Skip to content

Conversation

@Xunzhuo
Copy link
Member

@Xunzhuo Xunzhuo commented Nov 11, 2025

Description

This PR reorganizes the intelligent routing documentation to provide clearer, more focused guides for each routing method. The new structure aligns with the actual configuration files in config/intelligent-routing/ and provides comprehensive use cases for each approach.

Changes

Removed Files

  • overview.md - Replaced with focused routing guides
  • reasoning.md - Replaced with focused routing guides

New Files (4 focused routing guides)

  1. domain-routing.md - Fine-tuned classification routing (efficient, specialized)

    • Based on config/intelligent-routing/in-tree/bert_classification.yaml
    • Supports ModernBERT, Qwen3-Embedding, EmbeddingGemma models
    • LoRA adapter support for multi-task classification
    • Use cases: academic domains, PII detection, multilingual support
  2. embedding-routing.md - Semantic similarity routing (scalable, fast)

    • Based on config/intelligent-routing/in-tree/embedding.yaml
    • Multiple embedding models with aggregation methods
    • Use cases: customer support, product inquiries, scalable categories
  3. keyword-routing.md - Keyword-based routing (transparent, compliant)

    • Based on config/intelligent-routing/in-tree/keyword.yaml
    • Boolean operators (OR, AND, NOR) and regex patterns
    • Use cases: compliance, security, spam filtering, audit trails
  4. mcp-routing.md - External service routing (extensible, private)

    • Based on config/intelligent-routing/out-tree/config-mcp-classifier.yaml
    • HTTP API integration for custom classification logic
    • Use cases: LLM-powered classification, custom business rules, private deployment

Updated Files

  • lora-routing.md - Clarified that LoRA routing combines other routing methods (domain/embedding/keyword/MCP) with vLLM's LoRA adapter support
  • sidebars.ts - Updated navigation to reflect new structure

Structure Improvements

Each guide now follows a consistent, user-friendly structure:

  • Friendly introduction - "This guide shows you how to..."
  • Key Advantages - Clear benefits of each approach
  • What Problem Does It Solve - Problem-solution context
  • When to Use - Decision guidance for choosing the right method
  • Configuration - Practical examples with explanations
  • Real-World Use Cases - 5-6 scenarios with Problem/Solution/Impact
  • Next Steps - Links to related documentation

Benefits

  1. Clearer organization - Each routing method has its own focused guide
  2. Better discoverability - Users can quickly find the right routing method for their use case
  3. Comprehensive examples - Real-world use cases with concrete metrics
  4. Consistent structure - All guides follow the same format for easy navigation
  5. Accurate technical details - Reflects current multi-model support (ModernBERT, Qwen3, Gemma) and LoRA capabilities

BEFORE SUBMITTING, PLEASE READ THE CHECKLIST BELOW AND FILL IN THE DESCRIPTION ABOVE


  • Make sure the code changes pass the pre-commit checks.
  • Sign-off your commit by using -s when doing git commit
  • Try to classify PRs for easy understanding of the type of changes, such as [Bugfix], [Feat], and [CI].

Pull Request opened by Augment Code with guidance from the PR author

- Remove overview.md and reasoning.md
- Create 4 new focused routing guides:
  - domain-routing.md: Fine-tuned classification (efficient, specialized)
  - embedding-routing.md: Semantic similarity routing (scalable, fast)
  - keyword-routing.md: Keyword-based routing (transparent, compliant)
  - mcp-routing.md: External service routing (extensible, private)
- Update lora-routing.md to clarify it combines other routing methods
- Update sidebar navigation to reflect new structure
- Add comprehensive use cases and problem-solution context to each guide
- Align all guides with consistent structure and friendly tone

Signed-off-by: bitliu <bitliu@tencent.com>
@netlify
Copy link

netlify bot commented Nov 11, 2025

Deploy Preview for vllm-semantic-router ready!

Name Link
🔨 Latest commit e96bf84
🔍 Latest deploy log https://app.netlify.com/projects/vllm-semantic-router/deploys/691350ed3bb4470008a40686
😎 Deploy Preview https://deploy-preview-636--vllm-semantic-router.netlify.app
📱 Preview on mobile
Toggle QR Code...

QR Code

Use your smartphone camera to open QR code link.

To edit notification comments on pull requests, go to your Netlify project configuration.

@github-actions
Copy link

github-actions bot commented Nov 11, 2025

👥 vLLM Semantic Team Notification

The following members have been identified for the changed files in this PR and have been automatically assigned:

📁 website

Owners: @Xunzhuo, @rootfs, @yuluo-yx
Files changed:

  • website/docs/tutorials/intelligent-route/domain-routing.md
  • website/docs/tutorials/intelligent-route/embedding-routing.md
  • website/docs/tutorials/intelligent-route/keyword-routing.md
  • website/docs/tutorials/intelligent-route/mcp-routing.md
  • website/docs/tutorials/intelligent-route/lora-routing.md
  • website/sidebars.ts

vLLM

🎉 Thanks for your contributions!

This comment was automatically generated based on the OWNER files in the repository.

- Escape < characters in numeric comparisons (&lt;1%, &lt;1ms, etc.)
- Add blank lines around fenced code blocks
- Remove multiple consecutive blank lines at end of files
- Fix list formatting around code blocks

Signed-off-by: bitliu <bitliu@tencent.com>
Copy link
Contributor

@yuluo-yx yuluo-yx left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

/lgtm

@rootfs rootfs merged commit f193a19 into main Nov 11, 2025
9 checks passed
yossiovadia pushed a commit to yossiovadia/semantic-router that referenced this pull request Nov 11, 2025
…llm-project#636)

* [Doc] Reorganize intelligent routing tutorials into focused guides

- Remove overview.md and reasoning.md
- Create 4 new focused routing guides:
  - domain-routing.md: Fine-tuned classification (efficient, specialized)
  - embedding-routing.md: Semantic similarity routing (scalable, fast)
  - keyword-routing.md: Keyword-based routing (transparent, compliant)
  - mcp-routing.md: External service routing (extensible, private)
- Update lora-routing.md to clarify it combines other routing methods
- Update sidebar navigation to reflect new structure
- Add comprehensive use cases and problem-solution context to each guide
- Align all guides with consistent structure and friendly tone

Signed-off-by: bitliu <bitliu@tencent.com>

* [Doc] Fix MDX compilation and markdown lint errors

- Escape < characters in numeric comparisons (&lt;1%, &lt;1ms, etc.)
- Add blank lines around fenced code blocks
- Remove multiple consecutive blank lines at end of files
- Fix list formatting around code blocks

Signed-off-by: bitliu <bitliu@tencent.com>

---------

Signed-off-by: bitliu <bitliu@tencent.com>
@Xunzhuo Xunzhuo deleted the docs/reorganize-intelligent-routing-tutorials branch November 16, 2025 15:02
szedan-rh pushed a commit to szedan-rh/semantic-router that referenced this pull request Nov 19, 2025
…llm-project#636)

* [Doc] Reorganize intelligent routing tutorials into focused guides

- Remove overview.md and reasoning.md
- Create 4 new focused routing guides:
  - domain-routing.md: Fine-tuned classification (efficient, specialized)
  - embedding-routing.md: Semantic similarity routing (scalable, fast)
  - keyword-routing.md: Keyword-based routing (transparent, compliant)
  - mcp-routing.md: External service routing (extensible, private)
- Update lora-routing.md to clarify it combines other routing methods
- Update sidebar navigation to reflect new structure
- Add comprehensive use cases and problem-solution context to each guide
- Align all guides with consistent structure and friendly tone

Signed-off-by: bitliu <bitliu@tencent.com>

* [Doc] Fix MDX compilation and markdown lint errors

- Escape < characters in numeric comparisons (&lt;1%, &lt;1ms, etc.)
- Add blank lines around fenced code blocks
- Remove multiple consecutive blank lines at end of files
- Fix list formatting around code blocks

Signed-off-by: bitliu <bitliu@tencent.com>

---------

Signed-off-by: bitliu <bitliu@tencent.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants