cognee 0.4.0__py3-none-any.whl → 0.5.0__py3-none-any.whl

cognee/tests/test_edge_centered_payload.py

@@ -0,0 +1,170 @@
+"""
+End-to-end integration test for edge-centered payload and triplet embeddings.
+
+"""
+
+import os
+import pathlib
+import cognee
+from cognee.infrastructure.databases.graph import get_graph_engine
+from cognee.infrastructure.databases.vector import get_vector_engine
+from cognee.modules.search.types import SearchType
+from cognee.shared.logging_utils import get_logger
+from cognee.modules.ontology.rdf_xml.RDFLibOntologyResolver import RDFLibOntologyResolver
+from cognee.modules.ontology.ontology_config import Config
+
+logger = get_logger()
+
+text_data = """
+Apple is a technology company that produces the iPhone, iPad, and Mac computers.
+The company is known for its innovative products and ecosystem integration.
+
+Microsoft develops the Windows operating system and Office productivity suite.
+They are also major players in cloud computing with Azure.
+
+Google created the Android operating system and provides search engine services.
+The company is a leader in artificial intelligence and machine learning.
+"""
+
+ontology_content = """<?xml version="1.0"?>
+<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+         xmlns:owl="http://www.w3.org/2002/07/owl#"
+         xmlns:rdfs="http://www.w3.org/2000/01/rdf-schema#"
+         xmlns="http://example.org/tech#"
+         xml:base="http://example.org/tech">
+
+    <owl:Ontology rdf:about="http://example.org/tech"/>
+
+    <!-- Classes -->
+    <owl:Class rdf:ID="Company"/>
+    <owl:Class rdf:ID="TechnologyCompany"/>
+    <owl:Class rdf:ID="Product"/>
+    <owl:Class rdf:ID="Software"/>
+    <owl:Class rdf:ID="Hardware"/>
+    <owl:Class rdf:ID="Service"/>
+
+    <rdf:Description rdf:about="#TechnologyCompany">
+        <rdfs:subClassOf rdf:resource="#Company"/>
+        <rdfs:comment>A company operating in the technology sector.</rdfs:comment>
+    </rdf:Description>
+
+    <rdf:Description rdf:about="#Software">
+        <rdfs:subClassOf rdf:resource="#Product"/>
+        <rdfs:comment>Software products and applications.</rdfs:comment>
+    </rdf:Description>
+
+    <rdf:Description rdf:about="#Hardware">
+        <rdfs:subClassOf rdf:resource="#Product"/>
+        <rdfs:comment>Physical hardware products.</rdfs:comment>
+    </rdf:Description>
+
+    <!-- Individuals -->
+    <TechnologyCompany rdf:ID="apple">
+        <rdfs:label>Apple</rdfs:label>
+    </TechnologyCompany>
+
+    <TechnologyCompany rdf:ID="microsoft">
+        <rdfs:label>Microsoft</rdfs:label>
+    </TechnologyCompany>
+
+    <TechnologyCompany rdf:ID="google">
+        <rdfs:label>Google</rdfs:label>
+    </TechnologyCompany>
+
+    <Hardware rdf:ID="iphone">
+        <rdfs:label>iPhone</rdfs:label>
+    </Hardware>
+
+    <Software rdf:ID="windows">
+        <rdfs:label>Windows</rdfs:label>
+    </Software>
+
+    <Software rdf:ID="android">
+        <rdfs:label>Android</rdfs:label>
+    </Software>
+
+</rdf:RDF>"""
+
+
+async def main():
+    data_directory_path = str(
+        pathlib.Path(
+            os.path.join(
+                pathlib.Path(__file__).parent,
+                ".data_storage/test_edge_centered_payload",
+            )
+        ).resolve()
+    )
+    cognee_directory_path = str(
+        pathlib.Path(
+            os.path.join(
+                pathlib.Path(__file__).parent,
+                ".cognee_system/test_edge_centered_payload",
+            )
+        ).resolve()
+    )
+
+    cognee.config.data_root_directory(data_directory_path)
+    cognee.config.system_root_directory(cognee_directory_path)
+
+    dataset_name = "tech_companies"
+
+    await cognee.prune.prune_data()
+    await cognee.prune.prune_system(metadata=True)
+
+    await cognee.add(data=text_data, dataset_name=dataset_name)
+
+    import tempfile
+
+    with tempfile.NamedTemporaryFile(mode="w", suffix=".owl", delete=False) as f:
+        f.write(ontology_content)
+        ontology_file_path = f.name
+
+    try:
+        logger.info(f"Loading ontology from: {ontology_file_path}")
+        config: Config = {
+            "ontology_config": {
+                "ontology_resolver": RDFLibOntologyResolver(ontology_file=ontology_file_path)
+            }
+        }
+
+        await cognee.cognify(datasets=[dataset_name], config=config)
+        graph_engine = await get_graph_engine()
+        nodes_phase2, edges_phase2 = await graph_engine.get_graph_data()
+
+        vector_engine = get_vector_engine()
+        triplets_phase2 = await vector_engine.search(
+            query_text="technology", limit=None, collection_name="Triplet_text"
+        )
+
+        assert len(triplets_phase2) == len(edges_phase2), (
+            f"Triplet embeddings and number of edges do not match. Vector db contains {len(triplets_phase2)} edge triplets while graph db contains {len(edges_phase2)} edges."
+        )
+
+        search_results_phase2 = await cognee.search(
+            query_type=SearchType.TRIPLET_COMPLETION,
+            query_text="What products does Apple make?",
+        )
+
+        assert search_results_phase2 is not None, (
+            "Search should return results for triplet embeddings in simple ontology use case."
+        )
+
+    finally:
+        if os.path.exists(ontology_file_path):
+            os.unlink(ontology_file_path)
+
+
+if __name__ == "__main__":
+    import asyncio
+    from cognee.shared.logging_utils import setup_logging
+
+    setup_logging()
+
+    loop = asyncio.new_event_loop()
+    asyncio.set_event_loop(loop)
+    try:
+        loop.run_until_complete(main())
+    finally:
+        loop.run_until_complete(loop.shutdown_asyncgens())
+        loop.close()

cognee/tests/test_edge_ingestion.py

@@ -52,6 +52,33 @@ async def test_edge_ingestion():
 
     edge_type_counts = Counter(edge_type[2] for edge_type in graph[1])
 
+    "Tests edge_text presence and format"
+    contains_edges = [edge for edge in graph[1] if edge[2] == "contains"]
+    assert len(contains_edges) > 0, "Expected at least one contains edge for edge_text verification"
+
+    edge_properties = contains_edges[0][3]
+    assert "edge_text" in edge_properties, "Expected edge_text in edge properties"
+
+    edge_text = edge_properties["edge_text"]
+    assert "relationship_name: contains" in edge_text, (
+        f"Expected 'relationship_name: contains' in edge_text, got: {edge_text}"
+    )
+    assert "entity_name:" in edge_text, f"Expected 'entity_name:' in edge_text, got: {edge_text}"
+    assert "entity_description:" in edge_text, (
+        f"Expected 'entity_description:' in edge_text, got: {edge_text}"
+    )
+
+    all_edge_texts = [
+        edge[3].get("edge_text", "") for edge in contains_edges if "edge_text" in edge[3]
+    ]
+    expected_entities = ["dave", "ana", "bob", "dexter", "apples", "cognee"]
+    found_entity = any(
+        any(entity in text.lower() for entity in expected_entities) for text in all_edge_texts
+    )
+    assert found_entity, (
+        f"Expected to find at least one entity name in edge_text: {all_edge_texts[:3]}"
+    )
+
     "Tests the presence of basic nested edges"
     for basic_nested_edge in basic_nested_edges:
         assert edge_type_counts.get(basic_nested_edge, 0) >= 1, (

cognee/tests/test_feedback_enrichment.py

@@ -133,7 +133,7 @@ async def main():
         extraction_tasks=extraction_tasks,
         enrichment_tasks=enrichment_tasks,
         data=[{}],
-        dataset="feedback_enrichment_test_memify",
+        dataset=dataset_name,
     )
 
     nodes_after, edges_after = await graph_engine.get_graph_data()

cognee/tests/test_library.py

@@ -90,15 +90,17 @@ async def main():
         )
 
     search_results = await cognee.search(
-        query_type=SearchType.GRAPH_COMPLETION, query_text="What information do you contain?"
+        query_type=SearchType.GRAPH_COMPLETION,
+        query_text="What information do you contain?",
+        dataset_ids=[pipeline_run_obj.dataset_id],
     )
-    assert "Mark" in search_results[0], (
+    assert "Mark" in search_results[0]["search_result"][0], (
         "Failed to update document, no mention of Mark in search results"
     )
-    assert "Cindy" in search_results[0], (
+    assert "Cindy" in search_results[0]["search_result"][0], (
         "Failed to update document, no mention of Cindy in search results"
     )
-    assert "Artificial intelligence" not in search_results[0], (
+    assert "Artificial intelligence" not in search_results[0]["search_result"][0], (
         "Failed to update document, Artificial intelligence still mentioned in search results"
     )
 

cognee/tests/test_load.py

@@ -0,0 +1,62 @@
+import os
+import pathlib
+import asyncio
+import time
+
+import cognee
+from cognee.modules.search.types import SearchType
+from cognee.shared.logging_utils import get_logger
+
+logger = get_logger()
+
+
+async def process_and_search(num_of_searches):
+    start_time = time.time()
+
+    await cognee.cognify()
+
+    await asyncio.gather(
+        *[
+            cognee.search(
+                query_text="Tell me about the document", query_type=SearchType.GRAPH_COMPLETION
+            )
+            for _ in range(num_of_searches)
+        ]
+    )
+
+    end_time = time.time()
+
+    return end_time - start_time
+
+
+async def main():
+    data_directory_path = os.path.join(pathlib.Path(__file__).parent, ".data_storage/test_load")
+    cognee.config.data_root_directory(data_directory_path)
+
+    cognee_directory_path = os.path.join(pathlib.Path(__file__).parent, ".cognee_system/test_load")
+    cognee.config.system_root_directory(cognee_directory_path)
+
+    num_of_pdfs = 10
+    num_of_reps = 5
+    upper_boundary_minutes = 10
+    average_minutes = 8
+
+    recorded_times = []
+    for _ in range(num_of_reps):
+        await cognee.prune.prune_data()
+        await cognee.prune.prune_system(metadata=True)
+
+        s3_input = "s3://cognee-test-load-s3-bucket"
+        await cognee.add(s3_input)
+
+        recorded_times.append(await process_and_search(num_of_pdfs))
+
+    average_recorded_time = sum(recorded_times) / len(recorded_times)
+
+    assert average_recorded_time <= average_minutes * 60
+
+    assert all(rec_time <= upper_boundary_minutes * 60 for rec_time in recorded_times)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

cognee/tests/test_multi_tenancy.py

@@ -0,0 +1,165 @@
+import cognee
+import pytest
+
+from cognee.modules.users.exceptions import PermissionDeniedError
+from cognee.modules.users.tenants.methods import select_tenant
+from cognee.modules.users.methods import get_user
+from cognee.shared.logging_utils import get_logger
+from cognee.modules.search.types import SearchType
+from cognee.modules.users.methods import create_user
+from cognee.modules.users.permissions.methods import authorized_give_permission_on_datasets
+from cognee.modules.users.roles.methods import add_user_to_role
+from cognee.modules.users.roles.methods import create_role
+from cognee.modules.users.tenants.methods import create_tenant
+from cognee.modules.users.tenants.methods import add_user_to_tenant
+from cognee.modules.engine.operations.setup import setup
+from cognee.shared.logging_utils import setup_logging, CRITICAL
+
+logger = get_logger()
+
+
+async def main():
+    # Create a clean slate for cognee -- reset data and system state
+    print("Resetting cognee data...")
+    await cognee.prune.prune_data()
+    await cognee.prune.prune_system(metadata=True)
+    print("Data reset complete.\n")
+
+    # Set up the necessary databases and tables for user management.
+    await setup()
+
+    # Add document for user_1, add it under dataset name AI
+    text = """A quantum computer is a computer that takes advantage of quantum mechanical phenomena.
+    At small scales, physical matter exhibits properties of both particles and waves, and quantum computing leverages
+    this behavior, specifically quantum superposition and entanglement, using specialized hardware that supports the
+    preparation and manipulation of quantum state"""
+
+    print("Creating user_1: user_1@example.com")
+    user_1 = await create_user("user_1@example.com", "example")
+    await cognee.add([text], dataset_name="AI", user=user_1)
+
+    print("\nCreating user_2: user_2@example.com")
+    user_2 = await create_user("user_2@example.com", "example")
+
+    # Run cognify for both datasets as the appropriate user/owner
+    print("\nCreating different datasets for user_1 (AI dataset) and user_2 (QUANTUM dataset)")
+    ai_cognify_result = await cognee.cognify(["AI"], user=user_1)
+
+    # Extract dataset_ids from cognify results
+    def extract_dataset_id_from_cognify(cognify_result):
+        """Extract dataset_id from cognify output dictionary"""
+        for dataset_id, pipeline_result in cognify_result.items():
+            return dataset_id  # Return the first dataset_id
+        return None
+
+    # Get dataset IDs from cognify results
+    # Note: When we want to work with datasets from other users (search, add, cognify and etc.) we must supply dataset
+    # information through dataset_id using dataset name only looks for datasets owned by current user
+    ai_dataset_id = extract_dataset_id_from_cognify(ai_cognify_result)
+
+    # We can see here that user_1 can read his own dataset (AI dataset)
+    search_results = await cognee.search(
+        query_type=SearchType.GRAPH_COMPLETION,
+        query_text="What is in the document?",
+        user=user_1,
+        datasets=[ai_dataset_id],
+    )
+
+    # Verify that user_2 cannot access user_1's dataset without permission
+    with pytest.raises(PermissionDeniedError):
+        search_results = await cognee.search(
+            query_type=SearchType.GRAPH_COMPLETION,
+            query_text="What is in the document?",
+            user=user_2,
+            datasets=[ai_dataset_id],
+        )
+
+    # Create new tenant and role, add user_2 to tenant and role
+    tenant_id = await create_tenant("CogneeLab", user_1.id)
+    await select_tenant(user_id=user_1.id, tenant_id=tenant_id)
+    role_id = await create_role(role_name="Researcher", owner_id=user_1.id)
+    await add_user_to_tenant(
+        user_id=user_2.id, tenant_id=tenant_id, owner_id=user_1.id, set_as_active_tenant=True
+    )
+    await add_user_to_role(user_id=user_2.id, role_id=role_id, owner_id=user_1.id)
+
+    # Assert that user_1 cannot give permissions on his dataset to role before switching to the correct tenant
+    # AI dataset was made with default tenant and not CogneeLab tenant
+    with pytest.raises(PermissionDeniedError):
+        await authorized_give_permission_on_datasets(
+            role_id,
+            [ai_dataset_id],
+            "read",
+            user_1.id,
+        )
+
+    # We need to refresh the user object with changes made when switching tenants
+    user_1 = await get_user(user_1.id)
+    await cognee.add([text], dataset_name="AI_COGNEE_LAB", user=user_1)
+    ai_cognee_lab_cognify_result = await cognee.cognify(["AI_COGNEE_LAB"], user=user_1)
+
+    ai_cognee_lab_dataset_id = extract_dataset_id_from_cognify(ai_cognee_lab_cognify_result)
+
+    await authorized_give_permission_on_datasets(
+        role_id,
+        [ai_cognee_lab_dataset_id],
+        "read",
+        user_1.id,
+    )
+
+    search_results = await cognee.search(
+        query_type=SearchType.GRAPH_COMPLETION,
+        query_text="What is in the document?",
+        user=user_2,
+        dataset_ids=[ai_cognee_lab_dataset_id],
+    )
+    for result in search_results:
+        print(f"{result}\n")
+
+    # Let's test changing tenants
+    tenant_id = await create_tenant("CogneeLab2", user_1.id)
+    await select_tenant(user_id=user_1.id, tenant_id=tenant_id)
+
+    user_1 = await get_user(user_1.id)
+    await cognee.add([text], dataset_name="AI_COGNEE_LAB", user=user_1)
+    await cognee.cognify(["AI_COGNEE_LAB"], user=user_1)
+
+    search_results = await cognee.search(
+        query_type=SearchType.GRAPH_COMPLETION,
+        query_text="What is in the document?",
+        user=user_1,
+    )
+
+    # Assert only AI_COGNEE_LAB dataset from CogneeLab2 tenant is visible as the currently selected tenant
+    assert len(search_results) == 1, (
+        f"Search results must only contain one dataset from current tenant: {search_results}"
+    )
+    assert search_results[0]["dataset_name"] == "AI_COGNEE_LAB", (
+        f"Dict must contain dataset name 'AI_COGNEE_LAB': {search_results[0]}"
+    )
+    assert search_results[0]["dataset_tenant_id"] == user_1.tenant_id, (
+        f"Dataset tenant_id must be same as user_1 tenant_id: {search_results[0]}"
+    )
+
+    # Switch back to no tenant (default tenant)
+    await select_tenant(user_id=user_1.id, tenant_id=None)
+    # Refresh user_1 object
+    user_1 = await get_user(user_1.id)
+    search_results = await cognee.search(
+        query_type=SearchType.GRAPH_COMPLETION,
+        query_text="What is in the document?",
+        user=user_1,
+    )
+    assert len(search_results) == 1, (
+        f"Search results must only contain one dataset from default tenant: {search_results}"
+    )
+    assert search_results[0]["dataset_name"] == "AI", (
+        f"Dict must contain dataset name 'AI': {search_results[0]}"
+    )
+
+
+if __name__ == "__main__":
+    import asyncio
+
+    logger = setup_logging(log_level=CRITICAL)
+    asyncio.run(main())

cognee/tests/test_parallel_databases.py

@@ -33,11 +33,13 @@ async def main():
         "vector_db_url": "cognee1.test",
         "vector_db_key": "",
         "vector_db_provider": "lancedb",
+        "vector_db_name": "",
     }
     task_2_config = {
         "vector_db_url": "cognee2.test",
         "vector_db_key": "",
         "vector_db_provider": "lancedb",
+        "vector_db_name": "",
     }
 
     task_1_graph_config = {

cognee/tests/test_pipeline_cache.py

@@ -0,0 +1,164 @@
+"""
+Test suite for the pipeline_cache feature in Cognee pipelines.
+
+This module tests the behavior of the `pipeline_cache` parameter which controls
+whether a pipeline should skip re-execution when it has already been completed
+for the same dataset.
+
+Architecture Overview:
+---------------------
+The pipeline_cache mechanism works at the dataset level:
+1. When a pipeline runs, it logs its status (INITIATED -> STARTED -> COMPLETED)
+2. Before each run, `check_pipeline_run_qualification()` checks the pipeline status
+3. If `use_pipeline_cache=True` and status is COMPLETED/STARTED, the pipeline skips
+4. If `use_pipeline_cache=False`, the pipeline always re-executes regardless of status
+"""
+
+import pytest
+
+import cognee
+from cognee.modules.pipelines.tasks.task import Task
+from cognee.modules.pipelines import run_pipeline
+from cognee.modules.users.methods import get_default_user
+
+from cognee.modules.pipelines.layers.reset_dataset_pipeline_run_status import (
+    reset_dataset_pipeline_run_status,
+)
+from cognee.infrastructure.databases.relational import create_db_and_tables
+
+
+class ExecutionCounter:
+    """Helper class to track task execution counts."""
+
+    def __init__(self):
+        self.count = 0
+
+
+async def create_counting_task(data, counter: ExecutionCounter):
+    """Create a task that increments a counter from the ExecutionCounter instance when executed."""
+    counter.count += 1
+    return counter
+
+
+class TestPipelineCache:
+    """Tests for basic pipeline_cache on/off behavior."""
+
+    @pytest.mark.asyncio
+    async def test_pipeline_cache_off_allows_reexecution(self):
+        """
+        Test that with use_pipeline_cache=False, the pipeline re-executes
+        even when it has already completed for the dataset.
+
+        Expected behavior:
+        - First run: Pipeline executes fully, task runs once
+        - Second run: Pipeline executes again, task runs again (total: 2 times)
+        """
+        await cognee.prune.prune_data()
+        await cognee.prune.prune_system(metadata=True)
+        await create_db_and_tables()
+
+        counter = ExecutionCounter()
+        user = await get_default_user()
+
+        tasks = [Task(create_counting_task, counter=counter)]
+
+        # First run
+        pipeline_results_1 = []
+        async for result in run_pipeline(
+            tasks=tasks,
+            datasets="test_dataset_cache_off",
+            data=["sample data"],  # Data is necessary to trigger processing
+            user=user,
+            pipeline_name="test_cache_off_pipeline",
+            use_pipeline_cache=False,
+        ):
+            pipeline_results_1.append(result)
+
+        first_run_count = counter.count
+        assert first_run_count >= 1, "Task should have executed at least once on first run"
+
+        # Second run with pipeline_cache=False
+        pipeline_results_2 = []
+        async for result in run_pipeline(
+            tasks=tasks,
+            datasets="test_dataset_cache_off",
+            data=["sample data"],  # Data is necessary to trigger processing
+            user=user,
+            pipeline_name="test_cache_off_pipeline",
+            use_pipeline_cache=False,
+        ):
+            pipeline_results_2.append(result)
+
+        second_run_count = counter.count
+        assert second_run_count > first_run_count, (
+            f"With pipeline_cache=False, task should re-execute. "
+            f"First run: {first_run_count}, After second run: {second_run_count}"
+        )
+
+    @pytest.mark.asyncio
+    async def test_reset_pipeline_status_allows_reexecution_with_cache(self):
+        """
+        Test that resetting pipeline status allows re-execution even with
+        pipeline_cache=True.
+        """
+        await cognee.prune.prune_data()
+        await cognee.prune.prune_system(metadata=True)
+        await create_db_and_tables()
+
+        counter = ExecutionCounter()
+        user = await get_default_user()
+        dataset_name = "reset_status_test"
+        pipeline_name = "test_reset_pipeline"
+
+        tasks = [Task(create_counting_task, counter=counter)]
+
+        # First run
+        pipeline_result = []
+        async for result in run_pipeline(
+            tasks=tasks,
+            datasets=dataset_name,
+            user=user,
+            data=["sample data"],  # Data is necessary to trigger processing
+            pipeline_name=pipeline_name,
+            use_pipeline_cache=True,
+        ):
+            pipeline_result.append(result)
+
+        first_run_count = counter.count
+        assert first_run_count >= 1
+
+        # Second run without reset - should skip
+        async for _ in run_pipeline(
+            tasks=tasks,
+            datasets=dataset_name,
+            user=user,
+            data=["sample data"],  # Data is necessary to trigger processing
+            pipeline_name=pipeline_name,
+            use_pipeline_cache=True,
+        ):
+            pass
+
+        after_second_run = counter.count
+        assert after_second_run == first_run_count, "Should have skipped due to cache"
+
+        # Reset the pipeline status
+        await reset_dataset_pipeline_run_status(
+            pipeline_result[0].dataset_id, user, pipeline_names=[pipeline_name]
+        )
+
+        # Third run after reset - should execute
+        async for _ in run_pipeline(
+            tasks=tasks,
+            datasets=dataset_name,
+            user=user,
+            data=["sample data"],  # Data is necessary to trigger processing
+            pipeline_name=pipeline_name,
+            use_pipeline_cache=True,
+        ):
+            pass
+
+        after_reset_run = counter.count
+        assert after_reset_run > after_second_run, (
+            f"After reset, pipeline should re-execute. "
+            f"Before reset: {after_second_run}, After reset run: {after_reset_run}"
+        )