phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-07 04:45:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge 2a34226727 into ea15f2a270

Browse source
This commit is contained in:
Sébastien Han 2025-10-01 15:47:54 +02:00 • committed by GitHub
commit 79ced0c85b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
94 changed files with 341 additions and 209 deletions
Download patch file Download diff file Expand all files Collapse all files

1
llama_stack/providers/remote/inference/anthropic/anthropic.py
View file

@ -4,6 +4,7 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from llama_stack.providers.utils.inference.litellm_openai_mixin import LiteLLMOpenAIMixin
from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin

8
llama_stack/providers/remote/inference/anthropic/config.py
View file

@ -6,22 +6,20 @@
from typing import Any
from pydantic import BaseModel, Field
from pydantic import BaseModel, Field, SecretStr
from llama_stack.schema_utils import json_schema_type
class AnthropicProviderDataValidator(BaseModel):
anthropic_api_key: str | None = Field(
default=None,
anthropic_api_key: SecretStr = Field(
description="API key for Anthropic models",
)
@json_schema_type
class AnthropicConfig(BaseModel):
api_key: str | None = Field(
default=None,
api_key: SecretStr = Field(
description="API key for Anthropic models",
)

2
llama_stack/providers/remote/inference/azure/azure.py
View file

@ -21,7 +21,7 @@ class AzureInferenceAdapter(OpenAIMixin, LiteLLMOpenAIMixin):
LiteLLMOpenAIMixin.__init__(
self,
litellm_provider_name="azure",
api_key_from_config=config.api_key.get_secret_value(),
api_key_from_config=config.api_key,
provider_data_api_key_field="azure_api_key",
openai_compat_api_base=str(config.api_base),
)

1
llama_stack/providers/remote/inference/databricks/config.py
View file

@ -18,7 +18,6 @@ class DatabricksImplConfig(BaseModel):
description="The URL for the Databricks model serving endpoint",
)
api_token: SecretStr = Field(
default=SecretStr(None),
description="The Databricks API token",
)

3
llama_stack/providers/remote/inference/fireworks/config.py
View file

@ -18,8 +18,7 @@ class FireworksImplConfig(RemoteInferenceProviderConfig):
default="https://api.fireworks.ai/inference/v1",
description="The URL for the Fireworks server",
)
api_key: SecretStr | None = Field(
default=None,
api_key: SecretStr = Field(
description="The Fireworks.ai API Key",
)

8
llama_stack/providers/remote/inference/gemini/config.py
View file

@ -6,22 +6,20 @@
from typing import Any
from pydantic import BaseModel, Field
from pydantic import BaseModel, Field, SecretStr
from llama_stack.schema_utils import json_schema_type
class GeminiProviderDataValidator(BaseModel):
gemini_api_key: str | None = Field(
default=None,
gemini_api_key: SecretStr = Field(
description="API key for Gemini models",
)
@json_schema_type
class GeminiConfig(BaseModel):
api_key: str | None = Field(
default=None,
api_key: SecretStr = Field(
description="API key for Gemini models",
)

1
llama_stack/providers/remote/inference/gemini/gemini.py
View file

@ -4,6 +4,7 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from llama_stack.providers.utils.inference.litellm_openai_mixin import LiteLLMOpenAIMixin
from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin

8
llama_stack/providers/remote/inference/groq/config.py
View file

@ -6,23 +6,21 @@
from typing import Any
from pydantic import BaseModel, Field
from pydantic import BaseModel, Field, SecretStr
from llama_stack.schema_utils import json_schema_type
class GroqProviderDataValidator(BaseModel):
groq_api_key: str | None = Field(
default=None,
groq_api_key: SecretStr = Field(
description="API key for Groq models",
)
@json_schema_type
class GroqConfig(BaseModel):
api_key: str | None = Field(
api_key: SecretStr = Field(
# The Groq client library loads the GROQ_API_KEY environment variable by default
default=None,
description="The Groq API key",
)

8
llama_stack/providers/remote/inference/llama_openai_compat/config.py
View file

@ -6,22 +6,20 @@
from typing import Any
from pydantic import BaseModel, Field
from pydantic import BaseModel, Field, SecretStr
from llama_stack.schema_utils import json_schema_type
class LlamaProviderDataValidator(BaseModel):
llama_api_key: str | None = Field(
default=None,
llama_api_key: SecretStr = Field(
description="API key for api.llama models",
)
@json_schema_type
class LlamaCompatConfig(BaseModel):
api_key: str | None = Field(
default=None,
api_key: SecretStr = Field(
description="The Llama API key",
)

4
llama_stack/providers/remote/inference/nvidia/config.py
View file

@ -39,8 +39,8 @@ class NVIDIAConfig(BaseModel):
default_factory=lambda: os.getenv("NVIDIA_BASE_URL", "https://integrate.api.nvidia.com"),
description="A base url for accessing the NVIDIA NIM",
)
api_key: SecretStr | None = Field(
default_factory=lambda: SecretStr(os.getenv("NVIDIA_API_KEY")),
api_key: SecretStr = Field(
default_factory=lambda: SecretStr(os.getenv("NVIDIA_API_KEY", "")),
description="The NVIDIA API key, only needed of using the hosted service",
)
timeout: int = Field(

8
llama_stack/providers/remote/inference/openai/config.py
View file

@ -6,22 +6,20 @@
from typing import Any
from pydantic import BaseModel, Field
from pydantic import BaseModel, Field, SecretStr
from llama_stack.schema_utils import json_schema_type
class OpenAIProviderDataValidator(BaseModel):
openai_api_key: str | None = Field(
default=None,
openai_api_key: SecretStr = Field(
description="API key for OpenAI models",
)
@json_schema_type
class OpenAIConfig(BaseModel):
api_key: str | None = Field(
default=None,
api_key: SecretStr = Field(
description="API key for OpenAI models",
)
base_url: str = Field(

3
llama_stack/providers/remote/inference/passthrough/config.py
View file

@ -18,8 +18,7 @@ class PassthroughImplConfig(BaseModel):
description="The URL for the passthrough endpoint",
)
api_key: SecretStr | None = Field(
default=None,
api_key: SecretStr = Field(
description="API Key for the passthrouth endpoint",
)

5
llama_stack/providers/remote/inference/runpod/config.py
View file

@ -6,7 +6,7 @@
from typing import Any
from pydantic import BaseModel, Field
from pydantic import BaseModel, Field, SecretStr
from llama_stack.schema_utils import json_schema_type
@ -17,8 +17,7 @@ class RunpodImplConfig(BaseModel):
default=None,
description="The URL for the Runpod model serving endpoint",
)
api_token: str | None = Field(
default=None,
api_token: SecretStr = Field(
description="The API token",
)

5
llama_stack/providers/remote/inference/runpod/runpod.py
View file

@ -103,7 +103,10 @@ class RunpodInferenceAdapter(
tool_config=tool_config,
)
client = OpenAI(base_url=self.config.url, api_key=self.config.api_token)
client = OpenAI(
base_url=self.config.url,
api_key=self.config.api_token.get_secret_value() if self.config.api_token else None,
)
if stream:
return self._stream_chat_completion(request, client)
else:

6
llama_stack/providers/remote/inference/sambanova/config.py
View file

@ -12,8 +12,7 @@ from llama_stack.schema_utils import json_schema_type
class SambaNovaProviderDataValidator(BaseModel):
sambanova_api_key: str | None = Field(
default=None,
sambanova_api_key: SecretStr = Field(
description="Sambanova Cloud API key",
)
@ -24,8 +23,7 @@ class SambaNovaImplConfig(BaseModel):
default="https://api.sambanova.ai/v1",
description="The URL for the SambaNova AI server",
)
api_key: SecretStr | None = Field(
default=None,
api_key: SecretStr = Field(
description="The SambaNova cloud API Key",
)

2
llama_stack/providers/remote/inference/sambanova/sambanova.py
View file

@ -29,7 +29,7 @@ class SambaNovaInferenceAdapter(OpenAIMixin, LiteLLMOpenAIMixin):
LiteLLMOpenAIMixin.__init__(
self,
litellm_provider_name="sambanova",
api_key_from_config=self.config.api_key.get_secret_value() if self.config.api_key else None,
api_key_from_config=self.config.api_key,
provider_data_api_key_field="sambanova_api_key",
openai_compat_api_base=self.config.url,
download_images=True, # SambaNova requires base64 image encoding

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

@ -32,8 +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: SecretStr | None = Field(
default=None,
api_token: SecretStr = Field(
description="Your Hugging Face user access token (will default to locally saved token if not provided)",
)
@ -55,8 +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: SecretStr | None = Field(
default=None,
api_token: SecretStr = Field(
description="Your Hugging Face user access token (will default to locally saved token if not provided)",
)

3
llama_stack/providers/remote/inference/together/config.py
View file

@ -18,8 +18,7 @@ class TogetherImplConfig(RemoteInferenceProviderConfig):
default="https://api.together.xyz/v1",
description="The URL for the Together AI server",
)
api_key: SecretStr | None = Field(
default=None,
api_key: SecretStr = Field(
description="The Together AI API Key",
)

9
llama_stack/providers/remote/inference/vertexai/vertexai.py
View file

@ -8,6 +8,7 @@ from typing import Any
import google.auth.transport.requests
from google.auth import default
from pydantic import SecretStr
from llama_stack.apis.inference import ChatCompletionRequest
from llama_stack.providers.utils.inference.litellm_openai_mixin import (
@ -23,12 +24,12 @@ class VertexAIInferenceAdapter(OpenAIMixin, LiteLLMOpenAIMixin):
LiteLLMOpenAIMixin.__init__(
self,
litellm_provider_name="vertex_ai",
api_key_from_config=None, # Vertex AI uses ADC, not API keys
api_key_from_config=SecretStr(""), # Vertex AI uses ADC, not API keys
provider_data_api_key_field="vertex_project", # Use project for validation
)
self.config = config
def get_api_key(self) -> str:
def get_api_key(self) -> SecretStr:
"""
Get an access token for Vertex AI using Application Default Credentials.
@ -39,11 +40,11 @@ class VertexAIInferenceAdapter(OpenAIMixin, LiteLLMOpenAIMixin):
# Get default credentials - will read from GOOGLE_APPLICATION_CREDENTIALS
credentials, _ = default(scopes=["https://www.googleapis.com/auth/cloud-platform"])
credentials.refresh(google.auth.transport.requests.Request())
return str(credentials.token)
return SecretStr(credentials.token)
except Exception:
# If we can't get credentials, return empty string to let LiteLLM handle it
# This allows the LiteLLM mixin to work with ADC directly
return ""
return SecretStr("")
def get_base_url(self) -> str:
"""

6
llama_stack/providers/remote/inference/vllm/__init__.py
View file

@ -4,13 +4,15 @@
# 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
from pydantic import BaseModel, Field, SecretStr
from .config import VLLMInferenceAdapterConfig
class VLLMProviderDataValidator(BaseModel):
vllm_api_token: str | None = None
vllm_api_token: SecretStr = Field(
description="API token for vLLM models",
)
async def get_adapter_impl(config: VLLMInferenceAdapterConfig, _deps):

6
llama_stack/providers/remote/inference/vllm/config.py
View file

@ -6,7 +6,7 @@
from pathlib import Path
from pydantic import BaseModel, Field, field_validator
from pydantic import BaseModel, Field, SecretStr, field_validator
from llama_stack.schema_utils import json_schema_type
@ -21,8 +21,8 @@ class VLLMInferenceAdapterConfig(BaseModel):
default=4096,
description="Maximum number of tokens to generate.",
)
api_token: str | None = Field(
default="fake",
api_token: SecretStr = Field(
default=SecretStr("fake"),
description="The API token",
)
tls_verify: bool | str = Field(

4
llama_stack/providers/remote/inference/watsonx/config.py
View file

@ -24,8 +24,8 @@ class WatsonXConfig(BaseModel):
default_factory=lambda: os.getenv("WATSONX_BASE_URL", "https://us-south.ml.cloud.ibm.com"),
description="A base url for accessing the watsonx.ai",
)
api_key: SecretStr | None = Field(
default_factory=lambda: os.getenv("WATSONX_API_KEY"),
api_key: SecretStr = Field(
default_factory=lambda: SecretStr(os.getenv("WATSONX_API_KEY", "")),
description="The watsonx API key",
)
project_id: str | None = Field(