Streaming AI Responses

Normal response:

Request
   ↓
FM processes
   ↓
Wait
   ↓
Complete response

Streaming:

Request
   ↓
FM
   ↓
Chunk 1
Chunk 2
Chunk 3
Chunk 4
   ↓
Client displays progressively

This improves perceived responsiveness.

The model can return incremental output rather than waiting for the entire response.

Useful for persistent two-way communication.

Client ←──── WebSocket ────→ Server

SSE allows the server to send incremental updates to the client.

Server
  │
  ├── chunk 1 → Client
  ├── chunk 2 → Client
  ├── chunk 3 → Client
  └── chunk 4 → Client

The response can be delivered in pieces rather than as one complete payload.

If the question says:

"Display generated text to the user as it becomes available"

Think:

Streaming