mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-15 00:52:38 +00:00
6143b9b0c3
- RemoteInferenceProviderConfig now has auth_credential: SecretStr - the default alias is api_key (most common name) - some providers override to use api_token (RunPod, vLLM, Databricks) - some providers exclude it (Ollama, TGI, Vertex AI)
29 lines
869 B
Python
29 lines
869 B
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 urllib.parse import urljoin
|
|
|
|
from llama_stack.apis.inference import OpenAIEmbeddingsResponse
|
|
from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
|
|
|
|
from .config import CerebrasImplConfig
|
|
|
|
|
|
class CerebrasInferenceAdapter(OpenAIMixin):
|
|
config: CerebrasImplConfig
|
|
|
|
def get_base_url(self) -> str:
|
|
return urljoin(self.config.base_url, "v1")
|
|
|
|
async def openai_embeddings(
|
|
self,
|
|
model: str,
|
|
input: str | list[str],
|
|
encoding_format: str | None = "float",
|
|
dimensions: int | None = None,
|
|
user: str | None = None,
|
|
) -> OpenAIEmbeddingsResponse:
|
|
raise NotImplementedError()
|