Update README.md with TEI support (#16)

- Update README.md (3e955468f0e8204455096de62f1ae222bee9702f)


Co-authored-by: Alvaro Bartolome <[email protected]>

README.md

@@ -7,6 +7,7 @@ tags:
 - sentence-transformers
 - sentence-similarity
 - feature-extraction
+- text-embeddings-inference
 ---
 # Qwen3-Embedding-8B
 
@@ -197,6 +198,29 @@ print(scores.tolist())
 
 📌 **Tip**: We recommend that developers customize the `instruct` according to their specific scenarios, tasks, and languages. Our tests have shown that in most retrieval scenarios, not using an `instruct` on the query side can lead to a drop in retrieval performance by approximately 1% to 5%.
 
+### Text Embeddings Inference (TEI) Usage
+
+You can either run / deploy TEI on NVIDIA GPUs as:
+
+```bash
+docker run --gpus all -p 8080:80 -v hf_cache:/data --pull always ghcr.io/huggingface/text-embeddings-inference:1.7.2 --model-id Qwen/Qwen3-Embedding-8B --dtype float16
+```
+
+Or on CPU devices as:
+
+```bash
+docker run -p 8080:80 -v hf_cache:/data --pull always ghcr.io/huggingface/text-embeddings-inference:cpu-1.7.2 --model-id Qwen/Qwen3-Embedding-8B --dtype float16
+```
+
+And then, generate the embeddings sending a HTTP POST request as:
+
+```bash
+curl http://localhost:8080/embed \
+    -X POST \
+    -d '{"inputs": ["Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery: What is the capital of China?", "Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery: Explain gravity"]}' \
+    -H "Content-Type: application/json"
+```
+
 ## Evaluation
 
 ### MTEB (Multilingual)