weaviate-haystack 7.3.0__tar.gz → 7.4.0__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/CHANGELOG.md +7 -0
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/PKG-INFO +1 -1
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/src/haystack_integrations/document_stores/weaviate/document_store.py +0 -9
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/tests/test_document_store.py +20 -17
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/.gitignore +0 -0
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/LICENSE.txt +0 -0
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/README.md +0 -0
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/docker-compose.yml +0 -0
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/pydoc/config_docusaurus.yml +0 -0
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/pyproject.toml +0 -0
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/src/haystack_integrations/components/retrievers/py.typed +0 -0
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/src/haystack_integrations/components/retrievers/weaviate/__init__.py +0 -0
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/src/haystack_integrations/components/retrievers/weaviate/bm25_retriever.py +0 -0
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/src/haystack_integrations/components/retrievers/weaviate/embedding_retriever.py +0 -0
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/src/haystack_integrations/components/retrievers/weaviate/hybrid_retriever.py +0 -0
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/src/haystack_integrations/document_stores/py.typed +0 -0
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/src/haystack_integrations/document_stores/weaviate/__init__.py +0 -0
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/src/haystack_integrations/document_stores/weaviate/_filters.py +0 -0
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/src/haystack_integrations/document_stores/weaviate/auth.py +0 -0
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/tests/__init__.py +0 -0
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/tests/conftest.py +0 -0
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/tests/test_auth.py +0 -0
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/tests/test_bm25_retriever.py +0 -0
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/tests/test_bm25_retriever_async.py +0 -0
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/tests/test_document_store_async.py +0 -0
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/tests/test_embedding_retriever.py +0 -0
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/tests/test_embedding_retriever_async.py +0 -0
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/tests/test_files/robot1.jpg +0 -0
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/tests/test_filters.py +0 -0
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/tests/test_hybrid_retriever.py +0 -0
- {weaviate_haystack-7.3.0 → weaviate_haystack-7.4.0}/tests/test_hybrid_retriever_async.py +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: weaviate-haystack
|
|
3
|
-
Version: 7.
|
|
3
|
+
Version: 7.4.0
|
|
4
4
|
Summary: An integration of Weaviate vector database with Haystack
|
|
5
5
|
Project-URL: Source, https://github.com/deepset-ai/haystack-core-integrations
|
|
6
6
|
Project-URL: Documentation, https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/weaviate/README.md
|
|
@@ -745,15 +745,6 @@ class WeaviateDocumentStore:
|
|
|
745
745
|
# The embedding vector is stored separately from the rest of the data
|
|
746
746
|
del data["embedding"]
|
|
747
747
|
|
|
748
|
-
# _split_overlap meta field is unsupported because of a bug
|
|
749
|
-
# https://github.com/deepset-ai/haystack-core-integrations/issues/1172
|
|
750
|
-
if "_split_overlap" in data:
|
|
751
|
-
data.pop("_split_overlap")
|
|
752
|
-
logger.warning(
|
|
753
|
-
"Document {id} has the unsupported `_split_overlap` meta field. It will be ignored.",
|
|
754
|
-
id=data["_original_id"],
|
|
755
|
-
)
|
|
756
|
-
|
|
757
748
|
if "sparse_embedding" in data:
|
|
758
749
|
sparse_embedding = data.pop("sparse_embedding", None)
|
|
759
750
|
if sparse_embedding:
|
|
@@ -464,29 +464,32 @@ class TestWeaviateDocumentStore(DocumentStoreBaseExtendedTests):
|
|
|
464
464
|
],
|
|
465
465
|
)
|
|
466
466
|
|
|
467
|
-
def
|
|
467
|
+
def test_split_overlap_preserved(self, document_store):
|
|
468
|
+
"""Split overlap meta is written and read back correctly."""
|
|
469
|
+
overlap = [
|
|
470
|
+
{"range": [3.0, 13.0], "doc_id": "34326b7e6be489cb4c031152fc378cb50479ca5fcc3861e7e61dfb2e4e4e968b"},
|
|
471
|
+
{"range": [0.0, 13.0], "doc_id": "780f791c09d499c0bf01f87bce047b45c44224d36c79f0c9d8c1405a3197fc1a"},
|
|
472
|
+
]
|
|
468
473
|
doc = Document(
|
|
469
|
-
|
|
474
|
+
id="6edd24e8b01f3cd6e4b71fef7d57b52f17664e14db5ab01b8ef429f97add3620",
|
|
475
|
+
content="an eighth test. ",
|
|
470
476
|
meta={
|
|
471
|
-
"
|
|
472
|
-
"page_number": 1,
|
|
473
|
-
"split_id": 0,
|
|
474
|
-
"split_idx_start": 0,
|
|
475
|
-
"
|
|
476
|
-
{"doc_id": "68ed48ba830048c5d7815874ed2de794722e6d10866b6c55349a914fd9a0df65", "range": (0, 20)}
|
|
477
|
-
],
|
|
477
|
+
"_split_overlap": overlap,
|
|
478
|
+
"page_number": 1.0,
|
|
479
|
+
"split_id": 33.0,
|
|
480
|
+
"split_idx_start": 159.0,
|
|
481
|
+
"source_id": "fdbde6d217f04d3dd60c01f36541794f3153a61f13b4ca669655f4c5610c1664",
|
|
478
482
|
},
|
|
479
483
|
)
|
|
480
484
|
document_store.write_documents([doc])
|
|
481
|
-
|
|
482
485
|
written_doc = document_store.filter_documents()[0]
|
|
483
|
-
|
|
484
|
-
|
|
485
|
-
assert
|
|
486
|
-
assert
|
|
487
|
-
assert
|
|
488
|
-
assert
|
|
489
|
-
assert "
|
|
486
|
+
assert "_split_overlap" in written_doc.meta
|
|
487
|
+
written_overlap = written_doc.meta["_split_overlap"]
|
|
488
|
+
assert len(written_overlap) == 2
|
|
489
|
+
assert written_overlap[0]["doc_id"] == overlap[0]["doc_id"]
|
|
490
|
+
assert list(written_overlap[0]["range"]) == [3, 13]
|
|
491
|
+
assert written_overlap[1]["doc_id"] == overlap[1]["doc_id"]
|
|
492
|
+
assert list(written_overlap[1]["range"]) == [0, 13]
|
|
490
493
|
|
|
491
494
|
def test_bm25_retrieval(self, document_store):
|
|
492
495
|
document_store.write_documents(
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|