NVIDIA-NeMo / NVIDIA-NeMo/DataDesigner

Ability to control order of multi-modal context along with prompts

Open
#352 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement needs-discussion on-roadmap
Dominant language
Python
Stars
2.2k
Forks
211
Avg merge
2d 6h
Merged PRs (30d)
40

Description

Priority Level

Medium (Nice to have)

Is your feature request related to a problem? Please describe.

Right now all images are packed before text prompts. There is no way to control the order of multi-modal context with text prompts.

Describe the solution you'd like

The desire is to have finer control over the exact order of multi-modal context:

<images> <text>
Page1 <image1> page2 <image2> <more text>

{“<image1”>: path, “<image2>”: path2}
“Page1 <image1> page2 <image2>”

“Frame 1 timestamp x” <video frame1>
<audio> <image> <video> <image> <image> <audio>

This is necessary when working with multi-modal data.

Describe alternatives you've considered

No response

Additional context

No response

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

The issue names no files, tests, or entry points. Start by locating the multimodal context assembly that currently places images before text, then review how prompts and media are represented. Done should include a defined ordering mechanism supporting interleaved text and images, with coverage for the ordering examples described here.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.