nginx endpoints addition - grafana documentation update

docker/nginx.conf

@@ -81,6 +81,15 @@ http {
             proxy_set_header Host $host;
         }
 
+        # FastAPI Metrics endpoint for Prometheus
+        location /metrics {
+            proxy_pass http://fastapi/metrics;
+            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;
+        }
+
         # Grafana
         location = /grafana {
             return 301 /grafana/;

docs/design_choices.md

@@ -465,11 +465,12 @@ async def monitor_requests(request, call_next):
 ### Grafana Visualization
 
 **Dashboard Panels:**
-1. API Request Rate (time series)
-2. API Latency Percentiles (heatmap)
-3. Drift Detection Status (stat panel)
-4. Drift P-Value Trend (time series)
-5. Error Rate (gauge)
+1. Request Rate (gauge)
+2. Request Latency p50/p95 (time series)
+3. In-Progress Requests (stat panel)
+4. Error Rate 5xx (stat panel)
+5. Model Prediction Time (time series)
+6. Requests by Endpoint (bar chart)
 
 **Data Sources:**
 - Prometheus: Real-time metrics

docs/milestone_summaries.md

@@ -242,10 +242,12 @@ Jobs:
 
 ### Grafana Dashboards
 
-- **API Request Rate**: Real-time requests per second
-- **API Latency**: P50, P90, P99 percentiles
-- **Drift Detection Status**: Binary indicator (0/1)
-- **Drift P-Value**: Statistical significance metric
+- **Request Rate**: Real-time requests per second
+- **Request Latency (p50, p95)**: Response time percentiles
+- **In-Progress Requests**: Currently processing requests
+- **Error Rate (5xx)**: Failed request percentage
+- **Model Prediction Time**: Inference latency
+- **Requests by Endpoint**: Traffic distribution
 
 ### Data Drift Detection
 

docs/user_guide.md

@@ -406,11 +406,12 @@ The pre-configured dashboard includes:
 
 | Panel | Description |
 |-------|-------------|
-| API Request Rate | Real-time requests per endpoint |
-| API Latency | Response time distribution |
-| Drift Detection Status | Binary indicator (0=No Drift, 1=Drift) |
-| Drift P-Value | Statistical significance |
-| Drift Distance | KS test distance metric |
+| Request Rate | Real-time requests per second |
+| Request Latency (p50, p95) | Response time percentiles |
+| In-Progress Requests | Currently processing requests |
+| Error Rate (5xx) | Percentage of failed requests |
+| Model Prediction Time | Average model inference latency |
+| Requests by Endpoint | Traffic distribution per endpoint |
 
 ### Data Drift Detection