mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 12:07:34 +00:00
e1966b90d9
- introduce a slightly more general notion of an AutoRouted provider - the AutoRouted provider is associated with a RoutingTable provider - e.g. inference -> models - Introduced safety -> shields and memory -> memory_banks correspondences
67 lines
1.9 KiB
Python
67 lines
1.9 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
|
|
|
|
from typing import List, Optional
|
|
|
|
import fire
|
|
import httpx
|
|
from termcolor import cprint
|
|
|
|
from .memory_banks import * # noqa: F403
|
|
|
|
|
|
class MemoryBanksClient(MemoryBanks):
|
|
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_memory_banks(self) -> List[MemoryBankSpec]:
|
|
async with httpx.AsyncClient() as client:
|
|
response = await client.get(
|
|
f"{self.base_url}/memory_banks/list",
|
|
headers={"Content-Type": "application/json"},
|
|
)
|
|
response.raise_for_status()
|
|
return [MemoryBankSpec(**x) for x in response.json()]
|
|
|
|
async def get_memory_bank(
|
|
self, bank_type: MemoryBankType
|
|
) -> Optional[MemoryBankSpec]:
|
|
async with httpx.AsyncClient() as client:
|
|
response = await client.get(
|
|
f"{self.base_url}/memory_banks/get",
|
|
json={
|
|
"bank_type": bank_type,
|
|
},
|
|
headers={"Content-Type": "application/json"},
|
|
)
|
|
response.raise_for_status()
|
|
j = response.json()
|
|
if j is None:
|
|
return None
|
|
return MemoryBankSpec(**j)
|
|
|
|
|
|
async def run_main(host: str, port: int, stream: bool):
|
|
client = MemoryBanksClient(f"http://{host}:{port}")
|
|
|
|
response = await client.list_memory_banks()
|
|
cprint(f"list_memory_banks response={response}", "green")
|
|
|
|
|
|
def main(host: str, port: int, stream: bool = True):
|
|
asyncio.run(run_main(host, port, stream))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
fire.Fire(main)
|