sglang/docs/backend/openai_api_vision.ipynb

OpenAI APIs - Vision

SGLang provides OpenAI-compatible APIs to enable a smooth transition from OpenAI services to self-hosted local models. A complete reference for the API is available in the OpenAI API Reference. This tutorial covers the vision APIs for vision language models.

SGLang supports various vision language models such as Llama 3.2, LLaVA-OneVision, Qwen2.5-VL, Gemma3 and more.

As an alternative to the OpenAI API, you can also use the SGLang offline engine.

Launch A Server

Launch the server in your terminal and wait for it to initialize.

In [ ]:

from sglang.test.test_utils import is_in_ci

if is_in_ci():
    from patch import launch_server_cmd
else:
    from sglang.utils import launch_server_cmd

from sglang.utils import wait_for_server, print_highlight, terminate_process

vision_process, port = launch_server_cmd(
    """
python3 -m sglang.launch_server --model-path Qwen/Qwen2.5-VL-7B-Instruct
"""
)

wait_for_server(f"http://localhost:{port}")

Using cURL

Once the server is up, you can send test requests using curl or requests.

In [ ]:

import subprocess

curl_command = f"""
curl -s http://localhost:{port}/v1/chat/completions \\
  -d '{{
    "model": "Qwen/Qwen2.5-VL-7B-Instruct",
    "messages": [
      {{
        "role": "user",
        "content": [
          {{
            "type": "text",
            "text": "What’s in this image?"
          }},
          {{
            "type": "image_url",
            "image_url": {{
              "url": "https://github.com/sgl-project/sglang/blob/main/test/lang/example_image.png?raw=true"
            }}
          }}
        ]
      }}
    ],
    "max_tokens": 300
  }}'
"""

response = subprocess.check_output(curl_command, shell=True).decode()
print_highlight(response)


response = subprocess.check_output(curl_command, shell=True).decode()
print_highlight(response)

Using Python Requests

In [ ]:

import requests

url = f"http://localhost:{port}/v1/chat/completions"

data = {
    "model": "Qwen/Qwen2.5-VL-7B-Instruct",
    "messages": [
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What’s in this image?"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://github.com/sgl-project/sglang/blob/main/test/lang/example_image.png?raw=true"
                    },
                },
            ],
        }
    ],
    "max_tokens": 300,
}

response = requests.post(url, json=data)
print_highlight(response.text)

Using OpenAI Python Client

In [ ]:

from openai import OpenAI

client = OpenAI(base_url=f"http://localhost:{port}/v1", api_key="None")

response = client.chat.completions.create(
    model="Qwen/Qwen2.5-VL-7B-Instruct",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "What is in this image?",
                },
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://github.com/sgl-project/sglang/blob/main/test/lang/example_image.png?raw=true"
                    },
                },
            ],
        }
    ],
    max_tokens=300,
)

print_highlight(response.choices[0].message.content)

Multiple-Image Inputs

The server also supports multiple images and interleaved text and images if the model supports it.

In [ ]:

from openai import OpenAI

client = OpenAI(base_url=f"http://localhost:{port}/v1", api_key="None")

response = client.chat.completions.create(
    model="Qwen/Qwen2.5-VL-7B-Instruct",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://github.com/sgl-project/sglang/blob/main/test/lang/example_image.png?raw=true",
                    },
                },
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://raw.githubusercontent.com/sgl-project/sglang/main/assets/logo.png",
                    },
                },
                {
                    "type": "text",
                    "text": "I have two very different images. They are not related at all. "
                    "Please describe the first image in one sentence, and then describe the second image in another sentence.",
                },
            ],
        }
    ],
    temperature=0,
)

print_highlight(response.choices[0].message.content)

In [ ]:

terminate_process(vision_process)