> ## Documentation Index
> Fetch the complete documentation index at: https://docs.perceptron.inc/llms.txt
> Use this file to discover all available pages before exploring further.
# Multiple assets
> Ground answers across media and conversation history with asset_idx.
Send multiple media parts in a conversation to compare scenes, locate the same object in different inputs, or use a reference image to guide a search. The optional `asset_idx` attribute identifies which input an annotation describes. The model may omit it, including in multi-asset answers and when the prompt asks for it. If no explicit or inherited selector is present, the annotation refers to the last asset available to the model at that point in the conversation.
## How assets are numbered
Assets are numbered from zero in their order of appearance across the messages supplied in the request, then within each message's content array. An annotation refers to the media available up to its position in that conversation. Text does not consume an index. Images, videos, and standalone audio share one sequence.
| Supplied conversation content | Asset index |
| ------------------------------------------- | ------------ |
| First user message: reference image | `0` |
| First user message: video | `1` |
| Assistant answer containing annotation text | No new asset |
| Later tool result containing an image | `2` |
| Later user message containing another image | `3` |
Each media occurrence has a position. Repeating the same URL or uploaded `file_id` in a separate content part introduces another position; file reuse does not make the selector a persistent file identifier.
Keep these distinctions in mind:
* One `video_url`, `video_file_id`, or `video_frames` group is one asset. Individual frames inside that group are addressed by time.
* One `input_audio`, `audio_url`, or `audio_file_id` part is one asset. For an image followed by a standalone recording, the image is asset `0` and the audio is asset `1`. Enabling a video's soundtrack does not add another asset; its frames and audio belong to the same video.
* Frames supplied as separate `image_url` parts are separate image assets, even if they came from the same video.
* Images returned by functions count in the conversation's asset order. The original image and an image crop returned by a tool are separate assets with their own coordinate systems.
* Numbering does not reset at a new user turn. Resend the relevant conversation history when continuing a conversation.
* Removing or reordering earlier media changes the mapping. Recompute selectors for the actual request instead of reusing an index from a different history.
The request limit is 256 media units. This is a separate count from `asset_idx`: every frame inside a `video_frames` group consumes one media unit, although the group has only one asset index.
## Compare a reference image with a target
Install the Perceptron Python SDK and set `PERCEPTRON_API_KEY`. This example uses two public sample images and requests a box in the second image.
```bash theme={null}
pip install "perceptron>=0.4.0"
export PERCEPTRON_API_KEY="your-api-key"
```
```python theme={null}
import os
from perceptron import Client, image
client = Client(
api_key=os.environ["PERCEPTRON_API_KEY"],
provider="perceptron",
)
asset_root = (
"https://raw.githubusercontent.com/perceptron-ai-inc/perceptron/"
"main/cookbook/_shared/assets/in-context-learning/single/"
)
response = client.chat.completions.create(
model="perceptron-mk1.5",
messages=[
{
"role": "user",
"content": [
{"type": "text", "text": "Reference object (asset 0):"},
image(asset_root + "cake_mixer_example.webp"),
{"type": "text", "text": "Search this image (asset 1):"},
image(asset_root + "find_kitchen_item.webp"),
{
"type": "text",
"text": (
"Find the object in asset 1 that matches the reference in asset 0. "
"Return a point_box with asset_idx=\"1\". "
"If no matching object is visible, say so without inventing a box."
),
},
],
}
],
max_completion_tokens=512,
vision_config={"annotation_format": "box"},
)
choice = response.choices[0]
if choice.finish_reason != "stop":
raise RuntimeError(f"Incomplete answer: {choice.finish_reason}")
print(choice.message.content or "")
```
The response is text containing annotation markup, not a separate JSON array of boxes. An illustrative annotation is:
```html theme={null}
(400,300) (600,650)
```
The coordinates above demonstrate the format; they are not measured output for these sample images.
## Resolve selectors before drawing
Select the asset first, then use that asset's dimensions to convert normalized coordinates into pixels. For example, `(500,500)` is `(960,540)` on a 1920×1080 image and `(320,240)` on a 640×480 image.
An annotation can inherit its selector from a collection. An explicit child selector overrides the collection's selector:
```html theme={null}
(100,150) (300,350)
(400,300) (600,500)
```
Here the first box belongs to asset `0` and the second to asset `1`. This override is useful for collections; each `