0
$\begingroup$

I have to use Fasttext model to return word embeddings. In test I was calling it through API. Since there are too many words to compute embeddings, API call seems to be expensive. I would like to use fasttext without API. For that I need to load the model once and keep it in memory for further calls. How can this be done without using API. Any help is highly appreciated.

$\endgroup$
0
$\begingroup$

Surely, I will good idea to write embedding on some database like SQLite,Postgres or RocksDB. I highly appreciate using RocksDB as it is store data in the form of a key-value pair which is the best suit for your use case. Maybe it will take little more time but your main issue will get resolve through it. If u directly deal with python than there is support of SQLite and Postgres. If u work with java or .NET than RocksDB or LevelDB is supercool. I hope this explanation will help you. Please have review my answer for better reach.

$\endgroup$
2
  • $\begingroup$ Can you point to some resources which use embeddings with RocksDB. Also I need it in Python. If some wrapper is available then it would be good $\endgroup$ – prms Jul 16 '20 at 11:08
  • $\begingroup$ U can refer it from here. python-rocksdb.readthedocs.io/en/latest $\endgroup$ – Gaurav Koradiya Jul 16 '20 at 11:10

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.