NLP Cloud is an advanced API for text understanding and generation in production. The most recent AI models are easy to use on NLP Cloud (GPT-NeoX 20B, GPT-J, Bart Large, among others). More than 20,000 developers and data scientists use NLP Cloud successfully in production because NLP Cloud takes care of the complex infrastructure challenges related to AI (GPU reliability, redundancy, high availability, scaling, etc.).
Initially, NLP Cloud did very naive analytics by logging every API call to their main PostgreSQL database. They knew this was just a temporary solution as long as the volume of API calls remained reasonably low. The team developed their auto-cleaning routines on PostgreSQL to remove some data. It was highly inefficient, and some read queries were lagging. They evaluated the TIF solution (Telegraf, InfluxDB, and Grafana) but found the complexity was not worth it.
Switching to Timescale was simple because of the PostgreSQL ecosystem. The NLP Cloud team was already skilled in SQL and PostgreSQL, saving them much time and energy. Thanks to the Timescale continuous aggregates, NLP Cloud can automatically downsample data, keep the high-level data forever and remove the rest.
Julien Salinas
,
CTO and founder of NLP Cloud