mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
0850ad656a
The semantics of an Update on resources is very tricky to reason about especially for memory banks and models. The best way to go forward here is for the user to unregister and register a new resource. We don't have a compelling reason to support update APIs. Tests: pytest -v -s llama_stack/providers/tests/memory/test_memory.py -m "chroma" --env CHROMA_HOST=localhost --env CHROMA_PORT=8000 pytest -v -s llama_stack/providers/tests/memory/test_memory.py -m "pgvector" --env PGVECTOR_DB=postgres --env PGVECTOR_USER=postgres --env PGVECTOR_PASSWORD=mysecretpassword --env PGVECTOR_HOST=0.0.0.0 $CONDA_PREFIX/bin/pytest -v -s -m "ollama" llama_stack/providers/tests/inference/test_model_registration.py --------- Co-authored-by: Dinesh Yeduguru <dineshyv@fb.com>
59 lines
1.7 KiB
Python
59 lines
1.7 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 typing import Any, Dict, List, Literal, Optional, Protocol, runtime_checkable
|
|
|
|
from llama_models.schema_utils import json_schema_type, webmethod
|
|
from pydantic import BaseModel, Field
|
|
|
|
from llama_stack.apis.resource import Resource, ResourceType
|
|
|
|
|
|
class CommonModelFields(BaseModel):
|
|
metadata: Dict[str, Any] = Field(
|
|
default_factory=dict,
|
|
description="Any additional metadata for this model",
|
|
)
|
|
|
|
|
|
@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
|
|
|
|
|
|
class ModelInput(CommonModelFields):
|
|
model_id: str
|
|
provider_id: Optional[str] = None
|
|
provider_model_id: Optional[str] = None
|
|
|
|
|
|
@runtime_checkable
|
|
class Models(Protocol):
|
|
@webmethod(route="/models/list", method="GET")
|
|
async def list_models(self) -> List[Model]: ...
|
|
|
|
@webmethod(route="/models/get", method="GET")
|
|
async def get_model(self, identifier: str) -> Optional[Model]: ...
|
|
|
|
@webmethod(route="/models/register", 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: ...
|
|
|
|
@webmethod(route="/models/unregister", method="POST")
|
|
async def unregister_model(self, model_id: str) -> None: ...
|