Skip to content

Releases: gunthercox/ChatterBot

0.7.4

29 Jul 14:13
Compare
Choose a tag to compare

Bug fixes

  • Fix database name being ignored #866
  • Change SQL storage default to sqlite file instead of in-memory database #871

Deprecation

Deprecation warnings will now be triggered for the following classes and methods.
These items are schedule to be removed in ChatterBot version 0.8.

  • chatterbot.storage.JsonFileStorageAdapter
  • chatterbot.ChatBot.from_config

Enhancements

  • Remove direct dependency on jsondb for training file exports #869

0.7.3

19 Jul 23:38
Compare
Choose a tag to compare

Bug fixes

  • Add dateutil to the requirements #860
  • Add long description to setup.py #861

Improvements

  • Remove redundant text_search field is SQL adapter #856

0.7.2

18 Jul 11:10
Compare
Choose a tag to compare

Improvements

  • Add a base class for SQL Alchemy models #852
  • Add created_at field to response model #854
  • Remove development dependency on pandoc and setuptools-markdown #855

0.7.1

16 Jul 20:39
Compare
Choose a tag to compare

Bug fixes

  • Correct integrity error by checking for existing responses #850

Improvements

  • Use the correct convention for primary keys in SQL storage adapter #851

Performance

  • Improve memory efficiency of Ubuntu Corpus trainer #821

Testing

  • Use the same database for all tests when testing MongoDB #835

0.7.0

04 Jul 13:57
Compare
Choose a tag to compare

(Soft) breaking changes:

  • Switch to SQL adapter as the default storage adapter for ChatterBot #796
    • If you were previously using the default adapter (JsonFileStorageAdapter) and wish to continue using it you must specify storage_adapter="chatterbot.storage.JsonFileStorageAdapter" when initializeing your ChatBot.
  • Documentation and Example updated to reference SQLStorageAdapter #808

Updates and improvements:

  • Update initialization to download stopwords only if needed #803
  • Add command line utility to list NLTK data directories #805
  • Add search to response Django admin #810
  • Code clan up in training module #809
  • Update to next version of ChatterBot corpus #819
    • Document the format of the ChatterBot corpus #818

Bug fixes

  • Correct order responses are saved in #813
  • Correct file extraction check for Ubuntu dialog corpus #816

0.6.3

24 Jun 18:50
Compare
Choose a tag to compare
  • Rename the beta storage adapter SQLAlchemyDatabaseAdapter to SQLStorageAdapter #786
  • Create tables for SQLStorageAdapter automatically if they do not already exist #787
  • Fix logging statement in sql adapter #800

0.6.2

10 Jun 11:45
Compare
Choose a tag to compare
  • Run SQL storage adapter tests in memory #745
  • Improve NLTK corpus download error message #765
  • Make callable classes for comparing statements #766
  • Add performance benchmarking to main module #768
  • Open Ubuntu corpus tsv as utf-8 #782

0.6.1

01 Jun 23:36
Compare
Choose a tag to compare

Features

  • Introduce beta version of Sqlalchemy storage adapter #693 #712
  • Allow the Django app to be specified #705
  • Create and use abstract base models for Django #715

Testing

  • Enable PEP8 checks in Travis CI #702 #714
  • Only check if MongoDB is running once per Mongo test case #713

Documentation

  • Added term glossary to documentation #689

0.6.0

21 Mar 19:31
Compare
Choose a tag to compare

Bug fixes

  • Fix format of Django API view response data #608
  • Prevent non-string type values from breaking comparison algorithms #655

Improvements

  • Enhancement of the decimal percent of similarity in levenshtein_distance (via @addelll) #618
  • Add Django Setting to allow ChatterBot Statement objects to be used instead of Django Statement model (via @web-maker) #653

Breaking changes

  • Change logic adapters to just return one value #587
  • The confidence value is no longer returned from the generate_response method (it's available on the statement object now) #588
  • Remove confidence parameter from output adapter process methods #589
  • Require session id for generate_response method #598

Conversations

  • Create conversation model #594

Corpus

0.5.5

15 Jan 20:14
Compare
Choose a tag to compare

Features

  • Allow custom file paths to ChatterBot corpus files [https://github.com//pull/549]
  • Support for Turkish math words (via @yusuf-celik) [https://github.com//pull/558]
  • Return confidence value on statement object [https://github.com//pull/565]
  • Convert clean_whitespace utility into a preprocessor [https://github.com//pull/569]
  • Allow seed word to be set for Twitter training adapter [https://github.com//pull/578]
  • Fix issue whre ^ ends up being used as bitwise XOR instead of ** for powers (via @Martmists) [https://github.com//pull/582]

Bug fixes

  • The nltk.data.find argument needs to be a path, not just a filename (via @Gaboose) [https://github.com//pull/548]
  • Add missing serialize method to Response model [https://github.com//pull/557]
  • Fix comparison in levenshtein (via @gballardin) [https://github.com//pull/579]
  • Fix "empty generator" bug in ChatBot.filters (via @thesprockee) [https://github.com//pull/580]
  • Fix display formatting for exponents [https://github.com//pull/584]

Maintenance

  • Only control write permission in the ChatBot class [https://github.com//pull/561]
  • Disconnect storage from adapter class [https://github.com//pull/552]
  • Add tests for examples [https://github.com//pull/586]

Deprecation

  • Remove deprecated code [https://github.com//pull/542]

Documentation

  • Document training path methods [https://github.com//pull/550]
  • Add more examples and expand tutorial in documentation [https://github.com//pull/564]