Skip to content

feat: check if filepath exists for inmemory index #1537

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

Merged
JoanFM merged 2 commits into from
May 15, 2023
Merged

feat: check if filepath exists for inmemory index #1537

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d466474
feat: check filepath inmemory index
jupyterjazz May 15, 2023
b2284d6
refactor: if sttmnt
jupyterjazz May 15, 2023
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
34 changes: 26 additions & 8 deletions docarray/index/backends/in_memory.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
import os
from collections import defaultdict
from dataclasses import dataclass, field
from typing import (
Expand Down Expand Up @@ -57,15 +58,32 @@ def __init__(
)

if index_file_path:
self._docs = DocList.__class_getitem__(
cast(Type[BaseDoc], self._schema)
).load_binary(file=index_file_path)
if os.path.exists(index_file_path):
self._logger.info(
f'Loading index from a binary file: {index_file_path}'
)
self._docs = DocList.__class_getitem__(
cast(Type[BaseDoc], self._schema)
).load_binary(file=index_file_path)
else:
self._logger.warning(
f'Index file does not exist: {index_file_path}. '
f'Initializing empty InMemoryExactNNIndex.'
)
self._docs = DocList.__class_getitem__(
cast(Type[BaseDoc], self._schema)
)()
else:
self._docs = (
docs
if docs is not None
else DocList.__class_getitem__(cast(Type[BaseDoc], self._schema))()
)
if docs:
self._logger.info('Docs provided. Initializing with provided docs.')
self._docs = docs
else:
self._logger.info(
'No docs or index file provided. Initializing empty InMemoryExactNNIndex.'
)
self._docs = DocList.__class_getitem__(
cast(Type[BaseDoc], self._schema)
)()

def python_type_to_db_type(self, python_type: Type) -> Any:
"""Map python type to database type.
Expand Down
6 changes: 6 additions & 0 deletions tests/index/in_memory/test_in_memory.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -135,3 +135,9 @@ def test_save_and_load(doc_index, tmpdir):
assert len(docs) == 5
assert len(scores) == 5
assert new_doc_index.num_docs() == initial_num_docs

newer_doc_index = InMemoryExactNNIndex[SchemaDoc](
index_file_path='some_nonexistent_file.bin'
)

assert newer_doc_index.num_docs() == 0