NVIDIA / NVIDIA/GenerativeAIExamples
Incorrect Validation Warning When Using Multimodal Context With No Other Prompt References
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 4.2k
- Forks
- 1.1k
- Avg merge
- 10h 15m
- Merged PRs (30d)
- 1
Description
When an image is passed as context using the multi_modal_context parameter and no other column is referenced in the prompt, the validator throws an incorrect warning, PROMPT_WITHOUT_REFERENCES.
See visual-question-answering.ipynb to reproduce the error.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with nemo/NeMo-Data-Designer/advanced/multimodal/visual-question-answering-using-vlm.ipynb and run the visual-question-answering example to reproduce the PROMPT_WITHOUT_REFERENCES warning. Trace the validator path used by multi_modal_context; done means an image-only context no longer produces this warning while genuine prompts without references still do.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- jupyter-notebook
- Domain
- ai
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 45/100