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

Merge 1f421238b8 into 3216765c26

Browse source
This commit is contained in:
Eran Cohen 2025-07-25 04:24:59 +03:00 • committed by GitHub
commit e407f310f3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
12 changed files with 311 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
llama_stack/templates/ci-tests/build.yaml
View file

@ -18,6 +18,7 @@ distribution_spec:
- remote::openai
- remote::anthropic
- remote::gemini
- remote::vertexai
- remote::groq
- remote::llama-openai-compat
- remote::sambanova

34
llama_stack/templates/ci-tests/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:
@ -937,6 +942,35 @@ 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__}

1
llama_stack/templates/starter/build.yaml
View file

@ -18,6 +18,7 @@ distribution_spec:
- remote::openai
- remote::anthropic
- remote::gemini
- remote::vertexai
- remote::groq
- remote::llama-openai-compat
- remote::sambanova

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:
@ -937,6 +942,35 @@ 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__}

12
llama_stack/templates/starter/starter.py
View file

@ -64,6 +64,9 @@ from llama_stack.providers.remote.inference.sambanova.models import (
from llama_stack.providers.remote.inference.together.models import (
MODEL_ENTRIES as TOGETHER_MODEL_ENTRIES,
)
from llama_stack.providers.remote.inference.vertexai.models import (
MODEL_ENTRIES as VERTEXAI_MODEL_ENTRIES,
)
from llama_stack.providers.remote.vector_io.chroma.config import ChromaVectorIOConfig
from llama_stack.providers.remote.vector_io.pgvector.config import (
PGVectorVectorIOConfig,
@ -93,6 +96,7 @@ def _get_model_entries_for_provider(provider_type: str) -> list[ProviderModelEnt
"databricks": DATABRICKS_MODEL_ENTRIES,
"nvidia": NVIDIA_MODEL_ENTRIES,
"runpod": RUNPOD_MODEL_ENTRIES,
"vertexai": VERTEXAI_MODEL_ENTRIES,
}
# Special handling for providers with dynamic model entries
@ -357,6 +361,14 @@ def get_distribution_template() -> DistributionTemplate:
"",
"Gemini API Key",
),
"VERTEX_AI_PROJECT": (
"",
"Google Cloud Project ID for Vertex AI",
),
"VERTEX_AI_LOCATION": (
"us-central1",
"Google Cloud Location for Vertex AI",
),
"SAMBANOVA_API_KEY": (
"",
"SambaNova API Key",