cognee 0.5.0__py3-none-any.whl → 0.5.0.dev0__py3-none-any.whl

cognee/modules/retrieval/graph_completion_cot_retriever.py

@@ -65,8 +65,6 @@ class GraphCompletionCotRetriever(GraphCompletionRetriever):
         node_type: Optional[Type] = None,
         node_name: Optional[List[str]] = None,
         save_interaction: bool = False,
-        wide_search_top_k: Optional[int] = 100,
-        triplet_distance_penalty: Optional[float] = 3.5,
     ):
         super().__init__(
             user_prompt_path=user_prompt_path,
@@ -76,8 +74,6 @@ class GraphCompletionCotRetriever(GraphCompletionRetriever):
             node_type=node_type,
             node_name=node_name,
             save_interaction=save_interaction,
-            wide_search_top_k=wide_search_top_k,
-            triplet_distance_penalty=triplet_distance_penalty,
         )
         self.validation_system_prompt_path = validation_system_prompt_path
         self.validation_user_prompt_path = validation_user_prompt_path

cognee/modules/retrieval/graph_completion_retriever.py

@@ -47,8 +47,6 @@ class GraphCompletionRetriever(BaseGraphRetriever):
         node_type: Optional[Type] = None,
         node_name: Optional[List[str]] = None,
         save_interaction: bool = False,
-        wide_search_top_k: Optional[int] = 100,
-        triplet_distance_penalty: Optional[float] = 3.5,
     ):
         """Initialize retriever with prompt paths and search parameters."""
         self.save_interaction = save_interaction
@@ -56,10 +54,8 @@ class GraphCompletionRetriever(BaseGraphRetriever):
         self.system_prompt_path = system_prompt_path
         self.system_prompt = system_prompt
         self.top_k = top_k if top_k is not None else 5
-        self.wide_search_top_k = wide_search_top_k
         self.node_type = node_type
         self.node_name = node_name
-        self.triplet_distance_penalty = triplet_distance_penalty
 
     async def resolve_edges_to_text(self, retrieved_edges: list) -> str:
         """
@@ -109,8 +105,6 @@ class GraphCompletionRetriever(BaseGraphRetriever):
             collections=vector_index_collections or None,
             node_type=self.node_type,
             node_name=self.node_name,
-            wide_search_top_k=self.wide_search_top_k,
-            triplet_distance_penalty=self.triplet_distance_penalty,
         )
 
         return found_triplets
@@ -147,10 +141,6 @@ class GraphCompletionRetriever(BaseGraphRetriever):
 
         return triplets
 
-    async def convert_retrieved_objects_to_context(self, triplets: List[Edge]):
-        context = await self.resolve_edges_to_text(triplets)
-        return context
-
     async def get_completion(
         self,
         query: str,

cognee/modules/retrieval/graph_summary_completion_retriever.py

@@ -26,8 +26,6 @@ class GraphSummaryCompletionRetriever(GraphCompletionRetriever):
         node_type: Optional[Type] = None,
         node_name: Optional[List[str]] = None,
         save_interaction: bool = False,
-        wide_search_top_k: Optional[int] = 100,
-        triplet_distance_penalty: Optional[float] = 3.5,
     ):
         """Initialize retriever with default prompt paths and search parameters."""
         super().__init__(
@@ -38,8 +36,6 @@ class GraphSummaryCompletionRetriever(GraphCompletionRetriever):
             node_name=node_name,
             save_interaction=save_interaction,
             system_prompt=system_prompt,
-            wide_search_top_k=wide_search_top_k,
-            triplet_distance_penalty=triplet_distance_penalty,
         )
         self.summarize_prompt_path = summarize_prompt_path
 

cognee/modules/retrieval/temporal_retriever.py

@@ -47,8 +47,6 @@ class TemporalRetriever(GraphCompletionRetriever):
         top_k: Optional[int] = 5,
         node_type: Optional[Type] = None,
         node_name: Optional[List[str]] = None,
-        wide_search_top_k: Optional[int] = 100,
-        triplet_distance_penalty: Optional[float] = 3.5,
     ):
         super().__init__(
             user_prompt_path=user_prompt_path,
@@ -56,8 +54,6 @@ class TemporalRetriever(GraphCompletionRetriever):
             top_k=top_k,
             node_type=node_type,
             node_name=node_name,
-            wide_search_top_k=wide_search_top_k,
-            triplet_distance_penalty=triplet_distance_penalty,
         )
         self.user_prompt_path = user_prompt_path
         self.system_prompt_path = system_prompt_path

cognee/modules/retrieval/utils/brute_force_triplet_search.py

@@ -58,8 +58,6 @@ async def get_memory_fragment(
     properties_to_project: Optional[List[str]] = None,
     node_type: Optional[Type] = None,
     node_name: Optional[List[str]] = None,
-    relevant_ids_to_filter: Optional[List[str]] = None,
-    triplet_distance_penalty: Optional[float] = 3.5,
 ) -> CogneeGraph:
     """Creates and initializes a CogneeGraph memory fragment with optional property projections."""
     if properties_to_project is None:
@@ -76,8 +74,6 @@ async def get_memory_fragment(
             edge_properties_to_project=["relationship_name", "edge_text"],
             node_type=node_type,
             node_name=node_name,
-            relevant_ids_to_filter=relevant_ids_to_filter,
-            triplet_distance_penalty=triplet_distance_penalty,
         )
 
     except EntityNotFoundError:
@@ -99,8 +95,6 @@ async def brute_force_triplet_search(
     memory_fragment: Optional[CogneeGraph] = None,
     node_type: Optional[Type] = None,
     node_name: Optional[List[str]] = None,
-    wide_search_top_k: Optional[int] = 100,
-    triplet_distance_penalty: Optional[float] = 3.5,
 ) -> List[Edge]:
     """
     Performs a brute force search to retrieve the top triplets from the graph.
@@ -113,8 +107,6 @@ async def brute_force_triplet_search(
         memory_fragment (Optional[CogneeGraph]): Existing memory fragment to reuse.
         node_type: node type to filter
         node_name: node name to filter
-        wide_search_top_k (Optional[int]): Number of initial elements to retrieve from collections
-        triplet_distance_penalty (Optional[float]): Default distance penalty in graph projection
 
     Returns:
         list: The top triplet results.
@@ -124,10 +116,10 @@ async def brute_force_triplet_search(
     if top_k <= 0:
         raise ValueError("top_k must be a positive integer.")
 
-    # Setting wide search limit based on the parameters
-    non_global_search = node_name is None
-
-    wide_search_limit = wide_search_top_k if non_global_search else None
+    if memory_fragment is None:
+        memory_fragment = await get_memory_fragment(
+            properties_to_project, node_type=node_type, node_name=node_name
+        )
 
     if collections is None:
         collections = [
@@ -137,9 +129,6 @@ async def brute_force_triplet_search(
             "DocumentChunk_text",
         ]
 
-    if "EdgeType_relationship_name" not in collections:
-        collections.append("EdgeType_relationship_name")
-
     try:
         vector_engine = get_vector_engine()
     except Exception as e:
@@ -151,7 +140,7 @@ async def brute_force_triplet_search(
     async def search_in_collection(collection_name: str):
         try:
             return await vector_engine.search(
-                collection_name=collection_name, query_vector=query_vector, limit=wide_search_limit
+                collection_name=collection_name, query_vector=query_vector, limit=None
             )
         except CollectionNotFoundError:
             return []
@@ -167,40 +156,19 @@ async def brute_force_triplet_search(
             return []
 
         # Final statistics
-        vector_collection_search_time = time.time() - start_time
+        projection_time = time.time() - start_time
         logger.info(
-            f"Vector collection retrieval completed: Retrieved distances from {sum(1 for res in results if res)} collections in {vector_collection_search_time:.2f}s"
+            f"Vector collection retrieval completed: Retrieved distances from {sum(1 for res in results if res)} collections in {projection_time:.2f}s"
         )
 
         node_distances = {collection: result for collection, result in zip(collections, results)}
 
         edge_distances = node_distances.get("EdgeType_relationship_name", None)
 
-        if wide_search_limit is not None:
-            relevant_ids_to_filter = list(
-                {
-                    str(getattr(scored_node, "id"))
-                    for collection_name, score_collection in node_distances.items()
-                    if collection_name != "EdgeType_relationship_name"
-                    and isinstance(score_collection, (list, tuple))
-                    for scored_node in score_collection
-                    if getattr(scored_node, "id", None)
-                }
-            )
-        else:
-            relevant_ids_to_filter = None
-
-        if memory_fragment is None:
-            memory_fragment = await get_memory_fragment(
-                properties_to_project=properties_to_project,
-                node_type=node_type,
-                node_name=node_name,
-                relevant_ids_to_filter=relevant_ids_to_filter,
-                triplet_distance_penalty=triplet_distance_penalty,
-            )
-
         await memory_fragment.map_vector_distances_to_graph_nodes(node_distances=node_distances)
-        await memory_fragment.map_vector_distances_to_graph_edges(edge_distances=edge_distances)
+        await memory_fragment.map_vector_distances_to_graph_edges(
+            vector_engine=vector_engine, query_vector=query_vector, edge_distances=edge_distances
+        )
 
         results = await memory_fragment.calculate_top_triplet_importances(k=top_k)
 

cognee/modules/run_custom_pipeline/run_custom_pipeline.py

@@ -18,8 +18,6 @@ async def run_custom_pipeline(
     user: User = None,
     vector_db_config: Optional[dict] = None,
     graph_db_config: Optional[dict] = None,
-    use_pipeline_cache: bool = False,
-    incremental_loading: bool = False,
     data_per_batch: int = 20,
     run_in_background: bool = False,
     pipeline_name: str = "custom_pipeline",
@@ -42,10 +40,6 @@ async def run_custom_pipeline(
         user: User context for authentication and data access. Uses default if None.
         vector_db_config: Custom vector database configuration for embeddings storage.
         graph_db_config: Custom graph database configuration for relationship storage.
-        use_pipeline_cache: If True, pipelines with the same ID that are currently executing and pipelines with the same ID that were completed won't process data again.
-                        Pipelines ID is created based on the generate_pipeline_id function. Pipeline status can be manually reset with the reset_dataset_pipeline_run_status function.
-        incremental_loading: If True, only new or modified data will be processed to avoid duplication. (Only works if data is used with the Cognee python Data model).
-                            The incremental system stores and compares hashes of processed data in the Data model and skips data with the same content hash.
         data_per_batch: Number of data items to be processed in parallel.
         run_in_background: If True, starts processing asynchronously and returns immediately.
                           If False, waits for completion before returning.
@@ -69,8 +63,7 @@ async def run_custom_pipeline(
         datasets=dataset,
         vector_db_config=vector_db_config,
         graph_db_config=graph_db_config,
-        use_pipeline_cache=use_pipeline_cache,
-        incremental_loading=incremental_loading,
+        incremental_loading=False,
         data_per_batch=data_per_batch,
         pipeline_name=pipeline_name,
     )

cognee/modules/search/methods/get_search_type_tools.py

@@ -2,7 +2,6 @@ import os
 from typing import Callable, List, Optional, Type
 
 from cognee.modules.engine.models.node_set import NodeSet
-from cognee.modules.retrieval.triplet_retriever import TripletRetriever
 from cognee.modules.search.types import SearchType
 from cognee.modules.search.operations import select_search_type
 from cognee.modules.search.exceptions import UnsupportedSearchTypeError
@@ -23,6 +22,7 @@ from cognee.modules.retrieval.graph_completion_cot_retriever import GraphComplet
 from cognee.modules.retrieval.graph_completion_context_extension_retriever import (
     GraphCompletionContextExtensionRetriever,
 )
+from cognee.modules.retrieval.code_retriever import CodeRetriever
 from cognee.modules.retrieval.cypher_search_retriever import CypherSearchRetriever
 from cognee.modules.retrieval.natural_language_retriever import NaturalLanguageRetriever
 
@@ -37,8 +37,6 @@ async def get_search_type_tools(
     node_name: Optional[List[str]] = None,
     save_interaction: bool = False,
     last_k: Optional[int] = None,
-    wide_search_top_k: Optional[int] = 100,
-    triplet_distance_penalty: Optional[float] = 3.5,
 ) -> list:
     search_tasks: dict[SearchType, List[Callable]] = {
         SearchType.SUMMARIES: [
@@ -61,18 +59,6 @@ async def get_search_type_tools(
                 system_prompt=system_prompt,
             ).get_context,
         ],
-        SearchType.TRIPLET_COMPLETION: [
-            TripletRetriever(
-                system_prompt_path=system_prompt_path,
-                top_k=top_k,
-                system_prompt=system_prompt,
-            ).get_completion,
-            TripletRetriever(
-                system_prompt_path=system_prompt_path,
-                top_k=top_k,
-                system_prompt=system_prompt,
-            ).get_context,
-        ],
         SearchType.GRAPH_COMPLETION: [
             GraphCompletionRetriever(
                 system_prompt_path=system_prompt_path,
@@ -81,8 +67,6 @@ async def get_search_type_tools(
                 node_name=node_name,
                 save_interaction=save_interaction,
                 system_prompt=system_prompt,
-                wide_search_top_k=wide_search_top_k,
-                triplet_distance_penalty=triplet_distance_penalty,
             ).get_completion,
             GraphCompletionRetriever(
                 system_prompt_path=system_prompt_path,
@@ -91,8 +75,6 @@ async def get_search_type_tools(
                 node_name=node_name,
                 save_interaction=save_interaction,
                 system_prompt=system_prompt,
-                wide_search_top_k=wide_search_top_k,
-                triplet_distance_penalty=triplet_distance_penalty,
             ).get_context,
         ],
         SearchType.GRAPH_COMPLETION_COT: [
@@ -103,8 +85,6 @@ async def get_search_type_tools(
                 node_name=node_name,
                 save_interaction=save_interaction,
                 system_prompt=system_prompt,
-                wide_search_top_k=wide_search_top_k,
-                triplet_distance_penalty=triplet_distance_penalty,
             ).get_completion,
             GraphCompletionCotRetriever(
                 system_prompt_path=system_prompt_path,
@@ -113,8 +93,6 @@ async def get_search_type_tools(
                 node_name=node_name,
                 save_interaction=save_interaction,
                 system_prompt=system_prompt,
-                wide_search_top_k=wide_search_top_k,
-                triplet_distance_penalty=triplet_distance_penalty,
             ).get_context,
         ],
         SearchType.GRAPH_COMPLETION_CONTEXT_EXTENSION: [
@@ -125,8 +103,6 @@ async def get_search_type_tools(
                 node_name=node_name,
                 save_interaction=save_interaction,
                 system_prompt=system_prompt,
-                wide_search_top_k=wide_search_top_k,
-                triplet_distance_penalty=triplet_distance_penalty,
             ).get_completion,
             GraphCompletionContextExtensionRetriever(
                 system_prompt_path=system_prompt_path,
@@ -135,8 +111,6 @@ async def get_search_type_tools(
                 node_name=node_name,
                 save_interaction=save_interaction,
                 system_prompt=system_prompt,
-                wide_search_top_k=wide_search_top_k,
-                triplet_distance_penalty=triplet_distance_penalty,
             ).get_context,
         ],
         SearchType.GRAPH_SUMMARY_COMPLETION: [
@@ -147,8 +121,6 @@ async def get_search_type_tools(
                 node_name=node_name,
                 save_interaction=save_interaction,
                 system_prompt=system_prompt,
-                wide_search_top_k=wide_search_top_k,
-                triplet_distance_penalty=triplet_distance_penalty,
             ).get_completion,
             GraphSummaryCompletionRetriever(
                 system_prompt_path=system_prompt_path,
@@ -157,10 +129,12 @@ async def get_search_type_tools(
                 node_name=node_name,
                 save_interaction=save_interaction,
                 system_prompt=system_prompt,
-                wide_search_top_k=wide_search_top_k,
-                triplet_distance_penalty=triplet_distance_penalty,
             ).get_context,
         ],
+        SearchType.CODE: [
+            CodeRetriever(top_k=top_k).get_completion,
+            CodeRetriever(top_k=top_k).get_context,
+        ],
         SearchType.CYPHER: [
             CypherSearchRetriever().get_completion,
             CypherSearchRetriever().get_context,
@@ -171,16 +145,8 @@ async def get_search_type_tools(
         ],
         SearchType.FEEDBACK: [UserQAFeedback(last_k=last_k).add_feedback],
         SearchType.TEMPORAL: [
-            TemporalRetriever(
-                top_k=top_k,
-                wide_search_top_k=wide_search_top_k,
-                triplet_distance_penalty=triplet_distance_penalty,
-            ).get_completion,
-            TemporalRetriever(
-                top_k=top_k,
-                wide_search_top_k=wide_search_top_k,
-                triplet_distance_penalty=triplet_distance_penalty,
-            ).get_context,
+            TemporalRetriever(top_k=top_k).get_completion,
+            TemporalRetriever(top_k=top_k).get_context,
         ],
         SearchType.CHUNKS_LEXICAL: (
             lambda _r=JaccardChunksRetriever(top_k=top_k): [
@@ -203,19 +169,7 @@ async def get_search_type_tools(
     ):
         raise UnsupportedSearchTypeError("Cypher query search types are disabled.")
 
-    from cognee.modules.retrieval.registered_community_retrievers import (
-        registered_community_retrievers,
-    )
-
-    if query_type in registered_community_retrievers:
-        retriever = registered_community_retrievers[query_type]
-        retriever_instance = retriever(top_k=top_k)
-        search_type_tools = [
-            retriever_instance.get_completion,
-            retriever_instance.get_context,
-        ]
-    else:
-        search_type_tools = search_tasks.get(query_type)
+    search_type_tools = search_tasks.get(query_type)
 
     if not search_type_tools:
         raise UnsupportedSearchTypeError(str(query_type))

cognee/modules/search/methods/no_access_control_search.py

@@ -24,8 +24,6 @@ async def no_access_control_search(
     last_k: Optional[int] = None,
     only_context: bool = False,
     session_id: Optional[str] = None,
-    wide_search_top_k: Optional[int] = 100,
-    triplet_distance_penalty: Optional[float] = 3.5,
 ) -> Tuple[Any, Union[str, List[Edge]], List[Dataset]]:
     search_tools = await get_search_type_tools(
         query_type=query_type,
@@ -37,8 +35,6 @@ async def no_access_control_search(
         node_name=node_name,
         save_interaction=save_interaction,
         last_k=last_k,
-        wide_search_top_k=wide_search_top_k,
-        triplet_distance_penalty=triplet_distance_penalty,
     )
     graph_engine = await get_graph_engine()
     is_empty = await graph_engine.is_empty()

cognee/modules/search/methods/search.py

@@ -47,8 +47,6 @@ async def search(
     only_context: bool = False,
     use_combined_context: bool = False,
     session_id: Optional[str] = None,
-    wide_search_top_k: Optional[int] = 100,
-    triplet_distance_penalty: Optional[float] = 3.5,
 ) -> Union[CombinedSearchResult, List[SearchResult]]:
     """
 
@@ -92,8 +90,6 @@ async def search(
             only_context=only_context,
             use_combined_context=use_combined_context,
             session_id=session_id,
-            wide_search_top_k=wide_search_top_k,
-            triplet_distance_penalty=triplet_distance_penalty,
         )
     else:
         search_results = [
@@ -109,8 +105,6 @@ async def search(
                 last_k=last_k,
                 only_context=only_context,
                 session_id=session_id,
-                wide_search_top_k=wide_search_top_k,
-                triplet_distance_penalty=triplet_distance_penalty,
             )
         ]
 
@@ -225,8 +219,6 @@ async def authorized_search(
     only_context: bool = False,
     use_combined_context: bool = False,
     session_id: Optional[str] = None,
-    wide_search_top_k: Optional[int] = 100,
-    triplet_distance_penalty: Optional[float] = 3.5,
 ) -> Union[
     Tuple[Any, Union[List[Edge], str], List[Dataset]],
     List[Tuple[Any, Union[List[Edge], str], List[Dataset]]],
@@ -254,8 +246,6 @@ async def authorized_search(
             last_k=last_k,
             only_context=True,
             session_id=session_id,
-            wide_search_top_k=wide_search_top_k,
-            triplet_distance_penalty=triplet_distance_penalty,
         )
 
         context = {}
@@ -277,8 +267,6 @@ async def authorized_search(
             node_name=node_name,
             save_interaction=save_interaction,
             last_k=last_k,
-            wide_search_top_k=wide_search_top_k,
-            triplet_distance_penalty=triplet_distance_penalty,
         )
         search_tools = specific_search_tools
         if len(search_tools) == 2:
@@ -318,7 +306,6 @@ async def authorized_search(
         last_k=last_k,
         only_context=only_context,
         session_id=session_id,
-        wide_search_top_k=wide_search_top_k,
     )
 
     return search_results
@@ -338,8 +325,6 @@ async def search_in_datasets_context(
     only_context: bool = False,
     context: Optional[Any] = None,
     session_id: Optional[str] = None,
-    wide_search_top_k: Optional[int] = 100,
-    triplet_distance_penalty: Optional[float] = 3.5,
 ) -> List[Tuple[Any, Union[str, List[Edge]], List[Dataset]]]:
     """
     Searches all provided datasets and handles setting up of appropriate database context based on permissions.
@@ -360,8 +345,6 @@ async def search_in_datasets_context(
         only_context: bool = False,
         context: Optional[Any] = None,
         session_id: Optional[str] = None,
-        wide_search_top_k: Optional[int] = 100,
-        triplet_distance_penalty: Optional[float] = 3.5,
     ) -> Tuple[Any, Union[str, List[Edge]], List[Dataset]]:
         # Set database configuration in async context for each dataset user has access for
         await set_database_global_context_variables(dataset.id, dataset.owner_id)
@@ -395,8 +378,6 @@ async def search_in_datasets_context(
             node_name=node_name,
             save_interaction=save_interaction,
             last_k=last_k,
-            wide_search_top_k=wide_search_top_k,
-            triplet_distance_penalty=triplet_distance_penalty,
         )
         search_tools = specific_search_tools
         if len(search_tools) == 2:
@@ -432,8 +413,6 @@ async def search_in_datasets_context(
                 only_context=only_context,
                 context=context,
                 session_id=session_id,
-                wide_search_top_k=wide_search_top_k,
-                triplet_distance_penalty=triplet_distance_penalty,
             )
         )
 

cognee/modules/search/types/SearchType.py

@@ -5,9 +5,9 @@ class SearchType(Enum):
     SUMMARIES = "SUMMARIES"
     CHUNKS = "CHUNKS"
     RAG_COMPLETION = "RAG_COMPLETION"
-    TRIPLET_COMPLETION = "TRIPLET_COMPLETION"
     GRAPH_COMPLETION = "GRAPH_COMPLETION"
     GRAPH_SUMMARY_COMPLETION = "GRAPH_SUMMARY_COMPLETION"
+    CODE = "CODE"
     CYPHER = "CYPHER"
     NATURAL_LANGUAGE = "NATURAL_LANGUAGE"
     GRAPH_COMPLETION_COT = "GRAPH_COMPLETION_COT"

cognee/modules/settings/get_settings.py

@@ -16,7 +16,6 @@ class ModelName(Enum):
     anthropic = "anthropic"
     gemini = "gemini"
     mistral = "mistral"
-    bedrock = "bedrock"
 
 
 class LLMConfig(BaseModel):
@@ -78,10 +77,6 @@ def get_settings() -> SettingsDict:
             "value": "mistral",
             "label": "Mistral",
         },
-        {
-            "value": "bedrock",
-            "label": "Bedrock",
-        },
     ]
 
     return SettingsDict.model_validate(
@@ -162,20 +157,6 @@ def get_settings() -> SettingsDict:
                             "label": "Mistral Large 2.1",
                         },
                     ],
-                    "bedrock": [
-                        {
-                            "value": "eu.anthropic.claude-sonnet-4-5-20250929-v1:0",
-                            "label": "Claude 4.5 Sonnet",
-                        },
-                        {
-                            "value": "eu.anthropic.claude-haiku-4-5-20251001-v1:0",
-                            "label": "Claude 4.5 Haiku",
-                        },
-                        {
-                            "value": "eu.amazon.nova-lite-v1:0",
-                            "label": "Amazon Nova Lite",
-                        },
-                    ],
                 },
             },
             vector_db={

cognee/modules/users/methods/get_authenticated_user.py

@@ -12,8 +12,8 @@ logger = get_logger("get_authenticated_user")
 
 # Check environment variable to determine authentication requirement
 REQUIRE_AUTHENTICATION = (
-    os.getenv("REQUIRE_AUTHENTICATION", "true").lower() == "true"
-    or os.environ.get("ENABLE_BACKEND_ACCESS_CONTROL", "true").lower() == "true"
+    os.getenv("REQUIRE_AUTHENTICATION", "false").lower() == "true"
+    or backend_access_control_enabled()
 )
 
 fastapi_users = get_fastapi_users()

cognee/modules/users/models/DatasetDatabase.py

@@ -1,6 +1,6 @@
 from datetime import datetime, timezone
 
-from sqlalchemy import Column, DateTime, String, UUID, ForeignKey, JSON, text
+from sqlalchemy import Column, DateTime, String, UUID, ForeignKey
 from cognee.infrastructure.databases.relational import Base
 
 
@@ -12,29 +12,17 @@ class DatasetDatabase(Base):
         UUID, ForeignKey("datasets.id", ondelete="CASCADE"), primary_key=True, index=True
     )
 
-    vector_database_name = Column(String, unique=False, nullable=False)
-    graph_database_name = Column(String, unique=False, nullable=False)
+    vector_database_name = Column(String, unique=True, nullable=False)
+    graph_database_name = Column(String, unique=True, nullable=False)
 
     vector_database_provider = Column(String, unique=False, nullable=False)
     graph_database_provider = Column(String, unique=False, nullable=False)
 
-    graph_dataset_database_handler = Column(String, unique=False, nullable=False)
-    vector_dataset_database_handler = Column(String, unique=False, nullable=False)
-
     vector_database_url = Column(String, unique=False, nullable=True)
     graph_database_url = Column(String, unique=False, nullable=True)
 
     vector_database_key = Column(String, unique=False, nullable=True)
     graph_database_key = Column(String, unique=False, nullable=True)
 
-    # configuration details for different database types. This would make it more flexible to add new database types
-    # without changing the database schema.
-    graph_database_connection_info = Column(
-        JSON, unique=False, nullable=False, server_default=text("'{}'")
-    )
-    vector_database_connection_info = Column(
-        JSON, unique=False, nullable=False, server_default=text("'{}'")
-    )
-
     created_at = Column(DateTime(timezone=True), default=lambda: datetime.now(timezone.utc))
     updated_at = Column(DateTime(timezone=True), onupdate=lambda: datetime.now(timezone.utc))

cognee/shared/logging_utils.py

@@ -534,10 +534,6 @@ def setup_logging(log_level=None, name=None):
     # Get a configured logger and log system information
     logger = structlog.get_logger(name if name else __name__)
 
-    logger.warning(
-        "From version 0.5.0 onwards, Cognee will run with multi-user access control mode set to on by default. Data isolation between different users and datasets will be enforced and data created before multi-user access control mode was turned on won't be accessible by default. To disable multi-user access control mode and regain access to old data set the environment variable ENABLE_BACKEND_ACCESS_CONTROL to false before starting Cognee. For more information, please refer to the Cognee documentation."
-    )
-
     if logs_dir is not None:
         logger.info(f"Log file created at: {log_file_path}", log_file=log_file_path)
 

cognee/tasks/code/enrich_dependency_graph_checker.py

@@ -0,0 +1,35 @@
+import os
+import asyncio
+import argparse
+from cognee.tasks.repo_processor.get_repo_file_dependencies import get_repo_file_dependencies
+from cognee.tasks.repo_processor.enrich_dependency_graph import enrich_dependency_graph
+
+
+def main():
+    """
+    Execute the main logic of the dependency graph processor.
+
+    This function sets up argument parsing to retrieve the repository path, checks the
+    existence of the specified path, and processes the repository to produce a dependency
+    graph. If the repository path does not exist, it logs an error message and terminates
+    without further execution.
+    """
+    parser = argparse.ArgumentParser()
+    parser.add_argument("repo_path", help="Path to the repository")
+    args = parser.parse_args()
+
+    repo_path = args.repo_path
+    if not os.path.exists(repo_path):
+        print(f"Error: The provided repository path does not exist: {repo_path}")
+        return
+
+    graph = asyncio.run(get_repo_file_dependencies(repo_path))
+    graph = asyncio.run(enrich_dependency_graph(graph))
+    for node in graph.nodes:
+        print(f"Node: {node}")
+        for _, target, data in graph.out_edges(node, data=True):
+            print(f"  Edge to {target}, data: {data}")
+
+
+if __name__ == "__main__":
+    main()