MaartenGr BERTopic issues

MaartenGr / BERTopic

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

https://maartengr.github.io/BERTopic/

MIT License

6.19k stars 765 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

'Merge_Models' with new topic_model from outliers

#2222 OnAnd0n opened 9 hours ago
0
TypeError: Cannot use scipy.linalg.eigh for sparse A with k >= N. Use scipy.linalg.eigh(A.toarray()) or reduce k. -> _bertopic.py", line 3742, in _reduce_dimensionality

#2218 miha42-github opened 3 days ago
1
metric= "cosine" error reported

#2217 superseanyoung opened 1 week ago
4
Add LiteLLM as a representation model

#2213 MaartenGr opened 1 week ago
2
There are Chinese characters in my project, but after calling the visualize_document_datamap() method, the characters appear as garbled text.

#2211 superseanyoung opened 1 week ago
3
How can i use "precomputed" HDBSCAN in BerTopic?

#2209 shadabmeymandi opened 1 week ago
7
Treemap visualization instead of hierarchical tree

#2208 munt-create opened 1 week ago
1
Systematic test units for fit_transform()

#2206 PipaFlores opened 2 weeks ago
2
Not showing Topic after topic_model.get_topic_info()

#2205 hari-chalise opened 2 weeks ago
4
the 6 steps of BERTopic

#2204 TalaN1993 opened 2 weeks ago
4
Saving a trained model using pytorch and safetensor and then redownloading causes topics to be off

#2198 SkylarOconnell opened 3 weeks ago
12
Remove duplicated phrase "the model"

#2197 AndreaFrancis closed 3 weeks ago
1
serializing a model built with partial_fit

#2196 chadlillian opened 1 month ago
2
Align Logger Output with Documented Pipeline

#2192 PipaFlores opened 1 month ago
5
Fixed issue #2144

#2191 PipaFlores closed 2 weeks ago
11
fit_transform tries to access embedding_model if representation_model is not None

#2189 rasantangelo opened 1 month ago
1
Update LangChain Support

#2188 Skar0 opened 1 month ago
16
Update LangChain Support

#2187 Skar0 opened 1 month ago
6
How to calculate entropy with Bertopic

#2186 bruceszq opened 1 month ago
1
"doc_length" doesn't work with llama3.1

#2185 mjin990 opened 1 month ago
2
Base LLM topic representation on results from other representation model (e.g. KeyBERT or POS) instead of the default representation

#2184 Hveemos closed 1 month ago
2
Fixed Issue: #1977

#2181 SSivakumar12 opened 1 month ago
5
Fixed issue #2144

#2180 PipaFlores closed 1 month ago
3
OpenAI representation fails to produce output when response content is None

#2176 jeaninejuliettes opened 1 month ago
6
v0.16.4

#2175 MaartenGr closed 1 month ago
0
feat: add support for python 3.13

#2173 afuetterer opened 1 month ago
0
datamapplot is not defined

#2170 LauwXiang closed 1 month ago
2
Zero shot topic modelling

#2168 ankitkr3 opened 1 month ago
12
Zero-shot predefined Topics

#2164 mahmawad opened 1 month ago
1
Visualization doesn't show up on Jupyter Lab

#2163 liuzz10 closed 1 month ago
3
Update distribution.md

#2162 saikumaru closed 1 month ago
1
topic_model.transform(training_data) results in KeyError: 6467

#2161 registjl closed 1 month ago
6
Custom labels in dynamic modeling and topic per class

#2154 sercankiyak opened 2 months ago
4
PartOfSpeech errors when candidate topics contain special characters

#2153 woranov closed 2 months ago
1
How to do Hierarchical Topic Modeling on Merged Model?

#2152 shivamtawari opened 2 months ago
3
Zero topic distributions for some documents using approximate_distribution()

#2150 Connorwz opened 2 months ago
5
TypeError: unhashable type: 'numpy.ndarray'

#2149 cindyangelira closed 2 months ago
2
outlier reduction

#2148 Hanqingxu123 opened 2 months ago
2
Add system prompt for OpenAI representation model

#2146 Leo-LiHao opened 2 months ago
6
added system prompt for openai

#2145 Leo-LiHao opened 2 months ago
0
Representations from representation_models are generated twice when nr_topics="auto".

#2144 MaartenGr closed 2 weeks ago
14
Installation of BERTopic fails due to llvmlite version compatibility with Python 3.12 (macOS M1)

#2141 iamvarol closed 2 months ago
3
Different topic assignment on training data when using saved model

#2140 tmtsmrsl opened 2 months ago
1
openAI BERTopic coherence score

#2139 TalaN1993 opened 2 months ago
1
Fix regex matching being used in PartOfSpeech representation model

#2138 woranov closed 2 months ago
3
AttributeError: 'OpenAIBackend' object has no attribute 'encode'

#2136 mahmawad opened 2 months ago
1
Trying to use Zephyr for representation but facing error. But getting RuntimeError: Expected all tensors to be on the same device.

#2134 shivamtawari closed 2 months ago
5
Add nr_repr_docs parameter

#2130 robechun opened 2 months ago
5
Add custom labels to get topic tree

#2125 clfkenny opened 3 months ago
0
Custom labels for get_topic_tree

#2123 MaartenGr opened 3 months ago
2