Smart Transcription - Documentation Technique BFF¶

Version: 1.0.0
Date: 11 Mars 2026
Statut: Production

Vue d'Ensemble¶

Bienvenue dans la documentation technique complète du service Smart Transcription BFF (Backend For Frontend).

Cette documentation couvre l'architecture v3 avec séparation des services :
- Smart Transcription BFF (Port 8001) : Auth, RAG, Post-processing
- MeetNoo GPU Services (Port 8000) : Pipeline GPU, LLM Inference

Navigation¶

Architecture¶

Architecture complète, stack technique, communication BFF ↔ MeetNoo, déploiement et sécurité.

Pipeline & Workflow¶

Workflow complet en 4 phases : Upload → GPU → Post-Processing → Finalization.

RAG & Enrichissement¶

Architecture 3-priority (Voiceprint → RAG → LLM), mean pooling, auto-save voiceprints.

LLM & Prompting¶

Service LLM (clean_transcription, identify_speakers), Redis Streams, prompt engineering.

Redis Streams Architecture 🆕¶

Nouveau v2.0: Architecture dual-stream complète (pipeline:events + workflow:events), consumer unifié, communication SSE, analyse de cohérence et validation des flux.

Sous-sections spécialisées :
- Workflow Events Architecture - Stream BFF interne (indexing RAG, post-processing)
- Executive Summary Redis v2 - Synthèse exécutive de la migration async v2.0

Modèles de Données¶

Schémas PostgreSQL, EnrichedSegment, VoiceprintLibrary, relations ERD.

AI Engine (Unified RAG Gateway) 🆕¶

Architecture RAG Gateway v2.0 : AI Search cross-projet, AI Chat SSE streaming, feedback loop, collections Qdrant multi-niveaux, score de fiabilité.

Gestion d'Erreurs¶

Fallback chains, retry policies, circuit breaker, graceful degradation.

Performance¶

Benchmarks production, optimisations, scalabilité, monitoring.

Guide de Démarrage Rapide¶

Installation¶

# Clone repository
git clone https://github.com/your-org/smart-transcription.git
cd smart-transcription

# Virtual environment
python -m venv venv
source venv/bin/activate  # Linux/Mac
venv\Scripts\activate     # Windows

# Dependencies
pip install -r requirements.txt

# Environment variables
cp backend.env.example backend.env
# Edit backend.env with your credentials

Configuration¶

# PostgreSQL
DATABASE_URL=postgresql://user:pass@localhost:5432/smart_transcription

# Qdrant
QDRANT_HOST=localhost
QDRANT_PORT=6333

# Redis
REDIS_URL=redis://localhost:6379/0

# AWS S3
AWS_S3_BUCKET=meetnoo-storage
AWS_REGION=eu-west-3

# OpenAI
OPENAI_API_KEY=sk-...

# MeetNoo GPU Service
MEETNOO_API_URL=http://localhost:8000

Lancement¶

# Database migrations
alembic upgrade head

# Start server
uvicorn src.main:app --host 0.0.0.0 --port 8001 --reload

Endpoints Principaux¶

# Health check
GET http://localhost:8001/health

# Upload transcription with RAG enrichment
POST http://localhost:8001/api/transcripts/create-with-rag
Content-Type: multipart/form-data
Authorization: Bearer {token}
Fields: audio_file, title (optional), language (default: fr), contextual_files[] (optional)

Métriques de Production¶

Architecture Globale¶

Guides par Audience¶

Architectes Système¶

1. Architecture BFF - Séparation services, stack, déploiement
2. Pipeline Workflow - Orchestration complète
3. Performance - Scalabilité, benchmarks

Backend Developers¶

1. Modèles de Données - Schémas, relations, exemples
2. Gestion d'Erreurs - Fallbacks, retry, recovery
3. Architecture BFF - Structure projet, layering

ML/AI Engineers¶

1. RAG Enrichment - 3-priority, mean pooling, voiceprints
2. LLM Prompting - Prompt engineering, operations
3. Performance - Optimisations ML, resource usage

DevOps/SRE¶

1. Architecture - Déploiement - Docker, VPS, VPN
2. Performance - Monitoring - Métriques, alerting
3. Gestion d'Erreurs - Error tracking, logging

Ressources Externes¶

• Architecture v3 Détaillée
• API MeetNoo Services
• Architecture Speaker Identification

Support¶

Pour toute question ou problème :
- GitHub Issues : smart-transcription/issues
- Email : support@smart-transcription.com
- Documentation : Cette documentation MkDocs

Bonne lecture !