ti.sil/open-webui
1
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2025-12-12 12:25:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

feat: Add user header information for TTS/STT requests (#93) (#19323)

Browse source 
Resolves #19312

Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
Classic298 2025-11-20 22:43:22 +01:00 committed by GitHub
parent 22e85df448
commit 485896753d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 21 additions and 22 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

39
backend/open_webui/routers/audio.py
View file

@ -35,6 +35,7 @@ from pydantic import BaseModel
from open_webui.utils.auth import get_admin_user, get_verified_user from open_webui.utils.auth import get_admin_user, get_verified_user
from open_webui.utils.headers import include_user_info_headers
from open_webui.config import ( from open_webui.config import (
WHISPER_MODEL_AUTO_UPDATE, WHISPER_MODEL_AUTO_UPDATE,
WHISPER_MODEL_DIR, WHISPER_MODEL_DIR,
@ -364,23 +365,17 @@ async def speech(request: Request, user=Depends(get_verified_user)):
**(request.app.state.config.TTS_OPENAI_PARAMS or {}), **(request.app.state.config.TTS_OPENAI_PARAMS or {}),
} }
r = await session.post(
url=f"{request.app.state.config.TTS_OPENAI_API_BASE_URL}/audio/speech",
json=payload,
headers = { headers = {
"Content-Type": "application/json", "Content-Type": "application/json",
"Authorization": f"Bearer {request.app.state.config.TTS_OPENAI_API_KEY}", "Authorization": f"Bearer {request.app.state.config.TTS_OPENAI_API_KEY}",
**(
{
"X-OpenWebUI-User-Name": quote(user.name, safe=" "),
"X-OpenWebUI-User-Id": user.id,
"X-OpenWebUI-User-Email": user.email,
"X-OpenWebUI-User-Role": user.role,
} }
if ENABLE_FORWARD_USER_INFO_HEADERS if ENABLE_FORWARD_USER_INFO_HEADERS:
else {} headers = include_user_info_headers(headers, user)
),
}, r = await session.post(
url=f"{request.app.state.config.TTS_OPENAI_API_BASE_URL}/audio/speech",
json=payload,
headers=headers,
ssl=AIOHTTP_CLIENT_SESSION_SSL, ssl=AIOHTTP_CLIENT_SESSION_SSL,
) )
@ -570,7 +565,7 @@ async def speech(request: Request, user=Depends(get_verified_user)):
return FileResponse(file_path) return FileResponse(file_path)
def transcription_handler(request, file_path, metadata): def transcription_handler(request, file_path, metadata, user=None):
filename = os.path.basename(file_path) filename = os.path.basename(file_path)
file_dir = os.path.dirname(file_path) file_dir = os.path.dirname(file_path)
id = filename.split(".")[0] id = filename.split(".")[0]
@ -621,11 +616,15 @@ def transcription_handler(request, file_path, metadata):
if language: if language:
payload["language"] = language payload["language"] = language
r = requests.post(
url=f"{request.app.state.config.STT_OPENAI_API_BASE_URL}/audio/transcriptions",
headers = { headers = {
"Authorization": f"Bearer {request.app.state.config.STT_OPENAI_API_KEY}" "Authorization": f"Bearer {request.app.state.config.STT_OPENAI_API_KEY}"
}, }
if user and ENABLE_FORWARD_USER_INFO_HEADERS:
headers = include_user_info_headers(headers, user)
r = requests.post(
url=f"{request.app.state.config.STT_OPENAI_API_BASE_URL}/audio/transcriptions",
headers=headers,
files={"file": (filename, open(file_path, "rb"))}, files={"file": (filename, open(file_path, "rb"))},
data=payload, data=payload,
) )
@ -1027,7 +1026,7 @@ def transcription_handler(request, file_path, metadata):
) )
def transcribe(request: Request, file_path: str, metadata: Optional[dict] = None): def transcribe(request: Request, file_path: str, metadata: Optional[dict] = None, user=None):
log.info(f"transcribe: {file_path} {metadata}") log.info(f"transcribe: {file_path} {metadata}")
if is_audio_conversion_required(file_path): if is_audio_conversion_required(file_path):
@ -1054,7 +1053,7 @@ def transcribe(request: Request, file_path: str, metadata: Optional[dict] = None
with ThreadPoolExecutor() as executor: with ThreadPoolExecutor() as executor:
# Submit tasks for each chunk_path # Submit tasks for each chunk_path
futures = [ futures = [
executor.submit(transcription_handler, request, chunk_path, metadata) executor.submit(transcription_handler, request, chunk_path, metadata, user)
for chunk_path in chunk_paths for chunk_path in chunk_paths
] ]
# Gather results as they complete # Gather results as they complete
@ -1189,7 +1188,7 @@ def transcription(
if language: if language:
metadata = {"language": language} metadata = {"language": language}
result = transcribe(request, file_path, metadata) result = transcribe(request, file_path, metadata, user)
return { return {
**result, **result,

2
backend/open_webui/routers/files.py
View file

@ -102,7 +102,7 @@ def process_uploaded_file(request, file, file_path, file_item, file_metadata, us
) )
): ):
file_path = Storage.get_file(file_path) file_path = Storage.get_file(file_path)
result = transcribe(request, file_path, file_metadata) result = transcribe(request, file_path, file_metadata, user)
process_file( process_file(
request, request,