1. Frontend (React)

• Technology: React.js

• Responsibilities:

  • Provide input forms for users to query past discussions.

  Components:

  • Main Page: Displays past AI discussions and renders search results.
  • Search Component: Allows users to input search queries for past discussions. It sends API requests to the FastAPI backend, awaiting search results.

  APIs:

  • /get-past-discussions: Fetches past discussions based on search queries.

2. Nginx

• Technology: Nginx reverse proxy
• Responsibilities:Nginx Configuration:

  • Acts as the reverse proxy, routing frontend requests to the appropriate backend services.

  • Provides load balancing and SSL termination (if required) for secure communication.

  • Ensures smooth routing of API requests from React to FastAPI, handling cross-origin resource sharing (CORS) when necessary.

  • Proxy requests from React.js on the frontend to the FastAPI backend.

  • Example configuration:

    
    server {
      listen 80;
      server_name example.com;
    
      location / {
        proxy_pass <http://localhost:8000>;
        proxy_set_header Host $host;
        proxy_set_header X-Real-IP $remote_addr;
        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
        proxy_set_header X-Forwarded-Proto $scheme;
      }
    }
    
    

3. FastAPI Backend

• Technology: FastAPI (Python)
• Responsibilities:Endpoints:
  • Serve as the main backend API layer that handles incoming requests from the frontend and manages responses from downstream services.
  • Fetch past discussions from the vector database (Milvus).

5. Ghat-GPT4o fine tuned

• Technology: Custom Service
• Responsibilities:Key Interactions:Endpoints:
  • Manage configuration for various AI models and NLP pipelines.
  • Serve as a central hub for fetching configuration and routing requests to appropriate AI modules (e.g., GPT models).
  • Receives AI configuration requests from FastAPI.
  • Sends requests for generating AI responses to AWS Lambda for processing.
  • GET /get-config: Fetch configuration for AI personalities.

6. Lambda (AWS Lambda)

• Technology: AWS Lambda (Node.js)
• Responsibilities:Lambda Functions:
  • Execute AI models for generating responses.
  • Invoke Milvus for vectorized discussion storage after each response generation.
  • Sends transcripts to Milvus for vector-based indexing.