perf: build debug log messages lazily so disabled debug logs cost nothing (#27834)
GLOBAL_LOG_LEVEL defaults to INFO, so every log.debug(...) in the backend is discarded, but the message is built first: 187 call sites interpolate their payload into an f-string before the logging call runs, so the work happens on every request and the result is thrown away. The worst one sits in process_chat_payload and stringifies the whole request body, full conversation history included, once per chat completion.
That one line with DEBUG disabled, CPython 3.12:
| conversation | payload | before | after |
| ------------ | ------- | -------- | ------- |
| 4 messages | 1.2 kB | 3.4 us | 0.07 us |
| 20 messages | 17 kB | 24.8 us | 0.07 us |
| 60 messages | 123 kB | 216.6 us | 0.07 us |
The lazy form log.debug('form_data: %s', form_data) hands the payload to record.getMessage(), which the InterceptHandler only reaches once a record has passed the level check. With DEBUG enabled the emitted lines are byte-identical, f'{x=}' sites included: those map to %r. MistralLoader._debug_log callers get the same treatment, since that wrapper already forwards *args.
This commit is contained in:
Classic298 authored and GitHub committed
1 parent
b67804f2b6
commit
52cfb02c72
40 files changed
+198
-190
No files matched your search
@@ -98,7 +98,7 @@ class MinerULoader:
|
||||
files = {'files': (filename, f, 'application/octet-stream')}
|
||||
|
||||
log.info(f'Sending file to MinerU Local API: {filename}')
|
||||
log.debug(f'Local API parameters: {form_data}')
|
||||
log.debug('Local API parameters: %s', form_data)
|
||||
|
||||
response = requests.post(
|
||||
f'{self.api_url}/file_parse',
|
||||
@@ -233,7 +233,7 @@ class MinerULoader:
|
||||
request_body['files'][0]['page_ranges'] = self.page_ranges
|
||||
|
||||
log.info(f'Requesting upload URL for: {filename}')
|
||||
log.debug(f'Cloud API request body: {request_body}')
|
||||
log.debug('Cloud API request body: %s', request_body)
|
||||
|
||||
try:
|
||||
response = requests.post(
|
||||
|
||||
@@ -338,7 +338,7 @@ class MistralLoader:
|
||||
headers = {**self.headers, 'Accept': 'application/json'}
|
||||
|
||||
async def url_request():
|
||||
self._debug_log(f'Getting signed URL for file ID: {file_id}')
|
||||
self._debug_log('Getting signed URL for file ID: %s', file_id)
|
||||
async with session.get(
|
||||
url,
|
||||
headers=headers,
|
||||
@@ -450,7 +450,7 @@ class MistralLoader:
|
||||
try:
|
||||
|
||||
async def delete_request():
|
||||
self._debug_log(f'Deleting file ID: {file_id}')
|
||||
self._debug_log('Deleting file ID: %s', file_id)
|
||||
async with session.delete(
|
||||
url=f'{self.base_url}/files/{file_id}',
|
||||
headers=self.headers,
|
||||
@@ -460,7 +460,7 @@ class MistralLoader:
|
||||
return await self._handle_response_async(response)
|
||||
|
||||
await self._retry_request_async(delete_request)
|
||||
self._debug_log(f'File {file_id} deleted successfully')
|
||||
self._debug_log('File %s deleted successfully', file_id)
|
||||
|
||||
except Exception as e:
|
||||
# Don't fail the entire process if cleanup fails
|
||||
@@ -519,7 +519,7 @@ class MistralLoader:
|
||||
if page_content is None or page_index is None:
|
||||
skipped_pages += 1
|
||||
self._debug_log(
|
||||
f"Skipping page due to missing 'markdown' or 'index'. Data keys: {list(page_data.keys())}"
|
||||
"Skipping page due to missing 'markdown' or 'index'. Data keys: %s", list(page_data.keys())
|
||||
)
|
||||
continue
|
||||
|
||||
@@ -531,7 +531,7 @@ class MistralLoader:
|
||||
|
||||
if not cleaned_content:
|
||||
skipped_pages += 1
|
||||
self._debug_log(f'Skipping empty page {page_index}')
|
||||
self._debug_log('Skipping empty page %s', page_index)
|
||||
continue
|
||||
|
||||
# Create document with optimized metadata
|
||||
|
||||
@@ -90,7 +90,7 @@ class YoutubeLoader:
|
||||
|
||||
if self.proxy_url:
|
||||
youtube_proxies = GenericProxyConfig(http_url=self.proxy_url, https_url=self.proxy_url)
|
||||
log.debug(f'Using proxy URL: {self.proxy_url[:14]}...')
|
||||
log.debug('Using proxy URL: %s...', self.proxy_url[:14])
|
||||
else:
|
||||
youtube_proxies = None
|
||||
|
||||
@@ -106,23 +106,23 @@ class YoutubeLoader:
|
||||
try:
|
||||
transcript = transcript_list.find_transcript([lang])
|
||||
if transcript.is_generated:
|
||||
log.debug(f"Found generated transcript for language '{lang}'")
|
||||
log.debug("Found generated transcript for language '%s'", lang)
|
||||
try:
|
||||
transcript = transcript_list.find_manually_created_transcript([lang])
|
||||
log.debug(f"Found manual transcript for language '{lang}'")
|
||||
log.debug("Found manual transcript for language '%s'", lang)
|
||||
except NoTranscriptFound:
|
||||
log.debug(f"No manual transcript found for language '{lang}', using generated")
|
||||
log.debug("No manual transcript found for language '%s', using generated", lang)
|
||||
pass
|
||||
|
||||
log.debug(f"Found transcript for language '{lang}'")
|
||||
log.debug("Found transcript for language '%s'", lang)
|
||||
try:
|
||||
transcript_pieces: List[Dict[str, Any]] = transcript.fetch()
|
||||
except ParseError:
|
||||
log.debug(f"Empty or invalid transcript for language '{lang}'")
|
||||
log.debug("Empty or invalid transcript for language '%s'", lang)
|
||||
continue
|
||||
|
||||
if not transcript_pieces:
|
||||
log.debug(f"Empty transcript for language '{lang}'")
|
||||
log.debug("Empty transcript for language '%s'", lang)
|
||||
continue
|
||||
|
||||
transcript_text = ' '.join(
|
||||
@@ -135,7 +135,7 @@ class YoutubeLoader:
|
||||
)
|
||||
return [Document(page_content=transcript_text, metadata=self._metadata)]
|
||||
except NoTranscriptFound:
|
||||
log.debug(f"No transcript found for language '{lang}'")
|
||||
log.debug("No transcript found for language '%s'", lang)
|
||||
continue
|
||||
except Exception as e:
|
||||
log.info(f"Error finding transcript for language '{lang}'")
|
||||
|
||||
Reference in new issue
Block a user