MaartenGr / MaartenGr/BERTopic

Where is the full data set of embeddings?

Open
#1,988 3 comments 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 passing a list of approximately 700 articles to the default embeddings function as follows:

```
topic_model = BERTopic()
window_result = topic_model.fit_transform(d)
```

where d is a simple list of strings (representing approximately 200 word articles each).

However when I `topic_model.get_info()` I see only 11 topics, and their associated embeddings using attribute `topic_embeddings_`. Where can I get the full 700 actual embedding vectors?

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 tracing the BERTopic fit_transform call and the topic_embeddings_ attribute described in the issue. Determine whether the full 700 document-level vectors are retained or exposed, and define completion as providing a documented, verifiable way to access those vectors.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
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.