From 2074a2e6b6d474eb524a3dc9bc560d11abddf417 Mon Sep 17 00:00:00 2001
From: thyecust <thy@mail.ecust.edu.cn>
Date: Sat, 12 Apr 2025 17:18:55 +0800
Subject: [PATCH] Fix: docs/backend/structured_outputs.ipynb (#4884)

---
 docs/backend/structured_outputs.ipynb | 39 ++++++++++++++++++++++++---
 1 file changed, 35 insertions(+), 4 deletions(-)

diff --git a/docs/backend/structured_outputs.ipynb b/docs/backend/structured_outputs.ipynb
index acb2620db..6fb611279 100644
--- a/docs/backend/structured_outputs.ipynb
+++ b/docs/backend/structured_outputs.ipynb
@@ -385,6 +385,10 @@
     "import json\n",
     "from pydantic import BaseModel, Field\n",
     "\n",
+    "from transformers import AutoTokenizer\n",
+    "\n",
+    "tokenizer = AutoTokenizer.from_pretrained(\"meta-llama/Meta-Llama-3.1-8B-Instruct\")\n",
+    "\n",
     "\n",
     "# Define the schema using Pydantic\n",
     "class CapitalInfo(BaseModel):\n",
@@ -393,10 +397,19 @@
     "\n",
     "\n",
     "# Make API request\n",
+    "messages = [\n",
+    "    {\n",
+    "        \"role\": \"user\",\n",
+    "        \"content\": \"Here is the information of the capital of France in the JSON format.\\n\",\n",
+    "    }\n",
+    "]\n",
+    "text = tokenizer.apply_chat_template(\n",
+    "    messages, tokenize=False, add_generation_prompt=True\n",
+    ")\n",
     "response = requests.post(\n",
     "    f\"http://localhost:{port}/generate\",\n",
     "    json={\n",
-    "        \"text\": \"Here is the information of the capital of France in the JSON format.\\n\",\n",
+    "        \"text\": text,\n",
     "        \"sampling_params\": {\n",
     "            \"temperature\": 0,\n",
     "            \"max_new_tokens\": 64,\n",
@@ -441,7 +454,7 @@
     "response = requests.post(\n",
     "    f\"http://localhost:{port}/generate\",\n",
     "    json={\n",
-    "        \"text\": \"Here is the information of the capital of France in the JSON format.\\n\",\n",
+    "        \"text\": text,\n",
     "        \"sampling_params\": {\n",
     "            \"temperature\": 0,\n",
     "            \"max_new_tokens\": 64,\n",
@@ -466,10 +479,19 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "messages = [\n",
+    "    {\n",
+    "        \"role\": \"user\",\n",
+    "        \"content\": \"Give me the information of the capital of France.\",\n",
+    "    }\n",
+    "]\n",
+    "text = tokenizer.apply_chat_template(\n",
+    "    messages, tokenize=False, add_generation_prompt=True\n",
+    ")\n",
     "response = requests.post(\n",
     "    f\"http://localhost:{port}/generate\",\n",
     "    json={\n",
-    "        \"text\": \"Give me the information of the capital of France.\",\n",
+    "        \"text\": text,\n",
     "        \"sampling_params\": {\n",
     "            \"max_new_tokens\": 128,\n",
     "            \"temperature\": 0,\n",
@@ -503,10 +525,19 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "messages = [\n",
+    "    {\n",
+    "        \"role\": \"user\",\n",
+    "        \"content\": \"Paris is the capital of\",\n",
+    "    }\n",
+    "]\n",
+    "text = tokenizer.apply_chat_template(\n",
+    "    messages, tokenize=False, add_generation_prompt=True\n",
+    ")\n",
     "response = requests.post(\n",
     "    f\"http://localhost:{port}/generate\",\n",
     "    json={\n",
-    "        \"text\": \"Paris is the capital of\",\n",
+    "        \"text\": text,\n",
     "        \"sampling_params\": {\n",
     "            \"temperature\": 0,\n",
     "            \"max_new_tokens\": 64,\n",