260 lines
6.9 KiB
Plaintext
260 lines
6.9 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# 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"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from sglang.test.test_utils import is_in_ci\n",
|
|
"from sglang.utils import wait_for_server, print_highlight, terminate_process\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",
|
|
"# This is equivalent to running the following command in your terminal\n",
|
|
"\n",
|
|
"# python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-8B-Instruct --host 0.0.0.0\n",
|
|
"\n",
|
|
"server_process, port = launch_server_cmd(\n",
|
|
" \"\"\"\n",
|
|
"python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-8B-Instruct \\\n",
|
|
" --host 0.0.0.0\n",
|
|
"\"\"\"\n",
|
|
")\n",
|
|
"\n",
|
|
"wait_for_server(f\"http://localhost:{port}\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Using cURL\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import subprocess, json\n",
|
|
"\n",
|
|
"curl_command = f\"\"\"\n",
|
|
"curl -s http://localhost:{port}/v1/chat/completions \\\n",
|
|
" -H \"Content-Type: application/json\" \\\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": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import requests\n",
|
|
"\n",
|
|
"url = f\"http://localhost:{port}/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": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import openai\n",
|
|
"\n",
|
|
"client = openai.Client(base_url=f\"http://127.0.0.1:{port}/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": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import openai\n",
|
|
"\n",
|
|
"client = openai.Client(base_url=f\"http://127.0.0.1:{port}/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": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import requests\n",
|
|
"\n",
|
|
"response = requests.post(\n",
|
|
" f\"http://localhost:{port}/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": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import requests, json\n",
|
|
"\n",
|
|
"response = requests.post(\n",
|
|
" f\"http://localhost:{port}/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": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"terminate_process(server_process)"
|
|
]
|
|
}
|
|
],
|
|
"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
|
|
}
|