Owner

MaartenGr

11 indexed repositories · View on GitHub

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

Python · 7843 stars
KeyBERT
Minimal keyword extraction with BERT

Python · 4222 stars
PolyFuzz
Fuzzy string matching, grouping, and evaluation.

Python · 803 stars
Concept
Concept Modeling: Topic Modeling on Images and Text

Python · 230 stars
soan
Social Analysis based on Whatsapp data

Python · 154 stars
cTFIDF
Creating class-based TF-IDF matrices

Python · 92 stars
BERTopic_evaluation
Code and experiments for *BERTopic: Neural topic modeling with a class-based TF-IDF procedure*

Python · 85 stars
ReinLife
Creating Artificial Life with Reinforcement Learning

Python · 84 stars
CustomerSegmentation
Analysis for Customer Segmentation

Jupyter Notebook · 73 stars
boardgame
Heroku app to explore boardgame data

Jupyter Notebook · 23 stars
MaartenGr

Python · 5 stars

Beginner friendly Everything

Open All

Topic aspects are not updated when merging topics and the model uses a custom vectorizer Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 68/100

MaartenGr/BERTopic#2531 · Opened Aug 12, 2026
Creating topics over time fails if model has deleted topics Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 72/100

MaartenGr/BERTopic#2530 · Opened Aug 12, 2026
Topic deletion fails if topics have custom lables Open

bug

Difficulty 2/5 1-3 hours Newbie friendliness 84/100

MaartenGr/BERTopic#2529 · 1 comment · Opened Aug 12, 2026
Creating Topic Taxonomies Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

MaartenGr/BERTopic#2526 · Opened Jul 30, 2026
Add structured multi aspect output to the LangChain representation 2:06 AM Open

Difficulty 5/5 Over a week Newbie friendliness 45/100

MaartenGr/BERTopic#2523 · 1 reaction · Opened Jul 26, 2026
Add top-down (divisive) strategy for `hierarchical_topics()` Open

Difficulty 5/5 Over a week Newbie friendliness 35/100

MaartenGr/BERTopic#2508 · Opened Jul 8, 2026
Support pre-tokenized documents to avoid redundant tokenization across pipeline stages Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

MaartenGr/BERTopic#2507 · Opened Jul 8, 2026
Add contrastive and embedding-aware feature importance as representation aspects Open

Difficulty 4/5 3-5 days Newbie friendliness 42/100

MaartenGr/BERTopic#2506 · Opened Jul 8, 2026
Lightweight soft topic assignment via temperature-scaled embedding distances Open

Difficulty 4/5 3-5 days Newbie friendliness 38/100

MaartenGr/BERTopic#2505 · Opened Jul 8, 2026
Support reusing pre-computed UMAP embeddings across runs (grid search, caching) Open

Difficulty 4/5 3-5 days Newbie friendliness 45/100

MaartenGr/BERTopic#2504 · Opened Jul 8, 2026
`hierarchical_topics()` parent nodes show raw c-TF-IDF keywords instead of representation model labels Open

Difficulty 4/5 3-5 days Newbie friendliness 55/100

MaartenGr/BERTopic#2503 · Opened Jul 8, 2026
`approximate_distribution`: add target-based min_similarity ("at most N unassigned documents") Open

Difficulty 4/5 3-5 days Newbie friendliness 52/100

MaartenGr/BERTopic#2502 · Opened Jul 8, 2026
`reduce_outliers`: add target-based outlier reduction ("reduce to X% outliers") Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

MaartenGr/BERTopic#2501 · Opened Jul 8, 2026
Allow recalculating representative docs with a configurable count (currently hardcoded to 3) Open

Difficulty 4/5 3-5 days Newbie friendliness 45/100

MaartenGr/BERTopic#2500 · Opened Jul 8, 2026
`_extract_representative_docs` recomputes from scratch on every call — no caching Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

MaartenGr/BERTopic#2499 · Opened Jul 8, 2026
`MaximalMarginalRelevance` makes 2N embedding calls instead of 1 Open

Difficulty 3/5 1-2 days Newbie friendliness 68/100

MaartenGr/BERTopic#2498 · Opened Jul 8, 2026
Extract duplicated document-aggregation and topic-naming patterns into shared helpers Open

Difficulty 3/5 1-2 days Newbie friendliness 35/100

MaartenGr/BERTopic#2497 · Opened Jul 8, 2026
`_extract_representative_docs`: duplicate sampling (`replace=True`) and text-based index mapping select wrong documents Open

Difficulty 3/5 1-2 days Newbie friendliness 25/100

MaartenGr/BERTopic#2495 · 1 comment · Opened Jul 8, 2026
BERTopic.load(path, embedding_model=...) makes a redundant HuggingFace network request even when an embedder is explicitly provided Open

Difficulty 2/5 1-3 hours Newbie friendliness 30/100

MaartenGr/BERTopic#2493 · Opened Jun 18, 2026
ci: add uv_exclude_newer env in github actions workflow? Open

Difficulty 2/5 1-3 hours Newbie friendliness 64/100

MaartenGr/BERTopic#2485 · Opened May 13, 2026
Thinking models in ollama exit early Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 48/100

MaartenGr/BERTopic#2481 · Opened Apr 14, 2026
Untrusted impersonation of the project at bertopic.org Open

Difficulty 4/5 3-5 days Newbie friendliness 15/100

MaartenGr/BERTopic#2478 · Opened Apr 5, 2026
Untrusted impersonation of the project at bertopic.com Open

Difficulty 4/5 3-5 days Newbie friendliness 20/100

MaartenGr/BERTopic#2477 · Opened Apr 5, 2026
find_topics(topic) crashes if topic is a 1-element list Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 45/100

MaartenGr/BERTopic#2475 · Opened Mar 8, 2026
`Illegal instruction` on import Open

Difficulty 4/5 3-5 days Newbie friendliness 30/100

MaartenGr/KeyBERT#274 · Opened Feb 28, 2026
BadRequestError: Error code: 400 Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 35/100

MaartenGr/BERTopic#2469 · 1 comment · Opened Jan 26, 2026
German Language Issues: Umlaut Removal and Compound Word Truncation in c-TF-IDF Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

MaartenGr/BERTopic#2468 · 1 comment · Opened Jan 19, 2026
Reproducibility Open

Difficulty 3/5 1-2 days Newbie friendliness 35/100

MaartenGr/KeyBERT#273 · 1 comment · Opened Jan 1, 2026
Structured LLM JSON Output → Dynamic DataFrame Columns for Topic & Document Analysis Open

Difficulty 5/5 Over a week Newbie friendliness 30/100

MaartenGr/BERTopic#2466 · 1 comment · Opened Dec 28, 2025
Switch documentation from `mkdocs-material` to `zensical` Open

Difficulty 4/5 3-5 days Newbie friendliness 45/100

MaartenGr/BERTopic#2460 · 1 comment · Opened Dec 3, 2025
Allow option to show heatmap annotation Open

Difficulty 2/5 1-3 hours Newbie friendliness 48/100

MaartenGr/BERTopic#2458 · 2 comments · Opened Nov 16, 2025
Enable additional ruff rules Open

Difficulty 3/5 1-2 days Newbie friendliness 35/100

MaartenGr/BERTopic#2450 · 3 comments · Opened Oct 28, 2025
Topic names not set to zero-shot topic when `fit_transform` results in only zero-shot topics Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 45/100

MaartenGr/BERTopic#2447 · 2 comments · Opened Oct 25, 2025
Missing word in Getting started / Best practices / Pre-calculate embeddings / Tip Open

Difficulty 1/5 Under an hour Newbie friendliness 45/100

MaartenGr/BERTopic#2442 · 1 comment · Opened Oct 12, 2025
Potential Spam Page - bertopic.com is NOT the official site Open

Difficulty 5/5 Over a week Newbie friendliness 15/100

MaartenGr/BERTopic#2441 · 2 comments · 2 reactions · Opened Oct 11, 2025
When I use topic_model.visualize_barchart () for visualization, can I customize the first 5 topic words of the theme Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 30/100

MaartenGr/BERTopic#2438 · 1 comment · Opened Oct 11, 2025
`model.save()` fails with `TypeError` when `topic_mapper_.mappings_` contains `None` Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 45/100

MaartenGr/BERTopic#2432 · 1 comment · Opened Oct 2, 2025
Update topic embeddings and representations when merging clusters in `merge_models` Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

MaartenGr/BERTopic#2431 · 1 comment · Opened Sep 29, 2025
MLflow Autologging Integration for BERTopic Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

MaartenGr/BERTopic#2429 · 3 comments · Opened Sep 28, 2025
ImportError: cannot import name 'import_array_module' from 'narwhals._pandas_like.utils' Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 35/100

MaartenGr/BERTopic#2426 · 1 comment · Opened Sep 25, 2025
Topics over time: IndexError: index (68) out of range Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

MaartenGr/BERTopic#2425 · 2 comments · Opened Sep 23, 2025
Adding models Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

MaartenGr/KeyBERT#269 · 1 comment · Opened Sep 19, 2025
BadRequestError: Error code: 400 - {'error': {'message': "Unsupported parameter: 'stop' is not supported with this model.", 'type': 'invalid_request_error', 'param': 'stop', 'code': 'unsupported_parameter'}} Open

bug

Difficulty 2/5 1-3 hours Newbie friendliness 68/100

MaartenGr/BERTopic#2423 · 5 comments · 1 reaction · Opened Sep 12, 2025
A metric is needed to reflect the quality of a model, just like the perplexity of LDA Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

MaartenGr/BERTopic#2421 · 1 comment · Opened Sep 11, 2025
.merge_models() alters HDBSCAN clustering Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 35/100

MaartenGr/BERTopic#2415 · 1 comment · Opened Aug 27, 2025
MMR Multiprocessing Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

MaartenGr/KeyBERT#268 · 1 comment · Opened Aug 8, 2025
Zero-shot topics are merged during topic reduction Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 35/100

MaartenGr/BERTopic#2409 · 4 comments · Opened Aug 7, 2025
Model2Vec Open

Difficulty 2/5 1-3 hours Newbie friendliness 25/100

MaartenGr/KeyBERT#267 · 1 comment · Opened Aug 6, 2025
How to use other LLMs in the interface style of openai? Open

Difficulty 3/5 1-2 days Newbie friendliness 20/100

MaartenGr/KeyBERT#266 · 1 comment · Opened Jul 28, 2025
Ordering of MMR in chained representation models has no effect Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 35/100

MaartenGr/BERTopic#2394 · 5 comments · Opened Jul 8, 2025

Showing the newest 100

This page lists what was indexed most recently. Advanced filter has the whole inventory, narrowed by language, difficulty and how long a task takes.

Open advanced filter

MaartenGr

Showing the newest 100

Get new issues in your inbox