Simplify our docs with complicated functions into utils (#1807)

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

docs/embedding_model.ipynb

@@ -28,42 +28,16 @@
     }
    ],
    "source": [
-    "import subprocess\n",
-    "import time\n",
-    "import requests\n",
-    "\n",
     "# Equivalent to running this in the shell:\n",
     "# python -m sglang.launch_server --model-path Alibaba-NLP/gte-Qwen2-7B-instruct --port 30010 --host 0.0.0.0 --is-embedding --log-level error\n",
-    "embedding_process = subprocess.Popen(\n",
-    "    [\n",
-    "        \"python\",\n",
-    "        \"-m\",\n",
-    "        \"sglang.launch_server\",\n",
-    "        \"--model-path\",\n",
-    "        \"Alibaba-NLP/gte-Qwen2-7B-instruct\",\n",
-    "        \"--port\",\n",
-    "        \"30010\",\n",
-    "        \"--host\",\n",
-    "        \"0.0.0.0\",\n",
-    "        \"--is-embedding\",\n",
-    "        \"--log-level\",\n",
-    "        \"error\",\n",
-    "    ],\n",
-    "    text=True,\n",
-    "    stdout=subprocess.DEVNULL,\n",
-    "    stderr=subprocess.DEVNULL,\n",
-    ")\n",
+    "from sglang.utils import execute_shell_command, wait_for_server, terminate_process\n",
     "\n",
-    "while True:\n",
-    "    try:\n",
-    "        response = requests.get(\n",
-    "            \"http://localhost:30010/v1/models\",\n",
-    "            headers={\"Authorization\": \"Bearer None\"},\n",
-    "        )\n",
-    "        if response.status_code == 200:\n",
-    "            break\n",
-    "    except requests.exceptions.RequestException:\n",
-    "        time.sleep(1)\n",
+    "embedding_process = execute_shell_command(\"\"\"\n",
+    "python -m sglang.launch_server --model-path Alibaba-NLP/gte-Qwen2-7B-instruct \\\n",
+    "    --port 30010 --host 0.0.0.0 --is-embedding --log-level error\n",
+    "\"\"\")\n",
+    "\n",
+    "wait_for_server(\"http://localhost:30010\")\n",
     "\n",
     "print(\"Embedding server is ready. Proceeding with the next steps.\")"
    ]
@@ -134,6 +108,15 @@
     "embedding = response.data[0].embedding[:10]\n",
     "print(embedding)"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "terminate_process(embedding_process)"
+   ]
   }
  ],
  "metadata": {