mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 10:54:19 +00:00
9487ad8294
* 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>
91 lines
2.9 KiB
Python
91 lines
2.9 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.
|
|
|
|
from typing import Any, Dict, List, Tuple
|
|
|
|
from llama_stack.distribution.datatypes import Api
|
|
from llama_stack.apis.memory import * # noqa: F403
|
|
|
|
|
|
class MemoryRouterImpl(Memory):
|
|
"""Routes to an provider based on the memory bank type"""
|
|
|
|
def __init__(
|
|
self,
|
|
inner_impls: List[Tuple[str, Any]],
|
|
deps: List[Api],
|
|
) -> None:
|
|
self.deps = deps
|
|
|
|
bank_types = [v.value for v in MemoryBankType]
|
|
|
|
self.providers = {}
|
|
for routing_key, provider_impl in inner_impls:
|
|
if routing_key not in bank_types:
|
|
raise ValueError(
|
|
f"Unknown routing key `{routing_key}` for memory bank type"
|
|
)
|
|
self.providers[routing_key] = provider_impl
|
|
|
|
self.bank_id_to_type = {}
|
|
|
|
async def initialize(self) -> None:
|
|
pass
|
|
|
|
async def shutdown(self) -> None:
|
|
for p in self.providers.values():
|
|
await p.shutdown()
|
|
|
|
def get_provider(self, bank_type):
|
|
if bank_type not in self.providers:
|
|
raise ValueError(f"Memory bank type {bank_type} not supported")
|
|
|
|
return self.providers[bank_type]
|
|
|
|
async def create_memory_bank(
|
|
self,
|
|
name: str,
|
|
config: MemoryBankConfig,
|
|
url: Optional[URL] = None,
|
|
) -> MemoryBank:
|
|
provider = self.get_provider(config.type)
|
|
bank = await provider.create_memory_bank(name, config, url)
|
|
self.bank_id_to_type[bank.bank_id] = config.type
|
|
return bank
|
|
|
|
async def get_memory_bank(self, bank_id: str) -> Optional[MemoryBank]:
|
|
bank_type = self.bank_id_to_type.get(bank_id)
|
|
if not bank_type:
|
|
raise ValueError(f"Could not find bank type for {bank_id}")
|
|
|
|
provider = self.get_provider(bank_type)
|
|
return await provider.get_memory_bank(bank_id)
|
|
|
|
async def insert_documents(
|
|
self,
|
|
bank_id: str,
|
|
documents: List[MemoryBankDocument],
|
|
ttl_seconds: Optional[int] = None,
|
|
) -> None:
|
|
bank_type = self.bank_id_to_type.get(bank_id)
|
|
if not bank_type:
|
|
raise ValueError(f"Could not find bank type for {bank_id}")
|
|
|
|
provider = self.get_provider(bank_type)
|
|
return await provider.insert_documents(bank_id, documents, ttl_seconds)
|
|
|
|
async def query_documents(
|
|
self,
|
|
bank_id: str,
|
|
query: InterleavedTextMedia,
|
|
params: Optional[Dict[str, Any]] = None,
|
|
) -> QueryDocumentsResponse:
|
|
bank_type = self.bank_id_to_type.get(bank_id)
|
|
if not bank_type:
|
|
raise ValueError(f"Could not find bank type for {bank_id}")
|
|
|
|
provider = self.get_provider(bank_type)
|
|
return await provider.query_documents(bank_id, query, params)
|