mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 10:54:19 +00:00
314ee09ae3
llama-models should have extremely minimal cruft. Its sole purpose should be didactic -- show the simplest implementation of the llama models and document the prompt formats, etc. This PR is the complement to https://github.com/meta-llama/llama-models/pull/279 ## Test Plan Ensure all `llama` CLI `model` sub-commands work: ```bash llama model list llama model download --model-id ... llama model prompt-format -m ... ``` Ran tests: ```bash cd tests/client-sdk LLAMA_STACK_CONFIG=fireworks pytest -s -v inference/ LLAMA_STACK_CONFIG=fireworks pytest -s -v vector_io/ LLAMA_STACK_CONFIG=fireworks pytest -s -v agents/ ``` Create a fresh venv `uv venv && source .venv/bin/activate` and run `llama stack build --template fireworks --image-type venv` followed by `llama stack run together --image-type venv` <-- the server runs Also checked that the OpenAPI generator can run and there is no change in the generated files as a result. ```bash cd docs/openapi_generator sh run_openapi_generator.sh ```
59 lines
1.3 KiB
Python
59 lines
1.3 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 typing import List, Protocol, runtime_checkable
|
|
|
|
from pydantic import BaseModel
|
|
|
|
from llama_stack.schema_utils import json_schema_type, webmethod
|
|
|
|
|
|
@json_schema_type
|
|
class ProviderInfo(BaseModel):
|
|
api: str
|
|
provider_id: str
|
|
provider_type: str
|
|
|
|
|
|
@json_schema_type
|
|
class RouteInfo(BaseModel):
|
|
route: str
|
|
method: str
|
|
provider_types: List[str]
|
|
|
|
|
|
@json_schema_type
|
|
class HealthInfo(BaseModel):
|
|
status: str
|
|
# TODO: add a provider level status
|
|
|
|
|
|
@json_schema_type
|
|
class VersionInfo(BaseModel):
|
|
version: str
|
|
|
|
|
|
class ListProvidersResponse(BaseModel):
|
|
data: List[ProviderInfo]
|
|
|
|
|
|
class ListRoutesResponse(BaseModel):
|
|
data: List[RouteInfo]
|
|
|
|
|
|
@runtime_checkable
|
|
class Inspect(Protocol):
|
|
@webmethod(route="/inspect/providers", method="GET")
|
|
async def list_providers(self) -> ListProvidersResponse: ...
|
|
|
|
@webmethod(route="/inspect/routes", method="GET")
|
|
async def list_routes(self) -> ListRoutesResponse: ...
|
|
|
|
@webmethod(route="/health", method="GET")
|
|
async def health(self) -> HealthInfo: ...
|
|
|
|
@webmethod(route="/version", method="GET")
|
|
async def version(self) -> VersionInfo: ...
|