Documentation technique complète Osfria OS-FR-IA Platform

#!/bin/bash
# health-check.sh - Vérification santé complète

echo "=== Osfria Health Check $(date) ==="

# 1. Cluster K8s
echo "🔍 Kubernetes cluster:"
kubectl get nodes --no-headers | grep -v Ready | wc -l
kubectl get pods -A --field-selector=status.phase!=Running | grep -v Completed | wc -l

# 2. Services critiques
echo "🔍 Services critiques:"
kubectl get pods -n osfria-ai -l app=vllm-server --no-headers | grep -v Running | wc -l
kubectl get pods -n longhorn-system --no-headers | grep -v Running | wc -l

# 3. Performance GPU
echo "🔍 GPU utilisation:"
kubectl exec -n osfria-ai $(kubectl get pods -n osfria-ai -l app=vllm-server -o name | head -1) -- \
  nvidia-smi --query-gpu=utilization.gpu,memory.used,memory.total --format=csv,noheader,nounits

# 4. Stockage
echo "🔍 Stockage utilisé:"
kubectl exec -n longhorn-system $(kubectl get pods -n longhorn-system -l app=longhorn-manager -o name | head -1) -- \
  longhornctl get volume | grep -v "100%" | wc -l

# 5. Métriques réseau
echo "🔍 Latence inter-nœuds:"
kubectl get nodes -o wide | tail -n +2 | while read node; do
  ip=$(echo $node | awk '{print $6}')
  ping -c 3 $ip | tail -1 | awk '{print $4}' | cut -d'/' -f2
done

echo "=== Health Check Complete ==="

#!/bin/bash
# backup-osfria.sh - Backup complet automatisé

BACKUP_DATE=$(date +%Y%m%d-%H%M%S)
BACKUP_DIR="/backup/osfria-$BACKUP_DATE"

echo "🔄 Début backup Osfria - $BACKUP_DATE"

# 1. Backup etcd (K8s state)
mkdir -p $BACKUP_DIR/etcd
ETCDCTL_API=3 etcdctl snapshot save $BACKUP_DIR/etcd/snapshot.db \
  --endpoints=https://127.0.0.1:2379 \
  --cacert=/var/lib/rancher/k3s/server/tls/etcd/server-ca.crt \
  --cert=/var/lib/rancher/k3s/server/tls/etcd/server-client.crt \
  --key=/var/lib/rancher/k3s/server/tls/etcd/server-client.key

# 2. Backup Longhorn volumes
mkdir -p $BACKUP_DIR/volumes
kubectl get pv -o json > $BACKUP_DIR/volumes/persistent-volumes.json

# 3. Backup configurations
mkdir -p $BACKUP_DIR/config
kubectl get configmaps -A -o yaml > $BACKUP_DIR/config/configmaps.yaml
kubectl get secrets -A -o yaml > $BACKUP_DIR/config/secrets.yaml

# 4. Backup modèles IA
mkdir -p $BACKUP_DIR/models
rsync -av /opt/models/ $BACKUP_DIR/models/

# 5. Compression et stockage
tar -czf $BACKUP_DIR.tar.gz -C /backup osfria-$BACKUP_DATE
rm -rf $BACKUP_DIR

# 6. Rétention (garder 30 jours)
find /backup -name "osfria-*.tar.gz" -mtime +30 -delete

echo "✅ Backup terminé: $BACKUP_DIR.tar.gz"

# Upload document
curl -X POST "https://osfria.entreprise.local/api/v1/documents" \
  -H "Authorization: Bearer sk-osfria-..." \
  -F "[email protected]" \
  -F "collection=knowledge-base" \
  -F "metadata={\"department\":\"finance\",\"confidential\":true}"

# Réponse
{
  "document_id": "doc_abc123",
  "filename": "document.pdf",
  "status": "processing",
  "chunks_count": 0,
  "upload_time": "2024-12-03T15:30:00Z"
}

# Vérifier statut indexation
curl "https://osfria.entreprise.local/api/v1/documents/doc_abc123" \
  -H "Authorization: Bearer sk-osfria-..."

# Réponse après traitement
{
  "document_id": "doc_abc123",
  "filename": "document.pdf", 
  "status": "indexed",
  "chunks_count": 47,
  "collection": "knowledge-base",
  "metadata": {
    "department": "finance",
    "confidential": true,
    "pages": 12,
    "file_size": 2048576
  }
}

# Recherche dans documents
curl -X POST "https://osfria.entreprise.local/api/v1/search" \
  -H "Authorization: Bearer sk-osfria-..." \
  -H "Content-Type: application/json" \
  -d '{
    "query": "procédure remboursement frais",
    "collection": "knowledge-base",
    "filters": {
      "department": "finance",
      "confidential": true
    },
    "top_k": 5,
    "score_threshold": 0.7
  }'

# Réponse
{
  "results": [
    {
      "document_id": "doc_abc123",
      "chunk_id": "chunk_456",
      "content": "La procédure de remboursement...",
      "score": 0.89,
      "metadata": {
        "page": 3,
        "section": "Procédures financières"
      }
    }
  ],
  "total_results": 3,
  "search_time_ms": 45
}