0.7.4

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

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

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

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

(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

• 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

• 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

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

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

• Add data to English dialog corpus (via @vkosuri) #516
• Migrated corpus module to a new separate repository (https://github.com/gunthercox/chatterbot-corpus) [#654]

0.5.5

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]