LLM/DocsGPT
1
0
Fork 0
mirror of https://github.com/arc53/DocsGPT.git synced 2025-12-01 17:43:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

Frontend audit: Bug fixes and refinements (#2112)

Browse Source 
* (fix:attachements) sep id for redux ops

* (fix:ui) popups, toast, share modal

* (feat:agentsPreview) stable preview, ui fixes

* (fix:ui) light theme icon, sleek scroll

* (chore:i18n) missin keys

* (chore:i18n) missing keys

* (feat:preferrenceSlice) autoclear invalid source from storage

* (fix:general) delete all conv close btn

* (fix:tts) play one at a time

* (fix:tts) gracefully unmount

* (feat:tts) audio LRU cache

* (feat:tts) pointer on hovered area

* (feat:tts) clean text for speach

---------

Co-authored-by: GH Action - Upstream Sync <action@github.com>
This commit is contained in:
Manish Madan
2025-10-29 05:17:26 +05:30
committed by GitHub
parent 94f70e6de5
commit 6a4cb617f9
40 changed files with 1805 additions and 490 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
application/api/user/attachments/routes.py
View File

@@ -130,11 +130,15 @@ class TextToSpeech(Resource):
@api.expect(tts_model)
@api.doc(description="Synthesize audio speech from text")
def post(self):
from application.utils import clean_text_for_tts
data = request.get_json()
text = data["text"]
cleaned_text = clean_text_for_tts(text)
try:
tts_instance = TTSCreator.create_tts(settings.TTS_PROVIDER)
audio_base64, detected_language = tts_instance.text_to_speech(text)
audio_base64, detected_language = tts_instance.text_to_speech(cleaned_text)
return make_response(
jsonify(
{

41
application/utils.py
View File

@@ -187,3 +187,44 @@ def generate_image_url(image_path):
else:
base_url = getattr(settings, "API_URL", "http://localhost:7091")
return f"{base_url}/api/images/{image_path}"
def clean_text_for_tts(text: str) -> str:
"""
clean text for Text-to-Speech processing.
"""
# Handle code blocks and links
text = re.sub(r'```mermaid[\s\S]*?```', ' flowchart, ', text) ## ```mermaid...```
text = re.sub(r'```[\s\S]*?```', ' code block, ', text) ## ```code```
text = re.sub(r'\[([^\]]+)\]\([^\)]+\)', r'\1', text) ## [text](url)
text = re.sub(r'!\[([^\]]*)\]\([^\)]+\)', '', text) ## ![alt](url)
# Remove markdown formatting
text = re.sub(r'`([^`]+)`', r'\1', text) ## `code`
text = re.sub(r'\{([^}]*)\}', r' \1 ', text) ## {text}
text = re.sub(r'[{}]', ' ', text) ## unmatched {}
text = re.sub(r'\[([^\]]+)\]', r' \1 ', text) ## [text]
text = re.sub(r'[\[\]]', ' ', text) ## unmatched []
text = re.sub(r'(\*\*|__)(.*?)\1', r'\2', text) ## **bold** __bold__
text = re.sub(r'(\*|_)(.*?)\1', r'\2', text) ## *italic* _italic_
text = re.sub(r'^#{1,6}\s+', '', text, flags=re.MULTILINE) ## # headers
text = re.sub(r'^>\s+', '', text, flags=re.MULTILINE) ## > blockquotes
text = re.sub(r'^[\s]*[-\*\+]\s+', '', text, flags=re.MULTILINE) ## - * + lists
text = re.sub(r'^[\s]*\d+\.\s+', '', text, flags=re.MULTILINE) ## 1. numbered lists
text = re.sub(r'^[\*\-_]{3,}\s*$', '', text, flags=re.MULTILINE) ## --- *** ___ rules
text = re.sub(r'<[^>]*>', '', text) ## <html> tags
#Remove non-ASCII (emojis, special Unicode)
text = re.sub(r'[^\x20-\x7E\n\r\t]', '', text)
#Replace special sequences
text = re.sub(r'-->', ', ', text) ## -->
text = re.sub(r'<--', ', ', text) ## <--
text = re.sub(r'=>', ', ', text) ## =>
text = re.sub(r'::', ' ', text) ## ::
#Normalize whitespace
text = re.sub(r'\s+', ' ', text)
text = text.strip()
return text