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

feat: load config class when doing variable substitution

Browse source 
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>
This commit is contained in:
Sébastien Han 2025-09-25 10:27:41 +02:00
parent 4af141292f
commit bc64635835
No known key found for this signature in database
79 changed files with 381 additions and 216 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -8,7 +8,6 @@
from collections.abc import AsyncGenerator
from huggingface_hub import AsyncInferenceClient, HfApi
from pydantic import SecretStr
from llama_stack.apis.common.content_types import (
InterleavedContent,
@ -35,6 +34,7 @@ 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: SecretStr
api_key: MySecretStr
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 = SecretStr("NO_KEY")
self.api_key = MySecretStr("NO_KEY")
class InferenceAPIAdapter(_HfAdapter):