Native api (#1886)

Co-authored-by: Chayenne <zhaochenyang@g.ucla.edu>

docs/backend/openai_api_vision.ipynb

@@ -36,7 +36,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -63,21 +63,19 @@
    "source": [
     "## Using cURL\n",
     "\n",
-    "Once the server is up, you can send test requests using curl."
+    "Once the server is up, you can send test requests using curl or requests."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
     "import subprocess\n",
     "\n",
     "curl_command = \"\"\"\n",
-    "curl http://localhost:30010/v1/chat/completions \\\n",
-    "  -H \"Content-Type: application/json\" \\\n",
-    "  -H \"Authorization: Bearer None\" \\\n",
+    "curl -s http://localhost:30010/v1/chat/completions \\\n",
     "  -d '{\n",
     "    \"model\": \"meta-llama/Llama-3.2-11B-Vision-Instruct\",\n",
     "    \"messages\": [\n",
@@ -109,14 +107,57 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Using OpenAI Python Client\n",
-    "\n",
-    "You can use the OpenAI Python API library to send requests."
+    "## Using OpenAI Compatible API w/ Requests"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import requests\n",
+    "\n",
+    "url = \"http://localhost:30010/v1/chat/completions\"\n",
+    "\n",
+    "data = {\n",
+    "    \"model\": \"meta-llama/Llama-3.2-11B-Vision-Instruct\",\n",
+    "    \"messages\": [\n",
+    "        {\n",
+    "            \"role\": \"user\",\n",
+    "            \"content\": [\n",
+    "                {\n",
+    "                    \"type\": \"text\",\n",
+    "                    \"text\": \"What’s in this image?\"\n",
+    "                },\n",
+    "                {\n",
+    "                    \"type\": \"image_url\",\n",
+    "                    \"image_url\": {\n",
+    "                        \"url\": \"https://github.com/sgl-project/sglang/blob/main/test/lang/example_image.png?raw=true\"\n",
+    "                    }\n",
+    "                }\n",
+    "            ]\n",
+    "        }\n",
+    "    ],\n",
+    "    \"max_tokens\": 300\n",
+    "}\n",
+    "\n",
+    "response = requests.post(url, json=data)\n",
+    "print_highlight(response.text)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Using OpenAI Python Client\n",
+    "\n",
+    "Also, you can use the OpenAI Python API library to send requests."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -160,7 +201,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -202,7 +243,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -233,6 +274,18 @@
    "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.7"
   }
  },
  "nbformat": 4,