API: Fix issues with concurrent requests and queueing
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>
This commit is contained in:
parent
de91eade4b
commit
c82697fef2
4 changed files with 158 additions and 71 deletions
|
|
@ -1,15 +1,16 @@
|
|||
"""Generator functions for the tabbyAPI."""
|
||||
"""Generator handling"""
|
||||
|
||||
import asyncio
|
||||
import inspect
|
||||
from asyncio import Semaphore
|
||||
from functools import partialmethod
|
||||
from typing import AsyncGenerator
|
||||
from typing import AsyncGenerator, Generator, Union
|
||||
|
||||
generate_semaphore = Semaphore(1)
|
||||
generate_semaphore = asyncio.Semaphore(1)
|
||||
|
||||
|
||||
# Async generation that blocks on a semaphore
|
||||
async def generate_with_semaphore(generator: AsyncGenerator):
|
||||
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():
|
||||
|
|
@ -19,9 +20,11 @@ async def generate_with_semaphore(generator: AsyncGenerator):
|
|||
yield result
|
||||
|
||||
|
||||
# Block a function with semaphore
|
||||
async def call_with_semaphore(callback: partialmethod):
|
||||
if inspect.iscoroutinefunction(callback):
|
||||
return await callback()
|
||||
"""Call with a semaphore."""
|
||||
|
||||
async with generate_semaphore:
|
||||
return callback()
|
||||
if inspect.iscoroutinefunction(callback):
|
||||
return await callback()
|
||||
else:
|
||||
return callback()
|
||||
|
|
|
|||
|
|
@ -1,8 +1,8 @@
|
|||
"""Common utilities for the tabbyAPI"""
|
||||
import traceback
|
||||
from typing import Optional
|
||||
"""Common utility functions"""
|
||||
|
||||
import traceback
|
||||
from pydantic import BaseModel
|
||||
from typing import Optional
|
||||
|
||||
from common.logger import init_logger
|
||||
|
||||
|
|
@ -14,30 +14,41 @@ def load_progress(module, modules):
|
|||
yield module, modules
|
||||
|
||||
|
||||
class TabbyGeneratorErrorMessage(BaseModel):
|
||||
"""Common error types."""
|
||||
class TabbyRequestErrorMessage(BaseModel):
|
||||
"""Common request error type."""
|
||||
|
||||
message: str
|
||||
trace: Optional[str] = None
|
||||
|
||||
|
||||
class TabbyGeneratorError(BaseModel):
|
||||
"""Common error types."""
|
||||
class TabbyRequestError(BaseModel):
|
||||
"""Common request error type."""
|
||||
|
||||
error: TabbyGeneratorErrorMessage
|
||||
error: TabbyRequestErrorMessage
|
||||
|
||||
|
||||
def get_generator_error(message: str):
|
||||
"""Get a generator error."""
|
||||
error_message = TabbyGeneratorErrorMessage(
|
||||
|
||||
generator_error = handle_request_error(message)
|
||||
|
||||
return get_sse_packet(generator_error.model_dump_json())
|
||||
|
||||
|
||||
def handle_request_error(message: str):
|
||||
"""Log a request error to the console."""
|
||||
|
||||
error_message = TabbyRequestErrorMessage(
|
||||
message=message, trace=traceback.format_exc()
|
||||
)
|
||||
|
||||
generator_error = TabbyGeneratorError(error=error_message)
|
||||
request_error = TabbyRequestError(error=error_message)
|
||||
|
||||
# Log and send the exception
|
||||
logger.error(generator_error.error.trace)
|
||||
return get_sse_packet(generator_error.model_dump_json())
|
||||
# Log the error and provided message to the console
|
||||
logger.error(error_message.trace)
|
||||
logger.error(message)
|
||||
|
||||
return request_error
|
||||
|
||||
|
||||
def get_sse_packet(json_data: str):
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue