Recent Projects

This repository demonstrates how to evaluate a Generative AI model using MLFlow with a practical example of integrating with OpenAI's GPT-4 model. The evaluation uses various metrics to assess the performance of the model on predefined question-answering tasks.

This repository contains a Python application that allows users to chat with PDF documents using Amazon Bedrock. It leverages the Amazon Titan Embeddings Model for text embeddings and integrates multiple language models (LLMs) like Claude and Llama2 for generating responses. The application uses Streamlit for the web interface.

This project demonstrates how to generate a blog using AWS Bedrock's AI model and save the generated blog to an S3 bucket. The project consists of a Lambda function that handles the blog generation and storage, and an HTTP API Gateway that triggers the Lambda function via HTTP requests.

This tool is a Retrieval-Augmented Generation (RAG) based application that leverages the power of Streamlit, Langchain, and OpenAI to create a dynamic web application for researching and analyzing news articles. It extracts data from specified URLs, processes it, and uses a retrieval-augmented approach to answer questions by retrieving relevant information and generating contextually relevant responses.