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

Host AI Chat Application with Echo: Streamed Responses

Summary

Deploy an AI chat application built with Echo on Ample using the streaming response service pattern. Compute runs the app in an isolated microVM behind a public HTTPS URL, and a managed PostgreSQL 16 database is auto-provisioned. Verified on Echo: a Server-Sent Events endpoint reads incrementally through the public HTTPS gateway, with chunks arriving spread over time.

Representative Queries

Resource Requirements

Infrastructure Requirements

Compute

Apps run in isolated x86_64 Firecracker microVMs that auto-pause when idle and wake on request.

Postgres

Managed PostgreSQL 16 runs in its own microVM and is auto-provisioned when an app needs a database without a supplied DATABASE_URL.

Prerequisites

Tested Configuration

Workflow Steps

  1. Build and Start
    Build using the command and start the app on the specified template.
  2. Implement the Pattern on PostgreSQL
    Implement the streaming response service in your schema while maintaining migrational idempotency.
  3. Deploy
    Run the synchronous deploy once and check the exit result.
  4. Verify
    Fetch the live URL and run your own checks on the service.

Examples

Success Checks

Limitations

Cost Estimate

Next Actions