mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-26 06:07:43 +00:00
1f421238b8
- Add new Vertex AI remote inference provider with litellm integration - Support for Gemini models through Google Cloud Vertex AI platform - Uses Google Cloud Application Default Credentials (ADC) for authentication - Added VertexAI models: gemini-2.5-flash, gemini-2.5-pro, gemini-2.0-flash. - Updated provider registry to include vertexai provider - Updated starter template to support Vertex AI configuration - Added comprehensive documentation and sample configuration Signed-off-by: Eran Cohen <eranco@redhat.com>
45 lines
1.2 KiB
Python
45 lines
1.2 KiB
Python
# 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 pydantic import BaseModel, Field
|
|
|
|
from llama_stack.schema_utils import json_schema_type
|
|
|
|
|
|
class VertexAIProviderDataValidator(BaseModel):
|
|
vertex_project: str | None = Field(
|
|
default=None,
|
|
description="Google Cloud project ID for Vertex AI",
|
|
)
|
|
vertex_location: str | None = Field(
|
|
default=None,
|
|
description="Google Cloud location for Vertex AI (e.g., us-central1)",
|
|
)
|
|
|
|
|
|
@json_schema_type
|
|
class VertexAIConfig(BaseModel):
|
|
project: str = Field(
|
|
description="Google Cloud project ID for Vertex AI",
|
|
)
|
|
location: str = Field(
|
|
default="us-central1",
|
|
description="Google Cloud location for Vertex AI",
|
|
)
|
|
|
|
@classmethod
|
|
def sample_run_config(
|
|
cls,
|
|
project: str = "${env.VERTEX_AI_PROJECT}",
|
|
location: str = "${env.VERTEX_AI_LOCATION:=us-central1}",
|
|
**kwargs,
|
|
) -> dict[str, Any]:
|
|
return {
|
|
"project": project,
|
|
"location": location,
|
|
}
|