feat: Add database deletion on dataset delete

.github/workflows/e2e_tests.yml

@@ -237,6 +237,31 @@ jobs:
           EMBEDDING_API_VERSION: ${{ secrets.EMBEDDING_API_VERSION }}
         run: uv run python ./cognee/tests/test_dataset_database_handler.py
 
+  test-dataset-database-deletion:
+    name: Test dataset database deletion in Cognee
+    runs-on: ubuntu-22.04
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v4
+
+      - name: Cognee Setup
+        uses: ./.github/actions/cognee_setup
+        with:
+          python-version: '3.11.x'
+
+      - name: Run dataset databases deletion test
+        env:
+          ENV: 'dev'
+          LLM_MODEL: ${{ secrets.LLM_MODEL }}
+          LLM_ENDPOINT: ${{ secrets.LLM_ENDPOINT }}
+          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+          LLM_API_VERSION: ${{ secrets.LLM_API_VERSION }}
+          EMBEDDING_MODEL: ${{ secrets.EMBEDDING_MODEL }}
+          EMBEDDING_ENDPOINT: ${{ secrets.EMBEDDING_ENDPOINT }}
+          EMBEDDING_API_KEY: ${{ secrets.EMBEDDING_API_KEY }}
+          EMBEDDING_API_VERSION: ${{ secrets.EMBEDDING_API_VERSION }}
+        run: uv run python ./cognee/tests/test_dataset_delete.py
+
   test-permissions:
     name: Test permissions with different situations in Cognee
     runs-on: ubuntu-22.04

cognee/api/v1/cognify/cognify.py

@@ -53,7 +53,7 @@ async def cognify(
     custom_prompt: Optional[str] = None,
     temporal_cognify: bool = False,
     data_per_batch: int = 20,
-    **kwargs
+    **kwargs,
 ):
     """
     Transform ingested data into a structured knowledge graph.

cognee/api/v1/datasets/routers/get_datasets_router.py

@@ -208,14 +208,14 @@ async def delete_dataset(dataset_id: UUID, user: User = Depends(get_authenticate
             },
         )
 
-        from cognee.modules.data.methods import get_dataset, delete_dataset
+        from cognee.modules.data.methods import delete_dataset
 
-        dataset = await get_dataset(user.id, dataset_id)
+        dataset = await get_authorized_existing_datasets([dataset_id], "delete", user)
 
         if dataset is None:
             raise DatasetNotFoundError(message=f"Dataset ({str(dataset_id)}) not found.")
 
-        await delete_dataset(dataset)
+        await delete_dataset(dataset[0])
 
     @router.delete(
         "/{dataset_id}/data/{data_id}",

cognee/infrastructure/databases/utils/__init__.py

@@ -1,2 +1,4 @@
 from .get_or_create_dataset_database import get_or_create_dataset_database
 from .resolve_dataset_database_connection_info import resolve_dataset_database_connection_info
+from .get_graph_dataset_database_handler import get_graph_dataset_database_handler
+from .get_vector_dataset_database_handler import get_vector_dataset_database_handler

cognee/infrastructure/databases/utils/get_graph_dataset_database_handler.py

@@ -0,0 +1,10 @@
+from cognee.modules.users.models.DatasetDatabase import DatasetDatabase
+
+
+def get_graph_dataset_database_handler(dataset_database: DatasetDatabase) -> dict:
+    from cognee.infrastructure.databases.dataset_database_handler.supported_dataset_database_handlers import (
+        supported_dataset_database_handlers,
+    )
+
+    handler = supported_dataset_database_handlers[dataset_database.graph_dataset_database_handler]
+    return handler

cognee/infrastructure/databases/utils/get_vector_dataset_database_handler.py

@@ -0,0 +1,10 @@
+from cognee.modules.users.models.DatasetDatabase import DatasetDatabase
+
+
+def get_vector_dataset_database_handler(dataset_database: DatasetDatabase) -> dict:
+    from cognee.infrastructure.databases.dataset_database_handler.supported_dataset_database_handlers import (
+        supported_dataset_database_handlers,
+    )
+
+    handler = supported_dataset_database_handlers[dataset_database.vector_dataset_database_handler]
+    return handler

cognee/infrastructure/databases/utils/resolve_dataset_database_connection_info.py

@@ -1,24 +1,12 @@
+from cognee.infrastructure.databases.utils.get_graph_dataset_database_handler import (
+    get_graph_dataset_database_handler,
+)
+from cognee.infrastructure.databases.utils.get_vector_dataset_database_handler import (
+    get_vector_dataset_database_handler,
+)
 from cognee.modules.users.models.DatasetDatabase import DatasetDatabase
 
 
-async def _get_vector_db_connection_info(dataset_database: DatasetDatabase) -> DatasetDatabase:
-    from cognee.infrastructure.databases.dataset_database_handler.supported_dataset_database_handlers import (
-        supported_dataset_database_handlers,
-    )
-
-    handler = supported_dataset_database_handlers[dataset_database.vector_dataset_database_handler]
-    return await handler["handler_instance"].resolve_dataset_connection_info(dataset_database)
-
-
-async def _get_graph_db_connection_info(dataset_database: DatasetDatabase) -> DatasetDatabase:
-    from cognee.infrastructure.databases.dataset_database_handler.supported_dataset_database_handlers import (
-        supported_dataset_database_handlers,
-    )
-
-    handler = supported_dataset_database_handlers[dataset_database.graph_dataset_database_handler]
-    return await handler["handler_instance"].resolve_dataset_connection_info(dataset_database)
-
-
 async def resolve_dataset_database_connection_info(
     dataset_database: DatasetDatabase,
 ) -> DatasetDatabase:
@@ -31,6 +19,12 @@ async def resolve_dataset_database_connection_info(
     Returns:
         DatasetDatabase instance with resolved connection info
     """
-    dataset_database = await _get_vector_db_connection_info(dataset_database)
-    dataset_database = await _get_graph_db_connection_info(dataset_database)
+    vector_dataset_database_handler = get_vector_dataset_database_handler(dataset_database)
+    graph_dataset_database_handler = get_graph_dataset_database_handler(dataset_database)
+    dataset_database = await vector_dataset_database_handler[
+        "handler_instance"
+    ].resolve_dataset_connection_info(dataset_database)
+    dataset_database = await graph_dataset_database_handler[
+        "handler_instance"
+    ].resolve_dataset_connection_info(dataset_database)
     return dataset_database

cognee/infrastructure/llm/LLMGateway.py

@@ -31,7 +31,10 @@ def acreate_structured_output(
 
             llm_client = get_llm_client()
             return llm_client.acreate_structured_output(
-                text_input=text_input, system_prompt=system_prompt, response_model=response_model, **kwargs
+                text_input=text_input,
+                system_prompt=system_prompt,
+                response_model=response_model,
+                **kwargs,
             )
 
     @staticmethod

cognee/modules/data/deletion/prune_system.py

@@ -5,6 +5,10 @@
 from cognee.infrastructure.databases.vector import get_vector_engine
 from cognee.infrastructure.databases.graph.get_graph_engine import get_graph_engine
 from cognee.infrastructure.databases.relational import get_relational_engine
+from cognee.infrastructure.databases.utils import (
+    get_graph_dataset_database_handler,
+    get_vector_dataset_database_handler,
+)
 from cognee.shared.cache import delete_cache
 from cognee.modules.users.models import DatasetDatabase
 from cognee.shared.logging_utils import get_logger
@@ -13,22 +17,13 @@
 
 
 async def prune_graph_databases():
-    async def _prune_graph_db(dataset_database: DatasetDatabase) -> dict:
-        from cognee.infrastructure.databases.dataset_database_handler.supported_dataset_database_handlers import (
-            supported_dataset_database_handlers,
-        )
-
-        handler = supported_dataset_database_handlers[
-            dataset_database.graph_dataset_database_handler
-        ]
-        return await handler["handler_instance"].delete_dataset(dataset_database)
-
     db_engine = get_relational_engine()
     try:
-        data = await db_engine.get_all_data_from_table("dataset_database")
+        dataset_databases = await db_engine.get_all_data_from_table("dataset_database")
         # Go through each dataset database and delete the graph database
-        for data_item in data:
-            await _prune_graph_db(data_item)
+        for dataset_database in dataset_databases:
+            handler = get_graph_dataset_database_handler(dataset_database)
+            await handler["handler_instance"].delete_dataset(dataset_database)
     except (OperationalError, EntityNotFoundError) as e:
         logger.debug(
             "Skipping pruning of graph DB. Error when accessing dataset_database table: %s",
@@ -38,22 +33,13 @@ async def _prune_graph_db(dataset_database: DatasetDatabase) -> dict:
 
 
 async def prune_vector_databases():
-    async def _prune_vector_db(dataset_database: DatasetDatabase) -> dict:
-        from cognee.infrastructure.databases.dataset_database_handler.supported_dataset_database_handlers import (
-            supported_dataset_database_handlers,
-        )
-
-        handler = supported_dataset_database_handlers[
-            dataset_database.vector_dataset_database_handler
-        ]
-        return await handler["handler_instance"].delete_dataset(dataset_database)
-
     db_engine = get_relational_engine()
     try:
-        data = await db_engine.get_all_data_from_table("dataset_database")
+        dataset_databases = await db_engine.get_all_data_from_table("dataset_database")
         # Go through each dataset database and delete the vector database
-        for data_item in data:
-            await _prune_vector_db(data_item)
+        for dataset_database in dataset_databases:
+            handler = get_vector_dataset_database_handler(dataset_database)
+            await handler["handler_instance"].delete_dataset(dataset_database)
     except (OperationalError, EntityNotFoundError) as e:
         logger.debug(
             "Skipping pruning of vector DB. Error when accessing dataset_database table: %s",

cognee/modules/data/methods/delete_dataset.py

@@ -1,8 +1,34 @@
+from cognee.modules.users.models import DatasetDatabase
+from sqlalchemy import select
+
 from cognee.modules.data.models import Dataset
+from cognee.infrastructure.databases.utils.get_vector_dataset_database_handler import (
+    get_vector_dataset_database_handler,
+)
+from cognee.infrastructure.databases.utils.get_graph_dataset_database_handler import (
+    get_graph_dataset_database_handler,
+)
 from cognee.infrastructure.databases.relational import get_relational_engine
 
 
 async def delete_dataset(dataset: Dataset):
     db_engine = get_relational_engine()
 
+    async with db_engine.get_async_session() as session:
+        stmt = select(DatasetDatabase).where(
+            DatasetDatabase.dataset_id == dataset.id,
+        )
+        dataset_database: DatasetDatabase = await session.scalar(stmt)
+        if dataset_database:
+            graph_dataset_database_handler = get_graph_dataset_database_handler(dataset_database)
+            vector_dataset_database_handler = get_vector_dataset_database_handler(dataset_database)
+            await graph_dataset_database_handler["handler_instance"].delete_dataset(
+                dataset_database
+            )
+            await vector_dataset_database_handler["handler_instance"].delete_dataset(
+                dataset_database
+            )
+    # TODO: Remove dataset from pipeline_run_status in Data objects related to dataset as well
+    #       This blocks recreation of the dataset with the same name and data after deletion as
+    #       it's marked as completed and will be just skipped even though it's empty.
     return await db_engine.delete_entity_by_id(dataset.__tablename__, dataset.id)

cognee/tests/test_dataset_delete.py

@@ -0,0 +1,76 @@
+import os
+import asyncio
+import pathlib
+from uuid import UUID
+
+import cognee
+from cognee.shared.logging_utils import setup_logging, ERROR
+from cognee.modules.data.methods.delete_dataset import delete_dataset
+from cognee.modules.data.methods.get_dataset import get_dataset
+from cognee.modules.users.methods import get_default_user
+
+
+async def main():
+    # Set data and system directory paths
+    data_directory_path = str(
+        pathlib.Path(
+            os.path.join(pathlib.Path(__file__).parent, ".data_storage/test_dataset_delete")
+        ).resolve()
+    )
+    cognee.config.data_root_directory(data_directory_path)
+    cognee_directory_path = str(
+        pathlib.Path(
+            os.path.join(pathlib.Path(__file__).parent, ".cognee_system/test_dataset_delete")
+        ).resolve()
+    )
+    cognee.config.system_root_directory(cognee_directory_path)
+
+    # 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")
+
+    # cognee knowledge graph will be created based on this text
+    text = """
+    Natural language processing (NLP) is an interdisciplinary
+    subfield of computer science and information retrieval.
+    """
+
+    # Add the text, and make it available for cognify
+    await cognee.add(text, "nlp_dataset")
+    await cognee.add("Quantum computing is the study of quantum computers.", "quantum_dataset")
+
+    # Use LLMs and cognee to create knowledge graph
+    ret_val = await cognee.cognify()
+    user = await get_default_user()
+
+    for val in ret_val:
+        dataset_id = str(val)
+        vector_db_path = os.path.join(
+            cognee_directory_path, "databases", str(user.id), dataset_id + ".lance.db"
+        )
+        graph_db_path = os.path.join(
+            cognee_directory_path, "databases", str(user.id), dataset_id + ".pkl"
+        )
+
+        # Check if databases are properly created and exist before deletion
+        assert os.path.exists(graph_db_path), "Graph database file not found."
+        assert os.path.exists(vector_db_path), "Vector database file not found."
+
+        dataset = await get_dataset(user_id=user.id, dataset_id=UUID(dataset_id))
+        await delete_dataset(dataset)
+
+        # Confirm databases have been deleted
+        assert not os.path.exists(graph_db_path), "Graph database file found."
+        assert not os.path.exists(vector_db_path), "Vector database file found."
+
+
+if __name__ == "__main__":
+    logger = setup_logging(log_level=ERROR)
+    loop = asyncio.new_event_loop()
+    asyncio.set_event_loop(loop)
+    try:
+        loop.run_until_complete(main())
+    finally:
+        loop.run_until_complete(loop.shutdown_asyncgens())