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: update the vertexai inference impl to use openai-python for openai-compat functions (#3377)

Browse source 
# What does this PR do?

update VertexAI inference provider to use openai-python for
openai-compat functions

## Test Plan

```
$ VERTEX_AI_PROJECT=... uv run llama stack build --image-type venv --providers inference=remote::vertexai --run
...
$ LLAMA_STACK_CONFIG=http://localhost:8321 uv run --group test pytest -v -ra --text-model vertexai/vertex_ai/gemini-2.5-flash tests/integration/inference/test_openai_completion.py
...
```

i don't have an account to test this. `get_api_key` may also need to be
updated per
https://cloud.google.com/vertex-ai/generative-ai/docs/start/openai

---------

Signed-off-by: Sébastien Han <seb@redhat.com>
Co-authored-by: Sébastien Han <seb@redhat.com>
This commit is contained in:
Matthew Farrellee 2025-09-10 09:39:29 -04:00 • committed by GitHub
parent c836fa29e3
commit 0e27016cf2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 33 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

33
llama_stack/providers/remote/inference/vertexai/vertexai.py
View file

@ -6,16 +6,20 @@
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
from .models import MODEL_ENTRIES
class VertexAIInferenceAdapter(LiteLLMOpenAIMixin):
class VertexAIInferenceAdapter(OpenAIMixin, LiteLLMOpenAIMixin):
def __init__(self, config: VertexAIConfig) -> None:
LiteLLMOpenAIMixin.__init__(
self,
@ -27,9 +31,30 @@ class VertexAIInferenceAdapter(LiteLLMOpenAIMixin):
self.config = config
def get_api_key(self) -> str:
# Vertex AI doesn't use API keys, it uses Application Default Credentials
# Return empty string to let litellm handle authentication via ADC
return ""
"""
Get an access token for Vertex AI using Application Default Credentials.
Vertex AI uses ADC instead of API keys. This method obtains an access token
from the default credentials and returns it for use with the OpenAI-compatible client.
"""
try:
# 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 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 ""
def get_base_url(self) -> str:
"""
Get the Vertex AI OpenAI-compatible API base URL.
Returns the Vertex AI OpenAI-compatible endpoint URL.
Source: https://cloud.google.com/vertex-ai/generative-ai/docs/start/openai
"""
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