mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-30 19:53:44 +00:00
# What does this PR do? * Changes the registry to store only one RoutableObject per identifier. Before it was a list, which is not really required. * Adds impl for updates and deletes * Updates routing table to handle updates correctly ## Test Plan ``` ❯ llama-stack-client models list +------------------------+---------------+------------------------------------+------------+ | identifier | provider_id | provider_resource_id | metadata | +========================+===============+====================================+============+ | Llama3.1-405B-Instruct | fireworks-0 | fireworks/llama-v3p1-405b-instruct | {} | +------------------------+---------------+------------------------------------+------------+ | Llama3.1-8B-Instruct | fireworks-0 | fireworks/llama-v3p1-8b-instruct | {} | +------------------------+---------------+------------------------------------+------------+ | Llama3.2-3B-Instruct | fireworks-0 | fireworks/llama-v3p2-1b-instruct | {} | +------------------------+---------------+------------------------------------+------------+ ❯ llama-stack-client models register dineshyv-model --provider-model-id=fireworks/llama-v3p1-70b-instruct Successfully registered model dineshyv-model ❯ llama-stack-client models list +------------------------+---------------+------------------------------------+------------+ | identifier | provider_id | provider_resource_id | metadata | +========================+===============+====================================+============+ | Llama3.1-405B-Instruct | fireworks-0 | fireworks/llama-v3p1-405b-instruct | {} | +------------------------+---------------+------------------------------------+------------+ | Llama3.1-8B-Instruct | fireworks-0 | fireworks/llama-v3p1-8b-instruct | {} | +------------------------+---------------+------------------------------------+------------+ | Llama3.2-3B-Instruct | fireworks-0 | fireworks/llama-v3p2-1b-instruct | {} | +------------------------+---------------+------------------------------------+------------+ | dineshyv-model | fireworks-0 | fireworks/llama-v3p1-70b-instruct | {} | +------------------------+---------------+------------------------------------+------------+ ❯ llama-stack-client models update dineshyv-model --provider-model-id=fireworks/llama-v3p1-405b-instruct Successfully updated model dineshyv-model ❯ llama-stack-client models list +------------------------+---------------+------------------------------------+------------+ | identifier | provider_id | provider_resource_id | metadata | +========================+===============+====================================+============+ | Llama3.1-405B-Instruct | fireworks-0 | fireworks/llama-v3p1-405b-instruct | {} | +------------------------+---------------+------------------------------------+------------+ | Llama3.1-8B-Instruct | fireworks-0 | fireworks/llama-v3p1-8b-instruct | {} | +------------------------+---------------+------------------------------------+------------+ | Llama3.2-3B-Instruct | fireworks-0 | fireworks/llama-v3p2-1b-instruct | {} | +------------------------+---------------+------------------------------------+------------+ | dineshyv-model | fireworks-0 | fireworks/llama-v3p1-405b-instruct | {} | +------------------------+---------------+------------------------------------+------------+ llama-stack-client models delete dineshyv-model ❯ llama-stack-client models list +------------------------+---------------+------------------------------------+------------+ | identifier | provider_id | provider_resource_id | metadata | +========================+===============+====================================+============+ | Llama3.1-405B-Instruct | fireworks-0 | fireworks/llama-v3p1-405b-instruct | {} | +------------------------+---------------+------------------------------------+------------+ | Llama3.1-8B-Instruct | fireworks-0 | fireworks/llama-v3p1-8b-instruct | {} | +------------------------+---------------+------------------------------------+------------+ | Llama3.2-3B-Instruct | fireworks-0 | fireworks/llama-v3p2-1b-instruct | {} | +------------------------+---------------+------------------------------------+------------+ ``` --------- Co-authored-by: Dinesh Yeduguru <dineshyv@fb.com>
113 lines
3.5 KiB
Python
113 lines
3.5 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.
|
|
|
|
import asyncio
|
|
import json
|
|
|
|
from typing import Any, Dict, List, Optional
|
|
|
|
import fire
|
|
import httpx
|
|
from termcolor import cprint
|
|
|
|
from .models import * # noqa: F403
|
|
|
|
|
|
class ModelsClient(Models):
|
|
def __init__(self, base_url: str):
|
|
self.base_url = base_url
|
|
|
|
async def initialize(self) -> None:
|
|
pass
|
|
|
|
async def shutdown(self) -> None:
|
|
pass
|
|
|
|
async def list_models(self) -> List[Model]:
|
|
async with httpx.AsyncClient() as client:
|
|
response = await client.get(
|
|
f"{self.base_url}/models/list",
|
|
headers={"Content-Type": "application/json"},
|
|
)
|
|
response.raise_for_status()
|
|
return [Model(**x) for x in response.json()]
|
|
|
|
async def register_model(self, model: Model) -> None:
|
|
async with httpx.AsyncClient() as client:
|
|
response = await client.post(
|
|
f"{self.base_url}/models/register",
|
|
json={
|
|
"model": json.loads(model.json()),
|
|
},
|
|
headers={"Content-Type": "application/json"},
|
|
)
|
|
response.raise_for_status()
|
|
|
|
async def get_model(self, identifier: str) -> Optional[Model]:
|
|
async with httpx.AsyncClient() as client:
|
|
response = await client.get(
|
|
f"{self.base_url}/models/get",
|
|
params={
|
|
"identifier": identifier,
|
|
},
|
|
headers={"Content-Type": "application/json"},
|
|
)
|
|
response.raise_for_status()
|
|
j = response.json()
|
|
if j is None:
|
|
return None
|
|
return Model(**j)
|
|
|
|
async def update_model(
|
|
self,
|
|
model_id: str,
|
|
provider_model_id: Optional[str] = None,
|
|
provider_id: Optional[str] = None,
|
|
metadata: Optional[Dict[str, Any]] = None,
|
|
) -> Model:
|
|
async with httpx.AsyncClient() as client:
|
|
response = await client.put(
|
|
f"{self.base_url}/models/update",
|
|
json={
|
|
"model_id": model_id,
|
|
"provider_model_id": provider_model_id,
|
|
"provider_id": provider_id,
|
|
"metadata": metadata,
|
|
},
|
|
headers={"Content-Type": "application/json"},
|
|
)
|
|
response.raise_for_status()
|
|
return Model(**response.json())
|
|
|
|
async def delete_model(self, model_id: str) -> None:
|
|
async with httpx.AsyncClient() as client:
|
|
response = await client.delete(
|
|
f"{self.base_url}/models/delete",
|
|
params={"model_id": model_id},
|
|
headers={"Content-Type": "application/json"},
|
|
)
|
|
response.raise_for_status()
|
|
|
|
|
|
async def run_main(host: str, port: int, stream: bool):
|
|
client = ModelsClient(f"http://{host}:{port}")
|
|
|
|
response = await client.list_models()
|
|
cprint(f"list_models response={response}", "green")
|
|
|
|
response = await client.get_model("Llama3.1-8B-Instruct")
|
|
cprint(f"get_model response={response}", "blue")
|
|
|
|
response = await client.get_model("Llama-Guard-3-1B")
|
|
cprint(f"get_model response={response}", "red")
|
|
|
|
|
|
def main(host: str, port: int, stream: bool = True):
|
|
asyncio.run(run_main(host, port, stream))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
fire.Fire(main)
|