MaartenGr / MaartenGr/BERTopic
Google's Gemeni support for BERTopic's representation layer
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 7.8k
- Forks
- 920
- Avg merge
- 22h 24m
- Merged PRs (30d)
- 5
Description
### Feature request
Implementing Gemeni client as a new GenAI representation component
### Motivation
we use Gemeni API at work and would like to use BERTOPIC, so it should be helpful to have first class support without using langchain.
### Your contribution
after reading the code I'd like to develop:
1. creating a new `_gemeni.py` file in `bertopic\representation` path
2. inheriting `BaseRepresentation` parent class and implementing Gemeni specific code for LLM calls
3. adding guides for how to use it in `docs\getting_started\representation\llm.md`
4. If I could, I'd also like to add tests
@MaartenGr love to hear your thoughts on this
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 reading BaseRepresentation and the existing components in bertopic\representation, then review docs\getting_started\representation\llm.md. The work is complete when a Gemini representation component works without LangChain, the usage guide covers it, and appropriate tests are added if feasible.
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
- Mostly clear
- Newbie friendliness
- 35/100