Maarten Grootendorst
Maarten Grootendorst
You can use https://maartengr.github.io/KeyBERT/api/litellm.html
Yes and no. It should work with any length of document but just remember that when you have extremely long documents, the embeddings get averaged and may average out some...
Thank you for taking the time to go through this in this much detail! I haven't taken a look at this code for a while so I'll need some time...
No worries, glad to hear you understand. Do you perhaps have any reproducible code so that I can test this further? I think its best to have a practical example...
Thank you for sharing your description! Could you perhaps create a minimum reproducible example for me to try? I see some unformatted code here and there in your issue but...
@shaluchiipi Thank you for sharing the example, it is greatly appreciated! I typically don't download and open files from sources I'm not familiar with. Could you perhaps showcase the example...
Also, note that I updated your message to include these ``` brackets. Without them, it's not clear to me what the indentation is, where the code starts, etc. Please use...
Sorry for the late reply, I have been sick for the last week. I just checked the code and I believe it should work if you change this: ```python model...
@shaliniml The indices are currently not tracked, so you would have to merge them back yourself.
It's difficult to say without knowing more. Why not just use `get_matches`? Which version are you using? Also, what code are you currently using and could you provide an example?