perf: build info log messages lazily so raising the log level actually saves work (#27837)

Raising GLOBAL_LOG_LEVEL to WARNING buys quieter output but not less work: 241 INFO call sites interpolate their payload into an f-string before the logging call gets to drop it. The heaviest is get_doc, which logs every chunk id and metadata dict in a collection, so on the full-context retrieval path that is the entire knowledge base, once per chat request.

That one line at WARNING, CPython 3.12:

| knowledge base | payload | before   | after   |
| -------------- | ------- | -------- | ------- |
| top-k of 3     | 1.2 kB  | 3.8 us   | 0.07 us |
| 500 chunks     | 201 kB  | 583.6 us | 0.08 us |
| 5000 chunks    | 2.0 MB  | 5.8 ms   | 0.15 us |

The lazy form log.info('query_doc:result %s %s', result.ids, result.metadatas) hands the payload to record.getMessage(), which the InterceptHandler only reaches once a record has passed the level check. Output at INFO is byte-identical. Two sites that already built their message eagerly, one str concat and one % operator, move to the same lazy form.

backend/open_webui/retrieval/vector/dbs/milvus.py

@@ -125,7 +125,7 @@ class MilvusClient(VectorDBBase):
         index_type = MILVUS_INDEX_TYPE.upper()
         metric_type = MILVUS_METRIC_TYPE.upper()
 
-        log.info(f'Using Milvus index type: {index_type}, metric type: {metric_type}')
+        log.info('Using Milvus index type: %s, metric type: %s', index_type, metric_type)
 
         index_creation_params = {}
         if index_type == 'HNSW':
@@ -133,18 +133,18 @@ class MilvusClient(VectorDBBase):
                 'M': MILVUS_HNSW_M,
                 'efConstruction': MILVUS_HNSW_EFCONSTRUCTION,
             }
-            log.info(f'HNSW params: {index_creation_params}')
+            log.info('HNSW params: %s', index_creation_params)
         elif index_type == 'IVF_FLAT':
             index_creation_params = {'nlist': MILVUS_IVF_FLAT_NLIST}
-            log.info(f'IVF_FLAT params: {index_creation_params}')
+            log.info('IVF_FLAT params: %s', index_creation_params)
         elif index_type == 'DISKANN':
             index_creation_params = {
                 'max_degree': MILVUS_DISKANN_MAX_DEGREE,
                 'search_list_size': MILVUS_DISKANN_SEARCH_LIST_SIZE,
             }
-            log.info(f'DISKANN params: {index_creation_params}')
+            log.info('DISKANN params: %s', index_creation_params)
         elif index_type in ['FLAT', 'AUTOINDEX']:
-            log.info(f'Using {index_type} index with no specific build-time params.')
+            log.info('Using %s index with no specific build-time params.', index_type)
         else:
             log.warning(
                 f"Unsupported MILVUS_INDEX_TYPE: '{index_type}'. "
@@ -167,7 +167,11 @@ class MilvusClient(VectorDBBase):
             index_params=index_params,
         )
         log.info(
-            f"Successfully created collection '{self.collection_prefix}_{collection_name}' with index type '{index_type}' and metric '{metric_type}'."
+            "Successfully created collection '%s_%s' with index type '%s' and metric '%s'.",
+            self.collection_prefix,
+            collection_name,
+            index_type,
+            metric_type,
         )
 
     def has_collection(self, collection_name: str) -> bool:
@@ -220,7 +224,11 @@ class MilvusClient(VectorDBBase):
 
         try:
             log.info(
-                f"Querying collection {self.collection_prefix}_{collection_name} with filter: '{filter_string}', limit: {limit}"
+                "Querying collection %s_%s with filter: '%s', limit: %s",
+                self.collection_prefix,
+                collection_name,
+                filter_string,
+                limit,
             )
 
             iterator = self.client.query_iterator(
@@ -265,7 +273,7 @@ class MilvusClient(VectorDBBase):
         # Insert the items into the collection, if the collection does not exist, it will be created.
         collection_name = collection_name.replace('-', '_')
         if not self.client.has_collection(collection_name=f'{self.collection_prefix}_{collection_name}'):
-            log.info(f'Collection {self.collection_prefix}_{collection_name} does not exist. Creating now.')
+            log.info('Collection %s_%s does not exist. Creating now.', self.collection_prefix, collection_name)
             if not items:
                 log.error(
                     f'Cannot create collection {self.collection_prefix}_{collection_name} without items to determine dimension.'
@@ -273,7 +281,7 @@ class MilvusClient(VectorDBBase):
                 raise ValueError('Cannot create Milvus collection without items to determine vector dimension.')
             self._create_collection(collection_name=collection_name, dimension=len(items[0]['vector']))
 
-        log.info(f'Inserting {len(items)} items into collection {self.collection_prefix}_{collection_name}.')
+        log.info('Inserting %s items into collection %s_%s.', len(items), self.collection_prefix, collection_name)
         data = []
         for item in items:
             text = item['text'] or ''
@@ -301,7 +309,9 @@ class MilvusClient(VectorDBBase):
         # Update the items in the collection, if the items are not present, insert them. If the collection does not exist, it will be created.
         collection_name = collection_name.replace('-', '_')
         if not self.client.has_collection(collection_name=f'{self.collection_prefix}_{collection_name}'):
-            log.info(f'Collection {self.collection_prefix}_{collection_name} does not exist for upsert. Creating now.')
+            log.info(
+                'Collection %s_%s does not exist for upsert. Creating now.', self.collection_prefix, collection_name
+            )
             if not items:
                 log.error(
                     f'Cannot create collection {self.collection_prefix}_{collection_name} for upsert without items to determine dimension.'
@@ -311,7 +321,7 @@ class MilvusClient(VectorDBBase):
                 )
             self._create_collection(collection_name=collection_name, dimension=len(items[0]['vector']))
 
-        log.info(f'Upserting {len(items)} items into collection {self.collection_prefix}_{collection_name}.')
+        log.info('Upserting %s items into collection %s_%s.', len(items), self.collection_prefix, collection_name)
         data = []
         for item in items:
             text = item['text'] or ''
@@ -348,7 +358,7 @@ class MilvusClient(VectorDBBase):
             return None
 
         if ids:
-            log.info(f'Deleting items by IDs from {self.collection_prefix}_{collection_name}. IDs: {ids}')
+            log.info('Deleting items by IDs from %s_%s. IDs: %s', self.collection_prefix, collection_name, ids)
             return self.client.delete(
                 collection_name=f'{self.collection_prefix}_{collection_name}',
                 ids=ids,
@@ -356,7 +366,10 @@ class MilvusClient(VectorDBBase):
         elif filter:
             filter_string = ' && '.join([f'metadata["{key}"] == {JSONCodec.dumps(value)}' for key, value in filter.items()])
             log.info(
-                f'Deleting items by filter from {self.collection_prefix}_{collection_name}. Filter: {filter_string}'
+                'Deleting items by filter from %s_%s. Filter: %s',
+                self.collection_prefix,
+                collection_name,
+                filter_string,
             )
             return self.client.delete(
                 collection_name=f'{self.collection_prefix}_{collection_name}',
@@ -378,7 +391,7 @@ class MilvusClient(VectorDBBase):
                 try:
                     self.client.drop_collection(collection_name=collection_name_full)
                     deleted_collections.append(collection_name_full)
-                    log.info(f'Deleted collection: {collection_name_full}')
+                    log.info('Deleted collection: %s', collection_name_full)
                 except Exception as e:
                     log.error(f'Error deleting collection {collection_name_full}: {e}')
-        log.info(f'Milvus reset complete. Deleted collections: {deleted_collections}')
+        log.info('Milvus reset complete. Deleted collections: %s', deleted_collections)

backend/open_webui/retrieval/vector/dbs/milvus_multitenancy.py

@@ -146,7 +146,7 @@ class MilvusClient(VectorDBBase):
                 # The index only accelerates resource_id filters; never fail
                 # collection creation over it.
                 log.warning(f'Could not create {RESOURCE_ID_FIELD} index on {mt_collection_name}: {e}')
-        log.info(f'Created shared collection: {mt_collection_name}')
+        log.info('Created shared collection: %s', mt_collection_name)
 
     def _ensure_collection(self, mt_collection_name: str, dimension: int):
         if not self.client.has_collection(mt_collection_name):

backend/open_webui/retrieval/vector/dbs/opengauss.py

@@ -181,7 +181,7 @@ class OpenGaussClient(VectorDBBase):
                 new_items.append(new_chunk)
             self.session.bulk_save_objects(new_items)
             self.session.commit()
-            log.info(f"Inserting {len(new_items)} items into collection '{collection_name}'.")
+            log.info("Inserting %s items into collection '%s'.", len(new_items), collection_name)
         except Exception as e:
             self.session.rollback()
             log.exception(f'Failed to insert data: {e}')
@@ -207,7 +207,7 @@ class OpenGaussClient(VectorDBBase):
                     )
                     self.session.add(new_chunk)
             self.session.commit()
-            log.info(f"Inserting/updating {len(items)} items in collection '{collection_name}'.")
+            log.info("Inserting/updating %s items in collection '%s'.", len(items), collection_name)
         except Exception as e:
             self.session.rollback()
             log.exception(f'Failed to insert or update data.: {e}')
@@ -352,7 +352,7 @@ class OpenGaussClient(VectorDBBase):
                     query = query.filter(DocumentChunk.vmetadata[key].astext == str(value))
             deleted = query.delete(synchronize_session=False)
             self.session.commit()
-            log.info(f"Deleted {deleted} items from collection '{collection_name}'")
+            log.info("Deleted %s items from collection '%s'", deleted, collection_name)
         except Exception as e:
             self.session.rollback()
             log.exception(f'Failed to delete data: {e}')
@@ -362,7 +362,7 @@ class OpenGaussClient(VectorDBBase):
         try:
             deleted = self.session.query(DocumentChunk).delete()
             self.session.commit()
-            log.info(f'Reset completed. Deleted {deleted} items')
+            log.info('Reset completed. Deleted %s items', deleted)
         except Exception as e:
             self.session.rollback()
             log.exception(f'Reset failed: {e}')
@@ -386,4 +386,4 @@ class OpenGaussClient(VectorDBBase):
 
     def delete_collection(self, collection_name: str) -> None:
         self.delete(collection_name)
-        log.info(f"Collection '{collection_name}' has been deleted")
+        log.info("Collection '%s' has been deleted", collection_name)

backend/open_webui/retrieval/vector/dbs/oracle23ai.py

@@ -94,10 +94,10 @@ class Oracle23aiClient(VectorDBBase):
                 self._create_dbcs_pool()
 
             dsn = ORACLE_DB_DSN
-            log.info(f'Creating Connection Pool [{ORACLE_DB_USER}:**@{dsn}]')
+            log.info('Creating Connection Pool [%s:**@%s]', ORACLE_DB_USER, dsn)
 
             with self.get_connection() as connection:
-                log.info(f'Connection version: {connection.version}')
+                log.info('Connection version: %s', connection.version)
                 self._initialize_database(connection)
 
             log.info('Oracle Vector Search initialization complete.')
@@ -159,7 +159,7 @@ class Oracle23aiClient(VectorDBBase):
 
                 if attempt < max_retries - 1:
                     wait_time = 2**attempt
-                    log.info(f'Retrying in {wait_time} seconds...')
+                    log.info('Retrying in %s seconds...', wait_time)
                     time.sleep(wait_time)
                 else:
                     raise
@@ -184,7 +184,7 @@ class Oracle23aiClient(VectorDBBase):
 
         thread = threading.Thread(target=_monitor, daemon=True)
         thread.start()
-        log.info(f'Started DB health monitor every {interval_seconds} seconds.')
+        log.info('Started DB health monitor every %s seconds.', interval_seconds)
 
     def _reconnect_pool(self):
         """
@@ -412,7 +412,7 @@ class Oracle23aiClient(VectorDBBase):
             ... ]
             >>> client.insert("my_collection", items)
         """
-        log.info(f"Inserting {len(items)} items into collection '{collection_name}'.")
+        log.info("Inserting %s items into collection '%s'.", len(items), collection_name)
 
         with self.get_connection() as connection:
             try:
@@ -437,7 +437,7 @@ class Oracle23aiClient(VectorDBBase):
                         )
 
                 connection.commit()
-                log.info(f"Successfully inserted {len(items)} items into collection '{collection_name}'.")
+                log.info("Successfully inserted %s items into collection '%s'.", len(items), collection_name)
 
             except Exception as e:
                 connection.rollback()
@@ -466,7 +466,7 @@ class Oracle23aiClient(VectorDBBase):
             ... ]
             >>> client.upsert("my_collection", items)
         """
-        log.info(f"Upserting {len(items)} items into collection '{collection_name}'.")
+        log.info("Upserting %s items into collection '%s'.", len(items), collection_name)
 
         with self.get_connection() as connection:
             try:
@@ -505,7 +505,7 @@ class Oracle23aiClient(VectorDBBase):
                         )
 
                 connection.commit()
-                log.info(f"Successfully upserted {len(items)} items into collection '{collection_name}'.")
+                log.info("Successfully upserted %s items into collection '%s'.", len(items), collection_name)
 
             except Exception as e:
                 connection.rollback()
@@ -541,7 +541,7 @@ class Oracle23aiClient(VectorDBBase):
             ...     for i, (id, dist) in enumerate(zip(results.ids[0], results.distances[0])):
             ...         log.info(f"Match {i+1}: id={id}, distance={dist}")
         """
-        log.info(f"Searching items from collection '{collection_name}' with limit {limit}.")
+        log.info("Searching items from collection '%s' with limit %s.", collection_name, limit)
 
         try:
             if not vectors:
@@ -587,7 +587,7 @@ class Oracle23aiClient(VectorDBBase):
                             metadatas[qid].append(self._json_to_metadata(metadata_str))
                             distances[qid].append(float(row[3]))
 
-            log.info(f'Search completed. Found {sum(len(ids[i]) for i in range(num_queries))} total results.')
+            log.info('Search completed. Found %s total results.', sum(len(ids[i]) for i in range(num_queries)))
 
             return SearchResult(ids=ids, distances=distances, documents=documents, metadatas=metadatas)
 
@@ -616,7 +616,7 @@ class Oracle23aiClient(VectorDBBase):
             >>> if results:
             ...     print(f"Found {len(results.ids[0])} matching documents")
         """
-        log.info(f"Querying items from collection '{collection_name}' with filters.")
+        log.info("Querying items from collection '%s' with filters.", collection_name)
 
         try:
             limit = limit or 100
@@ -656,7 +656,7 @@ class Oracle23aiClient(VectorDBBase):
                 ]
             ]
 
-            log.info(f'Query completed. Found {len(results)} results.')
+            log.info('Query completed. Found %s results.', len(results))
 
             return GetResult(ids=ids, documents=documents, metadatas=metadatas)
 
@@ -747,7 +747,7 @@ class Oracle23aiClient(VectorDBBase):
             >>> # Or delete by metadata filter
             >>> client.delete("my_collection", filter={"source": "deprecated_source"})
         """
-        log.info(f"Deleting items from collection '{collection_name}'.")
+        log.info("Deleting items from collection '%s'.", collection_name)
 
         try:
             query = 'DELETE FROM document_chunk WHERE collection_name = :collection_name'
@@ -772,7 +772,7 @@ class Oracle23aiClient(VectorDBBase):
                     deleted = cursor.rowcount
                 connection.commit()
 
-            log.info(f"Deleted {deleted} items from collection '{collection_name}'.")
+            log.info("Deleted %s items from collection '%s'.", deleted, collection_name)
 
         except Exception as e:
             log.exception(f'Error during delete: {e}')
@@ -800,7 +800,7 @@ class Oracle23aiClient(VectorDBBase):
                     deleted = cursor.rowcount
                 connection.commit()
 
-            log.info(f"Reset complete. Deleted {deleted} items from 'document_chunk' table.")
+            log.info("Reset complete. Deleted %s items from 'document_chunk' table.", deleted)
 
         except Exception as e:
             log.exception(f'Error during reset: {e}')
@@ -875,7 +875,7 @@ class Oracle23aiClient(VectorDBBase):
             >>> client = Oracle23aiClient()
             >>> client.delete_collection("obsolete_collection")
         """
-        log.info(f"Deleting collection '{collection_name}'.")
+        log.info("Deleting collection '%s'.", collection_name)
 
         try:
             with self.get_connection() as connection:
@@ -891,7 +891,7 @@ class Oracle23aiClient(VectorDBBase):
                     deleted = cursor.rowcount
                 connection.commit()
 
-            log.info(f"Collection '{collection_name}' deleted. Removed {deleted} items.")
+            log.info("Collection '%s' deleted. Removed %s items.", collection_name, deleted)
 
         except Exception as e:
             log.exception(f"Error deleting collection '{collection_name}': {e}")

backend/open_webui/retrieval/vector/dbs/pgvector.py

@@ -326,7 +326,7 @@ class PgvectorClient(VectorDBBase):
                         },
                     )
                 self.session.commit()
-                log.info(f"Encrypted & inserted {len(items)} into '{collection_name}'")
+                log.info("Encrypted & inserted %s into '%s'", len(items), collection_name)
 
             else:
                 new_items = []
@@ -342,7 +342,7 @@ class PgvectorClient(VectorDBBase):
                     new_items.append(new_chunk)
                 self.session.bulk_save_objects(new_items)
                 self.session.commit()
-                log.info(f"Inserted {len(new_items)} items into collection '{collection_name}'.")
+                log.info("Inserted %s items into collection '%s'.", len(new_items), collection_name)
         except Exception as e:
             self.session.rollback()
             log.exception(f'Error during insert: {e}')
@@ -381,7 +381,7 @@ class PgvectorClient(VectorDBBase):
                         },
                     )
                 self.session.commit()
-                log.info(f"Encrypted & upserted {len(items)} into '{collection_name}'")
+                log.info("Encrypted & upserted %s into '%s'", len(items), collection_name)
             else:
                 for item in items:
                     vector = self.adjust_vector_length(item['vector'])
@@ -401,7 +401,7 @@ class PgvectorClient(VectorDBBase):
                         )
                         self.session.add(new_chunk)
                 self.session.commit()
-                log.info(f"Upserted {len(items)} items into collection '{collection_name}'.")
+                log.info("Upserted %s items into collection '%s'.", len(items), collection_name)
         except Exception as e:
             self.session.rollback()
             log.exception(f'Error during upsert: {e}')
@@ -712,7 +712,7 @@ class PgvectorClient(VectorDBBase):
                         query = query.filter(DocumentChunk.vmetadata[key].astext == str(value))
                 deleted = query.delete(synchronize_session=False)
             self.session.commit()
-            log.info(f"Deleted {deleted} items from collection '{collection_name}'.")
+            log.info("Deleted %s items from collection '%s'.", deleted, collection_name)
         except Exception as e:
             self.session.rollback()
             log.exception(f'Error during delete: {e}')
@@ -722,7 +722,7 @@ class PgvectorClient(VectorDBBase):
         try:
             deleted = self.session.query(DocumentChunk).delete()
             self.session.commit()
-            log.info(f"Reset complete. Deleted {deleted} items from 'document_chunk' table.")
+            log.info("Reset complete. Deleted %s items from 'document_chunk' table.", deleted)
         except Exception as e:
             self.session.rollback()
             log.exception(f'Error during reset: {e}')
@@ -746,4 +746,4 @@ class PgvectorClient(VectorDBBase):
 
     def delete_collection(self, collection_name: str) -> None:
         self.delete(collection_name)
-        log.info(f"Collection '{collection_name}' deleted.")
+        log.info("Collection '%s' deleted.", collection_name)

backend/open_webui/retrieval/vector/dbs/pinecone.py

@@ -106,16 +106,16 @@ class PineconeClient(VectorDBBase):
         try:
             # Check if index exists
             if self.index_name not in self.client.list_indexes().names():
-                log.info(f"Creating Pinecone index '{self.index_name}'...")
+                log.info("Creating Pinecone index '%s'...", self.index_name)
                 self.client.create_index(
                     name=self.index_name,
                     dimension=self.dimension,
                     metric=self.metric,
                     spec=ServerlessSpec(cloud=self.cloud, region=self.environment),
                 )
-                log.info(f"Successfully created Pinecone index '{self.index_name}'")
+                log.info("Successfully created Pinecone index '%s'", self.index_name)
             else:
-                log.info(f"Using existing Pinecone index '{self.index_name}'")
+                log.info("Using existing Pinecone index '%s'", self.index_name)
 
             # Connect to the index
             self.index = self.client.Index(
@@ -245,7 +245,7 @@ class PineconeClient(VectorDBBase):
         collection_name_with_prefix = self._get_collection_name_with_prefix(collection_name)
         try:
             self.index.delete(filter={'collection_name': collection_name_with_prefix})
-            log.info(f"Collection '{collection_name_with_prefix}' deleted (all vectors removed).")
+            log.info("Collection '%s' deleted (all vectors removed).", collection_name_with_prefix)
         except Exception as e:
             log.warning(f"Failed to delete collection '{collection_name_with_prefix}': {e}")
             raise
@@ -276,7 +276,7 @@ class PineconeClient(VectorDBBase):
         elapsed = time.time() - start_time
         log.debug('Insert of %s vectors took %.2f seconds', len(points), elapsed)
         log.info(
-            f"Successfully inserted {len(points)} vectors in parallel batches into '{collection_name_with_prefix}'"
+            "Successfully inserted %s vectors in parallel batches into '%s'", len(points), collection_name_with_prefix
         )
 
     def upsert(self, collection_name: str, items: List[VectorItem]) -> None:
@@ -305,7 +305,7 @@ class PineconeClient(VectorDBBase):
         elapsed = time.time() - start_time
         log.debug('Upsert of %s vectors took %.2f seconds', len(points), elapsed)
         log.info(
-            f"Successfully upserted {len(points)} vectors in parallel batches into '{collection_name_with_prefix}'"
+            "Successfully upserted %s vectors in parallel batches into '%s'", len(points), collection_name_with_prefix
         )
 
     async def insert_async(self, collection_name: str, items: List[VectorItem]) -> None:
@@ -326,7 +326,9 @@ class PineconeClient(VectorDBBase):
             if isinstance(result, Exception):
                 log.error(f'Error in async insert batch: {result}')
                 raise result
-        log.info(f"Successfully async inserted {len(points)} vectors in batches into '{collection_name_with_prefix}'")
+        log.info(
+            "Successfully async inserted %s vectors in batches into '%s'", len(points), collection_name_with_prefix
+        )
 
     async def upsert_async(self, collection_name: str, items: List[VectorItem]) -> None:
         """Async version of upsert using asyncio and run_in_executor for improved performance."""
@@ -346,7 +348,9 @@ class PineconeClient(VectorDBBase):
             if isinstance(result, Exception):
                 log.error(f'Error in async upsert batch: {result}')
                 raise result
-        log.info(f"Successfully async upserted {len(points)} vectors in batches into '{collection_name_with_prefix}'")
+        log.info(
+            "Successfully async upserted %s vectors in batches into '%s'", len(points), collection_name_with_prefix
+        )
 
     def search(
         self,
@@ -477,7 +481,7 @@ class PineconeClient(VectorDBBase):
                     log.debug(
                         "Deleted batch of %s vectors by ID from '%s'", len(batch_ids), collection_name_with_prefix
                     )
-                log.info(f"Successfully deleted {len(ids)} vectors by ID from '{collection_name_with_prefix}'")
+                log.info("Successfully deleted %s vectors by ID from '%s'", len(ids), collection_name_with_prefix)
 
             elif filter:
                 # Combine user filter with collection_name
@@ -486,7 +490,7 @@ class PineconeClient(VectorDBBase):
                     pinecone_filter.update(filter)
                 # Delete by metadata filter
                 self.index.delete(filter=pinecone_filter)
-                log.info(f"Successfully deleted vectors by filter from '{collection_name_with_prefix}'")
+                log.info("Successfully deleted vectors by filter from '%s'", collection_name_with_prefix)
 
             else:
                 log.warning('No ids or filter provided for delete operation')

backend/open_webui/retrieval/vector/dbs/qdrant.py

@@ -119,7 +119,7 @@ class QdrantClient(VectorDBBase):
                 on_disk=self.QDRANT_ON_DISK,
             ),
         )
-        log.info(f'collection {collection_name_with_prefix} successfully created!')
+        log.info('collection %s successfully created!', collection_name_with_prefix)
 
     def _create_collection_if_not_exists(self, collection_name, dimension):
         if not self.has_collection(collection_name=collection_name):

backend/open_webui/retrieval/vector/dbs/qdrant_multitenancy.py

@@ -148,7 +148,7 @@ class QdrantClient(VectorDBBase):
                 m=0,
             ),
         )
-        log.info(f'Multi-tenant collection {mt_collection_name} created with dimension {dimension}!')
+        log.info('Multi-tenant collection %s created with dimension %s!', mt_collection_name, dimension)
 
         self.client.create_payload_index(
             collection_name=mt_collection_name,

backend/open_webui/retrieval/vector/dbs/s3vector.py

@@ -36,7 +36,7 @@ class S3VectorClient(VectorDBBase):
         if self.bucket_name and self.region:
             try:
                 self.client = boto3.client('s3vectors', region_name=self.region)
-                log.info(f"S3Vector client initialized for bucket '{self.bucket_name}' in region '{self.region}'")
+                log.info("S3Vector client initialized for bucket '%s' in region '%s'", self.bucket_name, self.region)
             except Exception as e:
                 log.error(f'Failed to initialize S3Vector client: {e}')
                 self.client = None
@@ -70,7 +70,9 @@ class S3VectorClient(VectorDBBase):
                     ]
                 },
             )
-            log.info(f'Created S3 index: {index_name} (dim={dimension}, type={data_type}, metric={distance_metric})')
+            log.info(
+                'Created S3 index: %s (dim=%s, type=%s, metric=%s)', index_name, dimension, data_type, distance_metric
+            )
         except Exception as e:
             log.error(f"Error creating S3 index '{index_name}': {e}")
             raise
@@ -137,9 +139,9 @@ class S3VectorClient(VectorDBBase):
             return
 
         try:
-            log.info(f"Deleting collection '{collection_name}'")
+            log.info("Deleting collection '%s'", collection_name)
             self.client.delete_index(vectorBucketName=self.bucket_name, indexName=collection_name)
-            log.info(f"Successfully deleted collection '{collection_name}'")
+            log.info("Successfully deleted collection '%s'", collection_name)
         except Exception as e:
             log.error(f"Error deleting collection '{collection_name}': {e}")
             raise
@@ -156,7 +158,7 @@ class S3VectorClient(VectorDBBase):
 
         try:
             if not self.has_collection(collection_name):
-                log.info(f"Index '{collection_name}' does not exist. Creating index.")
+                log.info("Index '%s' does not exist. Creating index.", collection_name)
                 self._create_index(
                     index_name=collection_name,
                     dimension=dimension,
@@ -202,9 +204,11 @@ class S3VectorClient(VectorDBBase):
                     indexName=collection_name,
                     vectors=batch,
                 )
-                log.info(f"Inserted batch {i // batch_size + 1}: {len(batch)} vectors into index '{collection_name}'.")
+                log.info(
+                    "Inserted batch %s: %s vectors into index '%s'.", i // batch_size + 1, len(batch), collection_name
+                )
 
-            log.info(f"Completed insertion of {len(vectors)} vectors into index '{collection_name}'.")
+            log.info("Completed insertion of %s vectors into index '%s'.", len(vectors), collection_name)
         except Exception as e:
             log.error(f'Error inserting vectors: {e}')
             raise
@@ -218,11 +222,11 @@ class S3VectorClient(VectorDBBase):
             return
 
         dimension = len(items[0]['vector'])
-        log.info(f'Upsert dimension: {dimension}')
+        log.info('Upsert dimension: %s', dimension)
 
         try:
             if not self.has_collection(collection_name):
-                log.info(f"Index '{collection_name}' does not exist. Creating index for upsert.")
+                log.info("Index '%s' does not exist. Creating index for upsert.", collection_name)
                 self._create_index(
                     index_name=collection_name,
                     dimension=dimension,
@@ -264,10 +268,14 @@ class S3VectorClient(VectorDBBase):
                 batch = vectors[i : i + batch_size]
                 if i == 0:  # Log sample info for first batch only
                     log.info(
-                        f'Upserting batch 1: {len(batch)} vectors. First vector sample: key={batch[0]["key"]}, data_type={type(batch[0]["data"]["float32"])}, data_len={len(batch[0]["data"]["float32"])}'
+                        'Upserting batch 1: %s vectors. First vector sample: key=%s, data_type=%s, data_len=%s',
+                        len(batch),
+                        batch[0]['key'],
+                        type(batch[0]['data']['float32']),
+                        len(batch[0]['data']['float32']),
                     )
                 else:
-                    log.info(f'Upserting batch {i // batch_size + 1}: {len(batch)} vectors.')
+                    log.info('Upserting batch %s: %s vectors.', i // batch_size + 1, len(batch))
 
                 self.client.put_vectors(
                     vectorBucketName=self.bucket_name,
@@ -275,7 +283,7 @@ class S3VectorClient(VectorDBBase):
                     vectors=batch,
                 )
 
-            log.info(f"Completed upsert of {len(vectors)} vectors into index '{collection_name}'.")
+            log.info("Completed upsert of %s vectors into index '%s'.", len(vectors), collection_name)
         except Exception as e:
             log.error(f'Error upserting vectors: {e}')
             raise
@@ -300,7 +308,7 @@ class S3VectorClient(VectorDBBase):
             return None
 
         try:
-            log.info(f"Searching collection '{collection_name}' with {len(vectors)} query vectors, limit={limit}")
+            log.info("Searching collection '%s' with %s query vectors, limit=%s", collection_name, len(vectors), limit)
 
             # Initialize result lists
             all_ids = []
@@ -362,7 +370,7 @@ class S3VectorClient(VectorDBBase):
                 all_metadatas.append(query_metadatas)
                 all_distances.append(query_distances)
 
-            log.info(f'Search completed. Found results for {len(all_ids)} queries')
+            log.info('Search completed. Found results for %s queries', len(all_ids))
 
             # Return SearchResult format
             return SearchResult(
@@ -402,7 +410,7 @@ class S3VectorClient(VectorDBBase):
             return self.get(collection_name)
 
         try:
-            log.info(f"Querying collection '{collection_name}' with filter: {filter}")
+            log.info("Querying collection '%s' with filter: %s", collection_name, filter)
 
             # For S3 Vector, we need to use list_vectors and then filter results
             # Since S3 Vector may not support complex server-side filtering,
@@ -437,7 +445,7 @@ class S3VectorClient(VectorDBBase):
                     if limit and len(filtered_ids) >= limit:
                         break
 
-            log.info(f'Filter applied: {len(filtered_ids)} vectors match out of {len(all_ids)} total')
+            log.info('Filter applied: %s vectors match out of %s total', len(filtered_ids), len(all_ids))
 
             # Return GetResult format
             if filtered_ids:
@@ -472,7 +480,7 @@ class S3VectorClient(VectorDBBase):
             return GetResult(ids=[[]], documents=[[]], metadatas=[[]])
 
         try:
-            log.info(f"Retrieving all vectors from collection '{collection_name}'")
+            log.info("Retrieving all vectors from collection '%s'", collection_name)
 
             # Initialize result lists
             all_ids = []
@@ -534,7 +542,7 @@ class S3VectorClient(VectorDBBase):
                 if not next_token:
                     break
 
-            log.info(f"Retrieved {len(all_ids)} vectors from collection '{collection_name}'")
+            log.info("Retrieved %s vectors from collection '%s'", len(all_ids), collection_name)
 
             # Return in GetResult format
             # The Open WebUI GetResult expects lists of lists, so we wrap each list
@@ -576,17 +584,17 @@ class S3VectorClient(VectorDBBase):
         try:
             if ids:
                 # Delete by specific vector IDs/keys
-                log.info(f"Deleting {len(ids)} vectors by IDs from collection '{collection_name}'")
+                log.info("Deleting %s vectors by IDs from collection '%s'", len(ids), collection_name)
                 self.client.delete_vectors(
                     vectorBucketName=self.bucket_name,
                     indexName=collection_name,
                     keys=ids,
                 )
-                log.info(f"Deleted {len(ids)} vectors from index '{collection_name}'")
+                log.info("Deleted %s vectors from index '%s'", len(ids), collection_name)
 
             elif filter:
                 # Handle filter-based deletion
-                log.info(f"Deleting vectors by filter from collection '{collection_name}': {filter}")
+                log.info("Deleting vectors by filter from collection '%s': %s", collection_name, filter)
 
                 # If this is a knowledge collection and we have a file_id filter,
                 # also clean up the corresponding file-specific collection
@@ -595,7 +603,8 @@ class S3VectorClient(VectorDBBase):
                     file_collection_name = f'file-{file_id}'
                     if self.has_collection(file_collection_name):
                         log.info(
-                            f"Found related file-specific collection '{file_collection_name}', deleting it to prevent duplicates"
+                            "Found related file-specific collection '%s', deleting it to prevent duplicates",
+                            file_collection_name,
                         )
                         self.delete_collection(file_collection_name)
 
@@ -604,7 +613,7 @@ class S3VectorClient(VectorDBBase):
                 query_result = self.query(collection_name, filter)
                 if query_result and query_result.ids and query_result.ids[0]:
                     matching_ids = query_result.ids[0]
-                    log.info(f'Found {len(matching_ids)} vectors matching filter, deleting them')
+                    log.info('Found %s vectors matching filter, deleting them', len(matching_ids))
 
                     # Delete the matching vectors by ID
                     self.client.delete_vectors(
@@ -612,7 +621,7 @@ class S3VectorClient(VectorDBBase):
                         indexName=collection_name,
                         keys=matching_ids,
                     )
-                    log.info(f"Deleted {len(matching_ids)} vectors from index '{collection_name}' using filter")
+                    log.info("Deleted %s vectors from index '%s' using filter", len(matching_ids), collection_name)
                 else:
                     log.warning('No vectors found matching the filter criteria')
             else:
@@ -645,11 +654,11 @@ class S3VectorClient(VectorDBBase):
                     try:
                         self.client.delete_index(vectorBucketName=self.bucket_name, indexName=index_name)
                         deleted_count += 1
-                        log.info(f'Deleted index: {index_name}')
+                        log.info('Deleted index: %s', index_name)
                     except Exception as e:
                         log.error(f"Error deleting index '{index_name}': {e}")
 
-            log.info(f'Reset completed: deleted {deleted_count} indexes')
+            log.info('Reset completed: deleted %s indexes', deleted_count)
 
         except Exception as e:
             log.error(f'Error during reset: {e}')

backend/open_webui/retrieval/vector/dbs/valkey.py

@@ -279,7 +279,7 @@ class ValkeyClient(VectorDBBase):
                 f'{self._format_version(MIN_VALKEY_VERSION)}. valkey-search 1.2.0 requires Valkey core '
                 '9.0.1 or later. Upgrade your server or use valkey-bundle:9.1.0-rc2+.'
             )
-        log.info(f'Valkey core version: {self._format_version(version) if version else "unknown"}')
+        log.info('Valkey core version: %s', self._format_version(version) if version else 'unknown')
 
     def _check_search_module(self) -> None:
         try:
@@ -331,7 +331,7 @@ class ValkeyClient(VectorDBBase):
                 'TEXT field type and filter-only FT.SEARCH support required by this backend. '
                 'Upgrade to valkey-bundle:9.1.0-rc2+ or load valkey-search 1.2.0+ as a module.'
             )
-        log.info(f'valkey-search version: {self._format_version(search_version) if search_version else "unknown"}')
+        log.info('valkey-search version: %s', self._format_version(search_version) if search_version else 'unknown')
 
     def _index_name(self, collection_name: str) -> str:
         return f'idx:{self.collection_prefix}:{collection_name}'
@@ -385,8 +385,11 @@ class ValkeyClient(VectorDBBase):
         try:
             g['glide_ft'].create(self.client, index_name, schema, options)
             log.info(
-                f'Created Valkey index {index_name} with dimension={dimension}, '
-                f'type={self.index_type}, metric={self.distance_metric}'
+                'Created Valkey index %s with dimension=%s, type=%s, metric=%s',
+                index_name,
+                dimension,
+                self.index_type,
+                self.distance_metric,
             )
         except g['RequestError'] as e:
             if 'already exists' in str(e).lower():
@@ -456,7 +459,7 @@ class ValkeyClient(VectorDBBase):
         index_name = self._index_name(collection_name)
         try:
             self._g['glide_ft'].dropindex(self.client, index_name)
-            log.info(f'Dropped index {index_name}')
+            log.info('Dropped index %s', index_name)
         except self._g['RequestError'] as e:
             log.debug('Could not drop index %s: %s', index_name, e)
 
@@ -656,7 +659,7 @@ class ValkeyClient(VectorDBBase):
                     collections.append(name[len(idx_prefix) :])
                     try:
                         glide_ft.dropindex(self.client, idx)
-                        log.info(f'Dropped index: {name}')
+                        log.info('Dropped index: %s', name)
                     except Exception as e:
                         log.error(f'Error dropping index {name}: {e}')
         except Exception as e:
@@ -664,7 +667,7 @@ class ValkeyClient(VectorDBBase):
 
         for collection in collections:
             self._delete_keys_by_prefix(self._key_prefix(collection))
-        log.info(f'Valkey vector store reset complete (prefix: {self.collection_prefix})')
+        log.info('Valkey vector store reset complete (prefix: %s)', self.collection_prefix)
 
     def _delete_keys_by_prefix(self, prefix: str) -> None:
         cursor = '0'