Published April 21, 2024
| Version v0.16.1
Software
Open
MaartenGr/BERTopic: v0.16.1
Creators
- Maarten Grootendorst1
- zilch42
- Anubhab Das2
- Chris Inskip
- Joshua Sundance Bailey3
- dschwalm
- Ahmed Elashry
- Alex Gamble
- Anastasia Simonoff
- Anoop Thomas Mathew4
- Aratako
- Bob5
- Carlos Pegueros6
- Daniel Kapitan7
- Daniel van Strien8
- David Dai
- Domenic Rosati9
- Elton Liao
- Felipe Alves Siqueira10
- Franz Louis Cesista11
- Gus Moir12
- James Nicholson13
- Jamie Snape
- Jiaxin Wen14
- Josiah Outram Halstead
- LawrenceFulton
- Leland McInnes15
- Luis Oala16
- Mert Yanık17
- Nils Reimers18
- 1. IKNL
- 2. Textify AI (@T3xtifyai)
- 3. @swca
- 4. @iterflow
- 5. Proton AG
- 6. @Nubank
- 7. freelance data scientist
- 8. Hugging Face
- 9. @scitedotai
- 10. ICMC, University of São Paulo
- 11. Expedock
- 12. Mustang Analytics
- 13. @HarvardChanSchool
- 14. Tsinghua University
- 15. Tutte Institute for Mathematics and Computing
- 16. head of machine learning @dotphoton-ag
- 17. LC Waikiki
- 18. Cohere
Description
<h1><b>Highlights:</a></b></h1>
- Add Quantized LLM Tutorial
- Add optional datamapplot visualization using
topic_model.visualize_document_datamap
by @lmcinnes in #1750 - Migrated OpenAIBackend to openai>=1 by @peguerosdc in #1724
- Add automatic height scaling and font resize by @ir2718 in #1863
- Use
[KEYWORDS]
tags with the LangChain representation model by @mcantimmy in #1871
<h3><b>Fixes:</a></b></h3>
- Fixed issue with
.merge_models
seemingly skipping topic #1898 - Fixed Cohere client.embed TypeError #1904
- Fixed
AttributeError: 'TextGeneration' object has no attribute 'random_state'
#1870 - Fixed topic embeddings not properly updated if all outliers were removed #1838
- Fixed issue with representation models not properly merging #1762
- Fixed Embeddings not ordered correctly when using
.merge_models
#1804 - Fixed Outlier topic not in the 0th position when using zero-shot topic modeling causing prediction issues (amongst others) #1804
- Fixed Incorrect label in ZeroShot doc SVG #1732
- Fixed MultiModalBackend throws error with clip-ViT-B-32-multilingual-v1 #1670
- Fixed AuthenticationError while using OpenAI() #1678
- Update FAQ on Apple Silicon by @benz0li in #1901
- Add documentation DataMapPlot + FAQ for running on Apple Silicon by @dkapitan in #1854
- Remove commas from pip install reference in readme by @luisoala in #1850
- Spelling corrections by @joouha in #1801
- Replacing the deprecated
text-ada-001
model with the latesttext-embedding-3-small
from OpenAI by @atmb4u in #1800 - Prevent invalid empty input error when retrieving embeddings with openai backend by @liaoelton in #1827
- Remove spurious warning about missing embedding model by @sliedes in #1774
- Fix type hint in ClassTfidfTransformer constructor @snape in #1803
- Fix typo and simplify wording in OnlineCountVectorizer docstring by @chrisji in #1802
- Fixed warning when saving a topic model without an embedding model by @zilch42 in #1740
- Fix bug in
TextGeneration
by @manveersadhal in #1726 - Fix an incorrect link to usecases.md by @nicholsonjf in #1731
- Prevent
model
argument being passed twice when usinggenerator_kwargs
in OpenAI by @ninavandiermen in #1733 - Several fixes to the docstrings by @arpadikuma in #1719
- Remove unused
cluster_df
variable inhierarchical_topics
by @shadiakiki1986 in #1701 - Removed redundant quotation mark by @LawrenceFulton in #1695
- Fix typo in merge models docs by @zilch42 in #1660
Files
MaartenGr/BERTopic-v0.16.1.zip
Files
(5.8 MB)
Name | Size | Download all |
---|---|---|
md5:53159937de053e596657363ed926db20
|
5.8 MB | Preview Download |
Additional details
Related works
- Is supplement to
- Software: https://github.com/MaartenGr/BERTopic/tree/v0.16.1 (URL)