KeyBERT

KeyBERT copied to clipboard

Very short sentences support

1

Will KeyBERT give meaningful results for very short sentences like, `The United States is the only nation that grants legal permanent residency to more than a million people per year....

kshitijgundale

output arrangement

1

I am getting results arranged according to the importance ``` def keyword_exctraction(self,new_text): eng_stopwords = stopwords.words('english') hinglish_stopwords=pd.read_csv("stopwords_hinglish.csv") hinglish_stop_words=hinglish_stopwords['Stop_words'].tolist() stop=hinglish_stop_words+eng_stopwords multilingual = SentenceTransformer('sentence-transformers/paraphrase-MiniLM-L6-v2') kw_model = KeyBERT(model=multilingual) doc = new_text keyword = kw_model.extract_keywords(doc,...

iaditij

Candidates are not used in 0.6.0.

4

Hi! I would like to first thank the authors for the incredibly useful package! I updated my env from 0.5.1 to 0.6.0 and noticed that now candidates to keywords, that...

olarina

Setup check. Script to get keywords for comparing against SimpleMaths, TextRank and Philology results

5

So currently using the GPT and some read manuals. Did I correctly setup the code and transformer model? Or are there any suggestions which I could use? I will also...

hermanpetrov

Why and how the same model for doc_embeddings and word_embeddings?

1

BERT-based, or any transformer-based models output contextualized embeddings, which is correctly used for document embeddings generation. But to get word_embeddings, the same model is used, moreover, the array passed is...

Atharvalite

Extract keywords from multiple documents given a nested list of candidates for each document.

1

It's mentioned extracting keywords from multiple documents is faster, is it possible to do this along with candidates. If I extract candidates using Yake for multiple documents, I cannot add...

kevinmt24

KeyLLM error: AttributeError: 'str' object has no attribute 'completions'

9

I was trying to run the following code from your GitHub but got the following error: import openai from keybert.llm import OpenAI from keybert import KeyLLM from sentence_transformers import SentenceTransformer...

anonimoustt

Add more LLMs

1

Hi @MaartenGr, Could you please add more LLMs like supporting DataBricks, Anthropic, and other APis in your LLM arsenal?

behroozazarkhalili

KeyLLM Error: AttributeError: 'CompletionChoice' object has no attribute 'message'

6

using openai `v1.27.0` ```sh AttributeError: 'CompletionChoice' object has no attribute 'message' ```

cdolek

keybert benchmarks with respect to other phrase extraction techniques.

1

Hi Keybert supports extraction of keywords and key phrases. I came across UCPhrase (http://hanj.cs.illinois.edu/pdf/kdd21_xgu.pdf) which also mines phrase. Are there any benchmarks of keybert with other techniques. Thanks

vijayendra-g