docs: add local install guide

Signed-off-by: bitliu <[email protected]>

Author: Xunzhuo

CONTRIBUTING.md

@@ -21,10 +21,9 @@ Before you begin, ensure you have the following installed:
 
 - **Rust** (latest stable version)
 - **Go** 1.24.1 or later
-- **Python** 3.8+ (for training and testing)
-- **Envoy Proxy**
 - **Hugging Face CLI** (`pip install huggingface_hub`)
 - **Make** (for build automation)
+- **Python** 3.8+ (Optiona: for training and testing)
 
 ### Initial Setup
 
@@ -40,7 +39,7 @@ Before you begin, ensure you have the following installed:
    ```
    This downloads the pre-trained classification models from Hugging Face.
 
-3. **Install Python dependencies:**
+3. **Install Python dependencies(Optional):**
    ```bash
    # For training and development
    pip install -r requirements.txt
@@ -245,7 +244,7 @@ The test suite includes:
 
 ## Getting Help
 
-- Check the [documentation](https://llm-semantic-router.readthedocs.io/en/latest/)
+- Check the [documentation](https://vllm-semantic-router.com/)
 - Review existing issues and pull requests
 - Ask questions in discussions or create a new issue
 

Makefile

@@ -20,9 +20,11 @@ build-router: rust
 	@mkdir -p bin
 	@cd src/semantic-router && go build -o ../../bin/router cmd/main.go
 
-# Run the router
+
+
+# Run the router with Classification API
 run-router: build-router
-	@echo "Running router..."
+	@echo "Running router with Classification API..."
 	@export LD_LIBRARY_PATH=${PWD}/candle-binding/target/release && \
 		./bin/router -config=config/config.yaml
 
@@ -79,20 +81,41 @@ clean:
 	cd candle-binding && cargo clean
 	rm -f bin/router
 
+# e9197711aa400477d30fe1ff07679e
+# sk-Hm8vN3qR7wX2pK9sL4tY6Z
+
 # Test the Envoy extproc
-test-prompt:
+test-auto-prompt-reasoning:
 	@echo "Testing Envoy extproc with curl (Math)..."
 	curl -X POST http://localhost:8801/v1/chat/completions \
+		-H "Authorization: Bearer e9197711aa400477d30fe1ff07679e" \
 		-H "Content-Type: application/json" \
-		-d '{"model": "auto", "messages": [{"role": "assistant", "content": "You are a professional math teacher. Explain math concepts clearly and show step-by-step solutions to problems."}, {"role": "user", "content": "What is the derivative of f(x) = x^3 + 2x^2 - 5x + 7?"}], "temperature": 0.7}'
-	@echo "Testing Envoy extproc with curl (Creative Writing)..."
+		-d '{"model": "auto", "messages": [{"role": "system", "content": "You are a professional math teacher. Explain math concepts clearly and show step-by-step solutions to problems."}, {"role": "user", "content": "What is the derivative of f(x) = x^3 + 2x^2 - 5x + 7?"}]}'
+
+# Test the Envoy extproc
+test-auto-prompt-no-reasoning:
+	@echo "Testing Envoy extproc with curl (Math)..."
 	curl -X POST http://localhost:8801/v1/chat/completions \
+		-H "Authorization: Bearer e9197711aa400477d30fe1ff07679e" \
 		-H "Content-Type: application/json" \
-		-d '{"model": "auto", "messages": [{"role": "assistant", "content": "You are a story writer. Create interesting stories with good characters and settings."}, {"role": "user", "content": "Write a short story about a space cat."}], "temperature": 0.7}'
-	@echo "Testing Envoy extproc with curl (Default/General)..."
-	curl -X POST http://localhost:8801/v1/chat/completions \
+		-d '{"model": "auto", "messages": [{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Who are you?"}]}'
+
+# Test the Envoy extproc
+test-prompt-deepseekv3-thinking:
+	@echo "Testing Envoy extproc with curl (Math)..."
+	curl -i -v -X POST http://localhost:8801/v1/chat/completions \
+		-H "Authorization: Bearer e9197711aa400477d30fe1ff07679e" \
 		-H "Content-Type: application/json" \
-		-d '{"model": "auto", "messages": [{"role": "assistant", "content": "You are a helpful assistant."}, {"role": "user", "content": "What is the capital of France?"}], "temperature": 0.7}'
+		-d '{"model": "deepseek-v31", "chat_template_kwargs": { "thinking": true }, "messages": [{"role": "system", "content": "You are a professional math teacher. Explain math concepts clearly and show step-by-step solutions to problems."}, {"role": "user", "content": "What is the derivative of f(x) = x^3 + 2x^2 - 5x + 7?"}]}'
+
+# Test the Envoy extproc
+test-prompt-deepseekv3-no-thinking:
+	@echo "Testing Envoy extproc with curl (Math)..."
+	curl -i -v -X POST http://localhost:8801/v1/chat/completions \
+		-H "Authorization: Bearer e9197711aa400477d30fe1ff07679e" \
+		-H "Content-Type: application/json" \
+		-d '{"model": "deepseek-v31", "chat_template_kwargs": { "thinking": false }, "messages": [{"role": "system", "content": "You are a professional math teacher. Explain math concepts clearly and show step-by-step solutions to problems."}, {"role": "user", "content": "What is the derivative of f(x) = x^3 + 2x^2 - 5x + 7?"}]}'
+
 # Test prompts that contain PII
 test-pii:
 	@echo "Testing Envoy extproc with curl (Credit card number)..."

README.md

@@ -2,12 +2,12 @@
 
 <img src="website/static/img/repo.png" alt="vLLM Semantic Router"/>
 
-[![Documentation](https://img.shields.io/badge/docs-read%20the%20docs-blue)](https://llm-semantic-router.readthedocs.io/en/latest/)
+[![Documentation](https://img.shields.io/badge/docs-read%20the%20docs-blue)](https://vllm-semantic-router.com)
 [![Hugging Face](https://img.shields.io/badge/🤗%20Hugging%20Face-Community-yellow)](https://huggingface.co/LLM-Semantic-Router)
 [![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](LICENSE)
 [![Crates.io](https://img.shields.io/crates/v/candle-semantic-router.svg)](https://crates.io/crates/candle-semantic-router)
 
-**📚 [Complete Documentation](https://llm-semantic-router.readthedocs.io/en/latest/) | 🚀 [Quick Start](https://llm-semantic-router.readthedocs.io/en/latest/getting-started/quick-start/) | 🏗️ [Architecture](https://llm-semantic-router.readthedocs.io/en/latest/architecture/system-architecture/) | 📖 [API Reference](https://llm-semantic-router.readthedocs.io/en/latest/api/router/)**
+**📚 [Complete Documentation](https://vllm-semantic-router.com) | 🚀 [Quick Start](https://vllm-semantic-router.com/docs/getting-started/installation) | 🏗️ [Architecture](https://vllm-semantic-router.com/docs/architecture/system-architecture/) | 📖 [API Reference](https://vllm-semantic-router.com/docs/api/router/)**
 
 ![](./website/static/img/code.png)
 
@@ -53,11 +53,11 @@ Cache the semantic representation of the prompt so as to reduce the number of pr
 
 For comprehensive documentation including detailed setup instructions, architecture guides, and API references, visit:
 
-**👉 [Complete Documentation at Read the Docs](https://llm-semantic-router.readthedocs.io/en/latest/)**
+**👉 [Complete Documentation at Read the Docs](https://vllm-semantic-router.com/)**
 
 The documentation includes:
-- **[Installation Guide](https://llm-semantic-router.readthedocs.io/en/latest/getting-started/installation/)** - Complete setup instructions
-- **[Quick Start](https://llm-semantic-router.readthedocs.io/en/latest/getting-started/quick-start/)** - Get running in 5 minutes
-- **[System Architecture](https://llm-semantic-router.readthedocs.io/en/latest/architecture/system-architecture/)** - Technical deep dive
-- **[Model Training](https://llm-semantic-router.readthedocs.io/en/latest/training/training-overview/)** - How classification models work
-- **[API Reference](https://llm-semantic-router.readthedocs.io/en/latest/api/router/)** - Complete API documentation
+- **[Installation Guide](https://vllm-semantic-router.com/docs/getting-started/installation/)** - Complete setup instructions
+- **[Quick Start](https://vllm-semantic-router.com/docs/getting-started/quick-start/)** - Get running in 5 minutes
+- **[System Architecture](https://vllm-semantic-router.com/docs/architecture/system-architecture/)** - Technical deep dive
+- **[Model Training](https://vllm-semantic-router.com/docs/training/training-overview/)** - How classification models work
+- **[API Reference](https://vllm-semantic-router.com/docs/api/router/)** - Complete API documentation

website/.docusaurus/client-manifest.json

@@ -375,9 +375,9 @@
     "1164": {
       "js": [
         {
-          "file": "assets/js/2f3f46e5.f86819b2.js",
-          "hash": "5a77916e940717e3",
-          "publicPath": "/assets/js/2f3f46e5.f86819b2.js"
+          "file": "assets/js/2f3f46e5.6d1dae68.js",
+          "hash": "919c825a6bd8feb4",
+          "publicPath": "/assets/js/2f3f46e5.6d1dae68.js"
         }
       ]
     },
@@ -492,9 +492,9 @@
     "2634": {
       "js": [
         {
-          "file": "assets/js/c4f5d8e4.b7348ab3.js",
-          "hash": "cb6219784beae8ad",
-          "publicPath": "/assets/js/c4f5d8e4.b7348ab3.js"
+          "file": "assets/js/c4f5d8e4.f8ace742.js",
+          "hash": "bc380a5416bb30a6",
+          "publicPath": "/assets/js/c4f5d8e4.f8ace742.js"
         }
       ]
     },
@@ -528,9 +528,9 @@
     "3253": {
       "js": [
         {
-          "file": "assets/js/ca183480.bfb760f1.js",
-          "hash": "dfb7903bee6e8fb1",
-          "publicPath": "/assets/js/ca183480.bfb760f1.js"
+          "file": "assets/js/ca183480.627344bc.js",
+          "hash": "15d8b888bf16b004",
+          "publicPath": "/assets/js/ca183480.627344bc.js"
         }
       ]
     },
@@ -591,9 +591,9 @@
     "4324": {
       "js": [
         {
-          "file": "assets/js/588bd741.01c8b76d.js",
-          "hash": "407bf0a9be50fd70",
-          "publicPath": "/assets/js/588bd741.01c8b76d.js"
+          "file": "assets/js/588bd741.fecec436.js",
+          "hash": "556b5e775305a95c",
+          "publicPath": "/assets/js/588bd741.fecec436.js"
         }
       ]
     },
@@ -645,9 +645,9 @@
     "5024": {
       "js": [
         {
-          "file": "assets/js/9aaa5480.8b1e2834.js",
-          "hash": "684034423c6a370c",
-          "publicPath": "/assets/js/9aaa5480.8b1e2834.js"
+          "file": "assets/js/9aaa5480.38156aea.js",
+          "hash": "192d409d40414aed",
+          "publicPath": "/assets/js/9aaa5480.38156aea.js"
         }
       ]
     },
@@ -663,9 +663,9 @@
     "5354": {
       "js": [
         {
-          "file": "assets/js/runtime~main.9ae70a89.js",
-          "hash": "fd9cd34fb19d0d1d",
-          "publicPath": "/assets/js/runtime~main.9ae70a89.js"
+          "file": "assets/js/runtime~main.46ee5a72.js",
+          "hash": "1c4d34f445433a42",
+          "publicPath": "/assets/js/runtime~main.46ee5a72.js"
         }
       ]
     },
@@ -888,9 +888,9 @@
     "8792": {
       "js": [
         {
-          "file": "assets/js/main.8144efe4.js",
-          "hash": "654f0b440b68cbfa",
-          "publicPath": "/assets/js/main.8144efe4.js"
+          "file": "assets/js/main.74135e71.js",
+          "hash": "80981465b58ce032",
+          "publicPath": "/assets/js/main.74135e71.js"
         }
       ]
     },

website/.docusaurus/docusaurus.config.mjs

@@ -5,7 +5,7 @@
  */
 export default {
   "title": "vLLM Semantic Router",
-  "tagline": "Intelligent Mixture-of-Models Router for Efficient LLM Inference",
+  "tagline": "Intelligent Auto Reasoning Router for Efficient LLM Inference on Mixture-of-Models",
   "favicon": "img/vllm.png",
   "url": "https://your-docusaurus-test-site.com",
   "baseUrl": "/",

website/docs/api/router.md

@@ -124,7 +124,7 @@ The router provides health check endpoints for monitoring:
 
 ### Router Health
 
-**Endpoint:** `GET http://localhost:50051/health`
+**Endpoint:** `GET http://localhost:8080/health`
 
 ```json
 {