davebb/linear-coding-agent
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Génération TTS asynchrone pour éviter le blocage Flask

Browse Source 
Backend:
- Nouveau dictionnaire global tts_jobs pour tracker les jobs TTS
- Fonction _generate_audio_background() pour génération en thread
- POST /chat/generate-audio: lance génération et retourne job_id
- GET /chat/audio-status/<job_id>: polling du statut
- GET /chat/download-audio/<job_id>: télécharge l'audio terminé
- États: pending → processing → completed/failed

Frontend:
- Fonction exportToAudio() asynchrone avec polling (1s)
- Spinner animé pendant génération ("Génération...")
- Téléchargement automatique quand prêt
- Restauration bouton en cas d'erreur
- Animation CSS @keyframes spin pour le spinner

Avantages:
- Flask reste responsive pendant génération TTS
- Navigation possible pendant génération audio
- Expérience utilisateur améliorée avec feedback visuel

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
This commit is contained in:
David Blanc Brioir
2025-12-30 19:45:29 +01:00
parent f2303569b5
commit fd66917f03
2 changed files with 287 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

208
generations/library_rag/flask_app.py
View File

@@ -105,6 +105,9 @@ processing_jobs: Dict[str, Dict[str, Any]] = {} # {job_id: {"status": str, "que
# Stockage des sessions de chat en cours
chat_sessions: Dict[str, Dict[str, Any]] = {} # {session_id: {"status": str, "queue": Queue, "context": list}}
# Stockage des jobs TTS en cours
tts_jobs: Dict[str, Dict[str, Any]] = {} # {job_id: {"status": str, "filepath": Path, "error": str}}
# ═══════════════════════════════════════════════════════════════════════════════
# Weaviate Connection
# ═══════════════════════════════════════════════════════════════════════════════
@@ -1641,6 +1644,211 @@ def chat_export_audio() -> Union[WerkzeugResponse, tuple[Dict[str, Any], int]]:
return jsonify({"error": f"TTS failed: {str(e)}"}), 500
def _generate_audio_background(job_id: str, text: str, language: str) -> None:
"""Background worker for TTS audio generation.
Generates audio in a separate thread to avoid blocking Flask.
Updates the global tts_jobs dict with status and result.
Args:
job_id: Unique identifier for this TTS job.
text: Text to convert to speech.
language: Language code for TTS.
"""
try:
from utils.tts_generator import generate_speech
# Update status to processing
tts_jobs[job_id]["status"] = "processing"
# Generate audio file
filepath = generate_speech(
text=text,
output_dir=app.config["UPLOAD_FOLDER"],
language=language,
)
# Update job with success status
tts_jobs[job_id]["status"] = "completed"
tts_jobs[job_id]["filepath"] = filepath
except Exception as e:
# Update job with error status
tts_jobs[job_id]["status"] = "failed"
tts_jobs[job_id]["error"] = str(e)
print(f"TTS job {job_id} failed: {e}")
@app.route("/chat/generate-audio", methods=["POST"])
def chat_generate_audio() -> tuple[Dict[str, Any], int]:
"""Start asynchronous TTS audio generation (non-blocking).
Launches TTS generation in a background thread and immediately returns
a job ID for status polling. This allows the Flask app to remain responsive
during audio generation.
Request JSON:
assistant_response (str): The assistant's complete response (required).
language (str, optional): Language code for TTS ("fr", "en", etc.).
Default: "fr" (French).
Returns:
JSON response with job_id and 202 Accepted status on success.
JSON error response with 400 status on validation failure.
Example:
POST /chat/generate-audio
Content-Type: application/json
{
"assistant_response": "La phénoménologie est une approche philosophique...",
"language": "fr"
}
Response (202):
{
"job_id": "550e8400-e29b-41d4-a716-446655440000",
"status": "pending"
}
See Also:
- ``/chat/audio-status/<job_id>`` : Check generation status
- ``/chat/download-audio/<job_id>`` : Download completed audio
"""
try:
data = request.get_json()
if not data:
return {"error": "No JSON data provided"}, 400
assistant_response = data.get("assistant_response")
language = data.get("language", "fr")
if not assistant_response:
return {"error": "assistant_response is required"}, 400
# Generate unique job ID
job_id = str(uuid.uuid4())
# Initialize job in pending state
tts_jobs[job_id] = {
"status": "pending",
"filepath": None,
"error": None,
}
# Launch background thread for audio generation
thread = threading.Thread(
target=_generate_audio_background,
args=(job_id, assistant_response, language),
daemon=True,
)
thread.start()
# Return job ID immediately
return {"job_id": job_id, "status": "pending"}, 202
except Exception as e:
return {"error": f"Failed to start TTS job: {str(e)}"}, 500
@app.route("/chat/audio-status/<job_id>", methods=["GET"])
def chat_audio_status(job_id: str) -> tuple[Dict[str, Any], int]:
"""Check the status of a TTS audio generation job.
Args:
job_id: Unique identifier for the TTS job.
Returns:
JSON response with job status and 200 OK on success.
JSON error response with 404 status if job not found.
Status Values:
- "pending": Job created but not started yet
- "processing": Audio generation in progress
- "completed": Audio ready for download
- "failed": Generation failed (error message included)
Example:
GET /chat/audio-status/550e8400-e29b-41d4-a716-446655440000
Response (processing):
{
"job_id": "550e8400-e29b-41d4-a716-446655440000",
"status": "processing"
}
Response (completed):
{
"job_id": "550e8400-e29b-41d4-a716-446655440000",
"status": "completed",
"filename": "chat_audio_20250130_143045.wav"
}
Response (failed):
{
"job_id": "550e8400-e29b-41d4-a716-446655440000",
"status": "failed",
"error": "TTS generation failed: ..."
}
"""
job = tts_jobs.get(job_id)
if not job:
return {"error": "Job not found"}, 404
response = {
"job_id": job_id,
"status": job["status"],
}
if job["status"] == "completed" and job["filepath"]:
response["filename"] = job["filepath"].name
if job["status"] == "failed" and job["error"]:
response["error"] = job["error"]
return response, 200
@app.route("/chat/download-audio/<job_id>", methods=["GET"])
def chat_download_audio(job_id: str) -> Union[WerkzeugResponse, tuple[Dict[str, Any], int]]:
"""Download the generated audio file for a completed TTS job.
Args:
job_id: Unique identifier for the TTS job.
Returns:
Audio file download (.wav) if job completed successfully.
JSON error response with 404/400 status if job not found or not ready.
Example:
GET /chat/download-audio/550e8400-e29b-41d4-a716-446655440000
Response: chat_audio_20250130_143045.wav (download)
"""
job = tts_jobs.get(job_id)
if not job:
return {"error": "Job not found"}, 404
if job["status"] != "completed":
return {"error": f"Job not ready (status: {job['status']})"}, 400
filepath = job["filepath"]
if not filepath or not filepath.exists():
return {"error": "Audio file not found"}, 404
# Send file as download
return send_from_directory(
directory=filepath.parent,
path=filepath.name,
as_attachment=True,
download_name=filepath.name,
)
# ═══════════════════════════════════════════════════════════════════════════════
# PDF Upload & Processing
# ═══════════════════════════════════════════════════════════════════════════════

87
generations/library_rag/templates/chat.html
View File

@@ -422,6 +422,15 @@
}
}
@keyframes spin {
from {
transform: rotate(0deg);
}
to {
transform: rotate(360deg);
}
}
.reformulation-header {
display: flex;
align-items: center;
@@ -1065,7 +1074,7 @@
// Add click handler for Audio export
exportAudioBtn.addEventListener('click', async () => {
await exportToAudio(accumulatedText);
await exportToAudio(accumulatedText, exportAudioBtn);
});
}
@@ -1379,9 +1388,24 @@
}
}
async function exportToAudio(assistantResponse) {
async function exportToAudio(assistantResponse, buttonElement) {
try {
const response = await fetch('/chat/export-audio', {
// Save original button state
const originalHTML = buttonElement.innerHTML;
const originalDisabled = buttonElement.disabled;
// Update button to show loading state
buttonElement.disabled = true;
buttonElement.innerHTML = `
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="currentColor" style="animation: spin 1s linear infinite;">
<circle cx="12" cy="12" r="10" stroke="currentColor" stroke-width="2" fill="none" opacity="0.25"/>
<path d="M12 2a10 10 0 0 1 10 10" stroke="currentColor" stroke-width="2" fill="none"/>
</svg>
Génération...
`;
// Start async audio generation
const startResponse = await fetch('/chat/generate-audio', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
@@ -1390,25 +1414,64 @@
})
});
if (!response.ok) {
const error = await response.json();
throw new Error(error.error || 'TTS failed');
if (!startResponse.ok) {
const error = await startResponse.json();
throw new Error(error.error || 'Failed to start TTS job');
}
// Download file
const blob = await response.blob();
const url = window.URL.createObjectURL(blob);
const { job_id } = await startResponse.json();
// Poll for job status
const checkStatus = async () => {
const statusResponse = await fetch(`/chat/audio-status/${job_id}`);
if (!statusResponse.ok) {
throw new Error('Failed to check TTS status');
}
const status = await statusResponse.json();
if (status.status === 'completed') {
// Download the audio file
const downloadUrl = `/chat/download-audio/${job_id}`;
const a = document.createElement('a');
a.href = url;
a.download = `chat_audio_${new Date().getTime()}.wav`;
a.href = downloadUrl;
a.download = status.filename;
document.body.appendChild(a);
a.click();
window.URL.revokeObjectURL(url);
document.body.removeChild(a);
// Restore button state
buttonElement.innerHTML = originalHTML;
buttonElement.disabled = originalDisabled;
} else if (status.status === 'failed') {
throw new Error(status.error || 'TTS generation failed');
} else {
// Still processing, check again in 1 second
setTimeout(checkStatus, 1000);
}
};
// Start polling
await checkStatus();
} catch (error) {
console.error('TTS error:', error);
alert(`Erreur TTS: ${error.message}`);
// Restore button state on error
if (buttonElement) {
buttonElement.disabled = false;
buttonElement.innerHTML = `
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="currentColor">
<path d="M11 5L6 9H2v6h4l5 4V5z"/>
<path d="M15.54 8.46a5 5 0 0 1 0 7.07"/>
<path d="M19.07 4.93a10 10 0 0 1 0 14.14"/>
</svg>
Audio
`;
}
}
}