phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 04:04:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: turn OpenAIMixin into a pydantic.BaseModel

Browse source 
- implement get_api_key instead of relying on LiteLLMOpenAIMixin.get_api_key
 - remove use of LiteLLMOpenAIMixin
 - add default initialize/shutdown methods to OpenAIMixin
 - remove __init__s to allow proper pydantic construction
 - remove dead code from vllm adapter and associated / duplicate unit tests
 - update vllm adapter to use openaimixin for model registration
 - remove ModelRegistryHelper from fireworks & together adapters
 - remove Inference from nvidia adapter
 - complete type hints on embedding_model_metadata
 - allow extra fields on OpenAIMixin, for model_store, __provider_id__, etc
 - new recordings for ollama
This commit is contained in:
Matthew Farrellee 2025-10-02 20:47:54 -04:00
parent ce77c27ff8
commit 60f0056cbc
57 changed files with 12520 additions and 1254 deletions
Download patch file Download diff file Expand all files Collapse all files

50
llama_stack/providers/remote/inference/vertexai/vertexai.py
View file

@ -4,29 +4,19 @@
# 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
import google.auth.transport.requests
from google.auth import default
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 VertexAIConfig
class VertexAIInferenceAdapter(OpenAIMixin, LiteLLMOpenAIMixin):
def __init__(self, config: VertexAIConfig) -> None:
LiteLLMOpenAIMixin.__init__(
self,
litellm_provider_name="vertex_ai",
api_key_from_config=None, # Vertex AI uses ADC, not API keys
provider_data_api_key_field="vertex_project", # Use project for validation
)
self.config = config
class VertexAIInferenceAdapter(OpenAIMixin):
config: VertexAIConfig
provider_data_api_key_field: str = "vertex_project"
def get_api_key(self) -> str:
"""
@ -54,22 +44,22 @@ class VertexAIInferenceAdapter(OpenAIMixin, LiteLLMOpenAIMixin):
"""
return f"https://{self.config.location}-aiplatform.googleapis.com/v1/projects/{self.config.project}/locations/{self.config.location}/endpoints/openapi"
async def _get_params(self, request: ChatCompletionRequest) -> dict[str, Any]:
# Get base parameters from parent
params = await super()._get_params(request)
# async def _get_params(self, request: ChatCompletionRequest) -> dict[str, Any]:
# # Get base parameters from parent
# params = await super()._get_params(request)
# Add Vertex AI specific parameters
provider_data = self.get_request_provider_data()
if provider_data:
if getattr(provider_data, "vertex_project", None):
params["vertex_project"] = provider_data.vertex_project
if getattr(provider_data, "vertex_location", None):
params["vertex_location"] = provider_data.vertex_location
else:
params["vertex_project"] = self.config.project
params["vertex_location"] = self.config.location
# # Add Vertex AI specific parameters
# provider_data = self.get_request_provider_data()
# if provider_data:
# if getattr(provider_data, "vertex_project", None):
# params["vertex_project"] = provider_data.vertex_project
# if getattr(provider_data, "vertex_location", None):
# params["vertex_location"] = provider_data.vertex_location
# else:
# params["vertex_project"] = self.config.project
# params["vertex_location"] = self.config.location
# Remove api_key since Vertex AI uses ADC
params.pop("api_key", None)
# # Remove api_key since Vertex AI uses ADC
# params.pop("api_key", None)
return params
# return params