mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 12:07:34 +00:00
b67aef2fc4
# What does this PR do? - remove auto-download of ollama embedding models - add embedding model metadata to dynamic listing w/ unit test - add support and tests for allowed_models - removed inference provider models.py files where dynamic listing is enabled - store embedding metadata in embedding_model_metadata field on inference providers - make model_entries optional on ModelRegistryHelper and LiteLLMOpenAIMixin - make OpenAIMixin a ModelRegistryHelper - skip base64 embedding test for remote::ollama, always returns floats - only use OpenAI client for ollama model listing - remove unused build_model_entry function - remove unused get_huggingface_repo function ## Test Plan ci w/ new tests
36 lines
1.2 KiB
Python
36 lines
1.2 KiB
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.litellm_openai_mixin import LiteLLMOpenAIMixin
|
|
from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
|
|
|
|
from .config import GeminiConfig
|
|
|
|
|
|
class GeminiInferenceAdapter(OpenAIMixin, LiteLLMOpenAIMixin):
|
|
embedding_model_metadata = {
|
|
"text-embedding-004": {"embedding_dimension": 768, "context_length": 2048},
|
|
}
|
|
|
|
def __init__(self, config: GeminiConfig) -> None:
|
|
LiteLLMOpenAIMixin.__init__(
|
|
self,
|
|
litellm_provider_name="gemini",
|
|
api_key_from_config=config.api_key,
|
|
provider_data_api_key_field="gemini_api_key",
|
|
)
|
|
self.config = config
|
|
|
|
get_api_key = LiteLLMOpenAIMixin.get_api_key
|
|
|
|
def get_base_url(self):
|
|
return "https://generativelanguage.googleapis.com/v1beta/openai/"
|
|
|
|
async def initialize(self) -> None:
|
|
await super().initialize()
|
|
|
|
async def shutdown(self) -> None:
|
|
await super().shutdown()
|