forked from phoenix-oss/llama-stack-mirror
c029fbcd13
# What does this PR do? - Removed Optional return types for GET methods - Raised ValueError when requested resource is not found - Ensures proper 4xx response for missing resources - Updated the API generator to check for wrong signatures ``` $ uv run --with ".[dev]" ./docs/openapi_generator/run_openapi_generator.sh Validating API method return types... API Method Return Type Validation Errors: Method ScoringFunctions.get_scoring_function returns Optional type ``` Closes: https://github.com/meta-llama/llama-stack/issues/1630 ## Test Plan Run the server then: ``` curl http://127.0.0.1:8321/v1/models/foo {"detail":"Invalid value: Model 'foo' not found"}% ``` Server log: ``` INFO: 127.0.0.1:52307 - "GET /v1/models/foo HTTP/1.1" 400 Bad Request 09:51:42.654 [END] /v1/models/foo [StatusCode.OK] (134.65ms) 09:51:42.651 [ERROR] Error executing endpoint route='/v1/models/{model_id:path}' method='get' Traceback (most recent call last): File "/Users/leseb/Documents/AI/llama-stack/llama_stack/distribution/server/server.py", line 193, in endpoint return await maybe_await(value) File "/Users/leseb/Documents/AI/llama-stack/llama_stack/distribution/server/server.py", line 156, in maybe_await return await value File "/Users/leseb/Documents/AI/llama-stack/llama_stack/providers/utils/telemetry/trace_protocol.py", line 102, in async_wrapper result = await method(self, *args, **kwargs) File "/Users/leseb/Documents/AI/llama-stack/llama_stack/distribution/routers/routing_tables.py", line 217, in get_model raise ValueError(f"Model '{model_id}' not found") ValueError: Model 'foo' not found ``` Signed-off-by: Sébastien Han <seb@redhat.com>
85 lines
2.3 KiB
Python
85 lines
2.3 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
from enum import Enum
|
|
from typing import Any, Dict, List, Literal, Optional, Protocol, runtime_checkable
|
|
|
|
from pydantic import BaseModel, ConfigDict, Field
|
|
|
|
from llama_stack.apis.resource import Resource, ResourceType
|
|
from llama_stack.providers.utils.telemetry.trace_protocol import trace_protocol
|
|
from llama_stack.schema_utils import json_schema_type, webmethod
|
|
|
|
|
|
class CommonModelFields(BaseModel):
|
|
metadata: Dict[str, Any] = Field(
|
|
default_factory=dict,
|
|
description="Any additional metadata for this model",
|
|
)
|
|
|
|
|
|
@json_schema_type
|
|
class ModelType(str, Enum):
|
|
llm = "llm"
|
|
embedding = "embedding"
|
|
|
|
|
|
@json_schema_type
|
|
class Model(CommonModelFields, Resource):
|
|
type: Literal[ResourceType.model.value] = ResourceType.model.value
|
|
|
|
@property
|
|
def model_id(self) -> str:
|
|
return self.identifier
|
|
|
|
@property
|
|
def provider_model_id(self) -> str:
|
|
return self.provider_resource_id
|
|
|
|
model_config = ConfigDict(protected_namespaces=())
|
|
|
|
model_type: ModelType = Field(default=ModelType.llm)
|
|
|
|
|
|
class ModelInput(CommonModelFields):
|
|
model_id: str
|
|
provider_id: Optional[str] = None
|
|
provider_model_id: Optional[str] = None
|
|
model_type: Optional[ModelType] = ModelType.llm
|
|
model_config = ConfigDict(protected_namespaces=())
|
|
|
|
|
|
class ListModelsResponse(BaseModel):
|
|
data: List[Model]
|
|
|
|
|
|
@runtime_checkable
|
|
@trace_protocol
|
|
class Models(Protocol):
|
|
@webmethod(route="/models", method="GET")
|
|
async def list_models(self) -> ListModelsResponse: ...
|
|
|
|
@webmethod(route="/models/{model_id:path}", method="GET")
|
|
async def get_model(
|
|
self,
|
|
model_id: str,
|
|
) -> Model: ...
|
|
|
|
@webmethod(route="/models", method="POST")
|
|
async def register_model(
|
|
self,
|
|
model_id: str,
|
|
provider_model_id: Optional[str] = None,
|
|
provider_id: Optional[str] = None,
|
|
metadata: Optional[Dict[str, Any]] = None,
|
|
model_type: Optional[ModelType] = None,
|
|
) -> Model: ...
|
|
|
|
@webmethod(route="/models/{model_id:path}", method="DELETE")
|
|
async def unregister_model(
|
|
self,
|
|
model_id: str,
|
|
) -> None: ...
|