Refactor the docs (#9031)
This commit is contained in:
Lianmin Zheng
254
docs/basic_usage/openai_api_vision.ipynb
Normal file
254
docs/basic_usage/openai_api_vision.ipynb
Normal file
@@ -0,0 +1,254 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# OpenAI APIs - Vision\n",
|
||||
"\n",
|
||||
"SGLang provides OpenAI-compatible APIs to enable a smooth transition from OpenAI services to self-hosted local models.\n",
|
||||
"A complete reference for the API is available in the [OpenAI API Reference](https://platform.openai.com/docs/guides/vision).\n",
|
||||
"This tutorial covers the vision APIs for vision language models.\n",
|
||||
"\n",
|
||||
"SGLang supports various vision language models such as Llama 3.2, LLaVA-OneVision, Qwen2.5-VL, Gemma3 and [more](../supported_models/multimodal_language_models.md).\n",
|
||||
"\n",
|
||||
"As an alternative to the OpenAI API, you can also use the [SGLang offline engine](https://github.com/sgl-project/sglang/blob/main/examples/runtime/engine/offline_batch_inference_vlm.py)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Launch A Server\n",
|
||||
"\n",
|
||||
"Launch the server in your terminal and wait for it to initialize."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from sglang.test.doc_patch import launch_server_cmd\n",
|
||||
"from sglang.utils import wait_for_server, print_highlight, terminate_process\n",
|
||||
"\n",
|
||||
"vision_process, port = launch_server_cmd(\n",
|
||||
" \"\"\"\n",
|
||||
"python3 -m sglang.launch_server --model-path Qwen/Qwen2.5-VL-7B-Instruct\n",
|
||||
"\"\"\"\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"wait_for_server(f\"http://localhost:{port}\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Using cURL\n",
|
||||
"\n",
|
||||
"Once the server is up, you can send test requests using curl or requests."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import subprocess\n",
|
||||
"\n",
|
||||
"curl_command = f\"\"\"\n",
|
||||
"curl -s http://localhost:{port}/v1/chat/completions \\\\\n",
|
||||
" -H \"Content-Type: application/json\" \\\\\n",
|
||||
" -d '{{\n",
|
||||
" \"model\": \"Qwen/Qwen2.5-VL-7B-Instruct\",\n",
|
||||
" \"messages\": [\n",
|
||||
" {{\n",
|
||||
" \"role\": \"user\",\n",
|
||||
" \"content\": [\n",
|
||||
" {{\n",
|
||||
" \"type\": \"text\",\n",
|
||||
" \"text\": \"What’s in this image?\"\n",
|
||||
" }},\n",
|
||||
" {{\n",
|
||||
" \"type\": \"image_url\",\n",
|
||||
" \"image_url\": {{\n",
|
||||
" \"url\": \"https://github.com/sgl-project/sglang/blob/main/test/lang/example_image.png?raw=true\"\n",
|
||||
" }}\n",
|
||||
" }}\n",
|
||||
" ]\n",
|
||||
" }}\n",
|
||||
" ],\n",
|
||||
" \"max_tokens\": 300\n",
|
||||
" }}'\n",
|
||||
"\"\"\"\n",
|
||||
"\n",
|
||||
"response = subprocess.check_output(curl_command, shell=True).decode()\n",
|
||||
"print_highlight(response)\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"response = subprocess.check_output(curl_command, shell=True).decode()\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\": \"Qwen/Qwen2.5-VL-7B-Instruct\",\n",
|
||||
" \"messages\": [\n",
|
||||
" {\n",
|
||||
" \"role\": \"user\",\n",
|
||||
" \"content\": [\n",
|
||||
" {\"type\": \"text\", \"text\": \"What’s in this image?\"},\n",
|
||||
" {\n",
|
||||
" \"type\": \"image_url\",\n",
|
||||
" \"image_url\": {\n",
|
||||
" \"url\": \"https://github.com/sgl-project/sglang/blob/main/test/lang/example_image.png?raw=true\"\n",
|
||||
" },\n",
|
||||
" },\n",
|
||||
" ],\n",
|
||||
" }\n",
|
||||
" ],\n",
|
||||
" \"max_tokens\": 300,\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"response = requests.post(url, json=data)\n",
|
||||
"print_highlight(response.text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Using OpenAI Python Client"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from openai import OpenAI\n",
|
||||
"\n",
|
||||
"client = OpenAI(base_url=f\"http://localhost:{port}/v1\", api_key=\"None\")\n",
|
||||
"\n",
|
||||
"response = client.chat.completions.create(\n",
|
||||
" model=\"Qwen/Qwen2.5-VL-7B-Instruct\",\n",
|
||||
" messages=[\n",
|
||||
" {\n",
|
||||
" \"role\": \"user\",\n",
|
||||
" \"content\": [\n",
|
||||
" {\n",
|
||||
" \"type\": \"text\",\n",
|
||||
" \"text\": \"What is in this image?\",\n",
|
||||
" },\n",
|
||||
" {\n",
|
||||
" \"type\": \"image_url\",\n",
|
||||
" \"image_url\": {\n",
|
||||
" \"url\": \"https://github.com/sgl-project/sglang/blob/main/test/lang/example_image.png?raw=true\"\n",
|
||||
" },\n",
|
||||
" },\n",
|
||||
" ],\n",
|
||||
" }\n",
|
||||
" ],\n",
|
||||
" max_tokens=300,\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"print_highlight(response.choices[0].message.content)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Multiple-Image Inputs\n",
|
||||
"\n",
|
||||
"The server also supports multiple images and interleaved text and images if the model supports it."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from openai import OpenAI\n",
|
||||
"\n",
|
||||
"client = OpenAI(base_url=f\"http://localhost:{port}/v1\", api_key=\"None\")\n",
|
||||
"\n",
|
||||
"response = client.chat.completions.create(\n",
|
||||
" model=\"Qwen/Qwen2.5-VL-7B-Instruct\",\n",
|
||||
" messages=[\n",
|
||||
" {\n",
|
||||
" \"role\": \"user\",\n",
|
||||
" \"content\": [\n",
|
||||
" {\n",
|
||||
" \"type\": \"image_url\",\n",
|
||||
" \"image_url\": {\n",
|
||||
" \"url\": \"https://github.com/sgl-project/sglang/blob/main/test/lang/example_image.png?raw=true\",\n",
|
||||
" },\n",
|
||||
" },\n",
|
||||
" {\n",
|
||||
" \"type\": \"image_url\",\n",
|
||||
" \"image_url\": {\n",
|
||||
" \"url\": \"https://raw.githubusercontent.com/sgl-project/sglang/main/assets/logo.png\",\n",
|
||||
" },\n",
|
||||
" },\n",
|
||||
" {\n",
|
||||
" \"type\": \"text\",\n",
|
||||
" \"text\": \"I have two very different images. They are not related at all. \"\n",
|
||||
" \"Please describe the first image in one sentence, and then describe the second image in another sentence.\",\n",
|
||||
" },\n",
|
||||
" ],\n",
|
||||
" }\n",
|
||||
" ],\n",
|
||||
" temperature=0,\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"print_highlight(response.choices[0].message.content)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"terminate_process(vision_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
|
||||
}
|
||||
Reference in New Issue
Block a user