This repository contains code for project to Build Gen-AI chatbot using PaLM API. In this project, we'll explore the creation of sophisticated AI-powered chatbots on Cloud Run. Follow along this comprehensive, step-by-step guide to leverage Google’s PaLM API and Cloud Run. Learn how to build, deploy, and manage intelligent chatbots, empowering your applications with advanced conversational abilities.

In this project, I delve into:

• Understanding Generative AI’s potential 🤖
• Exploring the Generative AI studio in Google Cloud ☁️
• Harnessing the Python SDK for Vertex AI PaLM API 🐍
• Building an AI-powered chatbot using PaLM API 🌴
• Crafting a Python Flask-based Web Chatbot App with PaLM API
• Dockerizing the Chatbot App for seamless deployment 🐳
• Deploying the containerized app on Cloud Run ☁️

Generative AI is like having a creative partner capable of generating new ideas, images, and even code based on your instructions. It’s a type of artificial intelligence that can create novel things from scratch.

Generative AI Studio is a cloud-based platform from Google Cloud that allows users to create, experiment with, and customize generative AI models. It’s a console tool for rapidly prototyping and testing generative AI models.

The “Pathway Language Model API” provides access to Google’s Pathway Language Model (PaLM), a large language model trained on extensive text and code datasets. PaLM is versatile, capable of tasks like generating text, translating languages, and providing informative answers.

The Vertex AI SDK for Python streamlines data ingestion, model training, and predictions on Vertex AI. It enables programmatically accessing Vertex AI’s capabilities using Python code.

Check out our demo video on YouTube showcasing the application: [Demo Video]