fix ipynb

Author: thyecust

docs/backend/structured_outputs.ipynb

@@ -385,6 +385,12 @@
     "import json\n",
     "from pydantic import BaseModel, Field\n",
     "\n",
+    "from transformers import AutoTokenizer\n",
+    "tokenizer = AutoTokenizer.from_pretrained(\"meta-llama/Meta-Llama-3.1-8B-Instruct\")\n",
+    "\n",
+    "prompt = lambda x : tokenizer.apply_chat_template(\n",
+    "    x, tokenize=False, add_generation_prompt=True\n",
+    ")\n",
     "\n",
     "# Define the schema using Pydantic\n",
     "class CapitalInfo(BaseModel):\n",
@@ -396,7 +402,7 @@
     "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\": prompt(\"Here is the information of the capital of France in the JSON format.\\n\"),\n",
     "        \"sampling_params\": {\n",
     "            \"temperature\": 0,\n",
     "            \"max_new_tokens\": 64,\n",
@@ -441,7 +447,7 @@
     "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\": prompt(\"Here is the information of the capital of France in the JSON format.\\n\"),\n",
     "        \"sampling_params\": {\n",
     "            \"temperature\": 0,\n",
     "            \"max_new_tokens\": 64,\n",
@@ -469,7 +475,7 @@
     "response = requests.post(\n",
     "    f\"http://localhost:{port}/generate\",\n",
     "    json={\n",
-    "        \"text\": \"Give me the information of the capital of France.\",\n",
+    "        \"text\": prompt(\"Give me the information of the capital of France.\"),\n",
     "        \"sampling_params\": {\n",
     "            \"max_new_tokens\": 128,\n",
     "            \"temperature\": 0,\n",
@@ -506,7 +512,7 @@
     "response = requests.post(\n",
     "    f\"http://localhost:{port}/generate\",\n",
     "    json={\n",
-    "        \"text\": \"Paris is the capital of\",\n",
+    "        \"text\": prompt(\"Paris is the capital of\"),\n",
     "        \"sampling_params\": {\n",
     "            \"temperature\": 0,\n",
     "            \"max_new_tokens\": 64,\n",
@@ -530,16 +536,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from transformers import AutoTokenizer\n",
-    "\n",
-    "# generate an answer\n",
-    "tokenizer = AutoTokenizer.from_pretrained(\"meta-llama/Meta-Llama-3.1-8B-Instruct\")\n",
-    "\n",
-    "text = tokenizer.apply_chat_template(\n",
-    "    messages, tokenize=False, add_generation_prompt=True\n",
-    ")\n",
     "payload = {\n",
-    "    \"text\": text,\n",
+    "    \"text\": prompt(messages),\n",
     "    \"sampling_params\": {\n",
     "        \"structural_tag\": json.dumps(\n",
     "            {\n",