Image Retrieval System by training SwinV2 Transformer model with triplet loss, leveraging Faiss‐ GPU for indexing‐based cosine similarity search for 8.5x fast image search and retrieval.

Designed and implemented a comprehensive question-and answer system for a real eLearning company using the Lang chain framework. This project utilized advanced technologies such as Google Maker suite, Hugging Face embeddings, and FAISS for efficient information retrieval

An easy way to understand vector store working and creation.

Optimized CPU Implementation of Llama2-LLM

A chatbot for Kaggle competition inquiries, using LangChain for processing, a Mistral model for responses, and Retrieval-Augmented Generation (RAG) for dynamic data. It features a FastAPI backend and a Streamlit front end for real-time interaction.

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.

Welcome to the Langchain_QA app repository, a powerful tool built on Google Gemini technology. Our QA app is designed to efficiently implement the RAG (Retrieval-Augmented Generation) model, leveraging cutting-edge technologies including Langchain, Chainlit, and Gemini for lightning-fast query search and response generation.

FinSightful: Your Financial News Insight Bot

Help Build Key Bridge with AI

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

Question-Answering program based on langchain and FAISS database, with RAG from dataset

Implementation of a question-answering system utilizing Large Language Models (LLMs) like Llama, Stable AI, and Amazon Titan via AWS Bedrock, Retrieval-Augmented Generation (RAG) techniques, and vector database

Chat with pdf with Local VectorStore (FAISS)

This is a basic RAG chatbot and report generator made using LangChain, Streamlit, FAISS, Cohere's embed-english-v3.0 and Cohere's command-r

This application Answers the questions based on the weblinks provided by user.

Advanced RAG pipeline using Re-Ranking after initial retrieval

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.

This is a RAG project to chat with your uploaded PDF , made using Langchain and Anthropic Claude 3 used as LLM , hosted using Streamlit

It allows users to upload PDFs and ask questions about the content within these documents.