mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 19:04:19 +00:00
9e6561a1ec
# What does this PR do? The goal of this PR is code base modernization. Schema reflection code needed a minor adjustment to handle UnionTypes and collections.abc.AsyncIterator. (Both are preferred for latest Python releases.) Note to reviewers: almost all changes here are automatically generated by pyupgrade. Some additional unused imports were cleaned up. The only change worth of note can be found under `docs/openapi_generator` and `llama_stack/strong_typing/schema.py` where reflection code was updated to deal with "newer" types. Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
43 lines
1.1 KiB
Python
43 lines
1.1 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 pydantic import BaseModel, Field
|
|
|
|
from llama_stack.schema_utils import json_schema_type
|
|
|
|
|
|
@json_schema_type
|
|
class VLLMInferenceAdapterConfig(BaseModel):
|
|
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.",
|
|
)
|
|
api_token: str | None = Field(
|
|
default="fake",
|
|
description="The API token",
|
|
)
|
|
tls_verify: bool = Field(
|
|
default=True,
|
|
description="Whether to verify TLS certificates",
|
|
)
|
|
|
|
@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}",
|
|
}
|