Release 1.7.0

Improvements

• Added two NER DeBERTa models (#1691).

Release 1.6.0

Improvements

• Added Python 3.11 support (#1681).
• Added NER model with 37 entities (#1682).

Release 1.5.0

Improvements

• Added model usage examples to Quick Start (#1669).

Bug Fixes and Other Changes

• Fixed documentation building (#1673).
• Fixed wrong link in documentation, platforms list and multitask model evaluation (#1668, #1676, #1672).

Release 1.4.0

Major Features and Improvements

• Models documentation brought to a uniform format: 1. Introduction to the task. 2. Get started with the model. 3. Models list. 4. Use the model for prediction. 5. Customize the model. rst docs converted in ipynb format. (#1644).

Bug Fixes and Other Changes

• Updated requirements (#1662, #1665).
• Fixed error when using multiple GPUs for NER models (#1661).
• Fixed issue #1642 (#1661).

Release 1.3.0

Breaking Changes

• Removed model_name parameter from TorchModel and its derived classes. Now model should be initialized in component's __init__ method (#1617).
• Removed deeppavlov.core.models.lr_scheduled_model (#1617).
• TorchModel.__init__ now has one mandatory parameter - model (#1617).

Major Features and Improvements

• Few-Shot Text Classification Model (#1630).
• GLUE and SuperGLUE models major update (#1647).
• New components and configs for syntax parser and morphotagger (#1641).
• Improved quality and reduce RAM consumption of ODQA models (#1635).
• Removed code duplication and excessive parameters from classes derived from TorchModel (#1617).

Bug Fixes and Other Changes

• Fixed #1247, #1262, #1522 (#1655, #1656).
• Added wheel to requirements (#1650).

Release 1.2.0

Breaking Changes

• Removed RabbitMQ connector (#1631).
• Removed overrides decorator (#1631).

Major Features and Improvements

• Improvement of models for question answering over knowledge graphs (#1598).
• GLUE models update (#1645).

Bug Fixes and Other Changes

• Fix the Russian SuperGLUE certificates bug by loading the datasets from DeepPavlov servers (#1633).
• General requirements update (#1631, #1643).
• Fixed CRF save in torch_transformers_sequence_tagger (#1637).
• Fixes in tests (#1640).

Release 1.1.1

Major Features and Improvements

• Multitask learning implementation (#1627).

Release 1.1.0

Breaking Changes

Removed Models

• FAQ models, tfidf_vectorizer, tfidf_logreg_autofaq_psearch and cv_tfidf_autofaq (#1608)

Removed Components

• ru_tokenizer (#1608)

Major Features and Improvements

• Python 3.10 support (#1614).
• Few-shot classification example and few-shot sampling support added to basic_classification_iterator (#1608).

Other Changes

• pymorphy2 is replaced with spacy in entity_linker, ru_adj_to_noun and answer_types_extractor components (#1618).

Release 1.0.2

Fixes

• Fixed kbqa_cq_ru on Python 3.8/3.9 (#1609)

Documentation

• Added python inference pipelines example (#1613).

Other changes

• Updated model files upload script (#1607).

Release 1.0.1

Major Features and Improvements

• Added -i/--install CLI argument and install argument to deeppavlov.build_model, deeppavlov.evaluate_model, deeppavlov.train_model to install model requirements before interaction with model (#1603).

Bug Fixes and Other Changes

• Reduced library verbosity: redundant logging info messages replaced with debug ones. Set nltk.download to quiet mode. (#1601).
• Replaced docs/features/models/classifiers.rst with docs/features/models/classification.ipynb. Fixed minor typos in documentation, removed skill concept (#1600).
• Removed /examples from the README.md links (#1602).