mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 09:53:45 +00:00
840ad75fe9
# What does this PR do? Extract API definitions and provider specifications into a standalone llama-stack-api package that can be published to PyPI independently of the main llama-stack server. see: https://github.com/llamastack/llama-stack/pull/2978 and https://github.com/llamastack/llama-stack/pull/2978#issuecomment-3145115942 Motivation External providers currently import from llama-stack, which overrides the installed version and causes dependency conflicts. This separation allows external providers to: - Install only the type definitions they need without server dependencies - Avoid version conflicts with the installed llama-stack package - Be versioned and released independently This enables us to re-enable external provider module tests that were previously blocked by these import conflicts. Changes - Created llama-stack-api package with minimal dependencies (pydantic, jsonschema) - Moved APIs, providers datatypes, strong_typing, and schema_utils - Updated all imports from llama_stack.* to llama_stack_api.* - Configured local editable install for development workflow - Updated linting and type-checking configuration for both packages Next Steps - Publish llama-stack-api to PyPI - Update external provider dependencies - Re-enable external provider module tests Pre-cursor PRs to this one: - #4093 - #3954 - #4064 These PRs moved key pieces _out_ of the Api pkg, limiting the scope of change here. relates to #3237 ## Test Plan Package builds successfully and can be imported independently. All pre-commit hooks pass with expected exclusions maintained. --------- Signed-off-by: Charlie Doern <cdoern@redhat.com>
59 lines
1.9 KiB
Python
59 lines
1.9 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 pathlib import Path
|
|
|
|
from llama_stack_api import json_schema_type
|
|
from pydantic import Field, SecretStr, field_validator
|
|
|
|
from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
|
|
|
|
|
|
@json_schema_type
|
|
class VLLMInferenceAdapterConfig(RemoteInferenceProviderConfig):
|
|
url: str | None = Field(
|
|
default=None,
|
|
description="The URL for the vLLM model serving endpoint",
|
|
)
|
|
max_tokens: int = Field(
|
|
default=4096,
|
|
description="Maximum number of tokens to generate.",
|
|
)
|
|
auth_credential: SecretStr | None = Field(
|
|
default=None,
|
|
alias="api_token",
|
|
description="The API token",
|
|
)
|
|
tls_verify: bool | str = Field(
|
|
default=True,
|
|
description="Whether to verify TLS certificates. Can be a boolean or a path to a CA certificate file.",
|
|
)
|
|
|
|
@field_validator("tls_verify")
|
|
@classmethod
|
|
def validate_tls_verify(cls, v):
|
|
if isinstance(v, str):
|
|
# Otherwise, treat it as a cert path
|
|
cert_path = Path(v).expanduser().resolve()
|
|
if not cert_path.exists():
|
|
raise ValueError(f"TLS certificate file does not exist: {v}")
|
|
if not cert_path.is_file():
|
|
raise ValueError(f"TLS certificate path is not a file: {v}")
|
|
return v
|
|
return v
|
|
|
|
@classmethod
|
|
def sample_run_config(
|
|
cls,
|
|
url: str = "${env.VLLM_URL:=}",
|
|
**kwargs,
|
|
):
|
|
return {
|
|
"url": url,
|
|
"max_tokens": "${env.VLLM_MAX_TOKENS:=4096}",
|
|
"api_token": "${env.VLLM_API_TOKEN:=fake}",
|
|
"tls_verify": "${env.VLLM_TLS_VERIFY:=true}",
|
|
}
|