Fix Quick Start: complete runnable example with embedding generation

README.md

@@ -34,25 +34,30 @@ Official leaderboard results on 8,400 queries:
 ### Installation
 
 ```bash
-pip install scikit-learn numpy joblib huggingface_hub
+pip install scikit-learn numpy joblib huggingface_hub sentence-transformers
 ```
 
-### Load Pre-trained Checkpoints
+### Complete Example
 
 ```python
 from huggingface_hub import snapshot_download
+from sentence_transformers import SentenceTransformer
 import sys
 
-# Download model
+# 1. Download router
 path = snapshot_download("JiaqiXue/r2-router")
 sys.path.insert(0, path)
 
 from router import R2Router
 
-# Load pre-trained KNN checkpoints (no training needed)
+# 2. Load pre-trained KNN checkpoints
 router = R2Router.from_pretrained(path)
 
-# Route a query (requires 1024-dim embedding from Qwen3-0.6B)
+# 3. Embed your query with Qwen3-0.6B (1024-dim)
+embedder = SentenceTransformer("Qwen/Qwen3-0.6B")
+embedding = embedder.encode("What is the capital of France?")
+
+# 4. Route!
 result = router.route(embedding)
 print(f"Model: {result['model_full_name']}")
 print(f"Token Budget: {result['token_limit']}")
@@ -70,22 +75,17 @@ sys.path.insert(0, path)
 
 from router import R2Router
 
-# Train KNN from the provided sub_10 training data
+# Train KNN from the provided sub_10 training data (custom hyperparameters)
 router = R2Router.from_training_data(path, k=80)
-
-# Route a query
-result = router.route(embedding)
 ```
 
-### Get Query Embeddings
-
-R2-Router uses [Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) embeddings (1024-dim). You can generate them with:
+### Alternative: vLLM Embeddings (Faster for Batches)
 
 ```python
-from sentence_transformers import SentenceTransformer
-
-model = SentenceTransformer("Qwen/Qwen3-0.6B")
-embedding = model.encode("What is the capital of France?")
+from vllm import LLM
+llm = LLM(model="Qwen/Qwen3-0.6B", runner="pooling")
+outputs = llm.embed(["What is the capital of France?"])
+embedding = outputs[0].outputs.embedding
 ```
 
 Or with vLLM for faster batch inference: