phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-27 14:38:49 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(starter)!: simplify starter distro; litellm model registry changes (#2916)

Browse source
This commit is contained in:
Ashwin Bharambe 2025-07-25 15:02:04 -07:00 • committed by GitHub
parent 3344d8a9e5
commit 9583f468f8
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
64 changed files with 2027 additions and 4092 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/remote/inference/gemini/config.py
View file

@ -26,7 +26,7 @@ class GeminiConfig(BaseModel):
)
@classmethod
def sample_run_config(cls, api_key: str = "${env.GEMINI_API_KEY}", **kwargs) -> dict[str, Any]:
def sample_run_config(cls, api_key: str = "${env.GEMINI_API_KEY:=}", **kwargs) -> dict[str, Any]:
return {
"api_key": api_key,
}

1
llama_stack/providers/remote/inference/gemini/gemini.py
View file

@ -15,6 +15,7 @@ class GeminiInferenceAdapter(LiteLLMOpenAIMixin):
LiteLLMOpenAIMixin.__init__(
self,
MODEL_ENTRIES,
litellm_provider_name="gemini",
api_key_from_config=config.api_key,
provider_data_api_key_field="gemini_api_key",
)

12
llama_stack/providers/remote/inference/gemini/models.py
View file

@ -10,11 +10,11 @@ from llama_stack.providers.utils.inference.model_registry import (
)
LLM_MODEL_IDS = [
"gemini/gemini-1.5-flash",
"gemini/gemini-1.5-pro",
"gemini/gemini-2.0-flash",
"gemini/gemini-2.5-flash",
"gemini/gemini-2.5-pro",
"gemini-1.5-flash",
"gemini-1.5-pro",
"gemini-2.0-flash",
"gemini-2.5-flash",
"gemini-2.5-pro",
]
SAFETY_MODELS_ENTRIES = []
@ -23,7 +23,7 @@ MODEL_ENTRIES = (
[ProviderModelEntry(provider_model_id=m) for m in LLM_MODEL_IDS]
+ [
ProviderModelEntry(
provider_model_id="gemini/text-embedding-004",
provider_model_id="text-embedding-004",
model_type=ModelType.embedding,
metadata={"embedding_dimension": 768, "context_length": 2048},
),