Merge branch 'main' into aggiornamento-doc

Align aggiornamento-doc with latest main to resolve PR conflicts.

Dockerfile

@@ -14,6 +14,7 @@ RUN apt-get update && apt-get install -y \
     nginx \
     procps \
     curl \
+    prometheus \
     && rm -rf /var/lib/apt/lists/*
 
 # Create a non-root user
@@ -22,6 +23,27 @@ RUN useradd -m -u 1000 user
 # Set working directory
 WORKDIR /app
 
+# Grafana
+RUN apt-get update && apt-get install -y wget apt-transport-https && \
+    wget -q -O /usr/share/keyrings/grafana.key https://apt.grafana.com/gpg.key && \
+    echo "deb [signed-by=/usr/share/keyrings/grafana.key] https://apt.grafana.com stable main" | tee /etc/apt/sources.list.d/grafana.list && \
+    apt-get update && \
+    apt-get install -y grafana && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+# Prometheus
+RUN wget https://github.com/prometheus/prometheus/releases/download/v2.45.0/prometheus-2.45.0.linux-amd64.tar.gz && \
+    tar xvfz prometheus-*.tar.gz && \
+    mv prometheus-*/prometheus /usr/local/bin/ && \
+    mv prometheus-*/promtool /usr/local/bin/ && \
+    mkdir -p /etc/prometheus /var/lib/prometheus && \
+    rm -rf prometheus-*
+
+COPY monitoring/grafana/provisioning /etc/grafana/provisioning
+COPY monitoring/grafana/dashboards /var/lib/grafana/dashboards
+COPY monitoring/prometheus/prometheus.yml /etc/prometheus/prometheus.yml
+
 # Copy requirements first for caching
 COPY requirements.txt .
 

docker/nginx.conf

@@ -29,6 +29,10 @@ http {
         server 127.0.0.1:8000;
     }
 
+    upstream prometheus {
+        server 127.0.0.1:9090;
+    }
+
     server {
         listen 7860;
         server_name localhost;
@@ -69,6 +73,33 @@ http {
             proxy_set_header Host $host;
         }
 
+        # Grafana
+        location /grafana/ {
+            rewrite ^/grafana/(.*) /$1 break;
+            
+            proxy_pass http://127.0.0.1:3000;
+            proxy_set_header Host $host;
+            proxy_set_header X-Real-IP $remote_addr;
+            proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+            proxy_set_header X-Forwarded-Proto $scheme;
+            
+            proxy_set_header X-Forwarded-Host $host;
+            proxy_set_header X-Forwarded-Server $host;
+            
+            proxy_http_version 1.1;
+            proxy_set_header Upgrade $http_upgrade;
+            proxy_set_header Connection "upgrade";
+        }
+
+        # Prometheus UI
+        location /prometheus/ {
+            proxy_pass http://prometheus/prometheus/;
+            proxy_set_header Host $host;
+            proxy_set_header X-Real-IP $remote_addr;
+            proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+            proxy_set_header X-Forwarded-Proto $scheme;
+        }
+
         # Streamlit (Catch-all)
         location / {
             proxy_pass http://streamlit;

docker/scripts/start_space.sh

@@ -52,6 +52,55 @@ for i in {1..30}; do
     sleep 2
 done
 
+echo "$(date) - Configuring and starting Prometheus..."
+# Create a config for the space
+cat <<EOF > /tmp/prometheus.yml
+global:
+  scrape_interval: 15s
+  evaluation_interval: 15s
+
+scrape_configs:
+  - job_name: 'hopcroft-api'
+    metrics_path: '/metrics'
+    static_configs:
+      - targets: ['127.0.0.1:8000']
+    scrape_interval: 10s
+
+  - job_name: 'prometheus'
+    static_configs:
+      - targets: ['127.0.0.1:9090']
+EOF
+
+# Start Prometheus
+# --web.external-url needs to match the path in Nginx
+prometheus \
+    --config.file=/tmp/prometheus.yml \
+    --storage.tsdb.path=/tmp/prometheus_data \
+    --web.listen-address=0.0.0.0:9090 \
+    --web.external-url=/prometheus/ \
+    --web.route-prefix=/prometheus/ \
+    >> /tmp/prometheus.log 2>&1 &
+
+# Start Grafana
+echo "$(date) - Starting Grafana..."
+grafana-server --homepath=/usr/share/grafana \
+    --config=/app/monitoring/grafana/grafana.ini \
+    cfg:default.paths.data=/tmp/grafana_data \
+    cfg:default.paths.logs=/tmp/grafana_logs \
+    cfg:default.paths.plugins=/usr/share/grafana/plugins \
+    >> /tmp/grafana.log 2>&1 &
+
+# Wait for Grafana to start
+echo "$(date) - Waiting for Grafana (20s)..."
+for i in {1..20}; do
+    if curl -s http://127.0.0.1:3000/api/health > /dev/null; then
+        echo "$(date) - Grafana is UP!"
+        break
+    fi
+    sleep 1
+done
+
+
 echo "$(date) - Starting Nginx reverse proxy..."
 if ! command -v nginx &> /dev/null; then
     echo "$(date) - ERROR: nginx not found in PATH"

monitoring/README.md

@@ -49,6 +49,11 @@ We used Better Stack Uptime to monitor the availability of the production deploy
 - https://dacrow13-hopcroft-skill-classification.hf.space/openapi.json
 - https://dacrow13-hopcroft-skill-classification.hf.space/docs
 
+## Prometheus on Hugging Face Space
+
+Prometheus is also running directly on the Hugging Face Space and is accessible at:
+- https://dacrow13-hopcroft-skill-classification.hf.space/prometheus/
+
 **Checks and alerts**
 - Monitors are configured to run from multiple locations.
 - Email notifications are enabled for failures.

monitoring/grafana/grafana.ini

@@ -0,0 +1,20 @@
+[server]
+protocol = http
+http_port = 3000
+domain = localhost
+root_url = %(protocol)s://%(domain)s:%(http_port)s/grafana/
+serve_from_sub_path = true
+
+[auth.anonymous]
+enabled = true
+org_role = Viewer
+
+[security]
+allow_embedding = true
+
+[users]
+allow_sign_up = false
+
+[log]
+mode = console
+level = info