diff --git a/examples/runtime/engine/embedding.py b/examples/runtime/engine/embedding.py
new file mode 100644
index 000000000..b927a188b
--- /dev/null
+++ b/examples/runtime/engine/embedding.py
@@ -0,0 +1,27 @@
+import sglang as sgl
+
+
+def main():
+    # Sample prompts.
+    prompts = [
+        "Hello, my name is",
+        "The president of the United States is",
+        "The capital of France is",
+        "The future of AI is",
+    ]
+    # Create an LLM.
+    llm = sgl.Engine(
+        model_path="Alibaba-NLP/gte-Qwen2-1.5B-instruct", is_embedding=True
+    )
+
+    outputs = llm.encode(prompts)
+    # Print the outputs (embedding vectors)
+    for prompt, output in zip(prompts, outputs):
+        print("===============================")
+        print(f"Prompt: {prompt}\nEmbedding vector: {output['embedding']}")
+
+
+# The __main__ condition is necessary here because we use "spawn" to create subprocesses
+# Spawn starts a fresh program every time, if there is no __main__, it will run into infinite loop to keep spawning processes from sgl.Engine
+if __name__ == "__main__":
+    main()
diff --git a/examples/runtime/engine/readme.md b/examples/runtime/engine/readme.md
index 1d70e99d0..986e0b12e 100644
--- a/examples/runtime/engine/readme.md
+++ b/examples/runtime/engine/readme.md
@@ -4,7 +4,8 @@
 SGLang provides a direct inference engine without the need for an HTTP server. There are generally two use cases:
 
 1. **Offline Batch Inference**
-2. **Custom Server on Top of the Engine**
+2. **Embedding Generation**
+3. **Custom Server on Top of the Engine**
 
 ## Examples
 
@@ -12,7 +13,11 @@ SGLang provides a direct inference engine without the need for an HTTP server. T
 
 In this example, we launch an SGLang engine and feed a batch of inputs for inference. If you provide a very large batch, the engine will intelligently schedule the requests to process efficiently and prevent OOM (Out of Memory) errors.
 
-### 2. [Custom Server](./custom_server.py)
+### 2. [Embedding Generation](./embedding.py)
+
+In this example, we launch an SGLang engine and feed a batch of inputs for embedding generation.
+
+### 3. [Custom Server](./custom_server.py)
 
 This example demonstrates how to create a custom server on top of the SGLang Engine. We use [Sanic](https://sanic.dev/en/) as an example. The server supports both non-streaming and streaming endpoints.