Fix test with new required body, remove print statements and add check

.pre-commit-config.yaml

@@ -17,6 +17,15 @@ repos:
         types: [python]
         pass_filenames: false
 
+  - repo: local
+    hooks:
+      - id: check-print-statements
+        name: Check for print statements
+        entry: bash -c 'echo "Checking for print statements..." && find . -name "*.py" ! -path "./py/cli/*" ! -path "./py/core/examples/*" ! -path "./py/migrations/*" ! -path "./py/tests/*" | xargs grep -n "print(" || exit 0 && echo "Found print statements!" && exit 1'
+        language: system
+        types: [python]
+        pass_filenames: false
+
   - repo: local
     hooks:
       - id: isort

js/sdk/__tests__/DocumentsAndCollectionsIntegrationUser.test.ts

@@ -114,7 +114,7 @@ describe("r2rClient V3 System Integration Tests User", () => {
 
     expect(response.results.document_id).toBeDefined();
     user1DocumentId = response.results.document_id;
-  }, 10000);
+  }, 15000);
 
   test("Create document as user 2 with file path", async () => {
     const response = await user2Client.documents.create({
@@ -126,7 +126,7 @@ describe("r2rClient V3 System Integration Tests User", () => {
 
     expect(response.results.document_id).toBeDefined();
     user2DocumentId = response.results.document_id;
-  }, 10000);
+  }, 15000);
 
   test("Retrieve document as user 1", async () => {
     const response = await user1Client.documents.retrieve({

js/sdk/__tests__/GraphsIntegrationSuperUser.test.ts

@@ -228,6 +228,7 @@ describe("r2rClient V3 Graphs Integration Tests", () => {
       predicate: "falls in love with",
       object: "Dunia",
       objectId: entity2Id,
+      description: "Razumikhn and Dunia are central to the story",
     });
 
     relationshipId = response.results.id;
@@ -236,6 +237,7 @@ describe("r2rClient V3 Graphs Integration Tests", () => {
     expect(response.results.subject).toBe("Razumikhin");
     expect(response.results.object).toBe("Dunia");
     expect(response.results.predicate).toBe("falls in love with");
+    expect(response.results.description).toBe("Razumikhn and Dunia are central to the story");
   });
 
   test("Retrieve the relationship", async () => {

js/sdk/src/v3/clients/graphs.ts

@@ -233,7 +233,7 @@ export class GraphsClient {
     predicate: string;
     object: string;
     objectId: string;
-    description?: string;
+    description: string;
     weight?: number;
     metadata?: Record<string, any>;
   }): Promise<WrappedRelationshipResponse> {
@@ -243,7 +243,7 @@ export class GraphsClient {
       predicate: options.predicate,
       object: options.object,
       object_id: options.objectId,
-      ...(options.description && { description: options.description }),
+      description: options.description,
       ...(options.weight && { weight: options.weight }),
       ...(options.metadata && { metadata: options.metadata }),
     };

py/core/main/api/v3/chunks_router.py

@@ -324,7 +324,7 @@ async def delete_chunk(
             """
             # Get the existing chunk to get its chunk_id
             existing_chunk = await self.services["ingestion"].get_chunk(id)
-            print("existing_chunk = ", existing_chunk)
+
             if existing_chunk is None:
                 raise R2RException(
                     message=f"Chunk {id} not found", status_code=404

py/core/main/api/v3/conversations_router.py

@@ -276,7 +276,6 @@ async def get_conversation(
                 str(id),
                 branch_id,
             )
-            print("conversation", conversation)
             return conversation
 
         @self.router.delete(

py/core/main/api/v3/indices_router.py

@@ -258,13 +258,6 @@ async def create_index(
                                 offset=0,
                                 limit=10
                             )
-
-                            # Print index details
-                            for idx in indices:
-                                print(f"Index: {idx['name']}")
-                                print(f"Method: {idx['method']}")
-                                print(f"Size: {idx['size_bytes'] / 1024 / 1024:.2f} MB")
-                                print(f"Row count: {idx['row_count']}")
                             """
                         ),
                     },
@@ -363,11 +356,6 @@ async def list_indices(
 
                             # Get detailed information about a specific index
                             index = client.indices.retrieve("index_1")
-
-                            # Access index details
-                            print(f"Index Method: {index['method']}")
-                            print(f"Parameters: {index['parameters']}")
-                            print(f"Performance Stats: {index['stats']}")
                             """
                         ),
                     },

py/core/main/orchestration/hatchet/kg_workflow.py

@@ -197,10 +197,6 @@ async def kg_extract(self, context: Context) -> dict:
                     document_id=document_id,
                     **input_data["graph_creation_settings"],
                 ):
-                    print(
-                        "found extraction w/ entities = = ",
-                        len(extraction.entities),
-                    )
                     extractions.append(extraction)
                 await service.store_kg_extractions(extractions)
 
@@ -283,7 +279,6 @@ def __init__(self, kg_service: KgService):
         @orchestration_provider.step(retries=1)
         async def kg_extraction(self, context: Context) -> dict:
             request = context.workflow_input()["request"]
-            print('context.workflow_input()["request"] = ', request)
 
             input_data = get_input_data_dict(request)
             document_id = input_data.get("document_id", None)
@@ -299,7 +294,6 @@ async def kg_extraction(self, context: Context) -> dict:
                 workflows = []
 
                 for document_id in document_ids:
-                    print("extracting = ", document_id)
                     input_data_copy = input_data.copy()
                     input_data_copy["collection_id"] = str(
                         input_data_copy["collection_id"]

py/core/main/services/kg_service.py

@@ -1041,11 +1041,11 @@ async def parse_fn(response_str: str) -> Any:
                 if attempt < retries - 1:
                     await asyncio.sleep(delay)
                 else:
-                    print(
+                    logger.warning(
                         f"Failed after retries with for chunk {chunks[0].id} of document {chunks[0].document_id}: {e}"
                     )
 
-        print(
+        logger.info(
             f"KGExtractionPipe: Completed task number {task_id} of {total_tasks} for document {chunks[0].document_id}",
         )
 

py/core/main/services/management_service.py

@@ -309,7 +309,6 @@ def transform_chunk_id_to_id(
             vector_delete_results = await self.providers.database.delete(
                 filters_xf
             )
-            print("vector_delete_results = ", vector_delete_results)
         except Exception as e:
             logger.error(f"Error deleting from vector database: {e}")
             vector_delete_results = {}

py/core/providers/database/graph.py

@@ -2246,7 +2246,7 @@ async def get_entity_map(
                 )
 
         return entity_map
-        
+
     async def graph_search(
         self, query: str, **kwargs: Any
     ) -> AsyncGenerator[Any, None]:

py/core/providers/database/postgres.py

@@ -233,7 +233,6 @@ def _get_postgres_configuration_settings(
             if value is None:
                 value = os.getenv(env_var)
 
-            print(f"Setting: {setting}, Value: {value}")
             if value is not None:
                 field_type = settings.__annotations__[setting]
                 if field_type == Optional[int]:

py/sdk/v3/documents.py

@@ -147,7 +147,6 @@ async def download(
             version="v3",
             # No json parsing here, if possible
         )
-        print(response)
         if not isinstance(response, BytesIO):
             raise ValueError("Expected BytesIO response")
         return response

py/tests/integration/runner_user_documents_collections.py

@@ -4,7 +4,7 @@
 import time
 import uuid
 from dataclasses import dataclass
-from typing import List, Optional
+from typing import Optional
 
 from r2r import R2RClient, R2RException
 
@@ -39,7 +39,7 @@ def create_test_user(base_url: str) -> TestUser:
 
 
 def create_test_document(
-    client: R2RClient, content: str, collection_ids: List[str] = None
+    client: R2RClient, content: str, collection_ids: list[str] = None
 ) -> str:
     """Create a test document and return its ID"""
     response = client.documents.create(