reutersmedia/pyword2vec repository overview

See https://github.com/ReutersMedia/pyword2vec⁠

The Google Word2Vec pre-trained model is available here: https://drive.google.com/file/d/0B7XkCwpI5KDYNlNUTTlSS21pQmM/edit?usp=sharing⁠ The model contains 300-dimensional vectors for 3 million words and phrases.

Usage: curl http://localhost:8080/most_similar?positive=hello&topn=5⁠

The number of threads is set via an environment variable NUM_UWSGI_THREADS. Each of these threads will share the same Word2Vec model. The number of processes is set by NUM_PYTHON_PROCESSES, and defaults to one. Suggested usage is one thread per core.

See https://code.google.com/archive/p/word2vec/⁠ for license information on the mode.