* improve validation * remove to_gen_params functions * update changes for all endpoint types * OAI: Fix calls to generation Chat completion and completion need to have prompt split out before pushing to the backend. Signed-off-by: kingbri <bdashore3@proton.me> * Sampling: Convert Top-K values of -1 to 0 Some OAI implementations use -1 as disabled instead of 0. Therefore, add a coalesce case. Signed-off-by: kingbri <bdashore3@proton.me> * Sampling: Format and space out Make the code more readable. Signed-off-by: kingbri <bdashore3@proton.me> * Sampling: Fix mirostat Field items are nested in data within a Pydantic FieldInfo Signed-off-by: kingbri <bdashore3@proton.me> * Sampling: Format Signed-off-by: kingbri <bdashore3@proton.me> * Sampling: Fix banned_tokens and allowed_tokens conversion If the provided string has whitespace, trim it before splitting. Signed-off-by: kingbri <bdashore3@proton.me> * Sampling: Add helpful log to dry_sequence_breakers Let the user know if the sequence errors out. Signed-off-by: kingbri <bdashore3@proton.me> * Sampling: Apply validators in right order Validators need to be applied in order from top to bottom, this is why the after validator was not being applied properly. Set the model to validate default params for sampler override purposes. This can be turned off if there are unclear errors. Signed-off-by: kingbri <bdashore3@proton.me> * Endpoints: Format Cleanup and semantically fix field validators Signed-off-by: kingbri <bdashore3@proton.me> * Kobold: Update validators and fix parameter application Validators on parent fields cannot see child fields. Therefore, validate using the child fields instead and alter the parent field data from there. Also fix badwordsids casting. Signed-off-by: kingbri <bdashore3@proton.me> * Sampling: Remove validate defaults and fix mirostat If a user sets an override to a non-default value, that's their own fault. Run validator on the actual mirostat_mode parameter rather than the alternate mirostat parameter. Signed-off-by: kingbri <bdashore3@proton.me> * Kobold: Rework badwordsids Currently, this serves to ban the EOS token. All other functionality was legacy, so remove it. Signed-off-by: kingbri <bdashore3@proton.me> * Model: Remove HuggingfaceConfig This was only necessary for badwordsids. All other fields are handled by exl2. Keep the class as a stub if it's needed again. Signed-off-by: kingbri <bdashore3@proton.me> * Kobold: Bump kcpp impersonation TabbyAPI supports XTC now. Signed-off-by: kingbri <bdashore3@proton.me> * Sampling: Change alias to validation_alias Reduces the probability for errors and makes the class consistent. Signed-off-by: kingbri <bdashore3@proton.me> * OAI: Use constraints for validation Instead of adding a model_validator, use greater than or equal to constraints provided by Pydantic. Signed-off-by: kingbri <bdashore3@proton.me> * Tree: Lint Signed-off-by: kingbri <bdashore3@proton.me> --------- Co-authored-by: SecretiveShell <84923604+SecretiveShell@users.noreply.github.com> Co-authored-by: kingbri <bdashore3@proton.me>
96 lines
2.5 KiB
Python
96 lines
2.5 KiB
Python
import asyncio
|
|
from typing import Optional
|
|
import uvicorn
|
|
from fastapi import FastAPI
|
|
from fastapi.middleware.cors import CORSMiddleware
|
|
from loguru import logger
|
|
|
|
from common.logger import UVICORN_LOG_CONFIG
|
|
from common.networking import get_global_depends
|
|
from common.tabby_config import config
|
|
from endpoints.Kobold import router as KoboldRouter
|
|
from endpoints.OAI import router as OAIRouter
|
|
from endpoints.core.router import router as CoreRouter
|
|
|
|
|
|
def setup_app(host: Optional[str] = None, port: Optional[int] = None):
|
|
"""Includes the correct routers for startup"""
|
|
|
|
app = FastAPI(
|
|
title="TabbyAPI",
|
|
summary="An OAI compatible exllamav2 API that's both lightweight and fast",
|
|
description=(
|
|
"This docs page is not meant to send requests! Please use a service "
|
|
"like Postman or a frontend UI."
|
|
),
|
|
dependencies=get_global_depends(),
|
|
)
|
|
|
|
# ALlow CORS requests
|
|
app.add_middleware(
|
|
CORSMiddleware,
|
|
allow_origins=["*"],
|
|
allow_credentials=True,
|
|
allow_methods=["*"],
|
|
allow_headers=["*"],
|
|
)
|
|
|
|
api_servers = config.network.api_servers
|
|
api_servers = (
|
|
api_servers
|
|
if api_servers
|
|
else [
|
|
"oai",
|
|
]
|
|
)
|
|
|
|
# Map for API id to server router
|
|
router_mapping = {"oai": OAIRouter, "kobold": KoboldRouter}
|
|
|
|
# Include the OAI api by default
|
|
for server in api_servers:
|
|
selected_server = router_mapping.get(server.lower())
|
|
|
|
if selected_server:
|
|
app.include_router(selected_server.setup())
|
|
|
|
logger.info(f"Starting {selected_server.api_name} API")
|
|
for path, url in selected_server.urls.items():
|
|
formatted_url = url.format(host=host, port=port)
|
|
logger.info(f"{path}: {formatted_url}")
|
|
|
|
# Include core API request paths
|
|
app.include_router(CoreRouter)
|
|
|
|
return app
|
|
|
|
|
|
def export_openapi():
|
|
"""Function to return the OpenAPI JSON from the API server"""
|
|
|
|
app = setup_app()
|
|
return app.openapi()
|
|
|
|
|
|
async def start_api(host: str, port: int):
|
|
"""Isolated function to start the API server"""
|
|
|
|
# TODO: Move OAI API to a separate folder
|
|
logger.info(f"Developer documentation: http://{host}:{port}/redoc")
|
|
|
|
# Setup app
|
|
app = setup_app(host, port)
|
|
|
|
# Get the current event loop
|
|
loop = asyncio.get_running_loop()
|
|
|
|
config = uvicorn.Config(
|
|
app,
|
|
host=host,
|
|
port=port,
|
|
log_config=UVICORN_LOG_CONFIG,
|
|
loop=loop,
|
|
)
|
|
server = uvicorn.Server(config)
|
|
|
|
await server.serve()
|