Fan Out Concurrent LLM Calls with asyncio.gather
Awaiting retrieval and LLM calls one by one wastes seconds per request. Here's how to fan them out with asyncio.gather, bound it, and handle partial failures.
Awaiting retrieval and LLM calls one by one wastes seconds per request. Here's how to fan them out with asyncio.gather, bound it, and handle partial failures.
One blocking call in a FastAPI route stalls every other request, including live SSE streams. Here is how the event loop breaks, and how to keep it free.