Vision input

Kimi K2.5 and Gemma 3 27B support image input alongside text. The example below sends a local image as part of a chat completion request.

from openai import OpenAI
import base64
import os

# docker run --pull=always -p 8080:8080 ghcr.io/edgelesssys/privatemode/privatemode-proxy:latest
# PRIVATEMODE_API_KEY=<> uv run --with openai gemma-vision.py

api_key = os.environ.get("PRIVATEMODE_API_KEY")
api_base = "http://localhost:8080/v1"
image_path = ""  # insert path to image

client = OpenAI(
    api_key=api_key,
    base_url=api_base,
)

def encode_image_to_base64(image_path):
    with open(image_path, "rb") as image_file:
        return base64.b64encode(image_file.read()).decode("utf-8")

if not os.path.exists(image_path):
    print(f"Error: Image file not found at {image_path}")
    exit(1)

base64_image = encode_image_to_base64(image_path)

chat_response = client.chat.completions.create(
    model="gemma-3-27b",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What's in this image?"},
                {
                    "type": "image_url",
                    "image_url": {"url": f"data:image/png;base64,{base64_image}"},
                },
            ],
        }
    ],
)

print("Chat completion output:", chat_response.choices[0].message.content)