Zero-shot predefined Topics

Nobody has claimed this yet.

Hi, Thanks again for your great tool,

I have a question regarding predefined Topics, whenver I add a list of **zeroshot_topic_list**, I got different generated topics and not the one I added, is there a way to only do topicmodeling based only on these **zeroshot_topic_list** ?

Code :

from bertopic import BERTopic
# Initialize and train BERTopic model
topic_model = BERTopic(
embedding_model=embedding_model,
vectorizer_model=vectorizer_model,
umap_model=umap_model,
calculate_probabilities=True,
#hdbscan_model=hdbscan_model,
representation_model=representation_model,
verbose=True,
nr_topics=15,
min_topic_size=25,
zeroshot_topic_list=zeroshot_topic_list,
zeroshot_min_similarity=.85

)

# Fit the topic model and transform the data
topics, probs = topic_model.fit_transform(df['PreprocessedText'].values)

Start by reproducing the behavior with the provided BERTopic configuration, especially zeroshot_topic_list, zeroshot_min_similarity, and fit_transform. Determine whether the requested behavior is supported and define what it means for modeling to use only the predefined topics. Done means the expected topic assignments are produced or the limitation is documented clearly.

Written by the indexing model from the issue text.