phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-08 04:54:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into chroma

Browse source
This commit is contained in:
Bwook (Byoungwook) Kim 2025-09-11 20:51:31 +09:00 • committed by GitHub
commit 6bdcfc2627
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
27 changed files with 6409 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

1
llama_stack/distributions/ci-tests/build.yaml
View file

@ -17,6 +17,7 @@ distribution_spec:
- provider_type: remote::vertexai
- provider_type: remote::groq
- provider_type: remote::sambanova
- provider_type: remote::azure
- provider_type: inline::sentence-transformers
vector_io:
- provider_type: inline::faiss

7
llama_stack/distributions/ci-tests/run.yaml
View file

@ -81,6 +81,13 @@ providers:
config:
url: https://api.sambanova.ai/v1
api_key: ${env.SAMBANOVA_API_KEY:=}
- provider_id: ${env.AZURE_API_KEY:+azure}
provider_type: remote::azure
config:
api_key: ${env.AZURE_API_KEY:=}
api_base: ${env.AZURE_API_BASE:=}
api_version: ${env.AZURE_API_VERSION:=}
api_type: ${env.AZURE_API_TYPE:=}
- provider_id: sentence-transformers
provider_type: inline::sentence-transformers
vector_io:

1
llama_stack/distributions/starter-gpu/build.yaml
View file

@ -18,6 +18,7 @@ distribution_spec:
- provider_type: remote::vertexai
- provider_type: remote::groq
- provider_type: remote::sambanova
- provider_type: remote::azure
- provider_type: inline::sentence-transformers
vector_io:
- provider_type: inline::faiss

7
llama_stack/distributions/starter-gpu/run.yaml
View file

@ -81,6 +81,13 @@ providers:
config:
url: https://api.sambanova.ai/v1
api_key: ${env.SAMBANOVA_API_KEY:=}
- provider_id: ${env.AZURE_API_KEY:+azure}
provider_type: remote::azure
config:
api_key: ${env.AZURE_API_KEY:=}
api_base: ${env.AZURE_API_BASE:=}
api_version: ${env.AZURE_API_VERSION:=}
api_type: ${env.AZURE_API_TYPE:=}
- provider_id: sentence-transformers
provider_type: inline::sentence-transformers
vector_io:

1
llama_stack/distributions/starter/build.yaml
View file

@ -18,6 +18,7 @@ distribution_spec:
- provider_type: remote::vertexai
- provider_type: remote::groq
- provider_type: remote::sambanova
- provider_type: remote::azure
- provider_type: inline::sentence-transformers
vector_io:
- provider_type: inline::faiss

7
llama_stack/distributions/starter/run.yaml
View file

@ -81,6 +81,13 @@ providers:
config:
url: https://api.sambanova.ai/v1
api_key: ${env.SAMBANOVA_API_KEY:=}
- provider_id: ${env.AZURE_API_KEY:+azure}
provider_type: remote::azure
config:
api_key: ${env.AZURE_API_KEY:=}
api_base: ${env.AZURE_API_BASE:=}
api_version: ${env.AZURE_API_VERSION:=}
api_type: ${env.AZURE_API_TYPE:=}
- provider_id: sentence-transformers
provider_type: inline::sentence-transformers
vector_io:

18
llama_stack/distributions/starter/starter.py
View file

@ -59,6 +59,7 @@ ENABLED_INFERENCE_PROVIDERS = [
"cerebras",
"nvidia",
"bedrock",
"azure",
]
INFERENCE_PROVIDER_IDS = {
@ -68,6 +69,7 @@ INFERENCE_PROVIDER_IDS = {
"cerebras": "${env.CEREBRAS_API_KEY:+cerebras}",
"nvidia": "${env.NVIDIA_API_KEY:+nvidia}",
"vertexai": "${env.VERTEX_AI_PROJECT:+vertexai}",
"azure": "${env.AZURE_API_KEY:+azure}",
}
@ -277,5 +279,21 @@ def get_distribution_template(name: str = "starter") -> DistributionTemplate:
"http://localhost:11434",
"Ollama URL",
),
"AZURE_API_KEY": (
"",
"Azure API Key",
),
"AZURE_API_BASE": (
"",
"Azure API Base",
),
"AZURE_API_VERSION": (
"",
"Azure API Version",
),
"AZURE_API_TYPE": (
"azure",
"Azure API Type",
),
},
)

15
llama_stack/providers/registry/inference.py
View file

@ -295,4 +295,19 @@ Available Models:
description="IBM WatsonX inference provider for accessing AI models on IBM's WatsonX platform.",
),
),
remote_provider_spec(
api=Api.inference,
adapter=AdapterSpec(
adapter_type="azure",
pip_packages=["litellm"],
module="llama_stack.providers.remote.inference.azure",
config_class="llama_stack.providers.remote.inference.azure.AzureConfig",
provider_data_validator="llama_stack.providers.remote.inference.azure.config.AzureProviderDataValidator",
description="""
Azure OpenAI inference provider for accessing GPT models and other Azure services.
Provider documentation
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/overview
""",
),
),
]

15
llama_stack/providers/remote/inference/azure/__init__.py Normal file
View file

@ -0,0 +1,15 @@
# 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 .config import AzureConfig
async def get_adapter_impl(config: AzureConfig, _deps):
from .azure import AzureInferenceAdapter
impl = AzureInferenceAdapter(config)
await impl.initialize()
return impl

64
llama_stack/providers/remote/inference/azure/azure.py Normal file
View file

@ -0,0 +1,64 @@
# 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 typing import Any
from urllib.parse import urljoin
from llama_stack.apis.inference import ChatCompletionRequest
from llama_stack.providers.utils.inference.litellm_openai_mixin import (
LiteLLMOpenAIMixin,
)
from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
from .config import AzureConfig
from .models import MODEL_ENTRIES
class AzureInferenceAdapter(OpenAIMixin, LiteLLMOpenAIMixin):
def __init__(self, config: AzureConfig) -> None:
LiteLLMOpenAIMixin.__init__(
self,
MODEL_ENTRIES,
litellm_provider_name="azure",
api_key_from_config=config.api_key.get_secret_value(),
provider_data_api_key_field="azure_api_key",
openai_compat_api_base=str(config.api_base),
)
self.config = config
# Delegate the client data handling get_api_key method to LiteLLMOpenAIMixin
get_api_key = LiteLLMOpenAIMixin.get_api_key
def get_base_url(self) -> str:
"""
Get the Azure API base URL.
Returns the Azure API base URL from the configuration.
"""
return urljoin(str(self.config.api_base), "/openai/v1")
async def _get_params(self, request: ChatCompletionRequest) -> dict[str, Any]:
# Get base parameters from parent
params = await super()._get_params(request)
# Add Azure specific parameters
provider_data = self.get_request_provider_data()
if provider_data:
if getattr(provider_data, "azure_api_key", None):
params["api_key"] = provider_data.azure_api_key
if getattr(provider_data, "azure_api_base", None):
params["api_base"] = provider_data.azure_api_base
if getattr(provider_data, "azure_api_version", None):
params["api_version"] = provider_data.azure_api_version
if getattr(provider_data, "azure_api_type", None):
params["api_type"] = provider_data.azure_api_type
else:
params["api_key"] = self.config.api_key.get_secret_value()
params["api_base"] = str(self.config.api_base)
params["api_version"] = self.config.api_version
params["api_type"] = self.config.api_type
return params

63
llama_stack/providers/remote/inference/azure/config.py Normal file
View file

@ -0,0 +1,63 @@
# 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.
import os
from typing import Any
from pydantic import BaseModel, Field, HttpUrl, SecretStr
from llama_stack.schema_utils import json_schema_type
class AzureProviderDataValidator(BaseModel):
azure_api_key: SecretStr = Field(
description="Azure API key for Azure",
)
azure_api_base: HttpUrl = Field(
description="Azure API base for Azure (e.g., https://your-resource-name.openai.azure.com)",
)
azure_api_version: str | None = Field(
default=None,
description="Azure API version for Azure (e.g., 2024-06-01)",
)
azure_api_type: str | None = Field(
default="azure",
description="Azure API type for Azure (e.g., azure)",
)
@json_schema_type
class AzureConfig(BaseModel):
api_key: SecretStr = Field(
description="Azure API key for Azure",
)
api_base: HttpUrl = Field(
description="Azure API base for Azure (e.g., https://your-resource-name.openai.azure.com)",
)
api_version: str | None = Field(
default_factory=lambda: os.getenv("AZURE_API_VERSION"),
description="Azure API version for Azure (e.g., 2024-12-01-preview)",
)
api_type: str | None = Field(
default_factory=lambda: os.getenv("AZURE_API_TYPE", "azure"),
description="Azure API type for Azure (e.g., azure)",
)
@classmethod
def sample_run_config(
cls,
api_key: str = "${env.AZURE_API_KEY:=}",
api_base: str = "${env.AZURE_API_BASE:=}",
api_version: str = "${env.AZURE_API_VERSION:=}",
api_type: str = "${env.AZURE_API_TYPE:=}",
**kwargs,
) -> dict[str, Any]:
return {
"api_key": api_key,
"api_base": api_base,
"api_version": api_version,
"api_type": api_type,
}

28
llama_stack/providers/remote/inference/azure/models.py Normal file
View file

@ -0,0 +1,28 @@
# 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 llama_stack.providers.utils.inference.model_registry import (
ProviderModelEntry,
)
# https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models?tabs=global-standard%2Cstandard-chat-completions
LLM_MODEL_IDS = [
"gpt-5",
"gpt-5-mini",
"gpt-5-nano",
"gpt-5-chat",
"o1",
"o1-mini",
"o3-mini",
"o4-mini",
"gpt-4.1",
"gpt-4.1-mini",
"gpt-4.1-nano",
]
SAFETY_MODELS_ENTRIES = list[ProviderModelEntry]()
MODEL_ENTRIES = [ProviderModelEntry(provider_model_id=m) for m in LLM_MODEL_IDS] + SAFETY_MODELS_ENTRIES

8
llama_stack/testing/inference_recorder.py
View file

@ -105,8 +105,12 @@ def _deserialize_response(data: dict[str, Any]) -> Any:
return cls.model_validate(data["__data__"])
except (ImportError, AttributeError, TypeError, ValueError) as e:
logger.warning(f"Failed to deserialize object of type {data['__type__']}: {e}")
return data["__data__"]
logger.warning(f"Failed to deserialize object of type {data['__type__']} with model_validate: {e}")
try:
return cls.model_construct(**data["__data__"])
except Exception as e:
logger.warning(f"Failed to deserialize object of type {data['__type__']} with model_construct: {e}")
return data["__data__"]
return data