# Images

> Send up to two images with a request; a second engine on the same card reads them, and the answers have the same shape.

Source: https://opendecisio.com/docs/guides/images/

A request can carry images beside its text. Image input is served by a second engine on the same card, so it needs a server started for it, and it was measured with the Qwen base only.

 

[Figure: Images ride in the request; a second engine on the same card reads them. A request carries up to 2 images (PNG, JPEG or WebP, up to 20 MB each) beside its state and questions. A second engine on the same card, started with --image-model, serves it, and the answers have the same shape. ImajevBench scored 0.791 on the Qwen base.]

 

## TL;DR

 

On a GPU server started with `--image-model`, this script sends one image as a data URL with a question about it. It is a shape to adapt, not a command to run: it needs that server and an image of yours.

 

```
import base64
import json
import urllib.request

with open("photo.jpg", "rb") as f:
    image = "data:image/jpeg;base64," + base64.b64encode(f.read()).decode()

body = {
    "state": "A photo of a delivered parcel.",
    "images": [image],
    "questions": {"damaged": {"type": "noul", "instructions": "Is the parcel visibly damaged?"}},
}
request = urllib.request.Request(
    "http://127.0.0.1:8000/v1/systemone",
    data=json.dumps(body).encode(),
    headers={"Content-Type": "application/json"},
)
with urllib.request.urlopen(request) as response:
    print(json.load(response)["answers"]["damaged"]["noul"])
# the probability of yes, as for a text-only request
```

 

A shape to fill in, not a command to run.

  

| Word | Meaning |
| --- | --- |
| image engine | a second engine on the same card, started with `--image-model`, that serves the requests that carry images |
| data URL | an image written into the request as `data:image/...;base64,...` |
| route | which engine served the request; `x-decisio-route` is `image` for these |

 

## 1. Start a server for images

 

`--image-model` names the full multimodal checkpoint and starts the second engine, with its share of the card (`--image-gpu-memory-utilization`, 0.5 by default; the measured shares were 0.49 beside the text engine at 0.47). `--one-engine` loads only the image engine and serves text requests on it too, for a card that cannot hold both, and changes the text route’s class. A Mac’s MLX backend refuses the image route.

 

## 2. Send the images

 

Up to 2 images per request, PNG, JPEG or WebP, up to 20 MB each, as data URLs in `images`, as `data:image/...` URIs anywhere inside the state, or as a `multipart/form-data` request whose `request` field holds the JSON body and whose `image`, `images` or `image[]` fields hold the files. `x-decisio-route: text` or `image` chooses the route explicitly.

 

## 3. What was measured

 

On ImajevBench v2.0-lite, 254 labelled items, the Qwen base scored 0.717 on all items and 0.791 on the 230 answerable ones; with a “can’t tell” option offered, 0.756 and 0.813, with 5 of the 24 unanswerable items right and 2 false abstentions; the median request took 166 ms. The image route is not tempered, and it keeps the compact prompt layout.

 

Common mistake

The Gemma bases were not measured on the image route. Use the Qwen base for images, and say so when you quote a figure.

 

## What next

 

- [Flags and options](https://opendecisio.com/docs/flags/): every flag of the image engine.
- [The HTTP API](https://opendecisio.com/docs/api/): the images field and the multipart form.
- [Choosing a base](https://opendecisio.com/docs/bases/): why the Qwen base is the one measured for images.