Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 6 additions & 4 deletions website/docs/intro.md
Original file line number Diff line number Diff line change
Expand Up @@ -46,8 +46,10 @@ Our testing shows significant improvements in model accuracy through specialized

## 🛠️ Architecture Overview

```mermaid
graph TB
import ZoomableMermaid from '@site/src/components/ZoomableMermaid';

<ZoomableMermaid title="Architecture Overview" defaultZoom={3.1}>
{`graph TB
Client[Client Request] --> Envoy[Envoy Proxy]
Envoy --> Router[Semantic Router ExtProc]

Expand All @@ -74,8 +76,8 @@ graph TB
Models --> Math[Math Model]
Models --> Creative[Creative Model]
Models --> Code[Code Model]
Models --> General[General Model]
```
Models --> General[General Model]`}
</ZoomableMermaid>

## 🎯 Use Cases

Expand Down
18 changes: 10 additions & 8 deletions website/docs/overview/mixture-of-models.md
Original file line number Diff line number Diff line change
Expand Up @@ -100,8 +100,10 @@ Different models excel at different tasks. MoM leverages this specialization:

#### 3. **Improved System Reliability**

```mermaid
graph TB
import ZoomableMermaid from '@site/src/components/ZoomableMermaid';

<ZoomableMermaid title="System Architecture Overview" defaultZoom={5.5}>
{`graph TB
subgraph "Single Model Risk"
SingleQuery[Query] --> SingleModel[GPT-4]
SingleModel -->|Failure| SingleFailure[Complete System Down]
Expand All @@ -114,8 +116,8 @@ graph TB
Router --> Model3[Model C]
Model1 -->|Failure| Fallback[Automatic Fallback]
Fallback --> Model2
end
```
end`}
</ZoomableMermaid>

**Reliability Benefits:**

Expand Down Expand Up @@ -276,8 +278,8 @@ subject_routing = {

MoM architecture supports various deployment strategies:

```mermaid
graph TB
<ZoomableMermaid title="System Architecture Overview" defaultZoom={5.5}>
{`graph TB
subgraph "Cloud Deployment"
CloudQueries[Queries] --> CloudRouter[Cloud Router]
CloudRouter --> OpenAI[OpenAI GPT]
Expand All @@ -295,8 +297,8 @@ graph TB
OnPremQueries[Queries] --> OnPremRouter[On-Prem Router]
OnPremRouter --> LocalLLaMA[Local LLaMA Models]
OnPremRouter --> FineTuned[Fine-tuned Specialized Models]
end
```
end`}
</ZoomableMermaid>

### 2. **A/B Testing and Gradual Rollouts**

Expand Down
10 changes: 6 additions & 4 deletions website/docs/overview/semantic-router-overview.md
Original file line number Diff line number Diff line change
Expand Up @@ -151,8 +151,10 @@ GPT-5 introduces a revolutionary **router-as-coordinator** architecture:

**Operational Flow:**

```mermaid
sequenceDiagram
import ZoomableMermaid from '@site/src/components/ZoomableMermaid';

<ZoomableMermaid title="Operational Flow" defaultZoom={5.5}>
{`sequenceDiagram
participant User
participant Router as GPT-5 Router
participant Math as Math Specialist
Expand All @@ -164,8 +166,8 @@ sequenceDiagram
Router->>Router: Analyze query intent
Router->>Math: Route to math specialist
Math->>Router: Mathematical solution
Router->>User: Optimized response
```
Router->>User: Optimized response`}
</ZoomableMermaid>

**Business Impact:**

Expand Down
11 changes: 7 additions & 4 deletions website/docs/proposals/nvidia-dynamo-integration.md
Original file line number Diff line number Diff line change
Expand Up @@ -528,8 +528,11 @@ prompt_guard:

### 4.3 System Architecture

```mermaid
graph TB
import ZoomableMermaid from '@site/src/components/ZoomableMermaid';

<ZoomableMermaid title="System Architecture Overview" defaultZoom={10.5}>

{`graph TB
Client[LLM Application<br/>OpenAI SDK]

subgraph Main["Main Processing Flow"]
Expand Down Expand Up @@ -628,8 +631,8 @@ graph TB
style DynamoRouter fill:#c8e6c9
style SemanticCache fill:#fff9c4
style KVBM fill:#fff9c4
style SL fill:#f5f5f5
```
style SL fill:#f5f5f5`}
</ZoomableMermaid>

**Architecture Layers:**

Expand Down
10 changes: 6 additions & 4 deletions website/docs/proposals/prompt-classification-routing.md
Original file line number Diff line number Diff line change
Expand Up @@ -121,8 +121,10 @@ embedding_similarity:

### High-Level System Design

```mermaid
graph TD
import ZoomableMermaid from '@site/src/components/ZoomableMermaid';

<ZoomableMermaid title="System Architecture Overview" defaultZoom={5.5}>
{`graph TD
A[Envoy External Processor<br/>semantic-router ExtProc] --> B[Request Handler<br/>handleModelRouting]

B --> C{Execution Path}
Expand Down Expand Up @@ -166,8 +168,8 @@ graph TD
style E2 fill:#fff9c4
style F fill:#c8e6c9
style H fill:#ffcdd2
style M fill:#c8e6c9
```
style M fill:#c8e6c9`}
</ZoomableMermaid>

### Component Breakdown

Expand Down
Loading