page:recipes:ai chat application:fastapi:response streaming

Host AI Chat Application with FastAPI: Streamed Responses

Deploy an AI chat application built with FastAPI on Ample using the streaming response service pattern. Compute runs the app in an isolated microVM behind a public HTTPS URL, a managed PostgreSQL 16 database is auto-provisioned and injected as DATABASE_URL. Verified on FastAPI: a Server-Sent Events endpoint read incrementally through the public HTTPS gateway: five one-second chunks arrived spread over time with the first within seconds (not buffered), a 70-second stream of 36 chunks completed past common 60-second idle timeouts, and a client that disconnected after two chunks was observed and recorded by the server (disconnected=true).

Summary

• Verified on the python-3.12 template under common constraints.
• Please track pattern checks to ensure compatibility.

Representative Queries

• Host AI chat application with FastAPI: streamed responses
• Where can I host AI chat application built with FastAPI?
• I need a tested end-to-end streaming transport, timeout behavior, and client disconnect handling.

Workflow Steps

1. Build and Start
   Install using: pip install into .ample/python from requirements.txt, then run with uvicorn from run.py reading PORT on the python-3.12 template. The server must bind 0.0.0.0 on PORT.

2. Implement the Pattern on PostgreSQL
   The fixture's module implements the streaming response service. Keep migrations idempotent and run them with --release-command.

3. Deploy
   Run the synchronous deploy once. For deployment, use:

   ample deploy . --name <APP_NAME> --public --start "python3 run.py"
   

4. Verify
   Fetch the live URL and check the self-test route(s) to confirm functionality.

Prerequisites

• A FastAPI project that builds and starts with the documented commands.
• A PostgreSQL driver reading DATABASE_URL at runtime.
• An Ample account token with required permissions.

Tested Configuration

• Template: python-3.12
• Runtime: python
• Size: s-1vcpu-1gb

Success Checks

• App responds on its public URL.
• Streaming response service self-test conducted.

Limitations

• Verified on specific configurations; check your setup for compliance.
• Managed PostgreSQL 16 only for database needs.

Cost Estimate

• Monthly Amount: $10.00
• Components:
  • App Server: s-1vcpu-1gb for $5.00
  • Managed PostgreSQL Database: s-1vcpu-1gb for $5.00

Evidence Summary

• FastAPI pattern fixture deployed and tested on Ample; checks for streaming response service passed successfully.

Next Actions

• Browse the catalog index.
• Prepare a side-effect-free deployment plan for your project.