v8.10

mythz · mythz · commit dc24b337c5da · 2025-11-13T23:03:26.000+08:00
diff --git a/MyApp/_pages/ai-chat-analytics.md b/MyApp/_pages/ai-chat-analytics.md
@@ -0,0 +1,80 @@
+---
+title: Admin UI Analytics for AI Chat
+---
+
+ServiceStack's [AI Chat](/ai-chat-api) feature provides a unified API for integrating multiple AI providers into your applications. To gain visibility into usage patterns, costs, and performance across your AI infrastructure, the platform includes comprehensive chat history persistence and analytics capabilities.
+
+:::sh
+x mix chat
+:::
+
+Or by referencing the **ServiceStack.AI.Chat** NuGet package and adding the `ChatFeature` plugin:
+
+```csharp
+services.AddPlugin(new ChatFeature {
+    EnableProviders = [
+        "servicestack",
+    ]
+});
+```
+
+## AI Chat History Persistence
+
+Enabling chat history persistence allows you to maintain a complete audit trail of all AI interactions, track token consumption, monitor costs across providers and models, and analyze usage patterns over time that captures every 
+request and response flowing through AI Chat's UI, external OpenAI endpoints and internal `IChatStore` requests.
+
+### Database Storage Options
+
+ServiceStack provides two storage implementations to suit different deployment scenarios:
+
+`DbChatStore` - A universal solution that stores chat history in a single table compatible with any RDBMS 
+[supported by OrmLite](/ormlite/getting-started):
+
+```csharp
+services.AddSingleton<IChatStore,DbChatStore>();
+```
+
+`PostgresChatStore` - An optimized implementation for PostgreSQL that leverages monthly table partitioning for improved query performance and data management:
+
+```csharp
+services.AddSingleton<IChatStore, PostgresChatStore>();
+```
+
+Both implementations utilize indexed queries with result limits to ensure consistent performance even as your chat history grows. The partitioned approach in PostgreSQL offers additional benefits for long-term data retention and archival strategies.
+
+## Admin UI Analytics
+
+Once chat history persistence is enabled, the Admin UI provides comprehensive analytics dashboards that deliver actionable insights into your AI infrastructure. The analytics interface offers multiple views to help you understand costs, optimize token usage, and monitor activity patterns across all configured AI providers and models.
+
+The analytics dashboard includes three primary tabs:
+
+- **Cost Analysis** - Track spending across providers and models with daily and monthly breakdowns
+- **Token Usage** - Monitor input and output token consumption to identify optimization opportunities
+- **Activity** - Review detailed request logs with full conversation history and metadata
+
+These visualizations enable data-driven decisions about provider selection, model usage, and cost optimization strategies.
+
+### Cost Analysis
+
+The Cost Analysis tab provides financial visibility into your AI operations with interactive visualizations showing spending distribution across providers and models. Daily cost trends help identify usage spikes, while monthly aggregations reveal long-term patterns. Pie charts break down costs by individual models and providers, making it easy to identify your most expensive AI resources and opportunities for cost optimization.
+
+:::{.wideshot}
+![](/img/pages/ai-chat/admin-chat-costs.webp)
+:::
+
+### Token Usage
+
+The Token Usage tab tracks both input (prompt) and output (completion) tokens across all requests. Daily usage charts display token consumption trends over time, while model and provider breakdowns show which AI resources consume the most tokens. This granular visibility helps optimize prompt engineering, identify inefficient usage patterns, and forecast capacity requirements.
+
+:::{.wideshot}
+![](/img/pages/ai-chat/admin-chat-tokens.webp)
+:::
+
+### Activity Log
+
+The Activity tab maintains a searchable log of all AI chat requests, displaying timestamps, models, providers, and associated costs. Clicking any request opens a detailed view showing the complete conversation including user prompts, AI responses, token counts, duration, and the full request payload. This audit trail is invaluable for debugging, quality assurance, and understanding how your AI features are being used in production.
+
+:::{.wideshot}
+![](/img/pages/ai-chat/admin-chat-activity.webp)
+:::
+
diff --git a/MyApp/_pages/ai-chat-api.md b/MyApp/_pages/ai-chat-api.md
@@ -477,4 +477,75 @@ llms --serve 8000
 Incidentally as [llms.py UI](https://servicestack.net/posts/llms-py-ui) and AI Chat utilize the same UI you can 
 use its **import/export** features to transfer your AI Chat History between them.
 
-Checkout the [llms.py GitHub repo](https://github.com/ServiceStack/llms) for even more features.
+Checkout the [llms.py GitHub repo](https://github.com/ServiceStack/llms) for even more features.
+
+## FREE Gemini, Minimax M2, GLM 4.6, Kimi K2 in AI Chat
+
+To give AI Chat instant utility, we're making available a free `servicestack` OpenAI Chat provider that can be enabled with:
+
+```csharp
+services.AddPlugin(new ChatFeature {
+    EnableProviders = [
+        "servicestack",
+        // "groq",
+        // "google_free",
+        // "openrouter_free",
+        // "ollama",
+        // "google",
+        // "anthropic",
+        // "openai",
+        // "grok",
+        // "qwen",
+        // "z.ai",
+        // "mistral",
+        // "openrouter",
+    ]
+});
+```
+
+The `servicestack` provider is configured with a default `llms.json` which enables access to Gemini and the
+best value OSS models for FREE:
+
+```json
+{
+  "providers": {
+    "servicestack": {
+      "enabled": false,
+      "type": "OpenAiProvider",
+      "base_url": "http://okai.servicestack.com",
+      "api_key": "$SERVICESTACK_LICENSE",
+      "models": {
+        "gemini-flash-latest": "gemini-flash-latest",
+        "gemini-flash-lite-latest": "gemini-flash-lite-latest",
+        "kimi-k2": "kimi-k2",
+        "kimi-k2-thinking": "kimi-k2-thinking",
+        "minimax-m2": "minimax-m2",
+        "glm-4.6": "glm-4.6",
+        "gpt-oss:20b": "gpt-oss:20b",
+        "gpt-oss:120b": "gpt-oss:120b",
+        "llama4:400b": "llama4:400b",
+        "mistral-small3.2:24b": "mistral-small3.2:24b"
+      }
+    }
+  }
+}
+```
+
+The `servicestack` provider requires the `SERVICESTACK_LICENSE` Environment Variable, although any ServiceStack License Key can be used, including expired and Free ones.
+
+:::{.not-prose}
+:::{.my-8 .max-w-3xl .mx-auto .rounded-lg .overflow-hidden .shadow .hover:shadow-xl}
+[![](/img/pages/ai-chat/llms-syntax.webp)](/ai-chat-ui)
+:::
+:::
+
+### FREE for Personal Usage
+
+To be able to maintain this as a free service we're limiting usage for development or personal assistance and research 
+by limiting usage to **60 requests /hour** which should be more than enough for most personal usage and research whilst 
+deterring usage in automated tools or usage in production.
+
+:::tip info
+Rate limiting is implemented with a sliding [Token Bucket algorithm](https://en.wikipedia.org/wiki/Token_bucket) 
+that replenishes 1 additional request every 60s
+:::
diff --git a/MyApp/_pages/releases/v8_10.md b/MyApp/_pages/releases/v8_10.md
@@ -90,7 +90,7 @@ We're introducing three production-ready React templates, each optimized for dif
 
 ## Comprehensive React Component Library
 
-All three templates leverage our new [React Component Gallery](https://react.servicestack.net)—a high-fidelity port of our proven [Vue Component Library](https://docs.servicestack.net/vue/) and [Blazor Component Library](https://blazor.servicestack.net). This comprehensive collection provides everything needed to build highly productive, modern and responsive web applications.
+All three templates leverage our new [React Component Gallery](https://react.servicestack.net)—a high-fidelity port of our proven [Vue Component Library](/vue/) and [Blazor Component Library](https://blazor.servicestack.net). This comprehensive collection provides everything needed to build highly productive, modern and responsive web applications.
 
 :::{.not-prose}
 :::{.my-8 .max-w-3xl .mx-auto .rounded-lg .overflow-hidden .shadow .hover:shadow-xl}
@@ -111,7 +111,7 @@ ServiceStack's first-class React support positions your applications at the fore
 ## TypeScript Data Models
 
 As AI Models are not as adept at generating C# APIs or Migrations yet, they excel at generating TypeScript code, which our 
-[TypeScript Data Models](https://docs.servicestack.net/autoquery/okai-models) feature can take advantage of by generating all the C# AutoQuery CRUD APIs and DB Migrations needing to support it.
+[TypeScript Data Models](/autoquery/okai-models) feature can take advantage of by generating all the C# AutoQuery CRUD APIs and DB Migrations needing to support it.
 
 With just a TypeScript Definition:
 
@@ -125,11 +125,11 @@ npx okai Bookings.d.ts
 
 This is enough to generate a complete CRUD UI to manage Bookings 
 in your React App with the [React AutoQueryGrid Component](https://react.servicestack.net/gallery/autoquerygrid).
-or with ServiceStack's built-in [Locode UI](https://docs.servicestack.net/locode/):
+or with ServiceStack's built-in [Locode UI](/locode/):
 
 :::{.not-prose}
 :::{.my-8 .max-w-3xl .mx-auto .rounded-lg .overflow-hidden .shadow .hover:shadow-xl}
-[![](/img/pages/react/bookings-locode.webp)](https://docs.servicestack.net/locode/)
+[![](/img/pages/react/bookings-locode.webp)](/locode/)
 :::
 :::
 
@@ -313,7 +313,7 @@ Beyond llms.py's core features, ServiceStack's AI Chat adds integrated authentic
 
 ## AI Chat Admin Analytics
 
-ServiceStack's [AI Chat](https://docs.servicestack.net/ai-chat-api) feature provides a unified API for integrating multiple AI providers into your applications. To gain visibility into usage patterns, costs, and performance across your AI infrastructure, the platform includes comprehensive chat history persistence and analytics capabilities.
+ServiceStack's [AI Chat](/ai-chat-api) feature provides a unified API for integrating multiple AI providers into your applications. To gain visibility into usage patterns, costs, and performance across your AI infrastructure, the platform includes comprehensive chat history persistence and analytics capabilities.
 
 :::sh
 x mix chat
@@ -339,7 +339,7 @@ request and response flowing through AI Chat's UI, external OpenAI endpoints and
 ServiceStack provides two storage implementations to suit different deployment scenarios:
 
 `DbChatStore` - A universal solution that stores chat history in a single table compatible with any RDBMS 
-[supported by OrmLite](https://docs.servicestack.net/ormlite/getting-started):
+[supported by OrmLite](/ormlite/getting-started):
 
 ```csharp
 services.AddSingleton<IChatStore,DbChatStore>();
@@ -461,11 +461,11 @@ The lightweight implementation adds minimal footprint to your application while
 
 The `servicestack` provider requires the `SERVICESTACK_LICENSE` Environment Variable, although any ServiceStack License Key can be used, including expired and Free ones.
 
-Learn more about [AI Chat's UI](https://docs.servicestack.net/ai-chat-ui):
+Learn more about [AI Chat's UI](/ai-chat-ui):
 
 :::{.not-prose}
 :::{.my-8 .max-w-3xl .mx-auto .rounded-lg .overflow-hidden .shadow .hover:shadow-xl}
-[![](/img/pages/ai-chat/llms-syntax.webp)](https://docs.servicestack.net/ai-chat-ui)
+[![](/img/pages/ai-chat/llms-syntax.webp)](/ai-chat-ui)
 :::
 :::
 
diff --git a/MyApp/_pages/sidebar.json b/MyApp/_pages/sidebar.json
@@ -191,6 +191,10 @@
         "text": "AI Chat - ChatGPT-like UI",
         "link": "/ai-chat-ui"
       },
+      {
+        "text": "AI Chat - Admin UI Analytics",
+        "link": "/ai-chat-analytics"
+      },      
       {
         "text": "Custom API Explorer UI",
         "link": "/ai-chat-custom-explorer-ui"
