mirror of
https://github.com/theroyallab/tabbyAPI.git
synced 2026-03-15 00:07:28 +00:00
c82697fef2
This is the first in many future commits that will overhaul the API to be more robust and concurrent. The model is admin-first where the admin can do anything in-case something goes awry. Previously, calls to long running synchronous background tasks would block the entire API, making it ignore any terminal signals until generation is completed. To fix this, levrage FastAPI's run_in_threadpool to offload the long running tasks to another thread. However, signals to abort the process still kept the background thread running and made the terminal hang. This was due to an issue with Uvicorn not propegating the SIGINT signal across threads in its event loop. To fix this in a catch-all way, run the API processes in a separate thread so the main thread can still kill the process if needed. In addition, make request error logging more robust and refer to the console for full error logs rather than creating a long message on the client-side. Finally, add state checks to see if a model is fully loaded before generating a completion. Signed-off-by: kingbri <bdashore3@proton.me>
31 lines
794 B
Python
31 lines
794 B
Python
"""Generator handling"""
|
|
|
|
import asyncio
|
|
import inspect
|
|
from functools import partialmethod
|
|
from typing import AsyncGenerator, Generator, Union
|
|
|
|
generate_semaphore = asyncio.Semaphore(1)
|
|
|
|
|
|
async def generate_with_semaphore(generator: Union[AsyncGenerator, Generator]):
|
|
"""Generate with a semaphore."""
|
|
|
|
async with generate_semaphore:
|
|
if inspect.isasyncgenfunction:
|
|
async for result in generator():
|
|
yield result
|
|
else:
|
|
for result in generator():
|
|
yield result
|
|
|
|
|
|
async def call_with_semaphore(callback: partialmethod):
|
|
"""Call with a semaphore."""
|
|
|
|
async with generate_semaphore:
|
|
if inspect.iscoroutinefunction(callback):
|
|
return await callback()
|
|
else:
|
|
return callback()
|