phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

revert: do not use MySecretStr

Browse source 
We don't need this if we can set it to empty string.

Signed-off-by: Sébastien Han <seb@redhat.com>
This commit is contained in:
Sébastien Han 2025-09-26 10:33:33 +02:00
parent bc64635835
commit 2a34226727
No known key found for this signature in database
86 changed files with 208 additions and 263 deletions
Download patch file Download diff file Expand all files Collapse all files

7
llama_stack/providers/remote/inference/tgi/config.py
View file

@ -5,9 +5,8 @@
# the root directory of this source tree.
from pydantic import BaseModel, Field
from pydantic import BaseModel, Field, SecretStr
from llama_stack.core.secret_types import MySecretStr
from llama_stack.schema_utils import json_schema_type
@ -33,7 +32,7 @@ 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(
api_token: SecretStr = Field(
description="Your Hugging Face user access token (will default to locally saved token if not provided)",
)
@ -55,7 +54,7 @@ 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(
api_token: SecretStr = Field(
description="Your Hugging Face user access token (will default to locally saved token if not provided)",
)

6
llama_stack/providers/remote/inference/tgi/tgi.py
View file

@ -8,6 +8,7 @@
from collections.abc import AsyncGenerator
from huggingface_hub import AsyncInferenceClient, HfApi
from pydantic import SecretStr
from llama_stack.apis.common.content_types import (
InterleavedContent,
@ -34,7 +35,6 @@ from llama_stack.apis.inference import (
)
from llama_stack.apis.models import Model
from llama_stack.apis.models.models import ModelType
from llama_stack.core.secret_types import MySecretStr
from llama_stack.log import get_logger
from llama_stack.models.llama.sku_list import all_registered_models
from llama_stack.providers.datatypes import ModelsProtocolPrivate
@ -79,7 +79,7 @@ class _HfAdapter(
ModelsProtocolPrivate,
):
url: str
api_key: MySecretStr
api_key: SecretStr
hf_client: AsyncInferenceClient
max_tokens: int
@ -337,7 +337,7 @@ class TGIAdapter(_HfAdapter):
self.max_tokens = endpoint_info["max_total_tokens"]
self.model_id = endpoint_info["model_id"]
self.url = f"{config.url.rstrip('/')}/v1"
self.api_key = MySecretStr("NO_KEY")
self.api_key = SecretStr("NO_KEY")
class InferenceAPIAdapter(_HfAdapter):