mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-22 20:50:00 +00:00
4c1f715171
- 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 - Add vertexai to INFERENCE_PROVIDER_IDS in starter distribution template - Update VertexAI provider to be conditionally included in starter template when VERTEX_AI_PROJECT env var is set - Added comprehensive documentation and sample configuration Signed-off-by: Eran Cohen <eranco@redhat.com>
20 lines
641 B
Python
20 lines
641 B
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 llama_stack.providers.utils.inference.model_registry import (
|
|
ProviderModelEntry,
|
|
)
|
|
|
|
# Vertex AI model IDs with vertex_ai/ prefix as required by litellm
|
|
LLM_MODEL_IDS = [
|
|
"vertex_ai/gemini-2.0-flash",
|
|
"vertex_ai/gemini-2.5-flash",
|
|
"vertex_ai/gemini-2.5-pro",
|
|
]
|
|
|
|
SAFETY_MODELS_ENTRIES = list[ProviderModelEntry]()
|
|
|
|
MODEL_ENTRIES = [ProviderModelEntry(provider_model_id=m) for m in LLM_MODEL_IDS] + SAFETY_MODELS_ENTRIES
|