Gilda v1.4.1

What's Changed

• Fix corner case with trailing space in synonym by @bgyori in #153
• Add NER download as CSV option in web UI by @bgyori in #155

Full Changelog: 1.4.0...1.4.1

1.4.0

What's Changed

• Improve NER with word tokenization by @bgyori in #146
• Use coordinates in custom sentence split function by @kkaris in #147
• NER Benchmark Script by @galileosteinberg in #148
• Update tests.yml to use new punkt file from NLTK by @cmungall in #151

Full Changelog: 1.3.0...1.4.0

Gilda v1.3.0

What's Changed

• Web and REST service expansion to include NER annotation by @galileosteinberg in #145
• Implement context text for annotation and fix capitalization by @bgyori in #141
• Make annotation return a list of Annotation object with a list of ScoredMatches by @bgyori in #143
• Improve MeSH mappings by @bgyori in #140
• Add an extra word to README by @bgyori in #144

Full Changelog: 1.2.1...1.3.0

Gilda v1.2.1

What's Changed

• Allow for 'classic' gunicorn running by @kkaris in #138
• Upgrade for Python 3.12 compatibility by @bgyori in #139

New Contributors

• @kkaris made their first contribution in #138

Full Changelog: 1.2.0...1.2.1

Gilda v1.2.0

What's Changed

• Loading remote indexes by @cthoyt in #132
• Add default grounding resources to README by @bgyori in #135

Full Changelog: 1.1.0...1.2.0

Gilda v1.1.0

What's Changed

• Enable returning all NER results by @cthoyt in #120
• Include Python 3.11 in testing by @cthoyt in #121
• Make web UI dependencies optional by @cthoyt in #119
• Update flask and flask-restx dependencies by @cthoyt in #125
• Update docs by @cthoyt in #124
• Expose dump_terms from top level by @cthoyt in #126
• Update terms with latest resources by @bgyori in #128
• Improve safety of NER build by @cthoyt in #127
• Add convenience function Grounder.ground_best by @cthoyt in #129
• Make instantiation of Grounder more flexible by @cthoyt in #130
• Update footer text by @cthoyt in #131

Full Changelog: 1.0.0...1.1.0

Gilda v1.0.0

What's Changed

• Update resources by @bgyori in #102
• Fix double whitespace and typo in docstring by @EFord36 in #104
• Move filter_out_duplicates function by @cthoyt in #103
• Improve depluralization by @bgyori in #105
• Add form to matches page by @cthoyt in #90
• Strip whitespaces for input by @bgyori in #106
• Add pandas DataFrame utilities by @cthoyt in #107
• Add function to yield Terms from file by @bgyori in #108
• Enable passing custom terms to web application by @cthoyt in #109
• Make requirement obonet optional by @cthoyt in #110
• Fix invalid Adeft IDs by @bgyori in #111
• Improve filtering of duplicates by @cthoyt in #112
• Update signature of annotate() by @cthoyt in #114
• Return ScoredMatch objects in annotate() by @cthoyt in #113
• Add NER by @cthoyt, @bgyori and @kkaris in #115
• Make term prefix prioritization configurable by @cthoyt in #116
• Move dump_terms() by @cthoyt in #117
• Add NER tutorial and update documentation configuration by @cthoyt in #118

Full Changelog: 0.10.3...1.0.0

Gilda v0.10.3

What's Changed

• Add batched grounding endpoint to web service by @bgyori in #100
• Fix error responses from web service

Full Changelog: 0.10.2...0.10.3

Gilda v0.10.2

What's Changed

• Use legacy UniProt service to generate terms by @bgyori in #99
• Fix get_models function to load models before returning if models not loaded yet by @bgyori in #99

Full Changelog: 0.10.1...0.10.2

Gilda v0.10.1

• Lazy loading for disambiguation models for faster initialization and lower memory footprint in #96
• Implement optional SQLite back-end for low-memory environment in #97
• Update grounding resources