From 69276f619a1f03d35948719ff2460f79279bcc90 Mon Sep 17 00:00:00 2001
From: mlmz <54172054+minleminzui@users.noreply.github.com>
Date: Sun, 11 May 2025 23:22:11 +0800
Subject: [PATCH] doc: fix the erroneous documents and example codes about
 Alibaba-NLP/gme-Qwen2-VL-2B-Instruct (#6199)

---
 docs/backend/openai_api_embeddings.ipynb  |  8 ++++++
 docs/supported_models/embedding_models.md | 33 ++++++++++++++++++++---
 examples/runtime/multimodal_embedding.py  |  5 +---
 3 files changed, 39 insertions(+), 7 deletions(-)

diff --git a/docs/backend/openai_api_embeddings.ipynb b/docs/backend/openai_api_embeddings.ipynb
index 742185f82..89abeb830 100644
--- a/docs/backend/openai_api_embeddings.ipynb
+++ b/docs/backend/openai_api_embeddings.ipynb
@@ -171,6 +171,14 @@
    "source": [
     "terminate_process(embedding_process)"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Multi-Modal Embedding Model\n",
+    "Please refer to [Multi-Modal Embedding Model](../supported_models/embedding_models.md)"
+   ]
   }
  ],
  "metadata": {
diff --git a/docs/supported_models/embedding_models.md b/docs/supported_models/embedding_models.md
index 48ea379c5..738a201a7 100644
--- a/docs/supported_models/embedding_models.md
+++ b/docs/supported_models/embedding_models.md
@@ -6,15 +6,42 @@ SGLang provides robust support for embedding models by integrating efficient ser
 They are executed with `--is-embedding` and some may require `--trust-remote-code`
 ```
 
-## Example launch Command
+## Example Launch Command
 
 ```shell
 python3 -m sglang.launch_server \
-  --model-path Alibaba-NLP/gme-Qwen2-VL-2B-Instruct \  # example HF/local path
+  --model-path Alibaba-NLP/gme-Qwen2-VL-2B-Instruct \
   --is-embedding \
   --host 0.0.0.0 \
-  --port 30000 \
+  --chat-template gme-qwen2-vl \
+  --port 30000
 ```
+## Example Client Request
+```python
+import requests
+
+url = "http://127.0.0.1:30000"
+
+text_input = "Represent this image in embedding space."
+image_path = "https://huggingface.co/datasets/liuhaotian/llava-bench-in-the-wild/resolve/main/images/023.jpg"
+
+payload = {
+    "model": "gme-qwen2-vl",
+    "input": [
+        {
+            "text": text_input
+        },
+        {
+            "image": image_path
+        }
+    ],
+}
+
+response = requests.post(url + "/v1/embeddings", json=payload).json()
+
+print("Embeddings:", [x.get("embedding") for x in response.get("data", [])])
+```
+
 
 ## Supporting Matrixs
 
diff --git a/examples/runtime/multimodal_embedding.py b/examples/runtime/multimodal_embedding.py
index a924b381e..4e8d748b4 100644
--- a/examples/runtime/multimodal_embedding.py
+++ b/examples/runtime/multimodal_embedding.py
@@ -10,10 +10,7 @@ image_path = "https://huggingface.co/datasets/liuhaotian/llava-bench-in-the-wild
 
 payload = {
     "model": "gme-qwen2-vl",
-    "input": [
-        {"type": "text", "text": text_input},
-        {"type": "image", "url": image_path},
-    ],
+    "input": [{"text": text_input}, {"image": image_path}],
 }
 
 response = requests.post(url + "/v1/embeddings", json=payload).json()