phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: update the sambanova inference impl to use openai-python for openai-compat functions

Browse source
This commit is contained in:
Matthew Farrellee 2025-09-06 05:05:05 -04:00
parent 0c2757a05b
commit e03f1b61f3
2 changed files with 26 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/registry/inference.py
View file

@ -270,7 +270,7 @@ Available Models:
api=Api.inference,
adapter=AdapterSpec(
adapter_type="sambanova",
pip_packages=["litellm"],
pip_packages=["litellm", "openai"],
module="llama_stack.providers.remote.inference.sambanova",
config_class="llama_stack.providers.remote.inference.sambanova.SambaNovaImplConfig",
provider_data_validator="llama_stack.providers.remote.inference.sambanova.config.SambaNovaProviderDataValidator",

26
llama_stack/providers/remote/inference/sambanova/sambanova.py
View file

@ -4,13 +4,26 @@
# 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.litellm_openai_mixin import LiteLLMOpenAIMixin
from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
from .config import SambaNovaImplConfig
from .models import MODEL_ENTRIES
class SambaNovaInferenceAdapter(LiteLLMOpenAIMixin):
class SambaNovaInferenceAdapter(OpenAIMixin, LiteLLMOpenAIMixin):
"""
SambaNova Inference Adapter for Llama Stack.
Note: The inheritance order is important here. OpenAIMixin must come before
LiteLLMOpenAIMixin to ensure that OpenAIMixin.check_model_availability()
is used instead of LiteLLMOpenAIMixin.check_model_availability().
- OpenAIMixin.check_model_availability() queries the /v1/models to check if a model exists
- LiteLLMOpenAIMixin.check_model_availability() checks the static registry within LiteLLM
"""
def __init__(self, config: SambaNovaImplConfig):
self.config = config
self.environment_available_models = []
@ -24,3 +37,14 @@ class SambaNovaInferenceAdapter(LiteLLMOpenAIMixin):
download_images=True, # SambaNova requires base64 image encoding
json_schema_strict=False, # SambaNova doesn't support strict=True yet
)
# Delegate the client data handling get_api_key method to LiteLLMOpenAIMixin
get_api_key = LiteLLMOpenAIMixin.get_api_key
def get_base_url(self) -> str:
"""
Get the base URL for OpenAI mixin.
:return: The SambaNova base URL
"""
return self.config.url