phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-27 06:28:50 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: Add Google Vertex AI inference provider support

Browse source 
- 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>
This commit is contained in:
Eran Cohen 2025-07-22 15:27:33 +03:00
parent c0563c0560
commit 1f421238b8
12 changed files with 311 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

34
llama_stack/templates/starter/run.yaml
View file

@ -85,6 +85,11 @@ providers:
provider_type: remote::gemini
config:
api_key: ${env.GEMINI_API_KEY}
- provider_id: ${env.ENABLE_VERTEXAI:=__disabled__}
provider_type: remote::vertexai
config:
project: ${env.VERTEX_AI_PROJECT}
location: ${env.VERTEX_AI_LOCATION:=us-central1}
- provider_id: ${env.ENABLE_GROQ:=__disabled__}
provider_type: remote::groq
config:
@ -963,6 +968,35 @@ models:
provider_id: ${env.ENABLE_GEMINI:=__disabled__}
provider_model_id: gemini/text-embedding-004
model_type: embedding
- metadata: {}
model_id: ${env.ENABLE_VERTEXAI:=__disabled__}/vertex_ai/gemini-2.0-flash
provider_id: ${env.ENABLE_VERTEXAI:=__disabled__}
provider_model_id: vertex_ai/gemini-2.0-flash
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_VERTEXAI:=__disabled__}/vertex_ai/gemini-2.5-flash
provider_id: ${env.ENABLE_VERTEXAI:=__disabled__}
provider_model_id: vertex_ai/gemini-2.5-flash
model_type: llm
- metadata: {}
model_id: ${env.ENABLE_VERTEXAI:=__disabled__}/vertex_ai/gemini-2.5-pro
provider_id: ${env.ENABLE_VERTEXAI:=__disabled__}
provider_model_id: vertex_ai/gemini-2.5-pro
model_type: llm
- metadata:
embedding_dimension: 768
context_length: 2048
model_id: ${env.ENABLE_VERTEXAI:=__disabled__}/vertex_ai/text-embedding-004
provider_id: ${env.ENABLE_VERTEXAI:=__disabled__}
provider_model_id: vertex_ai/text-embedding-004
model_type: embedding
- metadata:
embedding_dimension: 768
context_length: 2048
model_id: ${env.ENABLE_VERTEXAI:=__disabled__}/vertex_ai/text-embedding-005
provider_id: ${env.ENABLE_VERTEXAI:=__disabled__}
provider_model_id: vertex_ai/text-embedding-005
model_type: embedding
- metadata: {}
model_id: ${env.ENABLE_GROQ:=__disabled__}/groq/llama3-8b-8192
provider_id: ${env.ENABLE_GROQ:=__disabled__}