Skip to content

fix: fix load from a database with subindices #581

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 1 commit into from
Oct 3, 2022
Merged

fix: fix load from a database with subindices #581

Show file tree
Hide file tree
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
11 changes: 9 additions & 2 deletions docarray/array/storage/base/backend.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,9 @@ def _init_storage(
):
self._load_offset2ids()

def _init_subindices(self, *args, **kwargs):
def _init_subindices(
self, _docs: Optional['DocumentArraySourceType'] = None, *args, **kwargs
):
self._subindices = {}
subindex_configs = kwargs.get('subindex_configs', None)
if subindex_configs:
Expand All @@ -39,7 +41,12 @@ def _init_subindices(self, *args, **kwargs):
config, config_subindex, config_joined, name
)
self._subindices[name] = self.__class__(config=config_joined)
self._subindices[name].extend(self.traverse_flat(name[1:]))
if _docs:
from docarray import DocumentArray

self._subindices[name].extend(
DocumentArray(_docs).traverse_flat(name[1:])
)

@abstractmethod
def _ensure_unique_config(
Expand Down
62 changes: 61 additions & 1 deletion tests/unit/array/test_backend_configuration.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,20 @@
import os
import random

import pytest
import requests

from docarray import DocumentArray, Document
from docarray import Document, DocumentArray, dataclass
from docarray.typing import Image, Text


@dataclass
class MyDocument:
image: Image
paragraph: Text


cur_dir = os.path.dirname(os.path.abspath(__file__))


def test_weaviate_hnsw(start_storage):
Expand Down Expand Up @@ -138,3 +151,50 @@ def test_cast_columns_qdrant(start_storage, type_da, type_column, request):
index.extend(docs)

assert len(index) == N


def test_random_subindices_config():
database_index = random.randint(0, 100)
database_name = "jina" + str(database_index) + ".db"
table_index = random.randint(0, 100)
table_name = "test" + str(table_index)
subindice_image_index = random.randint(0, 100)
subindice_image_name = "test" + str(subindice_image_index)
subindice_paragraph_index = random.randint(0, 100)
subindice_paragraph_name = "test" + str(subindice_paragraph_index)
sqlite3_config = {'connection': database_name, 'table_name': table_name}

common_subindex_config = {
'@.[image]': {'connection': database_name, 'table_name': subindice_image_name},
'@.[paragraph]': {
'connection': database_name,
'table_name': subindice_paragraph_name,
},
}
# extend with Documents, including embeddings
_docs = [
(
MyDocument(
image=os.path.join(cur_dir, '../document/toydata/test.png'),
paragraph='hello world',
)
)
]

da = DocumentArray(
storage='sqlite', # use SQLite as vector database
config=sqlite3_config,
subindex_configs=common_subindex_config, # set up subindices for image and description
)
da.summary()

for item in _docs:
d = Document(item)
da.append(d)

da = DocumentArray(
storage='sqlite', # use SQLite as vector database
config=sqlite3_config,
subindex_configs=common_subindex_config, # set up subindices for image and description
)
da.summary()