searchengines-web/MeiliSearch
searchengines-web/MeiliSearch
1
0
Fork 0
mirror of https://github.com/meilisearch/MeiliSearch synced 2025-07-04 04:17:10 +02:00
Code Issues Releases Wiki Activity

Expose an _semanticSimilarity as a dot product in the documents

Browse source
This commit is contained in:
Kerollmops 2023-06-20 14:38:58 +02:00 • committed by Clément Renault
parent 3e3c743392
commit 737aec1705
No known key found for this signature in database
GPG key ID: 92ADA4E935E71FA4
5 changed files with 39 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

1
meilisearch/Cargo.toml
View file

@ -48,6 +48,7 @@ mime = "0.3.17"
num_cpus = "1.15.0"
obkv = "0.2.0"
once_cell = "1.17.1"
ordered-float = "3.7.0"
parking_lot = "0.12.1"
permissive-json-pointer = { path = "../permissive-json-pointer" }
pin-project-lite = "0.2.9"

22
meilisearch/src/search.rs
View file

@ -10,6 +10,7 @@ use meilisearch_auth::IndexSearchRules;
use meilisearch_types::deserr::DeserrJsonError;
use meilisearch_types::error::deserr_codes::*;
use meilisearch_types::index_uid::IndexUid;
use meilisearch_types::milli::dot_product_similarity;
use meilisearch_types::milli::score_details::{ScoreDetails, ScoringStrategy};
use meilisearch_types::settings::DEFAULT_PAGINATION_MAX_TOTAL_HITS;
use meilisearch_types::{milli, Document};
@ -18,6 +19,7 @@ use milli::{
AscDesc, FieldId, FieldsIdsMap, Filter, FormatOptions, Index, MatchBounds, MatcherBuilder,
SortError, TermsMatchingStrategy, DEFAULT_VALUES_PER_FACET,
};
use ordered_float::OrderedFloat;
use regex::Regex;
use serde::Serialize;
use serde_json::{json, Value};
@ -457,6 +459,10 @@ pub fn perform_search(
insert_geo_distance(sort, &mut document);
}
if let Some(vector) = query.vector.as_ref() {
insert_semantic_similarity(&vector, &mut document);
}
let ranking_score =
query.show_ranking_score.then(|| ScoreDetails::global_score(score.iter()));
let ranking_score_details =
@ -542,6 +548,22 @@ fn insert_geo_distance(sorts: &[String], document: &mut Document) {
}
}
fn insert_semantic_similarity(query: &[f32], document: &mut Document) {
if let Some(value) = document.get("_vectors") {
let vectors: Vec<Vec<f32>> = match serde_json::from_value(value.clone()) {
Ok(Either::Left(vector)) => vec![vector],
Ok(Either::Right(vectors)) => vectors,
Err(_) => return,
};
let similarity = vectors
.into_iter()
.map(|v| OrderedFloat(dot_product_similarity(query, &v)))
.max()
.map(OrderedFloat::into_inner);
document.insert("_semanticSimilarity".to_string(), json!(similarity));
}
}
fn compute_formatted_options(
attr_to_highlight: &HashSet<String>,
attr_to_crop: &[String],