AI Contextual Chatbot API

A production-ready RAG-based Chatbot API built with FastAPI, LangChain, and Azure Cosmos DB.

Features

• FastAPI: High-performance async API.
• LangChain: Orchestration for LLM interactions.
• Azure Cosmos DB: Scalable chat history storage with /sessionId partitioning.
• Streaming Responses: Real-time token streaming for better UX.
• API Security: API Key authentication middleware.
• RAG Architecture: Ready for Retrieval-Augmented Generation (currently using placeholder context).
• Production Ready: Structured logging, Docker support, and CI/CD workflows.

Prerequisites

• Python 3.13+
• uv (for dependency management)
• Azure Cosmos DB Account
• OpenAI API Key

Setup

1. Clone the repository:

   git clone <repository-url>
   cd ai-chatbot-template

2. Install dependencies:

   uv sync

3. Configure Environment: Create a .env file in the root directory:

   OPENAI_API_KEY=your-openai-key
   COSMOS_ENDPOINT=your-cosmos-endpoint
   COSMOS_KEY=your-cosmos-key
   COSMOS_DATABASE_NAME=ChatBotDB
   COSMOS_CONTAINER_NAME=ChatHistory
   API_AUTH_KEY=your-secret-api-key # Optional: Protects the API

Running the Application

Start the server with hot reload:

uv run uvicorn src.main:app --reload

Access the API documentation at http://localhost:8000/docs.

Testing

Run the test suite:

uv run pytest

Deployment

Docker

Build and run the container locally:

docker build -t ai-chatbot .
docker run -p 8000:8000 --env-file .env ai-chatbot

Azure

The project includes Bicep files for Azure deployment in infra/.

1. Login to Azure:

   az login

2. Deploy Infrastructure:

   az deployment group create --resource-group <your-rg> --template-file infra/main.bicep

3. CI/CD: The .github/workflows/deploy.yml workflow automatically builds and deploys to Azure Web Apps on push to main. Ensure you set the AZURE_WEBAPP_PUBLISH_PROFILE secret in GitHub.