MaartenGr / MaartenGr/BERTopic
Where is the full data set of embeddings?
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
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
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