mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-28 02:11:59 +00:00
4de45560bf
Implement remote ramalama provider using AsyncOpenAI as the client since ramalama doesn't have its own Async library. Ramalama is similar to ollama, as it is a lightweight local inference server. However, it runs by default in a containerized mode. RAMALAMA_URL is http://localhost:8080 by default Signed-off-by: Charlie Doern <cdoern@redhat.com>
19 lines
547 B
Python
19 lines
547 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, Dict
|
|
|
|
from pydantic import BaseModel
|
|
|
|
DEFAULT_RAMALAMA_URL = "http://localhost:8080"
|
|
|
|
|
|
class RamalamaImplConfig(BaseModel):
|
|
url: str = DEFAULT_RAMALAMA_URL
|
|
|
|
@classmethod
|
|
def sample_run_config(cls, url: str = "${env.RAMALAMA_URL:http://localhost:8080}", **kwargs) -> Dict[str, Any]:
|
|
return {"url": url}
|