My Journey to a serverless transformers pipeline on Google Cloud

By huggingface - 2021-03-18

Description

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Summary

This article will discuss my journey to deploy the transformerssentiment-analysis pipeline on Google Cloud.
After that, I tried out the API that Hugging Face offers and read a bit more about the pipeline feature they offer.
The idea is to receive a GET request containing two fields.
You can find more details about it in the Google's guide - Before you begin, Second, we need to build the docker image and deploy it to cloud run by selecting the correct project (replace PROJECT-ID) and set the name of the instance such as ai-customer-review.

Topics

Backend (0.42)
NLP (0.08)
Machine_Learning (0.04)

Similar Articles

Machine Learning in Production. Using Google Cloud Functions (Part

By Medium - 2020-12-25

This is going to be the last article in this series where we will explore Google Cloud Functions as our third option of choice when deploying machine learning models. In the previous articles, we…

How to build a fraud detection solution

By Google Cloud Blog - 2021-03-03

In collaboration with our partner Quantiphi, we developed a smart analytics design pattern that enables you to build a scalable real-time fraud detection solution in one hour using serverless, no-ops ...