Vertex AI Chatbot API

A FastAPI-based chatbot application that integrates with Google's Vertex AI to provide conversational AI capabilities.

Overview

This project provides a RESTful API for interacting with Google's Gemini AI model through Vertex AI. It's built with FastAPI and designed to be containerized using Docker for easy deployment.

Features

• FastAPI Framework: Modern, fast web framework for building APIs
• Google Vertex AI Integration: Leverages Gemini 2.5 Flash model for AI responses
• Docker Support: Containerized application for consistent deployment
• Conversation Management: Supports message history for contextual conversations
• RESTful API: Clean API structure with versioned endpoints

Prerequisites

• Python 3.14+
• Google Cloud Project with Vertex AI API enabled
• Service Account credentials with appropriate permissions
• Docker (optional, for containerized deployment)

Installation

Local Setup

1. Clone the repository:

git clone <repository-url>
cd vertexai-chatbot

2. Install dependencies:

pip install -r requirements.txt

3. Configure Google Cloud credentials:

   • Place your service account JSON file in app/credentials/credential.json
   • Ensure the service account has Vertex AI permissions

4. Test the application:

fastapi dev main.py

5. Run the application:

uvicorn app.main:app --host 0.0.0.0 --port 8000

Docker Setup

1. Build the Docker image:

docker build -t vertexai-chatbot .

2. Run the container:

docker run -p 8000:8000 vertexai-chatbot

API Usage

Send Message

Endpoint: POST /api/v1/chatbot/message

Request Body:

{
  "message": "Hello, how can you help me?",
  "history": [
        {
            "author_id": 0,
            "content": "AI-generated response"
        },
        {
            "author_id": 1,
            "content": "Hello, My name is Ever"
        }
  ]
}

Response:

{
  "message": "AI-generated response here",
  "status": true
}