MaartenGr / MaartenGr/BERTopic

Adding custom topic aspect after training

Open
#1,575 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
7.8k
Forks
920
Avg merge
22h 24m
Merged PRs (30d)
5

Description

I'm having diffulcties with assigning labels/representatives of topics to the topic_model after training.

I have trained the model and and I happy with the clusters it made. I did not choose the multiple representation or any representation model.

I see the possibilty to update a label per topic and also upload list of topics but this will be updated to column CustomName.

I want to implement multiple representation after the training. Is it possible to apply Generative AI and a custom list of topics under the custom aspects "openai" and "customList"?

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

Start by reviewing BERTopic's post-training topic representation and custom-aspect APIs, focusing on whether representations can be added after training. Check how the existing CustomName update and multiple-representation options are exposed, then verify whether OpenAI-generated and custom-list aspects can both be attached without retraining.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.