Extra Credit
Official docs outline
13 sections- spaCy 101
Tokens, pipeline components, containers like Doc and Span, vocab, and lookups.
- Models and languages
Trained pipelines, packages, and how to load them.
- Linguistic features
POS tagging, dependency parsing, named entities, tokenization, and sentence segmentation.
- Processing pipelines
Pipeline components, custom components, and nlp.pipe for batch processing.
- Rule-based matching
Matcher, PhraseMatcher, DependencyMatcher, and EntityRuler.
- Vectors and similarity
Word vectors and semantic similarity comparison.
- Embeddings and transformers
Using transformer models and pretrained embeddings in pipelines.
- Training pipelines
Config system, training data, spacy train, and evaluation.
- Layers and model architectures
Thinc models and custom architectures.
- spaCy projects
Reproducible workflows for training and packaging.
- Large language models in spaCy
spacy-llm integration for LLM-backed components.
- Saving and loading
Serialization, to_disk, from_disk, and packaging pipelines.
- Visualizers
displaCy for dependency trees and entities.
Each section links to the official page. Titles and summaries by Extra Credit; the docs belong to their authors.
