Spaces:

seanpedrickcase
/

topic_modelling

Running

App Files Files Community

topic_modelling / funcs

Ctrl+K

3 contributors

History: 36 commits

seanpedrickcase

Removed some requirements from Dockerfile for AWS deployment to reduce container size

51ba1cb 10 months ago

__init__.py

0 Bytes

first commit over 1 year ago
anonymiser.py

12.2 kB

Only aggregate topics not 'other', allowed for minimum sentence length, default max_topics now will auto aggregate topics. Added Cognito Auth functionality (boto3 with AWS). 10 months ago
auth.py

1.88 kB

Only aggregate topics not 'other', allowed for minimum sentence length, default max_topics now will auto aggregate topics. Added Cognito Auth functionality (boto3 with AWS). 10 months ago
bertopic_vis_documents.py

47.6 kB

Can split passages into sentences. Improved embedding, LLM representation models, improved zero shot capabilities 11 months ago
clean_funcs.py

4.86 kB

Only aggregate topics not 'other', allowed for minimum sentence length, default max_topics now will auto aggregate topics. Added Cognito Auth functionality (boto3 with AWS). 10 months ago
embeddings.py

3.36 kB

Can split passages into sentences. Improved embedding, LLM representation models, improved zero shot capabilities 11 months ago
helper_functions.py

18.3 kB

Only aggregate topics not 'other', allowed for minimum sentence length, default max_topics now will auto aggregate topics. Added Cognito Auth functionality (boto3 with AWS). 10 months ago
presidio_analyzer_custom.py

4.18 kB

Added clean data options, improved re-representation options and visualisation. General format changes over 1 year ago
prompts.py

6.24 kB

Updated packages. Improve hierarchy vis. Better models - mixedbread and phi3. Now option to split texts into sentences before modelling. 11 months ago
representation_model.py

7.83 kB

Removed some requirements from Dockerfile for AWS deployment to reduce container size 10 months ago
topic_core_funcs.py

38.2 kB

Allowed for app running on AWS to use smaller embedding model and not to load representation LLM (due to size restrictions). 10 months ago