{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Launch A Server\n",
    "\n",
    "Launch the server with a reasoning model (Qwen 3.5-4B) and reasoning parser."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sglang import separate_reasoning, assistant_begin, assistant_end\n",
    "from sglang import assistant, function, gen, system, user\n",
    "from sglang import image\n",
    "from sglang import RuntimeEndpoint, set_default_backend\n",
    "from sglang.srt.utils import load_image\n",
    "from sglang.test.test_utils import is_in_ci\n",
    "from sglang.utils import print_highlight, terminate_process, wait_for_server\n",
    "\n",
    "\n",
    "if is_in_ci():\n",
    "    from patch import launch_server_cmd\n",
    "else:\n",
    "    from sglang.utils import launch_server_cmd\n",
    "\n",
    "\n",
    "server_process, port = launch_server_cmd(\n",
    "    \"python3 -m sglang.launch_server --model-path Qwen/Qwen3-4B --reasoning-parser qwen3 --host 0.0.0.0\"\n",
    ")\n",
    "\n",
    "wait_for_server(f\"http://localhost:{port}\")\n",
    "print(f\"Server started on http://localhost:{port}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Set the default backend. Note: you can set chat_template_name in RontimeEndpoint. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "set_default_backend(\n",
    "    RuntimeEndpoint(f\"http://localhost:{port}\", chat_template_name=\"qwen\")\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's start with a basic question-answering task. And see how the reasoning content is generated."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "@function\n",
    "def basic_qa(s, question):\n",
    "    s += system(f\"You are a helpful assistant than can answer questions.\")\n",
    "    s += user(question)\n",
    "    s += assistant_begin()\n",
    "    s += gen(\"answer\", max_tokens=512)\n",
    "    s += assistant_end()\n",
    "\n",
    "\n",
    "state = basic_qa(\"List 3 countries and their capitals.\")\n",
    "print_highlight(state[\"answer\"])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "With `separate_reasoning`, you can move the reasoning content to `{param_name}_reasoning_content` in the state."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "@function\n",
    "def basic_qa_separate_reasoning(s, question):\n",
    "    s += system(f\"You are a helpful assistant than can answer questions.\")\n",
    "    s += user(question)\n",
    "    s += assistant_begin()\n",
    "    s += separate_reasoning(gen(\"answer\", max_tokens=512), model_type=\"qwen3\")\n",
    "    s += assistant_end()\n",
    "\n",
    "\n",
    "reasoning_state = basic_qa_separate_reasoning(\"List 3 countries and their capitals.\")\n",
    "print_highlight(reasoning_state.stream_executor.variable_event.keys())\n",
    "print_highlight(\n",
    "    f\"\\nSeparated Reasoning Content:\\n{reasoning_state['answer_reasoning_content']}\"\n",
    ")\n",
    "\n",
    "print_highlight(f\"\\n\\nContent:\\n{reasoning_state['answer']}\")\n",
    "print_highlight(f\"\\n\\nMessages:\\n{reasoning_state.messages()[-1]}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "`separate_reasoning` can also be used in multi-turn conversations."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "@function\n",
    "def multi_turn_qa(s):\n",
    "    s += system(f\"You are a helpful assistant than can answer questions.\")\n",
    "    s += user(\"Please give me a list of 3 countries and their capitals.\")\n",
    "    s += assistant(\n",
    "        separate_reasoning(gen(\"first_answer\", max_tokens=512), model_type=\"qwen3\")\n",
    "    )\n",
    "    s += user(\"Please give me another list of 3 countries and their capitals.\")\n",
    "    s += assistant(\n",
    "        separate_reasoning(gen(\"second_answer\", max_tokens=512), model_type=\"qwen3\")\n",
    "    )\n",
    "    return s\n",
    "\n",
    "\n",
    "reasoning_state = multi_turn_qa()\n",
    "print_highlight(f\"\\n\\nfirst_answer:\\n{reasoning_state['first_answer']}\")\n",
    "print_highlight(\n",
    "    f\"\\n\\nfirst_answer_reasoning_content:\\n{reasoning_state['first_answer_reasoning_content']}\"\n",
    ")\n",
    "print_highlight(f\"\\n\\nsecond_answer:\\n{reasoning_state['second_answer']}\")\n",
    "print_highlight(\n",
    "    f\"\\n\\nsecond_answer_reasoning_content:\\n{reasoning_state['second_answer_reasoning_content']}\"\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Using No thinking as Qwen 3's advanced feature \n",
    "\n",
    "sglang separate_reasoning is particularly useful when combined with Qwen 3's advanced feature.\n",
    "\n",
    "[Qwen 3's advanced usages](https://qwenlm.github.io/blog/qwen3/#advanced-usages)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "reasoning_state = basic_qa_separate_reasoning(\n",
    "    \"List 3 countries and their capitals. /no_think\"\n",
    ")\n",
    "print_highlight(f\"Reasoning Content:\\n{reasoning_state['answer_reasoning_content']}\")\n",
    "print_highlight(f\"Content:\\n{reasoning_state['answer']}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "`separate_reasoning` can also be used in regular expression generation."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "@function\n",
    "def regular_expression_gen(s):\n",
    "    s += user(\n",
    "        \"What is the IP address of the Google DNS servers? just provide the answer\"\n",
    "    )\n",
    "    s += assistant(\n",
    "        separate_reasoning(\n",
    "            gen(\n",
    "                \"answer\",\n",
    "                temperature=0,\n",
    "                regex=r\"((25[0-5]|2[0-4]\\d|[01]?\\d\\d?).){3}(25[0-5]|2[0-4]\\d|[01]?\\d\\d?)\",\n",
    "                max_tokens=512,\n",
    "            ),\n",
    "            model_type=\"qwen3\",\n",
    "        ),\n",
    "    )\n",
    "\n",
    "\n",
    "reasoning_state = regular_expression_gen()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print_highlight(f\"Answer:\\n{reasoning_state['answer']}\")\n",
    "print_highlight(\n",
    "    f\"\\n\\nReasoning Content:\\n{reasoning_state['answer_reasoning_content']}\"\n",
    ")"
   ]
  }
 ],
 "metadata": {
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}