NVIDIA / NVIDIA/NeMo-Retriever

[FEA]: Support arbitrary python functions to determine document split points

Open
#194 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

In an ideal world we'd have cleanly extracted document section header metadata including location.

Then we could use the location of such document demarcations to support splitting on those demarcations.

However, some separators are arbitrary text content not likely to ever be identified by an ootb model. As a result, users would like to be able to run an arbitrary python function which can return split locations.

Describe the feature, and optionally a solution or implementation and any alternatives

See above

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

No files, tests, or entry points are named. Start by locating the document-splitting implementation and existing section-header metadata handling, then determine how arbitrary Python functions could provide split locations. Done should include a defined callable interface, documented behavior, and coverage for custom split points.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
backend
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.