MaartenGr / MaartenGr/BERTopic
Representation model diversity parameter is not working
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 7.8k
- Forks
- 920
- Avg merge
- 22h 24m
- Merged PRs (30d)
- 5
Description
Hi Maarten,
Thanks for this great package.
I am using OpenAI as a representation model to get title and one line summary.
As I have many duplicates in my data. So I want to use a diversity parameter to select documents that are sufficiently diverse, but it's not working.
It is effecting representation doc of topics
Also , Within my prompt I am using [DOCUMENTS], How can I check which documents are sent to LLM ?
`openai_model = OpenAI(
client = client,
model="gpt-3.5-turbo",
exponential_backoff=True,
prompt=prompt,
delay_in_seconds=2,
chat=True,
nr_docs=60,
doc_length=100,
diversity = 0.75,
tokenizer=tokenizer)
`
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 with the OpenAI representation configuration shown in the issue, then trace how nr_docs, doc_length, diversity, and [DOCUMENTS] are processed. Reproduce the duplicate-document behavior and verify which documents reach the LLM; done means diversity affects representative documents and the selected inputs can be inspected.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100