We need to collect feature vectors from elasticsearch as part of the machine learning pipeline. As a first step lets do the simplest thing possible, query elasticsearch directly. The firewall is open between analytics and the prod search clusters so this shouldn't be a problem. We will need to make this a bit more advanced with T162072 in the future when we want to talk to relforge.
|Invalid||None||T174064 [FY 2017-18 Objective] Implement advanced search methodologies|
|Resolved||EBernhardson||T161632 [Epic] Improve search by researching and deploying machine learning to re-rank search results|
|Resolved||EBernhardson||T162053 backend data engineering and plumbing for LTRank|
|Resolved||EBernhardson||T163407 Collect feature vectors from elasticsearch in mjolnir|