Ellery generated those datasets manually.
We hsould productionize them (or is it Nathaniel's job?).
https://github.com/ewulczyn/wiki-vectors
https://github.com/ewulczyn/wmf/blob/master/util/wikidata_utils.py
Ellery generated those datasets manually.
We hsould productionize them (or is it Nathaniel's job?).
https://github.com/ewulczyn/wiki-vectors
https://github.com/ewulczyn/wmf/blob/master/util/wikidata_utils.py
Status | Subtype | Assigned | Task | ||
---|---|---|---|---|---|
Resolved | • schana | T148129 Productization of Recommendation API | |||
Declined | None | T158973 productionize recommendation vectors |
@JAllemandou As I understand it, there is still some ongoing discussion about how/what parts of the Recommendation API to productionize. If it is decided that the Related Articles type should be included, then at that time I think this task will become a priority. Until then, it's something that would be nice to have, but is not critical.
@Fjalapeno I'm adding you to this thread, to keep an eye on it. As schana says above, there is no decision to productionize recommendation vectors atm, so this is fyi.
@Capt_Swing's recommendation based on https://meta.wikimedia.org/wiki/Research:Evaluating_RelatedArticles_recommendations#Results is for us not to productionize this service. I will leave this ticket open until we all get a chance to go over the results. We should consider declining this ticket in a week or so.
This task is related to productionizing related-article type and since we have declined that task (T159528), I'll go ahead and decline this as well. Feel free to open it when/if relevant.