Updated api

README.md

@@ -845,6 +845,162 @@ The API includes intelligent fallback responses when AI services are unavailable
 - **Risk Mitigation**: Provides category-based mitigation strategies
 - **Geographic Assessment**: Returns general location risk factors
 
+## 🔧 Deployment Troubleshooting
+
+### Hugging Face Spaces Deployment Issues
+
+#### **Problem**: "Connection error" or "Error generating risks: Connection error."
+**Symptoms**:
+- 500 Internal Server Error responses
+- API endpoints failing with connection errors
+- "GROQ API connection failed" messages
+
+**Solutions**:
+
+1. **Check GROQ API Key Configuration**:
+   - Go to your Hugging Face Space settings
+   - Navigate to "Variables and secrets" 
+   - Ensure `GROQ_API_KEY` is set as a **Secret** (not a variable)
+   - Verify the API key is valid and has sufficient credits
+   - Restart the Space after adding/updating the key
+
+2. **Verify Environment Variable Format**:
+   ```bash
+   # Correct format in HF Spaces:
+   GROQ_API_KEY=gsk_your_actual_api_key_here
+   ```
+
+3. **Test API Key Validity**:
+   ```bash
+   curl -X GET "https://api.groq.com/openai/v1/models" \
+     -H "Authorization: Bearer gsk_your_api_key_here"
+   ```
+
+4. **Check Space Logs**:
+   - Go to your Space's "Logs" tab
+   - Look for startup errors or API connection failures
+   - Restart the Space if environment variables were updated
+
+#### **Problem**: 404 Not Found on API endpoints
+**Symptoms**:
+- Endpoints returning 404 errors
+- API documentation not showing expected routes
+
+**Solutions**:
+
+1. **Verify Endpoint URLs**:
+   ```bash
+   # Correct URLs for HF Spaces:
+   https://your-space-name.hf.space/enterprise/api/enterprise-ra/generate-risks
+   https://your-space-name.hf.space/threat/api/threat-ra/generate-threat-risks
+   https://your-space-name.hf.space/dashboard/api/dashboard/generate-kpis
+   ```
+
+2. **Check API Documentation**:
+   ```bash
+   # Access Swagger UI:
+   https://your-space-name.hf.space/docs
+   ```
+
+#### **Problem**: Space not starting or constant restarts
+**Symptoms**:
+- Space shows "Building" status indefinitely
+- Frequent application restarts
+- Import errors in logs
+
+**Solutions**:
+
+1. **Check Dependencies**:
+   - Ensure all packages in `requirements.txt` are compatible
+   - Verify Python version compatibility (use Python 3.10)
+
+2. **Review Dockerfile**:
+   ```dockerfile
+   FROM python:3.10-slim
+   RUN mkdir -p /data/huggingface && chmod -R 777 /data/huggingface
+   ENV HF_HOME=/data/huggingface
+   WORKDIR /app
+   COPY requirements.txt .
+   RUN pip install --no-cache-dir -r requirements.txt
+   COPY . .
+   CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
+   ```
+
+3. **Port Configuration**:
+   - Hugging Face Spaces require port 7860
+   - Ensure Dockerfile uses the correct port
+
+### Local Development Issues
+
+#### **Problem**: Import errors or module not found
+**Solutions**:
+```bash
+# Ensure all dependencies are installed:
+pip install -r requirements.txt
+
+# Verify Python path:
+export PYTHONPATH="${PYTHONPATH}:$(pwd)"
+```
+
+#### **Problem**: GROQ API rate limits
+**Solutions**:
+- Implement exponential backoff
+- Consider upgrading GROQ plan for higher rate limits
+- Use fallback responses during high traffic
+
+### Testing Deployment
+
+#### **Test Endpoints Programmatically**:
+```python
+import requests
+import json
+
+# Test HF Space endpoint
+base_url = "https://your-space-name.hf.space"
+test_data = {
+    "category": "Financial",
+    "department": "Finance",
+    "business_context": "Test deployment",
+    "specific_concerns": "API connectivity test",
+    "number_of_risks": 1
+}
+
+response = requests.post(
+    f"{base_url}/enterprise/api/enterprise-ra/generate-risks",
+    json=test_data,
+    timeout=30
+)
+
+print(f"Status: {response.status_code}")
+print(f"Response: {response.text}")
+```
+
+#### **Quick Health Check**:
+```bash
+# Check if the Space is responding:
+curl -X GET "https://your-space-name.hf.space/docs"
+
+# Test a simple endpoint:
+curl -X POST "https://your-space-name.hf.space/enterprise/api/enterprise-ra/generate-risks" \
+  -H "Content-Type: application/json" \
+  -d '{"category":"Test","department":"Test","business_context":"Health check","specific_concerns":"Deployment test","number_of_risks":1}'
+```
+
+### Performance Optimization
+
+1. **Cold Start Mitigation**:
+   - HF Spaces may have cold starts after inactivity
+   - First request after idle period may be slower
+   - Consider implementing a keepalive mechanism
+
+2. **Timeout Settings**:
+   - Set appropriate timeouts for API calls (30+ seconds)
+   - Handle timeout gracefully with fallback responses
+
+3. **Resource Monitoring**:
+   - Monitor Space resource usage in HF interface
+   - Consider upgrading to faster hardware tiers for production
+
 ## 🔧 Technical Architecture
 
 ### Components

app.py

@@ -19,20 +19,28 @@ app.include_router(threat_ra_router, prefix="/threat")
 app.include_router(dashboard_router, prefix="/dashboard")
 
 # Environment Variables
-GROQ_API_KEY = os.environ.get("GROQ_API_KEY").strip()
+GROQ_API_KEY = os.environ.get("GROQ_API_KEY")
+if GROQ_API_KEY:
+    GROQ_API_KEY = GROQ_API_KEY.strip()
 
 # Model Setup
 def generate_response(system_prompt: str, user_message: str):
+    if not GROQ_API_KEY:
+        raise Exception("GROQ_API_KEY environment variable is not set")
+    
     client = openai.OpenAI(api_key=GROQ_API_KEY, base_url="https://api.groq.com/openai/v1")
-    response = client.chat.completions.create(
-        model="llama3-8b-8192",  # Try this supported model
-        messages=[
-            {"role": "system", "content": system_prompt},
-            {"role": "user", "content": user_message}
-        ],
-        temperature=0.4
-    )
-    return response.choices[0].message.content
+    try:
+        response = client.chat.completions.create(
+            model="llama3-8b-8192",  # Try this supported model
+            messages=[
+                {"role": "system", "content": system_prompt},
+                {"role": "user", "content": user_message}
+            ],
+            temperature=0.4
+        )
+        return response.choices[0].message.content
+    except Exception as e:
+        raise Exception(f"GROQ API connection failed: {str(e)}")
 
 # Request models
 class Message(BaseModel):

dashboard_analytics.py

@@ -8,21 +8,27 @@ import json
 from datetime import datetime, timedelta
 import random
 
-# Environment Variables
+# Environment Variables  
 GROQ_API_KEY = os.environ.get("GROQ_API_KEY")
-
-# Model Setup
+if GROQ_API_KEY:
+    GROQ_API_KEY = GROQ_API_KEY.strip()# Model Setup
 def generate_response(system_prompt: str, user_message: str):
+    if not GROQ_API_KEY:
+        raise Exception("GROQ_API_KEY environment variable is not set")
+    
     client = openai.OpenAI(api_key=GROQ_API_KEY, base_url="https://api.groq.com/openai/v1")
-    response = client.chat.completions.create(
-        model="llama3-8b-8192",
-        messages=[
-            {"role": "system", "content": system_prompt},
-            {"role": "user", "content": user_message}
-        ],
-        temperature=0.4
-    )
-    return response.choices[0].message.content
+    try:
+        response = client.chat.completions.create(
+            model="llama3-8b-8192",
+            messages=[
+                {"role": "system", "content": system_prompt},
+                {"role": "user", "content": user_message}
+            ],
+            temperature=0.4
+        )
+        return response.choices[0].message.content
+    except Exception as e:
+        raise Exception(f"GROQ API connection failed: {str(e)}")
 
 # Request Models
 class DashboardAnalyticsRequest(BaseModel):

enterprise_ra.py

@@ -9,19 +9,27 @@ import uuid
 
 # Environment Variables
 GROQ_API_KEY = os.environ.get("GROQ_API_KEY")
+if GROQ_API_KEY:
+    GROQ_API_KEY = GROQ_API_KEY.strip()
 
 # Model Setup
 def generate_response(system_prompt: str, user_message: str):
+    if not GROQ_API_KEY:
+        raise Exception("GROQ_API_KEY environment variable is not set")
+    
     client = openai.OpenAI(api_key=GROQ_API_KEY, base_url="https://api.groq.com/openai/v1")
-    response = client.chat.completions.create(
-        model="llama3-8b-8192",
-        messages=[
-            {"role": "system", "content": system_prompt},
-            {"role": "user", "content": user_message}
-        ],
-        temperature=0.4
-    )
-    return response.choices[0].message.content
+    try:
+        response = client.chat.completions.create(
+            model="llama3-8b-8192",
+            messages=[
+                {"role": "system", "content": system_prompt},
+                {"role": "user", "content": user_message}
+            ],
+            temperature=0.4
+        )
+        return response.choices[0].message.content
+    except Exception as e:
+        raise Exception(f"GROQ API connection failed: {str(e)}")
 
 # Request Models
 class RiskGenerationRequest(BaseModel):

threat_ra.py

@@ -9,19 +9,27 @@ import uuid
 
 # Environment Variables
 GROQ_API_KEY = os.environ.get("GROQ_API_KEY")
+if GROQ_API_KEY:
+    GROQ_API_KEY = GROQ_API_KEY.strip()
 
 # Model Setup
 def generate_response(system_prompt: str, user_message: str):
+    if not GROQ_API_KEY:
+        raise Exception("GROQ_API_KEY environment variable is not set")
+    
     client = openai.OpenAI(api_key=GROQ_API_KEY, base_url="https://api.groq.com/openai/v1")
-    response = client.chat.completions.create(
-        model="llama3-8b-8192",
-        messages=[
-            {"role": "system", "content": system_prompt},
-            {"role": "user", "content": user_message}
-        ],
-        temperature=0.4
-    )
-    return response.choices[0].message.content
+    try:
+        response = client.chat.completions.create(
+            model="llama3-8b-8192",
+            messages=[
+                {"role": "system", "content": system_prompt},
+                {"role": "user", "content": user_message}
+            ],
+            temperature=0.4
+        )
+        return response.choices[0].message.content
+    except Exception as e:
+        raise Exception(f"GROQ API connection failed: {str(e)}")
 
 # Request Models
 class ThreatRiskGenerationRequest(BaseModel):