mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-08 21:04:39 +00:00
e892a3f7f4
# What does this PR do? inference adapters can now configure `refresh_models: bool` to control periodic model listing from their providers BREAKING CHANGE: together inference adapter default changed. previously always refreshed, now follows config. addresses "models: refresh" on #3517 ## Test Plan ci w/ new tests
21 lines
643 B
Python
21 lines
643 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 typing import Any
|
|
|
|
from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
|
|
|
|
DEFAULT_OLLAMA_URL = "http://localhost:11434"
|
|
|
|
|
|
class OllamaImplConfig(RemoteInferenceProviderConfig):
|
|
url: str = DEFAULT_OLLAMA_URL
|
|
|
|
@classmethod
|
|
def sample_run_config(cls, url: str = "${env.OLLAMA_URL:=http://localhost:11434}", **kwargs) -> dict[str, Any]:
|
|
return {
|
|
"url": url,
|
|
}
|