No Streaming Response for Application Load Balancer + Lambda (Fastapi : server sent event -> streaming response)

[GxWwT]

from fastapi.responses import StreamingResponse

if chat_request.stream:
    return StreamingResponse(
        content=model.chat_stream(chat_request), media_type="text/event-stream"
    )

This approach, when redirected to ALB through Mangum, loses the streaming response. Instead, all chunks are printed out all at once.

[KamilLegault]

I dont think this is a mangum issue, the Python runtimes on AWS Lambda do not support streaming.

Look into the AWS lambda web adapter https://github.com/awslabs/aws-lambda-web-adapter/tree/main/examples/fastapi-response-streaming