fix: Simplify Dockerfile and add startup logging for HF Space debugging

Dockerfile

@@ -2,32 +2,29 @@ FROM python:3.12-slim
 
 WORKDIR /app
 
-# Install system deps
+# Install system dependencies
 RUN apt-get update && apt-get install -y --no-install-recommends \
     gcc g++ curl && \
     rm -rf /var/lib/apt/lists/*
 
-# Install Python deps
+# Copy and install Python dependencies
 COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
 
-# Download spaCy model
-RUN python -m spacy download en_core_web_sm
+# Download spaCy model (with retry)
+RUN python -m spacy download en_core_web_sm || \
+    python -m spacy download en_core_web_sm || \
+    echo "spaCy model download failed, will retry at startup"
 
-# Copy project
+# Copy application code
 COPY . .
 
-# Make startup script executable
-RUN chmod +x start.sh
-
-# Create output dir
-ENV OUTPUT_DIR=/tmp/geo-output
+# Create output directory
 RUN mkdir -p /tmp/geo-output
+ENV OUTPUT_DIR=/tmp/geo-output
 
-# Health check
-HEALTHCHECK --interval=30s --timeout=10s --start-period=40s --retries=3 \
-  CMD curl -f http://localhost:7860/health || exit 1
-
+# Expose port
 EXPOSE 7860
 
-CMD ["./start.sh"]
+# Start application
+CMD ["python", "-m", "uvicorn", "server.api:app", "--host", "0.0.0.0", "--port", "7860", "--log-level", "info"]

Dockerfile.minimal

@@ -0,0 +1,13 @@
+FROM python:3.12-slim
+
+WORKDIR /app
+
+# Minimal dependencies
+RUN pip install --no-cache-dir fastapi uvicorn
+
+# Create minimal app
+RUN echo 'from fastapi import FastAPI\napp = FastAPI()\n@app.get("/")\ndef read_root():\n    return {"status": "ok", "message": "GEO Platform Running"}\n@app.get("/health")\ndef health():\n    return {"status": "healthy"}' > main.py
+
+EXPOSE 7860
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

server/api.py

@@ -12,26 +12,75 @@ from dotenv import load_dotenv
 
 load_dotenv()
 
+print(" GEO Platform API starting...")
+print(f" Working directory: {os.getcwd()}")
+print(f" Python version: {os.sys.version}")
+
 # lazily import heavy pipeline to avoid startup failures when optional deps
 # (like spaCy) are not installed. import inside handlers that need it.
 run_pipeline = None
-from server import ai_visibility
-from server import ai_analysis
-from server import job_queue
-from server import keyword_engine
-from server import users as user_mgmt
-from server import search_intel
+
+try:
+    from server import ai_visibility
+    print(" ai_visibility loaded")
+except Exception as e:
+    print(f"  ai_visibility failed: {e}")
+    ai_visibility = None
+
+try:
+    from server import ai_analysis
+    print(" ai_analysis loaded")
+except Exception as e:
+    print(f" ai_analysis failed: {e}")
+    ai_analysis = None
+
+try:
+    from server import job_queue
+    print(" job_queue loaded")
+except Exception as e:
+    print(f" job_queue failed: {e}")
+    job_queue = None
+
+try:
+    from server import keyword_engine
+    print(" keyword_engine loaded")
+except Exception as e:
+    print(f"  keyword_engine failed: {e}")
+    keyword_engine = None
+
+try:
+    from server import users as user_mgmt
+    print(" users loaded")
+except Exception as e:
+    print(f" users failed: {e}")
+    user_mgmt = None
+
+try:
+    from server import search_intel
+    print(" search_intel loaded")
+except Exception as e:
+    print(f" search_intel failed: {e}")
+    search_intel = None
+
 from fastapi import WebSocket
 import asyncio
 
 OUTPUT_DIR = Path(os.environ.get('OUTPUT_DIR', str(Path(__file__).resolve().parent.parent / 'output')))
 OUTPUT_DIR.mkdir(parents=True, exist_ok=True)
 
+print(f" Output directory: {OUTPUT_DIR}")
+
 app = FastAPI(title='GEO Platform API')
 
+print(" FastAPI app created")
+
 # Serve frontend static files
 frontend_dir = Path(__file__).resolve().parent.parent / 'frontend'
-app.mount('/static', StaticFiles(directory=str(frontend_dir)), name='static')
+if frontend_dir.exists():
+    app.mount('/static', StaticFiles(directory=str(frontend_dir)), name='static')
+    print(f" Frontend mounted: {frontend_dir}")
+else:
+    print(f" Frontend directory not found: {frontend_dir}")
 
 class CrawlRequest(BaseModel):
     url: str
@@ -342,6 +391,12 @@ async def api_results(ts: str | None = None):
         out['schema'] = schema_path.read_text(encoding='utf-8')
     return out
 
+@app.on_event("startup")
+async def startup_event():
+    print(" GEO Platform API is ready!")
+    print(f" Access at: http://0.0.0.0:7860")
+    print(f" Health check: http://0.0.0.0:7860/health")
+
 @app.get('/health')
 async def health_check():
     return {'status': 'healthy', 'service': 'GEO Platform'}