semantic-search

Consider https://www.nltk.org/ for tokenization

I had to add once: nltk.download('punkt_tab') nltk.download('averaged_perceptron_tagger_eng')

These for chunks: nltk.download('maxent_ne_chunker_tab') nltk.download('words')

Name		Name	Last commit message	Last commit date
Latest commit History 4 Commits
asia_data		asia_data
books		books
.gitignore		.gitignore
README.md		README.md
config.py		config.py
ingest.py		ingest.py
main.py		main.py
main_asia.py		main_asia.py
size.py		size.py

Navigation Menu