phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-08 19:10:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

inference registry updates

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-05 22:25:48 -07:00 • committed by Ashwin Bharambe
parent 4215cc9331
commit 59302a86df
12 changed files with 570 additions and 535 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/impls/meta_reference/memory/faiss.py
View file

@ -13,7 +13,6 @@ import numpy as np
from numpy.typing import NDArray
from llama_models.llama3.api.datatypes import * # noqa: F403
from llama_stack.distribution.datatypes import RoutableProvider
from llama_stack.apis.memory import * # noqa: F403
from llama_stack.providers.utils.memory.vector_store import (
@ -62,7 +61,7 @@ class FaissIndex(EmbeddingIndex):
return QueryDocumentsResponse(chunks=chunks, scores=scores)
class FaissMemoryImpl(Memory, RoutableProvider):
class FaissMemoryImpl(Memory):
def __init__(self, config: FaissImplConfig) -> None:
self.config = config
self.cache = {}
@ -83,7 +82,6 @@ class FaissMemoryImpl(Memory, RoutableProvider):
bank=memory_bank, index=FaissIndex(ALL_MINILM_L6_V2_DIMENSION)
)
self.cache[memory_bank.identifier] = index
return bank
async def get_memory_bank(self, identifier: str) -> Optional[MemoryBankDef]:
index = self.cache.get(identifier)