Errors OpenAI as a representation model and

Hi @MaartenGr

I am using bertopic==0.16.0 (with default settings) in a dedicated environment and getting the following errors:

Code:

                          # KeyBERT
                          keybert = KeyBERTInspired()
                          
                          # MMR
                          mmr = MaximalMarginalRelevance(diversity=0.3)
                          
                          representation_models = [mmr, rep_model_chatgpt]
                          
                          topic_model = BERTopic(language="english", 
					                              top_n_words=100,
                                                  verbose=True, 
                                                  seed_topic_list=seed_topic_list,
                                                  representation_model=representation_models,
                                                  vectorizer_model=CountVectorizer(ngram_range=(1, 3) , stop_words="english")
                                                  ) 
                          
                          
                          topics, probs = topic_model.fit_transform(docs)
                          topic_model.save('my_model')

1. When I use OpenAI as a representation model, it generate the following error when trying to save the model using model.save().

Error:
2023-12-11 16:26:00,118 - BERTopic - WARNING: When you use pickle to save/load a BERTopic model,please make sure that the environments in which you saveand load the model are exactly the same. The version of BERTopic,its dependencies, and python need to remain the same.
Traceback (most recent call last):
…
TypeError: cannot pickle '_thread.RLock' object

2. When tried bertopic.fit_transform() with seed_topic_list for guided topic modelling (with or without rewpresentation model). getting the following error
   Error:
   topics, probs = topic_model.fit_transform(docs)
   File ".conda\envs\bertopic2\lib\site-packages\bertopic_bertopic.py", line 399, in fit_transform
   y, embeddings = self._guided_topic_modeling(embeddings)
   File ".conda\envs\bertopic2\lib\site-packages\bertopic_bertopic.py", line 3617, in _guided_topic_modeling
   embeddings[indices] = np.average([embeddings[indices], seed_topic_embeddings[seed_topic]], weights=[3, 1])
   File ".conda\envs\bertopic2\lib\site-packages\numpy\lib\function_base.py", line 511, in average
   a = np.asanyarray(a)
   ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (2,) + inhomogeneous part.

Thanks

Start by reproducing the two reported failures with BERTopic 0.16.0: saving a model using the OpenAI representation model, and running fit_transform with seed_topic_list. Inspect the model.save path and _guided_topic_modeling in _bertopic.py; done means both workflows complete without the reported pickle or NumPy shape errors.