mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-03 19:57:35 +00:00
bc64635835
When using bash style substitution env variable in distribution
template, we are processing the string and convert it to the type
associated with the provider's config class. This allows us to return
the proper type. This is crucial for api key since they are not strings
anymore but SecretStr. If the key is unset we will get an empty string
which will result in a Pydantic error like:
```
ERROR 2025-09-25 21:40:44,565 __main__:527 core::server: Error creating app: 1 validation error for AnthropicConfig
api_key
Input should be a valid string
For further information visit
https://errors.pydantic.dev/2.11/v/string_type
```
Signed-off-by: Sébastien Han <seb@redhat.com>
72 lines
2.1 KiB
Python
72 lines
2.1 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.core.secret_types import MySecretStr
|
|
from llama_stack.schema_utils import json_schema_type
|
|
|
|
|
|
@json_schema_type
|
|
class TGIImplConfig(BaseModel):
|
|
url: str = Field(
|
|
description="The URL for the TGI serving endpoint",
|
|
)
|
|
|
|
@classmethod
|
|
def sample_run_config(
|
|
cls,
|
|
url: str = "${env.TGI_URL:=}",
|
|
**kwargs,
|
|
):
|
|
return {
|
|
"url": url,
|
|
}
|
|
|
|
|
|
@json_schema_type
|
|
class InferenceEndpointImplConfig(BaseModel):
|
|
endpoint_name: str = Field(
|
|
description="The name of the Hugging Face Inference Endpoint in the format of '{namespace}/{endpoint_name}' (e.g. 'my-cool-org/meta-llama-3-1-8b-instruct-rce'). Namespace is optional and will default to the user account if not provided.",
|
|
)
|
|
api_token: MySecretStr = Field(
|
|
description="Your Hugging Face user access token (will default to locally saved token if not provided)",
|
|
)
|
|
|
|
@classmethod
|
|
def sample_run_config(
|
|
cls,
|
|
endpoint_name: str = "${env.INFERENCE_ENDPOINT_NAME}",
|
|
api_token: str = "${env.HF_API_TOKEN}",
|
|
**kwargs,
|
|
):
|
|
return {
|
|
"endpoint_name": endpoint_name,
|
|
"api_token": api_token,
|
|
}
|
|
|
|
|
|
@json_schema_type
|
|
class InferenceAPIImplConfig(BaseModel):
|
|
huggingface_repo: str = Field(
|
|
description="The model ID of the model on the Hugging Face Hub (e.g. 'meta-llama/Meta-Llama-3.1-70B-Instruct')",
|
|
)
|
|
api_token: MySecretStr = Field(
|
|
description="Your Hugging Face user access token (will default to locally saved token if not provided)",
|
|
)
|
|
|
|
@classmethod
|
|
def sample_run_config(
|
|
cls,
|
|
repo: str = "${env.INFERENCE_MODEL}",
|
|
api_token: str = "${env.HF_API_TOKEN}",
|
|
**kwargs,
|
|
):
|
|
return {
|
|
"huggingface_repo": repo,
|
|
"api_token": api_token,
|
|
}
|