Merge branch 'dev' into feature/cog-3160-redis-session-conversation

cognee/api/v1/search/search.py

@@ -1,6 +1,7 @@
 from uuid import UUID
 from typing import Union, Optional, List, Type
 
+from cognee.infrastructure.databases.graph import get_graph_engine
 from cognee.modules.engine.models.node_set import NodeSet
 from cognee.modules.users.models import User
 from cognee.modules.search.types import SearchResult, SearchType, CombinedSearchResult
@@ -9,6 +10,9 @@ from cognee.modules.search.methods import search as search_function
 from cognee.modules.data.methods import get_authorized_existing_datasets
 from cognee.modules.data.exceptions import DatasetNotFoundError
 from cognee.context_global_variables import set_session_user_context_variable
+from cognee.shared.logging_utils import get_logger
+
+logger = get_logger()
 
 
 async def search(
@@ -181,6 +185,13 @@ async def search(
         if not datasets:
             raise DatasetNotFoundError(message="No datasets found.")
 
+    graph_engine = await get_graph_engine()
+    is_empty = await graph_engine.is_empty()
+
+    if is_empty:
+        logger.warning("Search attempt on an empty knowledge graph")
+        return []
+
     filtered_search_results = await search_function(
         query_text=query_text,
         query_type=query_type,

cognee/infrastructure/databases/graph/graph_db_interface.py

@@ -159,6 +159,11 @@ class GraphDBInterface(ABC):
     - get_connections
     """
 
+    @abstractmethod
+    async def is_empty(self) -> bool:
+        logger.warning("is_empty() is not implemented")
+        return True
+
     @abstractmethod
     async def query(self, query: str, params: dict) -> List[Any]:
         """

cognee/infrastructure/databases/graph/kuzu/adapter.py

@@ -198,6 +198,15 @@ class KuzuAdapter(GraphDBInterface):
         except FileNotFoundError:
             logger.warning(f"Kuzu S3 storage file not found: {self.db_path}")
 
+    async def is_empty(self) -> bool:
+        query = """
+        MATCH (n)
+        RETURN true
+        LIMIT 1;
+        """
+        query_result = await self.query(query)
+        return len(query_result) == 0
+
     async def query(self, query: str, params: Optional[dict] = None) -> List[Tuple]:
         """
         Execute a Kuzu query asynchronously with automatic reconnection.

cognee/infrastructure/databases/graph/neo4j_driver/adapter.py

@@ -87,6 +87,15 @@ class Neo4jAdapter(GraphDBInterface):
         async with self.driver.session(database=self.graph_database_name) as session:
             yield session
 
+    async def is_empty(self) -> bool:
+        query = """
+        RETURN EXISTS {
+        MATCH (n)
+        } AS node_exists;
+        """
+        query_result = await self.query(query)
+        return not query_result[0]["node_exists"]
+
     @deadlock_retry()
     async def query(
         self,

cognee/tests/test_kuzu.py

@@ -47,10 +47,26 @@ async def main():
             pathlib.Path(__file__).parent, "test_data/Quantum_computers.txt"
         )
 
+        from cognee.infrastructure.databases.graph import get_graph_engine
+
+        graph_engine = await get_graph_engine()
+
+        is_empty = await graph_engine.is_empty()
+
+        assert is_empty, "Kuzu graph database is not empty"
+
         await cognee.add([explanation_file_path_quantum], dataset_name)
 
+        is_empty = await graph_engine.is_empty()
+
+        assert is_empty, "Kuzu graph database should be empty before cognify"
+
         await cognee.cognify([dataset_name])
 
+        is_empty = await graph_engine.is_empty()
+
+        assert not is_empty, "Kuzu graph database should not be empty"
+
         from cognee.infrastructure.databases.vector import get_vector_engine
 
         vector_engine = get_vector_engine()
@@ -114,11 +130,10 @@ async def main():
         assert not os.path.isdir(data_root_directory), "Local data files are not deleted"
 
         await cognee.prune.prune_system(metadata=True)
-        from cognee.infrastructure.databases.graph import get_graph_engine
 
-        graph_engine = await get_graph_engine()
+        is_empty = await graph_engine.is_empty()
-        nodes, edges = await graph_engine.get_graph_data()
+
-        assert len(nodes) == 0 and len(edges) == 0, "Kuzu graph database is not empty"
+        assert is_empty, "Kuzu graph database is not empty"
 
     finally:
         # Ensure cleanup even if tests fail

cognee/tests/test_neo4j.py

@@ -35,6 +35,14 @@ async def main():
     explanation_file_path_nlp = os.path.join(
         pathlib.Path(__file__).parent, "test_data/Natural_language_processing.txt"
     )
+    from cognee.infrastructure.databases.graph import get_graph_engine
+
+    graph_engine = await get_graph_engine()
+
+    is_empty = await graph_engine.is_empty()
+
+    assert is_empty, "Graph has to be empty"
+
     await cognee.add([explanation_file_path_nlp], dataset_name)
 
     explanation_file_path_quantum = os.path.join(
@@ -42,9 +50,16 @@ async def main():
     )
 
     await cognee.add([explanation_file_path_quantum], dataset_name)
+    is_empty = await graph_engine.is_empty()
+
+    assert is_empty, "Graph has to be empty before cognify"
 
     await cognee.cognify([dataset_name])
 
+    is_empty = await graph_engine.is_empty()
+
+    assert not is_empty, "Graph shouldn't be empty"
+
     from cognee.infrastructure.databases.vector import get_vector_engine
 
     vector_engine = get_vector_engine()
@@ -117,11 +132,8 @@ async def main():
     assert not os.path.isdir(data_root_directory), "Local data files are not deleted"
 
     await cognee.prune.prune_system(metadata=True)
-    from cognee.infrastructure.databases.graph import get_graph_engine
+    is_empty = await graph_engine.is_empty()
-
+    assert is_empty, "Neo4j graph database is not empty"
-    graph_engine = await get_graph_engine()
-    nodes, edges = await graph_engine.get_graph_data()
-    assert len(nodes) == 0 and len(edges) == 0, "Neo4j graph database is not empty"
 
 
 if __name__ == "__main__":

cognee/tests/unit/api/test_search.py

@@ -0,0 +1,21 @@
+import pytest
+import cognee
+
+
+@pytest.mark.asyncio
+async def test_empty_search_raises_SearchOnEmptyGraphError_on_empty_graph():
+    await cognee.prune.prune_data()
+    await cognee.prune.prune_system(metadata=True)
+    await cognee.add("Sample input")
+    result = await cognee.search("Sample query")
+    assert result == []
+
+
+@pytest.mark.asyncio
+async def test_empty_search_doesnt_raise_SearchOnEmptyGraphError():
+    await cognee.prune.prune_data()
+    await cognee.prune.prune_system(metadata=True)
+    await cognee.add("Sample input")
+    await cognee.cognify()
+    result = await cognee.search("Sample query")
+    assert result != []