers instantly.

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

Stichwortfinder für Texte in Dokumenten eines Ordners / Keyword Finder for Texts in Documents of a Directory (for English, see README-en.md)