apunkt/SurfSense
1
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2026-04-26 17:26:23 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: address code review feedback for STT implementation

Browse source 
- Add header to local STT transcription for consistency
- Add empty text validation for external STT path
- Refactor external STT to eliminate duplication in atranscription calls
- Ensure both local and external paths have consistent error handling
This commit is contained in:
Nabhan 2025-10-13 14:26:36 +05:00
parent 15ba2b86f6
commit 9b72ec65b5
1 changed files with 16 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

28
surfsense_backend/app/routes/documents_routes.py
View file

@ -798,6 +798,11 @@ async def process_file_in_background(
if not transcribed_text:
raise ValueError("Transcription returned empty text")
# Add metadata about the transcription
transcribed_text = (
f"# Transcription of {filename}\n\n{transcribed_text}"
)
except Exception as e:
raise HTTPException(
status_code=422,
@ -817,22 +822,21 @@ async def process_file_in_background(
else:
# Use LiteLLM for audio transcription
with open(file_path, "rb") as audio_file:
transcription_kwargs = {
"model": app_config.STT_SERVICE,
"file": audio_file,
"api_key": app_config.STT_SERVICE_API_KEY,
}
if app_config.STT_SERVICE_API_BASE:
transcription_response = await atranscription(
model=app_config.STT_SERVICE,
file=audio_file,
api_base=app_config.STT_SERVICE_API_BASE,
api_key=app_config.STT_SERVICE_API_KEY,
)
else:
transcription_response = await atranscription(
model=app_config.STT_SERVICE,
api_key=app_config.STT_SERVICE_API_KEY,
file=audio_file,
)
transcription_kwargs["api_base"] = app_config.STT_SERVICE_API_BASE
transcription_response = await atranscription(**transcription_kwargs)
# Extract the transcribed text
transcribed_text = transcription_response.get("text", "")
if not transcribed_text:
raise ValueError("Transcription returned empty text")
# Add metadata about the transcription
transcribed_text = (