send_request.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Quick Start: Sending Requests\n",
    "This notebook provides a quick-start guide to use SGLang in chat completions after installation.\n",
    "\n",
    "- For Vision Language Models, see [OpenAI APIs - Vision](../backend/openai_api_vision.ipynb).\n",
    "- For Embedding Models, see [OpenAI APIs - Embedding](../backend/openai_api_embeddings.ipynb) and [Encode (embedding model)](../backend/native_api.html#Encode-(embedding-model)).\n",
    "- For Reward Models, see [Classify (reward model)](../backend/native_api.html#Classify-(reward-model))."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Launch A Server\n",
    "\n",
    "This code block is equivalent to executing \n",
    "\n",
    "```bash\n",
    "python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-8B-Instruct \\\n",
    "--port 30000 --host 0.0.0.0\n",
    "```\n",
    "\n",
    "in your terminal and wait for the server to be ready. Once the server is running, you can send test requests using curl or requests. The server implements the [OpenAI-compatible APIs](https://platform.openai.com/docs/api-reference/chat)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-11-07T18:48:52.032229Z",
     "iopub.status.busy": "2024-11-07T18:48:52.032105Z",
     "iopub.status.idle": "2024-11-07T18:49:20.226042Z",
     "shell.execute_reply": "2024-11-07T18:49:20.225562Z"
    }
   },
   "outputs": [],
   "source": [
    "from sglang.utils import (\n",
    "    execute_shell_command,\n",
    "    wait_for_server,\n",
    "    terminate_process,\n",
    "    print_highlight,\n",
    ")\n",
    "\n",
    "server_process = execute_shell_command(\n",
    "    \"\"\"\n",
    "python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-8B-Instruct \\\n",
    "--port 30000 --host 0.0.0.0\n",
    "\"\"\"\n",
    ")\n",
    "\n",
    "wait_for_server(\"http://localhost:30000\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Using cURL\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-11-07T18:49:20.228006Z",
     "iopub.status.busy": "2024-11-07T18:49:20.227572Z",
     "iopub.status.idle": "2024-11-07T18:49:20.469885Z",
     "shell.execute_reply": "2024-11-07T18:49:20.469518Z"
    }
   },
   "outputs": [],
   "source": [
    "import subprocess, json\n",
    "\n",
    "curl_command = \"\"\"\n",
    "curl -s http://localhost:30000/v1/chat/completions \\\n",
    "  -d '{\"model\": \"meta-llama/Meta-Llama-3.1-8B-Instruct\", \"messages\": [{\"role\": \"user\", \"content\": \"What is the capital of France?\"}]}'\n",
    "\"\"\"\n",
    "\n",
    "response = json.loads(subprocess.check_output(curl_command, shell=True))\n",
    "print_highlight(response)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Using Python Requests"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-11-07T18:49:20.471956Z",
     "iopub.status.busy": "2024-11-07T18:49:20.471811Z",
     "iopub.status.idle": "2024-11-07T18:49:20.667997Z",
     "shell.execute_reply": "2024-11-07T18:49:20.667630Z"
    }
   },
   "outputs": [],
   "source": [
    "import requests\n",
    "\n",
    "url = \"http://localhost:30000/v1/chat/completions\"\n",
    "\n",
    "data = {\n",
    "    \"model\": \"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n",
    "    \"messages\": [{\"role\": \"user\", \"content\": \"What is the capital of France?\"}],\n",
    "}\n",
    "\n",
    "response = requests.post(url, json=data)\n",
    "print_highlight(response.json())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Using OpenAI Python Client"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-11-07T18:49:20.669977Z",
     "iopub.status.busy": "2024-11-07T18:49:20.669826Z",
     "iopub.status.idle": "2024-11-07T18:49:22.004855Z",
     "shell.execute_reply": "2024-11-07T18:49:22.004472Z"
    }
   },
   "outputs": [],
   "source": [
    "import openai\n",
    "\n",
    "client = openai.Client(base_url=\"http://127.0.0.1:30000/v1\", api_key=\"None\")\n",
    "\n",
    "response = client.chat.completions.create(\n",
    "    model=\"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n",
    "    messages=[\n",
    "        {\"role\": \"user\", \"content\": \"List 3 countries and their capitals.\"},\n",
    "    ],\n",
    "    temperature=0,\n",
    "    max_tokens=64,\n",
    ")\n",
    "print_highlight(response)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Streaming"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-11-07T18:49:22.006983Z",
     "iopub.status.busy": "2024-11-07T18:49:22.006858Z",
     "iopub.status.idle": "2024-11-07T18:49:23.029098Z",
     "shell.execute_reply": "2024-11-07T18:49:23.028697Z"
    }
   },
   "outputs": [],
   "source": [
    "import openai\n",
    "\n",
    "client = openai.Client(base_url=\"http://127.0.0.1:30000/v1\", api_key=\"None\")\n",
    "\n",
    "# Use stream=True for streaming responses\n",
    "response = client.chat.completions.create(\n",
    "    model=\"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n",
    "    messages=[\n",
    "        {\"role\": \"user\", \"content\": \"List 3 countries and their capitals.\"},\n",
    "    ],\n",
    "    temperature=0,\n",
    "    max_tokens=64,\n",
    "    stream=True,\n",
    ")\n",
    "\n",
    "# Handle the streaming output\n",
    "for chunk in response:\n",
    "    if chunk.choices[0].delta.content:\n",
    "        print(chunk.choices[0].delta.content, end=\"\", flush=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Using Native Generation APIs\n",
    "\n",
    "You can also use the native `/generate` endpoint with requests, which provides more flexiblity. An API reference is available at [Sampling Parameters](../references/sampling_params.md)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-11-07T18:49:23.031712Z",
     "iopub.status.busy": "2024-11-07T18:49:23.031571Z",
     "iopub.status.idle": "2024-11-07T18:49:23.787752Z",
     "shell.execute_reply": "2024-11-07T18:49:23.787368Z"
    }
   },
   "outputs": [],
   "source": [
    "import requests\n",
    "\n",
    "response = requests.post(\n",
    "    \"http://localhost:30000/generate\",\n",
    "    json={\n",
    "        \"text\": \"The capital of France is\",\n",
    "        \"sampling_params\": {\n",
    "            \"temperature\": 0,\n",
    "            \"max_new_tokens\": 32,\n",
    "        },\n",
    "    },\n",
    ")\n",
    "\n",
    "print_highlight(response.json())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Streaming"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-11-07T18:49:23.789840Z",
     "iopub.status.busy": "2024-11-07T18:49:23.789702Z",
     "iopub.status.idle": "2024-11-07T18:49:24.545631Z",
     "shell.execute_reply": "2024-11-07T18:49:24.545241Z"
    }
   },
   "outputs": [],
   "source": [
    "import requests, json\n",
    "\n",
    "response = requests.post(\n",
    "    \"http://localhost:30000/generate\",\n",
    "    json={\n",
    "        \"text\": \"The capital of France is\",\n",
    "        \"sampling_params\": {\n",
    "            \"temperature\": 0,\n",
    "            \"max_new_tokens\": 32,\n",
    "        },\n",
    "        \"stream\": True,\n",
    "    },\n",
    "    stream=True,\n",
    ")\n",
    "\n",
    "prev = 0\n",
    "for chunk in response.iter_lines(decode_unicode=False):\n",
    "    chunk = chunk.decode(\"utf-8\")\n",
    "    if chunk and chunk.startswith(\"data:\"):\n",
    "        if chunk == \"data: [DONE]\":\n",
    "            break\n",
    "        data = json.loads(chunk[5:].strip(\"\\n\"))\n",
    "        output = data[\"text\"]\n",
    "        print(output[prev:], end=\"\", flush=True)\n",
    "        prev = len(output)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-11-07T18:49:24.547641Z",
     "iopub.status.busy": "2024-11-07T18:49:24.547497Z",
     "iopub.status.idle": "2024-11-07T18:49:25.888864Z",
     "shell.execute_reply": "2024-11-07T18:49:25.888114Z"
    }
   },
   "outputs": [],
   "source": [
    "terminate_process(server_process)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "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,
 "nbformat_minor": 2
}