Merge pull request #29 from se4ai2526-uniba/milestone-5-sync-6

.gitattributes

@@ -0,0 +1 @@
+docs/img/*.png filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -11,6 +11,9 @@ ENV PYTHONDONTWRITEBYTECODE=1 \
 RUN apt-get update && apt-get install -y \
     git \
     dos2unix \
+    nginx \
+    procps \
+    curl \
     && rm -rf /var/lib/apt/lists/*
 
 # Create a non-root user

README.md

@@ -5,6 +5,7 @@ colorFrom: blue
 colorTo: green
 sdk: docker
 app_port: 7860
+api_docs_url: /docs
 ---
 
 # Hopcroft_Skill-Classification-Tool-Competition

nginx.conf

@@ -0,0 +1,92 @@
+worker_processes 1;
+pid /tmp/nginx.pid;
+error_log stderr info; # Log to stderr to see errors in HF Space Logs
+
+events {
+    worker_connections 1024;
+}
+
+http {
+    include       /etc/nginx/mime.types;
+    default_type  application/octet-stream;
+
+    # HF Space runs as non-root, use /tmp for everything
+    access_log /dev/stdout;
+    client_body_temp_path /tmp/client_temp;
+    proxy_temp_path       /tmp/proxy_temp;
+    fastcgi_temp_path     /tmp/fastcgi_temp;
+    uwsgi_temp_path       /tmp/uwsgi_temp;
+    scgi_temp_path        /tmp/scgi_temp;
+
+    sendfile        on;
+    keepalive_timeout  65;
+
+    upstream streamlit {
+        server 127.0.0.1:8501;
+    }
+
+    upstream fastapi {
+        server 127.0.0.1:8000;
+    }
+
+    server {
+        listen 7860;
+        server_name localhost;
+
+        # Health endpoint for HF readiness check
+        location /health {
+            proxy_pass http://fastapi/health;
+            proxy_set_header Host $host;
+        }
+
+        # FastAPI Documentation
+        location /docs {
+            proxy_pass http://fastapi/docs;
+            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;
+        }
+
+        location /redoc {
+            proxy_pass http://fastapi/redoc;
+            proxy_set_header Host $host;
+        }
+
+        location /openapi.json {
+            proxy_pass http://fastapi/openapi.json;
+            proxy_set_header Host $host;
+        }
+
+        # FastAPI API Endpoints
+        location /predict {
+            proxy_pass http://fastapi/predict;
+            proxy_set_header Host $host;
+        }
+
+        location /predictions {
+            proxy_pass http://fastapi/predictions;
+            proxy_set_header Host $host;
+        }
+
+        # Streamlit (Catch-all)
+        location / {
+            proxy_pass http://streamlit;
+            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;
+            
+            # WebSocket support for Streamlit
+            proxy_http_version 1.1;
+            proxy_set_header Upgrade $http_upgrade;
+            proxy_set_header Connection "upgrade";
+            proxy_read_timeout 86400;
+            
+            # Prevent 502 if Streamlit is slow
+            proxy_connect_timeout 60s;
+            proxy_send_timeout 60s;
+        }
+    }
+}

requirements.txt

@@ -49,7 +49,6 @@ pytest-xdist>=3.0.0
 
 # Load testing
 locust>=2.20.0
-
 # Data validation and quality
 great_expectations>=0.18.0
 deepchecks>=0.18.0

scripts/start_space.sh

@@ -16,28 +16,82 @@ USER=${DAGSHUB_USERNAME:-$MLFLOW_TRACKING_USERNAME}
 PASS=${DAGSHUB_TOKEN:-$MLFLOW_TRACKING_PASSWORD}
 
 if [ -n "$USER" ] && [ -n "$PASS" ]; then
-    echo "Configuring DVC authentication for DagsHub..."
+    echo "$(date) - Configuring DVC authentication for DagsHub..."
     # Configure local config (not committed)
     dvc remote modify origin --local auth basic
     dvc remote modify origin --local user "$USER"
     dvc remote modify origin --local password "$PASS"
 else
-    echo "WARNING: No DagsHub credentials found. DVC pull might fail if the remote is private."
+    echo "$(date) - WARNING: No DagsHub credentials found. DVC pull might fail if the remote is private."
 fi
 
-echo "Pulling models from DVC..."
+echo "$(date) - Pulling models from DVC..."
 # Pull only the necessary files for inference
 dvc pull models/random_forest_tfidf_gridsearch.pkl.dvc \
          models/tfidf_vectorizer.pkl.dvc \
-         models/label_names.pkl.dvc
+         models/label_names.pkl.dvc || echo "DVC pull failed, but continuing..."
 
-echo "Starting FastAPI application in background..."
-uvicorn hopcroft_skill_classification_tool_competition.main:app --host 0.0.0.0 --port 8000 &
+# Create Nginx temp directories
+mkdir -p /tmp/client_temp /tmp/proxy_temp /tmp/fastcgi_temp /tmp/uwsgi_temp /tmp/scgi_temp
+
+echo "$(date) - Checking models existence..."
+ls -la models/
+
+echo "$(date) - Starting FastAPI application in background..."
+# Using 0.0.0.0 to be safe
+uvicorn hopcroft_skill_classification_tool_competition.main:app --host 0.0.0.0 --port 8000 >> /tmp/fastapi.log 2>&1 &
 
 # Wait for API to start
-echo "Waiting for API to start..."
-sleep 10
+echo "$(date) - Waiting for API to start (30s)..."
+for i in {1..30}; do
+    if curl -s http://127.0.0.1:8000/health > /dev/null; then
+        echo "$(date) - API is UP!"
+        break
+    fi
+    echo "$(date) - Waiting... ($i/30)"
+    sleep 2
+done
+
+echo "$(date) - Starting Nginx reverse proxy..."
+if ! command -v nginx &> /dev/null; then
+    echo "$(date) - ERROR: nginx not found in PATH"
+    exit 1
+fi
+nginx -c /app/nginx.conf -g "daemon off;" >> /tmp/nginx_startup.log 2>&1 &
+
+echo "$(date) - Waiting for Nginx to initialize..."
+sleep 5
+
+# Check if Nginx is running
+if ps aux | grep -v grep | grep -q "nginx"; then
+    echo "$(date) - Nginx is running."
+else
+    echo "$(date) - ERROR: Nginx failed to start. Logs:"
+    cat /tmp/nginx_startup.log
+fi
+
+echo "$(date) - Final backend check before starting Streamlit..."
+curl -v http://127.0.0.1:8000/health || echo "FastAPI health check failed!"
+
+echo "$(date) - Starting Streamlit application on 127.0.0.1:8501..."
+export API_BASE_URL="http://127.0.0.1:8000"
+streamlit run hopcroft_skill_classification_tool_competition/streamlit_app.py \
+    --server.port 8501 \
+    --server.address 127.0.0.1 \
+    --server.enableCORS=false \
+    --server.enableXsrfProtection=false \
+    --server.headless true &
+
+# Wait for Streamlit to start
+echo "$(date) - Waiting for Streamlit to start (30s)..."
+for i in {1..30}; do
+    if curl -s http://127.0.0.1:8501/healthz > /dev/null; then
+        echo "$(date) - Streamlit is UP!"
+        break
+    fi
+    echo "$(date) - Waiting for Streamlit... ($i/30)"
+    sleep 2
+done
 
-echo "Starting Streamlit application..."
-export API_BASE_URL="http://localhost:8000"
-streamlit run hopcroft_skill_classification_tool_competition/streamlit_app.py --server.port 7860 --server.address 0.0.0.0
+echo "$(date) - Process started. Tailing Nginx logs for debug..."
+tail -f /tmp/nginx_startup.log /tmp/fastapi.log