NVIDIA / NVIDIA/NeMo-Retriever

[FEA]: Take multi-modal html files as input

Open
#243 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

feature request
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

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

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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.