Skip to content

test: OpensearchDocumentStore use more Mixin tests #3002

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
davidsbatista merged 5 commits into from
Mar 20, 2026
Merged

test: OpensearchDocumentStore use more Mixin tests #3002

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
b6bd9b9
adding Mixin tests + removing repetead tests
davidsbatista Mar 13, 2026
51b409e
adding Mixin tests + removing repetead tests
davidsbatista Mar 13, 2026
d0a9ae2
chore: update haystack-ai dependency to >=2.26.1
davidsbatista Mar 19, 2026
1830172
Merge branch 'main' into test/opensearch-use-mixin-tests
davidsbatista Mar 20, 2026
484805e
fix formatting
davidsbatista Mar 20, 2026
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
2 changes: 1 addition & 1 deletion integrations/opensearch/pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,7 @@ classifiers = [
]

dependencies = [
"haystack-ai>=2.26.0",
"haystack-ai>=2.26.1",
"opensearch-py[async]>=3.0.0"
]

Expand Down
173 changes: 17 additions & 156 deletions integrations/opensearch/tests/test_document_store.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,14 @@
from haystack.dataclasses.document import Document
from haystack.document_stores.errors import DocumentStoreError, DuplicateDocumentError
from haystack.document_stores.types import DuplicatePolicy
from haystack.testing.document_store import DocumentStoreBaseExtendedTests
from haystack.testing.document_store import (
CountDocumentsByFilterTest,
CountUniqueMetadataByFilterTest,
DocumentStoreBaseExtendedTests,
GetMetadataFieldMinMaxTest,
GetMetadataFieldsInfoTest,
GetMetadataFieldUniqueValuesTest,
)
from opensearchpy.exceptions import RequestError

from haystack_integrations.document_stores.opensearch import OpenSearchDocumentStore
Expand Down Expand Up @@ -218,10 +225,16 @@ def test_routing_in_delete(mock_bulk, _mock_opensearch_client):


@pytest.mark.integration
class TestDocumentStore(DocumentStoreBaseExtendedTests):
class TestDocumentStore(
CountDocumentsByFilterTest,
CountUniqueMetadataByFilterTest,
DocumentStoreBaseExtendedTests,
GetMetadataFieldsInfoTest,
GetMetadataFieldMinMaxTest,
GetMetadataFieldUniqueValuesTest,
):
"""
Common test cases will be provided by `DocumentStoreBaseExtendedTests` but
you can add more to this class.
Common test cases will be provided by `DocumentStoreBaseExtendedTests` but you can add more to this class.
"""

@pytest.fixture
Expand Down Expand Up @@ -607,158 +620,6 @@ def test_delete_all_documents_index_recreation(self, document_store: OpenSearchD
assert len(results) == 1
assert results[0].content == "New document after delete all"

def test_count_documents_by_filter(self, document_store: OpenSearchDocumentStore):
docs = [
Document(content="Doc 1", meta={"category": "A", "status": "active"}),
Document(content="Doc 2", meta={"category": "B", "status": "active"}),
Document(content="Doc 3", meta={"category": "A", "status": "inactive"}),
Document(content="Doc 4", meta={"category": "A", "status": "active"}),
]
document_store.write_documents(docs)
assert document_store.count_documents() == 4

count_a = document_store.count_documents_by_filter(
filters={"field": "meta.category", "operator": "==", "value": "A"}
)
assert count_a == 3

count_a_active = document_store.count_documents_by_filter(
filters={
"operator": "AND",
"conditions": [
{"field": "meta.category", "operator": "==", "value": "A"},
{"field": "meta.status", "operator": "==", "value": "active"},
],
}
)
assert count_a_active == 2

def test_count_unique_metadata_by_filter(self, document_store: OpenSearchDocumentStore):
docs = [
Document(content="Doc 1", meta={"category": "A", "status": "active", "priority": 1}),
Document(content="Doc 2", meta={"category": "B", "status": "active", "priority": 2}),
Document(content="Doc 3", meta={"category": "A", "status": "inactive", "priority": 1}),
Document(content="Doc 4", meta={"category": "A", "status": "active", "priority": 3}),
Document(content="Doc 5", meta={"category": "C", "status": "active", "priority": 2}),
]
document_store.write_documents(docs)
assert document_store.count_documents() == 5

# Count distinct values for all documents
distinct_counts = document_store.count_unique_metadata_by_filter(
filters={}, metadata_fields=["category", "status", "priority"]
)
assert distinct_counts["category"] == 3 # A, B, C
assert distinct_counts["status"] == 2 # active, inactive
assert distinct_counts["priority"] == 3 # 1, 2, 3

# Count distinct values for documents with category="A"
distinct_counts_a = document_store.count_unique_metadata_by_filter(
filters={"field": "meta.category", "operator": "==", "value": "A"},
metadata_fields=["category", "status", "priority"],
)
assert distinct_counts_a["category"] == 1 # Only A
assert distinct_counts_a["status"] == 2 # active, inactive
assert distinct_counts_a["priority"] == 2 # 1, 3

# Count distinct values for documents with status="active"
distinct_counts_active = document_store.count_unique_metadata_by_filter(
filters={"field": "meta.status", "operator": "==", "value": "active"},
metadata_fields=["category", "status", "priority"],
)
assert distinct_counts_active["category"] == 3 # A, B, C
assert distinct_counts_active["status"] == 1 # Only active
assert distinct_counts_active["priority"] == 3 # 1, 2, 3

# Count distinct values with complex filter (category="A" AND status="active")
distinct_counts_a_active = document_store.count_unique_metadata_by_filter(
filters={
"operator": "AND",
"conditions": [
{"field": "meta.category", "operator": "==", "value": "A"},
{"field": "meta.status", "operator": "==", "value": "active"},
],
},
metadata_fields=["category", "status", "priority"],
)
assert distinct_counts_a_active["category"] == 1 # Only A
assert distinct_counts_a_active["status"] == 1 # Only active
assert distinct_counts_a_active["priority"] == 2 # 1, 3

# Test with only a subset of fields
distinct_counts_subset = document_store.count_unique_metadata_by_filter(
filters={}, metadata_fields=["category", "status"]
)
assert distinct_counts_subset["category"] == 3
assert distinct_counts_subset["status"] == 2
assert "priority" not in distinct_counts_subset

# Test field name normalization (with "meta." prefix)
distinct_counts_normalized = document_store.count_unique_metadata_by_filter(
filters={}, metadata_fields=["meta.category", "status", "meta.priority"]
)
assert distinct_counts_normalized["category"] == 3
assert distinct_counts_normalized["status"] == 2
assert distinct_counts_normalized["priority"] == 3

# Test error handling when field doesn't exist
with pytest.raises(ValueError, match="Fields not found in index mapping"):
document_store.count_unique_metadata_by_filter(filters={}, metadata_fields=["nonexistent_field"])

def test_get_metadata_fields_info(self, document_store: OpenSearchDocumentStore):
docs = [
Document(content="Doc 1", meta={"category": "A", "status": "active", "priority": 1}),
Document(content="Doc 2", meta={"category": "B", "status": "inactive"}),
]
document_store.write_documents(docs)

fields_info = document_store.get_metadata_fields_info()

# Verify that fields_info contains expected fields
assert "category" in fields_info
assert "status" in fields_info
assert "priority" in fields_info

assert fields_info["category"]["type"] == "keyword"
assert fields_info["status"]["type"] == "keyword"
assert fields_info["priority"]["type"] == "long"

def test_get_metadata_field_min_max(self, document_store: OpenSearchDocumentStore):
# Test with integer values
docs = [
Document(content="Doc 1", meta={"priority": 1, "age": 10}),
Document(content="Doc 2", meta={"priority": 5, "age": 20}),
Document(content="Doc 3", meta={"priority": 3, "age": 15}),
Document(content="Doc 4", meta={"priority": 10, "age": 5}),
Document(content="Doc 6", meta={"rating": 10.5}),
Document(content="Doc 7", meta={"rating": 20.3}),
Document(content="Doc 8", meta={"rating": 15.7}),
Document(content="Doc 9", meta={"rating": 5.2}),
]
document_store.write_documents(docs)

# Test with "meta." prefix for integer field
min_max_priority = document_store.get_metadata_field_min_max("meta.priority")
assert min_max_priority["min"] == 1
assert min_max_priority["max"] == 10

# Test with "meta." prefix for another integer field
min_max_rating = document_store.get_metadata_field_min_max("meta.age")
assert min_max_rating["min"] == 5
assert min_max_rating["max"] == 20

# Test with single value
single_doc = [Document(content="Doc 5", meta={"single_value": 42})]
document_store.write_documents(single_doc)
min_max_single = document_store.get_metadata_field_min_max("meta.single_value")
assert min_max_single["min"] == 42
assert min_max_single["max"] == 42

# Test with float values
min_max_score = document_store.get_metadata_field_min_max("meta.rating")
assert min_max_score["min"] == pytest.approx(5.2)
assert min_max_score["max"] == pytest.approx(20.3)

def test_get_metadata_field_unique_values(self, document_store: OpenSearchDocumentStore):
# Test with string values
docs = [
Expand Down
Loading