📊 Legal RAG Analytics Dashboard

Real-time metrics and performance monitoring for Legal RAG services

Auto-refresh:
Sample rate: 5min buckets
-
Total Requests
-
Avg Latency (ms)
-
Total Cost ($)
Based on AWS Bedrock pricing: $3/1M input + $15/1M output tokens

🗄️ Vector Store Router Controls

Routing Mode

AI automatically selects the best vector store based on query analysis

🤖 AI-Driven Routing Active

The system automatically selects the optimal vector store based on query complexity, performance metrics, and circuit breaker status.

Aurora
Complex queries
S3
Simple queries
OpenSearch
Search queries
Direct access: http://3.14.252.129:8004

📈 Request Volume Over Time

Loading request data...

⚡ Model Performance (Latency)

Loading performance data...

💰 Cost Analysis

Loading cost data...
const sonnetWeight = document.getElementById('sonnet-weight').textContent; const sonnet35Weight = document.getElementById('sonnet35-weight').textContent; // Send to backend API (placeholder) fetch('/api/v1/config/model-weights', { method: 'POST', headers: {'Content-Type': 'application/json'}, body: JSON.stringify({ 'haiku-4.5': parseInt(sonnetWeight), 'opus-4.5': parseInt(sonnet35Weight) }) }).then(() => { alert('Model traffic distribution updated!'); }).catch(() => { alert('Traffic distribution applied locally (backend API not available)'); }); } function applyVectorWeights() { const auroraWeight = document.getElementById('aurora-weight').textContent; const s3Weight = document.getElementById('s3-weight').textContent; const opensearchWeight = document.getElementById('opensearch-weight').textContent; // Send to backend API (placeholder) fetch('/api/v1/config/vector-weights', { method: 'POST', headers: {'Content-Type': 'application/json'}, body: JSON.stringify({ 'aurora': parseInt(auroraWeight), 's3': parseInt(s3Weight), 'opensearch': parseInt(opensearchWeight) }) }).then(() => { alert('Vector store distribution updated!'); }).catch(() => { alert('Vector store distribution applied locally (backend API not available)'); }); }