Michele Riva

A facility for distributing a search index for a corpus of documents is described. The facility accesses multiple search index segments collectively making up the search index. Each of the segments is executable to traverse an index subtree embedded in the segment to find in the index subtree a node representing a query term specified in an argument. Each of the segments corresponds to a particular indexed document field that is indexed by the search index.
For each of the segments, the… Show more

A facility for distributing a search index for a corpus of documents is described. The facility accesses multiple search index segments collectively making up the search index. Each of the segments is executable to traverse an index subtree embedded in the segment to find in the index subtree a node representing a query term specified in an argument. Each of the segments corresponds to a particular indexed document field that is indexed by the search index.
For each of the segments, the index subtree embedded the segment has nodes representing query terms that all produce a particular hash result. The facility calls a programmatic publication interface for a content delivery network to publish the plurality of search index segments on the content delivery network. Show less

An index shard data structure that is part of a search index is described. The data structure includes an executable routine that takes as an argument a semantic meaning representation of a query, embeds list of mappings from semantic meaning representations each of a different one of the documents of the corpus to a document ID identifying the document, traverses the list of mappings to select the document IDs mapped-to from semantic meaning representations that are within a threshold level of… Show more

An index shard data structure that is part of a search index is described. The data structure includes an executable routine that takes as an argument a semantic meaning representation of a query, embeds list of mappings from semantic meaning representations each of a different one of the documents of the corpus to a document ID identifying the document, traverses the list of mappings to select the document IDs mapped-to from semantic meaning representations that are within a threshold level of similarity to the semantic meaning representation of a query contained by the argument, and returns a list of the selected document identifiers, and such that a particular shard can be executed with respect to a distinguished query semantic meaning representation to obtain a list of document identifiers that identify documents of the corpus each having similar semantic meaning representations. Show less

A facility is described for automatically selecting document properties to be included in an index on a corpus of documents. In some cases, the facility performs this automatic selection by subjecting a list of the document properties for which the documents have contents to an inference model. In some cases, the facility conducts this automatic selection by submitting to a large language model a prompt automatically constructed to include, for each of one or more documents, the document's… Show more

A facility is described for automatically selecting document properties to be included in an index on a corpus of documents. In some cases, the facility performs this automatic selection by subjecting a list of the document properties for which the documents have contents to an inference model. In some cases, the facility conducts this automatic selection by submitting to a large language model a prompt automatically constructed to include, for each of one or more documents, the document's contents for each document property, in each case together with the document property's name. Show less