mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-27 14:38:49 +00:00
1463b79218
This flips #2823 and #2805 by making the Stack periodically query the providers for models rather than the providers going behind the back and calling "register" on to the registry themselves. This also adds support for model listing for all other providers via `ModelRegistryHelper`. Once this is done, we do not need to manually list or register models via `run.yaml` and it will remove both noise and annoyance (setting `INFERENCE_MODEL` environment variables, for example) from the new user experience. In addition, it adds a configuration variable `allowed_models` which can be used to optionally restrict the set of models exposed from a provider.
25 lines
691 B
Python
25 lines
691 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 pydantic import BaseModel, Field
|
|
|
|
DEFAULT_OLLAMA_URL = "http://localhost:11434"
|
|
|
|
|
|
class OllamaImplConfig(BaseModel):
|
|
url: str = DEFAULT_OLLAMA_URL
|
|
refresh_models: bool = Field(
|
|
default=False,
|
|
description="Whether to refresh models periodically",
|
|
)
|
|
|
|
@classmethod
|
|
def sample_run_config(cls, url: str = "${env.OLLAMA_URL:=http://localhost:11434}", **kwargs) -> dict[str, Any]:
|
|
return {
|
|
"url": url,
|
|
}
|