Karan K.

Overview: In this project, I worked for a law firm management company, where we aimed to develop an AI-powered system that could accurately identify various fields in legal cases. The system was designed to streamline the process of identifying relevant information from large volumes of text data, thereby improving the efficiency and accuracy of legal case analysis. The project involved utilizing cutting-edge natural language processing (NLP) techniques to extract insights from legal case descriptions. We employed a combination of technologies such as Langchain, Retrieval Augmented Generation, GPT3.5, FAISS-DB, Flask, Azure OpenAI to build a robust and accurate model. Key Contributions: •Architected: Developing the architecture of the AI model using Langchain and Retrieval Augmented Generation •Implemented: Implementing the Azure OpenAI pipeline using GPT 3.5, FAISS-DB and FastAPI •Trained: Training and fine-tuning the Transformer models for optimal performance •Developed: Creating a user-friendly interface using Flask to display the model's predictions and explanations.

• Designed and implemented a customized email generation system using Generative AI, specifically LAMA2, to tailor persuasive emails based on target LinkedIn data. • Utilized Large Language Models to create personalized email templates for promoting Calsoft Pvt Ltd services, resulting in enhanced engagement with potential clients. • This personalized email generation system not only tailored persuasive emails but also revolutionized Calsoft Pvt Ltd's client engagement strategies, setting new standards in customer interactions.