mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-19 11:20:03 +00:00
Some checks failed
Integration Tests / discover-tests (push) Successful in 13s
Test Llama Stack Build / generate-matrix (push) Successful in 14s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 21s
Python Package Build Test / build (3.12) (push) Failing after 25s
Test Llama Stack Build / build-single-provider (push) Failing after 30s
Vector IO Integration Tests / test-matrix (3.13, remote::pgvector) (push) Failing after 30s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 30s
Unit Tests / unit-tests (3.12) (push) Failing after 32s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 40s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 29s
Vector IO Integration Tests / test-matrix (3.12, remote::chromadb) (push) Failing after 32s
Unit Tests / unit-tests (3.13) (push) Failing after 36s
Vector IO Integration Tests / test-matrix (3.13, inline::faiss) (push) Failing after 42s
Vector IO Integration Tests / test-matrix (3.13, inline::milvus) (push) Failing after 36s
Test External Providers / test-external-providers (venv) (push) Failing after 36s
Vector IO Integration Tests / test-matrix (3.12, inline::faiss) (push) Failing after 36s
Vector IO Integration Tests / test-matrix (3.12, inline::milvus) (push) Failing after 42s
Vector IO Integration Tests / test-matrix (3.13, inline::sqlite-vec) (push) Failing after 40s
Vector IO Integration Tests / test-matrix (3.12, inline::sqlite-vec) (push) Failing after 49s
Vector IO Integration Tests / test-matrix (3.13, remote::chromadb) (push) Failing after 47s
Python Package Build Test / build (3.13) (push) Failing after 1m51s
Vector IO Integration Tests / test-matrix (3.12, remote::pgvector) (push) Failing after 1m58s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 2m5s
Integration Tests / test-matrix (push) Failing after 36s
Test Llama Stack Build / build (push) Failing after 37s
Pre-commit / pre-commit (push) Successful in 3m40s
- POST /v1/models accepts optional provider_model_id - ModelsRoutingTable.register_model handler ensures it is non-None, providing a default usage of Model.provider_model_id will no longer need to detect None
147 lines
4 KiB
Python
147 lines
4 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 StrEnum
|
|
from typing import Any, Literal, Protocol, runtime_checkable
|
|
|
|
from pydantic import BaseModel, ConfigDict, Field, field_validator
|
|
|
|
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(StrEnum):
|
|
llm = "llm"
|
|
embedding = "embedding"
|
|
|
|
|
|
@json_schema_type
|
|
class Model(CommonModelFields, Resource):
|
|
type: Literal[ResourceType.model] = ResourceType.model
|
|
|
|
@property
|
|
def model_id(self) -> str:
|
|
return self.identifier
|
|
|
|
@property
|
|
def provider_model_id(self) -> str:
|
|
assert self.provider_resource_id is not None, "Provider resource ID must be set"
|
|
return self.provider_resource_id
|
|
|
|
model_config = ConfigDict(protected_namespaces=())
|
|
|
|
model_type: ModelType = Field(default=ModelType.llm)
|
|
|
|
@field_validator("provider_resource_id")
|
|
@classmethod
|
|
def validate_provider_resource_id(cls, v):
|
|
if v is None:
|
|
raise ValueError("provider_resource_id cannot be None")
|
|
return v
|
|
|
|
|
|
class ModelInput(CommonModelFields):
|
|
model_id: str
|
|
provider_id: str | None = None
|
|
provider_model_id: str | None = None
|
|
model_type: ModelType | None = ModelType.llm
|
|
model_config = ConfigDict(protected_namespaces=())
|
|
|
|
|
|
class ListModelsResponse(BaseModel):
|
|
data: list[Model]
|
|
|
|
|
|
@json_schema_type
|
|
class OpenAIModel(BaseModel):
|
|
"""A model from OpenAI.
|
|
|
|
:id: The ID of the model
|
|
:object: The object type, which will be "model"
|
|
:created: The Unix timestamp in seconds when the model was created
|
|
:owned_by: The owner of the model
|
|
"""
|
|
|
|
id: str
|
|
object: Literal["model"] = "model"
|
|
created: int
|
|
owned_by: str
|
|
|
|
|
|
class OpenAIListModelsResponse(BaseModel):
|
|
data: list[OpenAIModel]
|
|
|
|
|
|
@runtime_checkable
|
|
@trace_protocol
|
|
class Models(Protocol):
|
|
@webmethod(route="/models", method="GET")
|
|
async def list_models(self) -> ListModelsResponse:
|
|
"""List all models.
|
|
|
|
:returns: A ListModelsResponse.
|
|
"""
|
|
...
|
|
|
|
@webmethod(route="/openai/v1/models", method="GET")
|
|
async def openai_list_models(self) -> OpenAIListModelsResponse:
|
|
"""List models using the OpenAI API.
|
|
|
|
:returns: A OpenAIListModelsResponse.
|
|
"""
|
|
...
|
|
|
|
@webmethod(route="/models/{model_id:path}", method="GET")
|
|
async def get_model(
|
|
self,
|
|
model_id: str,
|
|
) -> Model:
|
|
"""Get a model by its identifier.
|
|
|
|
:param model_id: The identifier of the model to get.
|
|
:returns: A Model.
|
|
"""
|
|
...
|
|
|
|
@webmethod(route="/models", method="POST")
|
|
async def register_model(
|
|
self,
|
|
model_id: str,
|
|
provider_model_id: str | None = None,
|
|
provider_id: str | None = None,
|
|
metadata: dict[str, Any] | None = None,
|
|
model_type: ModelType | None = None,
|
|
) -> Model:
|
|
"""Register a model.
|
|
|
|
:param model_id: The identifier of the model to register.
|
|
:param provider_model_id: The identifier of the model in the provider.
|
|
:param provider_id: The identifier of the provider.
|
|
:param metadata: Any additional metadata for this model.
|
|
:param model_type: The type of model to register.
|
|
:returns: A Model.
|
|
"""
|
|
...
|
|
|
|
@webmethod(route="/models/{model_id:path}", method="DELETE")
|
|
async def unregister_model(
|
|
self,
|
|
model_id: str,
|
|
) -> None:
|
|
"""Unregister a model.
|
|
|
|
:param model_id: The identifier of the model to unregister.
|
|
"""
|
|
...
|