👑 spaCy building blocks and visualizers for Streamlit apps
NEW visualize_spans
for span support in displaCy.:
visualize_{parser,ner,spans}
functions now take a manual
argument for rendering data manually
Updated docstrings with correct arguments & types
visualize_parser
now takes displacy_options
for providing options for that visualizer.
New examples scripts:
@pmbaumgartner, @svlandeg, @rmitsch
visualize_spans
function + manual
argument + docstrings by @pmbaumgartner in https://github.com/explosion/spacy-streamlit/pull/37
Full Changelog: https://github.com/explosion/spacy-streamlit/compare/v1.0.3...v1.0.4
Improvements to visualize_ner
:
manual
option in visualize_ner
displacy_options
to be passed to visualize_ner
PR https://github.com/explosion/spacy-streamlit/pull/25: Use the streamlit theming options directly in visualizer.py
PR https://github.com/explosion/spacy-streamlit/pull/29: Ensure the correct texts are passed onwards in visualize_similarity
New examples scripts:
@callistachang, @honnibal, @ines, @Jette16, @narayanacharya6, @svlandeg
beta_
prefixes for compatibility with streamlit v0.86.0+.🌙 This release is a pre-release and requires spaCy v3 (nightly).
show_config
setting to show config.cfg
of currently loaded model.default_model
setting to specify option to auto-select in dropdown.show_pipeline_info
setting to toggle pipeline description in sidebar.Token.morph
and Token.is_sent_start
.get_default_text
callback to generate default text based on nlp
object (e.g. language).🌙 This release is a pre-release and requires spaCy v3 (nightly).
show_config
setting to show config.cfg
of currently loaded model.default_model
setting to specify option to auto-select in dropdown.show_pipeline_info
setting to toggle pipeline description in sidebar.Token.morph
and Token.is_sent_start
.show_visualizer_select
option to allow user to toggle displayed visualizers (based on the specified options).Doc
and model meta.key
argument to widgets to prevent problem with duplicate widgets.colors
parameter to ner_visualizer
.Thanks to @Jcharis, @yagays, @pmbaumgartner, @andfanilo and @discdiver for the pull requests!