Serena Lotreck

> pip install git+https://github.com/diging/tethne THANK YOU @mhaeussermann !! Going to post this to the Google Group, as it looks like folks there haven't gotten this answer yet.

@muellerzr got the same `chardet` error when I ran `accelerate env` in the 0.19.0 image

@muellerzr just wanted to follow up on this!

Why would `.visualize_hierarchy` be different if `hierarchical_topics` is the same, since `hierarchical_topics` is passed to `.visualize_hierarchy`? I can go check, but if that is the case, I'd like a way...

Ok I checked, and it is `.hierarchical_topics` that's giving different results, I saved out the results and read them back in, and when I ran `.visualize_hierarchy`, I got the same...

Here is the code with 20NewsGroups: ``` from bertopic import BERTopic from bertopic.representation import MaximalMarginalRelevance import openai from sentence_transformers import SentenceTransformer from umap import UMAP from hdbscan import HDBSCAN from...

Yes they're the same! I launched a jupyter notebook instance using the same kernel that I made from a conda environment, and haven't changed any packages in the conda environment...

Very weird.. I'm going to stick with reading in the hierarcical topics when I need to regenerate the figure for now, I'll let you know if I figure anything else...

So I did some digging and it looks like OpenAI [natively supports batching](https://platform.openai.com/docs/guides/rate-limits/error-mitigation?context=tier-free), all you have to do is pass a list of prompts to the `create` instance. However, they...

> Is there additional slowdown elsewhere in the system, like in the grounding steps? That is a fantastic question -- I hadn't thought about it, but in another NER algorithm...