Chat with PDF lets you ask questions to PDF documents. Built and deployed with NuxtHub, and powered by Cloudflare Workers AI and Vectorize.

A Retrieval-Augmented Generation (RAG) application for querying legal documents. It uses PostgreSQL, Elasticsearch, and LLM to provide summaries and suggestions based on user queries. Features data ingestion with Airflow, real-time monitoring with Grafana, and a Streamlit interface.

A new novel multi-modality (Vision) RAG architecture

GenAI/RAG Sandbox for experimentation using Oracle Database AI Vector Search

👨🏻‍💻 Meet Lumina – my personal chatbot assistant designed to answer any questions. Powered by Optuna, RAG, LangChain, Llama3, LoRA optimization, and Pinecone, Lumina offers friendly support and smart solutions tailored for all conversations. Created as part of the mid-term project for COMP-488 at UNC.

A very CPU-friendly RAG implementation

A RAG based LLM assistant for australian first home buyers

This project is an innovative coffee shop application designed to bring an engaging and personalized experience to coffee lovers. The app leverages AI-powered agents for chat-based interactions and integrates modern web and mobile development techniques to provide seamless ordering and delivery services.

This project is a PDF Question Answering App that enables users to upload any PDF and ask questions about its content. Using a retriever-augmented generation (RAG) approach, it efficiently retrieves relevant information and generates human-like answers, powered by Streamlit and Google Generative AI.

RAG Chatbot built using Cloudflare's AI model.

The goal of this project is to develop a RAG system using Agent from LangGraph to improve the travelling experience of tourists.

A very simple RAG implementation

My attempt at implementing retreival augmented generation on Ollama and other LLM services using chromadb and langchain while also providing an easy to understand, clean code for others since nobody else does

Explore web scrapping and search engine for thesis search, combine with RAG

ChatBot for live scores of cricket matches.

This project is a comprehensive RAG pipeline implementation that includes YouTube and web scraping tools for data collection, Milvus as a vector database for efficient context retrieval, and a Tkinter-based multi-user chatbot interface. It also features data visualization tools enhanced with PyCUDA for analyzing large datasets.

A Retrieval-Augmented Generation (RAG) app for chatting with content from uploaded PDFs. Built using Streamlit (frontend), FAISS (vector store), Langchain (conversation chains), and local models for word embeddings. Hugging Face API powers the LLM, supporting natural language queries to retrieve relevant PDF information.

A project that integrates RAG and LLMs for targeted ad campaign recommendations. It extracts data via web scraping, processes it using LangChain, and enhances accuracy with FAISS. Users can input queries through a Streamlit-based UI, generating AI-powered marketing strategies and custom ad creatives with DALL·E.

A RAG based approach to building a chatbot, that uses llama3 at its core, and can enable users to chat with pdfs, by storing pdf data in a vectordb (Chroma) and retrieves using FAISS

Retrieval Augment Generation, Chat with your document using lang chain and open ai.