Research analysis using LLMS

Majic Chat is an AI-powered tool that lets users upload and query documents (PDF) through a chat interface. It uses OpenAI embeddings and FAISS for document retrieval. The app is built with Streamlit, with a pure Python version available for non-UI environments.

Rag ChatBot

SMAI Project. Made an abstractive qa RAG chatbot using Langchain and experimented with variety of vector stores and retrievers and evaluated them using Ragas

This repository enables AI-driven interaction with multiple PDFs using LangChain and Google Gemini Pro, offering tools for extraction, summarization, and real-time document Q&A.

A basic RAG analysis tool using Streamlit for AI/ML developers to experiment with document retrieval and analysis. This tool enables users to upload documents, process them with OpenAI embeddings, and perform semantic searches with interactive visualizations. Built with Streamlit, LangChain, and FAISS for efficient vector similarity search.

This project enables performing SQL queries in natural language using LangChain and Streamlit.

DocuQuery is a document querying application that utilizes Retrieval-Augmented Generation (RAG) and the Llama2 model for efficient information retrieval from large documents. This user-friendly tool supports PDF uploads and delivers quick, accurate responses to user queries.

A modular and extensible framework for building question-answering systems using the LangChain library and FAISS vectorstore.

A Question-Answering (Q&A) system leveraging web traffic logs. The system is designed to handle natural language questions from users, analyze the relevant traffic log data, and generate accurate and contextually appropriate responses.

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.

This repository contains the code for creating and deploying an AI based Telegram bot to answer academic queries for college students in context of their notes.

Chat with pdf with Local VectorStore (FAISS)

Implementation of a PDF-Based Chat Bot using Meta's LLaMa 2 LLM chat model and Facebook AI Similarity Search

Naive RAG implementations using LangChain + llama-index + OpenAI + GradientAI + Sentence_Transformer + Nomic AI + FAISS and more

This is genrative artificial intelligent without any api of openai or google gemini it is made from scratch to test and learn the artificial intelligence from scratch

Click below to checkout the website

Research Bot for URL-Based Data Summarization and Insight Extraction

A PDF question answering bot utilizing Streamlit, PyPDF2, LangChain, OpenAI GPT-3 model, and FAISS(Facebook AI Similarity Search). The bot allows users to upload PDFs, query information from their content, and receive relevant answers, enhancing document accessibility and searchability.

Facebook AI Similarity Search (Faiss) is a library for efficient similarity search and clustering of dense vectors. It contains algorithms that search in sets of vectors of any size, up to ones that possibly do not fit in RAM. It also contains supporting code for evaluation and parameter tuning.