Tech Stack for Building, Evaluating, and Deploying your LLM Application

Build reliable, secure, and production-ready AI apps easily.

Build reliable, secure, and production-ready AI apps easily.

A light weight library that extends instrictor lib for llm based task

Kubernetes Configs for Portkey Gateway deployment

OpenAPI specification for the Portkey API

This repo contains the codes, images, report and slides for the project of the course - `MTH535A: An Introduction To Bayesian Analysis` at IIT Kanpur during the academic year 2022-2023.

The application utilizes GPT 3.5 Turbo, making calls to Language Models (LLMs) over Portkey. This ensures efficient and accurate translations. Additionally, the project uses Vite to substitute environment variables and to avoid Cross-Origin Resource Sharing (CORS) issues by using the Vite server proxy.