Skip to content

perf: use deque for iterator object cache #1968

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
giulio-leone wants to merge 1 commit into
base: main
Choose a base branch
from
Open

perf: use deque for iterator object cache #1968

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 9 additions & 8 deletions weaviate/collections/iterator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
from collections import deque
from dataclasses import dataclass
from typing import (
Any,
Expand Down Expand Up @@ -54,14 +55,14 @@ def __init__(
self.__query = query
self.__inputs = inputs

self.__iter_object_cache: List[Object[TProperties, TReferences]] = []
self.__iter_object_cache: deque[Object[TProperties, TReferences]] = deque()
self.__iter_object_last_uuid: Optional[UUID] = _parse_after(self.__inputs.after)
self.__iter_cache_size = cache_size or ITERATOR_CACHE_SIZE

def __iter__(
self,
) -> Iterator[Object[TProperties, TReferences]]:
self.__iter_object_cache = []
self.__iter_object_cache = deque()
self.__iter_object_last_uuid = _parse_after(self.__inputs.after)
return self

Expand All @@ -75,11 +76,11 @@ def __next__(self) -> Object[TProperties, TReferences]:
return_properties=self.__inputs.return_properties,
return_references=self.__inputs.return_references,
)
self.__iter_object_cache = res.objects # type: ignore
self.__iter_object_cache = deque(res.objects) # type: ignore
if len(self.__iter_object_cache) == 0:
raise StopIteration

ret_object = self.__iter_object_cache.pop(0)
ret_object = self.__iter_object_cache.popleft()
self.__iter_object_last_uuid = ret_object.uuid
assert (
self.__iter_object_last_uuid is not None
Expand All @@ -100,14 +101,14 @@ def __init__(
self.__query = query
self.__inputs = inputs

self.__iter_object_cache: List[Object[TProperties, TReferences]] = []
self.__iter_object_cache: deque[Object[TProperties, TReferences]] = deque()
self.__iter_object_last_uuid: Optional[UUID] = _parse_after(self.__inputs.after)
self.__iter_cache_size = cache_size or ITERATOR_CACHE_SIZE

def __aiter__(
self,
) -> AsyncIterator[Object[TProperties, TReferences]]:
self.__iter_object_cache = []
self.__iter_object_cache = deque()
self.__iter_object_last_uuid = _parse_after(self.__inputs.after)
return self

Expand All @@ -123,11 +124,11 @@ async def __anext__(
return_properties=self.__inputs.return_properties,
return_references=self.__inputs.return_references,
)
self.__iter_object_cache = res.objects # type: ignore
self.__iter_object_cache = deque(res.objects) # type: ignore
if len(self.__iter_object_cache) == 0:
raise StopAsyncIteration

ret_object = self.__iter_object_cache.pop(0)
ret_object = self.__iter_object_cache.popleft()
self.__iter_object_last_uuid = ret_object.uuid
assert (
self.__iter_object_last_uuid is not None
Expand Down