mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
* API Keys passed from Client instead of distro configuration * delete distribution registry * Rename the "package" word away * Introduce a "Router" layer for providers Some providers need to be factorized and considered as thin routing layers on top of other providers. Consider two examples: - The inference API should be a routing layer over inference providers, routed using the "model" key - The memory banks API is another instance where various memory bank types will be provided by independent providers (e.g., a vector store is served by Chroma while a keyvalue memory can be served by Redis or PGVector) This commit introduces a generalized routing layer for this purpose. * update `apis_to_serve` * llama_toolchain -> llama_stack * Codemod from llama_toolchain -> llama_stack - added providers/registry - cleaned up api/ subdirectories and moved impls away - restructured api/api.py - from llama_stack.apis.<api> import foo should work now - update imports to do llama_stack.apis.<api> - update many other imports - added __init__, fixed some registry imports - updated registry imports - create_agentic_system -> create_agent - AgenticSystem -> Agent * Moved some stuff out of common/; re-generated OpenAPI spec * llama-toolchain -> llama-stack (hyphens) * add control plane API * add redis adapter + sqlite provider * move core -> distribution * Some more toolchain -> stack changes * small naming shenanigans * Removing custom tool and agent utilities and moving them client side * Move control plane to distribution server for now * Remove control plane from API list * no codeshield dependency randomly plzzzzz * Add "fire" as a dependency * add back event loggers * stack configure fixes * use brave instead of bing in the example client * add init file so it gets packaged * add init files so it gets packaged * Update MANIFEST * bug fix --------- Co-authored-by: Hardik Shah <hjshah@fb.com> Co-authored-by: Xi Yan <xiyan@meta.com> Co-authored-by: Ashwin Bharambe <ashwin@meta.com>
62 lines
2 KiB
Python
62 lines
2 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.
|
|
|
|
from datetime import datetime, timedelta
|
|
from typing import Any, List, Optional
|
|
|
|
from redis.asyncio import Redis
|
|
|
|
from llama_stack.apis.control_plane import * # noqa: F403
|
|
|
|
|
|
from .config import RedisImplConfig
|
|
|
|
|
|
class RedisControlPlaneAdapter(ControlPlane):
|
|
def __init__(self, config: RedisImplConfig):
|
|
self.config = config
|
|
|
|
async def initialize(self) -> None:
|
|
self.redis = Redis.from_url(self.config.url)
|
|
|
|
def _namespaced_key(self, key: str) -> str:
|
|
if not self.config.namespace:
|
|
return key
|
|
return f"{self.config.namespace}:{key}"
|
|
|
|
async def set(
|
|
self, key: str, value: Any, expiration: Optional[datetime] = None
|
|
) -> None:
|
|
key = self._namespaced_key(key)
|
|
await self.redis.set(key, value)
|
|
if expiration:
|
|
await self.redis.expireat(key, expiration)
|
|
|
|
async def get(self, key: str) -> Optional[ControlPlaneValue]:
|
|
key = self._namespaced_key(key)
|
|
value = await self.redis.get(key)
|
|
if value is None:
|
|
return None
|
|
ttl = await self.redis.ttl(key)
|
|
expiration = datetime.now() + timedelta(seconds=ttl) if ttl > 0 else None
|
|
return ControlPlaneValue(key=key, value=value, expiration=expiration)
|
|
|
|
async def delete(self, key: str) -> None:
|
|
key = self._namespaced_key(key)
|
|
await self.redis.delete(key)
|
|
|
|
async def range(self, start_key: str, end_key: str) -> List[ControlPlaneValue]:
|
|
start_key = self._namespaced_key(start_key)
|
|
end_key = self._namespaced_key(end_key)
|
|
|
|
keys = await self.redis.keys(f"{start_key}*")
|
|
result = []
|
|
for key in keys:
|
|
if key <= end_key:
|
|
value = await self.get(key)
|
|
if value:
|
|
result.append(value)
|
|
return result
|