I am happy to know that Google has shared TF-Ranking, a scalable TensorFlow-based library for learning-to-rank. TensorFlow library was discussed in the past Google Cloud Event I attended and I was very satisfied with the functionalities described and the demos presented. It is a great tool!
TF-Ranking has been described in a recent paper, it provides a unified framework that includes a suite of state-of-the-art learning-to-rank algorithms, and supports pairwise or listwise loss functions, multi-item scoring, ranking metric optimization, and unbiased learning-to-rank.
You could know more details in the post published in the Google AI Blog.