Implement Azure OpenAI, Azure Cache for Redis, and Azure AI Search providers

.env.example

@@ -1,12 +1,62 @@
 # Copy to .env and fill in real values. Never commit .env.
 
-OPENAI_MODEL_NAME=gpt-4o-mini
+# ============================================================================
+# LLM Configuration
+# ============================================================================
+LLM_PROVIDER=openai                    # openai | huggingface | azure_openai
+OPENAI_API_KEY=                        # Required for openai provider
+OPENAI_MODEL_NAME=gpt-4o
 OPENAI_TEMPERATURE=0.0
 OPENAI_MAX_TOKENS=1500
-HF_TOKEN=
-LLM_PROVIDER=openai
+HF_TOKEN=                              # Required for huggingface provider
+
+# Azure OpenAI (if LLM_PROVIDER=azure_openai)
+AZURE_OPENAI_ENDPOINT=
+AZURE_OPENAI_API_KEY=
+AZURE_OPENAI_API_VERSION=2024-10-21
+AZURE_OPENAI_CHAT_DEPLOYMENT_NAME=
+AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME=
+
+# ============================================================================
+# Embedding Configuration
+# ============================================================================
+EMBEDDING_PROVIDER=openai              # openai | azure_openai
+# Azure embedding config uses AZURE_OPENAI_* vars above
+
+# ============================================================================
+# Memory Configuration
+# ============================================================================
+MEMORY_PROVIDER=redis                  # redis | azure_redis
+REDIS_URL=redis://localhost:6379/0     # Used by Docker Compose: redis://redis:6379/0
+AZURE_REDIS_CONNECTION_STRING=         # If MEMORY_PROVIDER=azure_redis
+
+# ============================================================================
+# Vector Store Configuration
+# ============================================================================
+VECTOR_STORE_PROVIDER=chroma           # chroma | azure_search
+CHAT_VECTOR_STORE_PROVIDER=chroma      # chroma | azure_search
+
+# Azure Search (if using azure_search provider)
+AZURE_SEARCH_ENDPOINT=
+AZURE_SEARCH_API_KEY=
+AZURE_SEARCH_INDEX_NAME=cortex-rag-chunks
+AZURE_SEARCH_EMBEDDING_DIM=1536
+
+# ============================================================================
+# Live Data Integration (NEW)
+# ============================================================================
+LIVE_DATA_PROVIDER=mock                # mock (default) | duckduckgo | newsapi
+NEWS_API_KEY=                          # Required if LIVE_DATA_PROVIDER=newsapi
+                                       # Get free key at: https://newsapi.org/register
+
+# ============================================================================
+# Unstructured Data (PDF ingestion)
+# ============================================================================
 UNSTRUCTURED_API_KEY=
 
-# Used by the Docker Compose stack (Docker/docker-compose.yml)
-REDIS_URL=redis://redis:6379/0
-GRAFANA_ADMIN_PASSWORD=admin
+# ============================================================================
+# Docker / Infrastructure
+# ============================================================================
+GRAFANA_ADMIN_PASSWORD=admin           # Used by Docker Compose stack
+PROMETHEUS_SCRAPE_INTERVAL=15s
+PROMETHEUS_EVALUATION_INTERVAL=15s

.gitignore

@@ -177,6 +177,7 @@ Temporary Items
 .apdisk
 data/rag_uploads/
 data/rag_vectorstore/
+data/library/
 
 # Windows
 Thumbs.db
@@ -244,4 +245,7 @@ src/ui/node_modules/
 
 # Vite / build cache
 .vite/
-dist/
+dist/
+# Any env variant (e.g. .env2) holds real credentials. Keep a template tracked.
+.env*
+!.env.example

Docker/alertmanager/alertmanager.yml

@@ -1,4 +1,4 @@
-# Alertmanager configuration for the personal-chatbot monitoring stack.
+# Alertmanager configuration for the Cortex (personal-chatbot) monitoring stack.
 #
 # This ships with NO notification channel configured — alerts are grouped and
 # de-duplicated but not delivered anywhere. Firing/resolved alerts are still

Docker/grafana/provisioning/dashboards/dashboard.yml

@@ -1,7 +1,7 @@
 apiVersion: 1
 
 providers:
-  - name: "personal-chatbot"
+  - name: "cortex"
     orgId: 1
     folder: ""
     type: file

Docker/grafana/provisioning/dashboards/json/api-overview.json

@@ -1,13 +1,13 @@
 {
-  "title": "Personal Chatbot - Overview",
+  "title": "Cortex - Overview",
   "uid": "personal-chatbot-overview",
   "schemaVersion": 39,
-  "version": 1,
+  "version": 2,
   "editable": true,
   "timezone": "browser",
   "time": { "from": "now-6h", "to": "now" },
   "refresh": "30s",
-  "tags": ["personal-chatbot"],
+  "tags": ["cortex", "personal-chatbot"],
   "panels": [
     {
       "id": 1,
@@ -258,6 +258,98 @@
         }
       ],
       "fieldConfig": { "defaults": { "unit": "percentunit", "min": 0, "max": 1 }, "overrides": [] }
+    },
+    {
+      "id": 16,
+      "type": "stat",
+      "title": "Total LLM cost (USD)",
+      "gridPos": { "h": 6, "w": 6, "x": 0, "y": 46 },
+      "datasource": { "type": "prometheus", "uid": "prometheus" },
+      "targets": [
+        { "expr": "sum(chat_cost_total)", "refId": "A" }
+      ],
+      "fieldConfig": {
+        "defaults": { "unit": "currencyUSD", "decimals": 2 },
+        "overrides": []
+      }
+    },
+    {
+      "id": 17,
+      "type": "stat",
+      "title": "Total embedding cost (USD)",
+      "gridPos": { "h": 6, "w": 6, "x": 6, "y": 46 },
+      "datasource": { "type": "prometheus", "uid": "prometheus" },
+      "targets": [
+        { "expr": "sum(embedding_cost_total)", "refId": "A" }
+      ],
+      "fieldConfig": {
+        "defaults": { "unit": "currencyUSD", "decimals": 4 },
+        "overrides": []
+      }
+    },
+    {
+      "id": 18,
+      "type": "stat",
+      "title": "Cost per request (avg)",
+      "gridPos": { "h": 6, "w": 6, "x": 12, "y": 46 },
+      "datasource": { "type": "prometheus", "uid": "prometheus" },
+      "targets": [
+        {
+          "expr": "sum(chat_cost_total) / sum(chat_model_requests_total)",
+          "legendFormat": "USD/request",
+          "refId": "A"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": { "unit": "currencyUSD", "decimals": 6 },
+        "overrides": []
+      }
+    },
+    {
+      "id": 19,
+      "type": "stat",
+      "title": "Embedding requests (total)",
+      "gridPos": { "h": 6, "w": 6, "x": 18, "y": 46 },
+      "datasource": { "type": "prometheus", "uid": "prometheus" },
+      "targets": [
+        { "expr": "sum(embedding_requests_total)", "refId": "A" }
+      ]
+    },
+    {
+      "id": 20,
+      "type": "timeseries",
+      "title": "LLM cost over time by model",
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 52 },
+      "datasource": { "type": "prometheus", "uid": "prometheus" },
+      "targets": [
+        {
+          "expr": "sum(rate(chat_cost_total[5m])) by (model)",
+          "legendFormat": "{{model}}",
+          "refId": "A"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": { "unit": "currencyUSD" },
+        "overrides": []
+      }
+    },
+    {
+      "id": 21,
+      "type": "timeseries",
+      "title": "Embedding cost over time",
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 52 },
+      "datasource": { "type": "prometheus", "uid": "prometheus" },
+      "targets": [
+        {
+          "expr": "rate(embedding_cost_total[5m])",
+          "legendFormat": "cost/sec",
+          "refId": "A"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": { "unit": "currencyUSD" },
+        "overrides": []
+      }
     }
   ]
 }

Docker/prometheus/alert_rules.yml

@@ -7,7 +7,7 @@ groups:
         labels:
           severity: critical
         annotations:
-          summary: "Personal chatbot API is down"
+          summary: "Cortex API is down"
           description: "Prometheus has not been able to scrape {{ $labels.instance }} (job {{ $labels.job }}) for 1 minute."
 
       - alert: PrometheusTargetMissing
@@ -31,7 +31,7 @@ groups:
         labels:
           severity: critical
         annotations:
-          summary: "High 5xx error rate on the chatbot API"
+          summary: "High 5xx error rate on the Cortex API"
           description: "More than 5% of HTTP requests have returned 5xx over the last 5 minutes (current: {{ $value | humanizePercentage }})."
 
       - alert: APIHighLatencyP95