NVIDIA / NVIDIA/NeMo-Retriever
[FEA]: Take multi-modal html files as input
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3k
- Forks
- 349
- Avg merge
- 1d 23h
- Merged PRs (30d)
- 116
Description
Is this a new feature, an improvement, or a change to existing functionality?
New Feature
How would you describe the priority of this feature request
Currently preventing usage
Please provide a clear description of problem this feature solves
It's quite common for web system offerring online document(such as PRD) editing functions(wysiwyg editor). So there is a need that we save all the pages from the web online editor as html files.
Describe the feature, and optionally a solution or implementation and any alternatives
It will be very helpful that nv-ingest could suppor html files as input.
Additional context
In the html file, there're a lot of pictures,which is very important, and should not be ignored.
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
No files, tests, or entry points are named. Start by locating the existing document input handling and determine how HTML pages and embedded pictures should be represented. Done means HTML files are accepted and their important images are preserved for downstream extraction.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- html, python
- Domain
- backend, data-engineering
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100