Techniques for retrieving and presenting content items using a fuzzy cache are presented herein. A computing
system can include a fuzzy cache having a plurality of cluster identifiers. Each cluster identifier in the plurality of cluster identifiers can have a result associated with a previously executed request. Additionally, the computing
system can include a first
machine-learned model configured to generate a vector embedding, and a second
machine-learned model configured to generate a cluster identifier. Moreover, the
system can receive, from a
user device, a first request having a first feature. Furthermore, the system can process, using the first
machine-learned model, the request to generate a first vector embedding associated with the first request. Subsequently, the system can process, using the second machine-learned model, the first vector embedding to determine a first cluster identifier. The system can retrieve, from the fuzzy cache, a first result on the first cluster identifier.