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/routers/knowledge.py

@@ -351,7 +351,7 @@ async def reindex_knowledge_files(
     failed_files = []
     start_time = time.monotonic()
 
-    log.info(f'Starting reindexing for {len(knowledge_bases)} knowledge bases ({total_files} files)')
+    log.info('Starting reindexing for %s knowledge bases (%s files)', len(knowledge_bases), total_files)
 
     for kb_idx, (knowledge_base, files) in enumerate(knowledge_base_files, start=1):
         try:
@@ -371,8 +371,13 @@ async def reindex_knowledge_files(
                     eta = f', ETA: {round(elapsed / (processed_files - 1) * remaining_files)}s'
 
                 log.info(
-                    f'Reindexing knowledge base {kb_idx}/{len(knowledge_bases)} '
-                    f'file {processed_files}/{total_files}{eta}: {file.filename}'
+                    'Reindexing knowledge base %s/%s file %s/%s%s: %s',
+                    kb_idx,
+                    len(knowledge_bases),
+                    processed_files,
+                    total_files,
+                    eta,
+                    file.filename,
                 )
 
                 try:
@@ -397,7 +402,7 @@ async def reindex_knowledge_files(
         for failed in failed_files:
             log.warning(f'File ID: {failed["file_id"]}, Error: {failed["error"]}')
 
-    log.info(f'Reindexing completed in {round(time.monotonic() - start_time)}s.')
+    log.info('Reindexing completed in %ss.', round(time.monotonic() - start_time))
     await publish_event(
         request,
         EVENTS.KNOWLEDGE_REINDEXED,
@@ -426,14 +431,14 @@ async def reindex_knowledge_base_metadata_embeddings(
     this entire operation would exhaust the connection pool.
     """
     knowledge_bases = await Knowledges.get_knowledge_bases()
-    log.info(f'Reindexing embeddings for {len(knowledge_bases)} knowledge bases')
+    log.info('Reindexing embeddings for %s knowledge bases', len(knowledge_bases))
 
     success_count = 0
     for kb in knowledge_bases:
         if await embed_knowledge_base_metadata(request, kb.id, kb.name, kb.description):
             success_count += 1
 
-    log.info(f'Embedding reindex complete: {success_count}/{len(knowledge_bases)}')
+    log.info('Embedding reindex complete: %s/%s', success_count, len(knowledge_bases))
     return {'total': len(knowledge_bases), 'success': success_count}
 
 
@@ -1687,11 +1692,11 @@ async def delete_knowledge_by_id(
             detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
         )
 
-    log.info(f'Deleting knowledge base: {id} (name: {knowledge.name})')
+    log.info('Deleting knowledge base: %s (name: %s)', id, knowledge.name)
 
     # Get all models
     models = await Models.get_all_models(db=db)
-    log.info(f'Found {len(models)} models to check for knowledge base {id}')
+    log.info('Found %s models to check for knowledge base %s', len(models), id)
 
     # Update models that reference this knowledge base
     for model in models:
@@ -1702,7 +1707,7 @@ async def delete_knowledge_by_id(
 
             # If the knowledge list changed, update the model
             if len(updated_knowledge) != len(knowledge_list):
-                log.info(f'Updating model {model.id} to remove knowledge base {id}')
+                log.info('Updating model %s to remove knowledge base %s', model.id, id)
                 model.meta.knowledge = updated_knowledge
                 model_form = ModelForm(**model.model_dump())
                 await Models.update_model_by_id(model.id, model_form, db=db)
@@ -2022,7 +2027,7 @@ async def add_files_to_knowledge_batch(
         )
 
     # Batch-fetch all files to avoid N+1 queries
-    log.info(f'files/batch/add - {len(form_data)} files')
+    log.info('files/batch/add - %s files', len(form_data))
     file_ids = [form.file_id for form in form_data]
     files = await Files.get_files_by_ids(file_ids, db=db)