mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-08 04:54:38 +00:00
724dac498c
# What does this PR do? close the _model_cache abstraction leak ## Test Plan ci w/ new tests
83 lines
2.6 KiB
Python
83 lines
2.6 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 collections.abc import Iterable
|
|
from typing import Any
|
|
|
|
from databricks.sdk import WorkspaceClient
|
|
|
|
from llama_stack.apis.inference import (
|
|
Inference,
|
|
OpenAICompletion,
|
|
)
|
|
from llama_stack.log import get_logger
|
|
from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
|
|
|
|
from .config import DatabricksImplConfig
|
|
|
|
logger = get_logger(name=__name__, category="inference::databricks")
|
|
|
|
|
|
class DatabricksInferenceAdapter(
|
|
OpenAIMixin,
|
|
Inference,
|
|
):
|
|
# source: https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models
|
|
embedding_model_metadata = {
|
|
"databricks-gte-large-en": {"embedding_dimension": 1024, "context_length": 8192},
|
|
"databricks-bge-large-en": {"embedding_dimension": 1024, "context_length": 512},
|
|
}
|
|
|
|
def __init__(self, config: DatabricksImplConfig) -> None:
|
|
self.config = config
|
|
|
|
def get_api_key(self) -> str:
|
|
return self.config.api_token.get_secret_value()
|
|
|
|
def get_base_url(self) -> str:
|
|
return f"{self.config.url}/serving-endpoints"
|
|
|
|
async def initialize(self) -> None:
|
|
return
|
|
|
|
async def shutdown(self) -> None:
|
|
pass
|
|
|
|
async def openai_completion(
|
|
self,
|
|
model: str,
|
|
prompt: str | list[str] | list[int] | list[list[int]],
|
|
best_of: int | None = None,
|
|
echo: bool | None = None,
|
|
frequency_penalty: float | None = None,
|
|
logit_bias: dict[str, float] | None = None,
|
|
logprobs: bool | None = None,
|
|
max_tokens: int | None = None,
|
|
n: int | None = None,
|
|
presence_penalty: float | None = None,
|
|
seed: int | None = None,
|
|
stop: str | list[str] | None = None,
|
|
stream: bool | None = None,
|
|
stream_options: dict[str, Any] | None = None,
|
|
temperature: float | None = None,
|
|
top_p: float | None = None,
|
|
user: str | None = None,
|
|
guided_choice: list[str] | None = None,
|
|
prompt_logprobs: int | None = None,
|
|
suffix: str | None = None,
|
|
) -> OpenAICompletion:
|
|
raise NotImplementedError()
|
|
|
|
async def list_provider_model_ids(self) -> Iterable[str]:
|
|
return [
|
|
endpoint.name
|
|
for endpoint in WorkspaceClient(
|
|
host=self.config.url, token=self.get_api_key()
|
|
).serving_endpoints.list() # TODO: this is not async
|
|
]
|
|
|
|
async def should_refresh_models(self) -> bool:
|
|
return False
|