snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2025-07-26 16:21:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge #4666

Browse Source 
4666: Add a score threshold search parameter r=ManyTheFish a=dureuill

# Pull Request

## Related issue
Fixes https://github.com/meilisearch/meilisearch/issues/4609

## What does this PR do?
- See [usage](https://meilisearch.notion.site/Filter-by-score-usage-224a183ce7b24ca99b6a9a8da755668a?pvs=25#95b76ded400342ba9ab3d67c734836f0) and [the known limitation](https://meilisearch.notion.site/Filter-by-score-usage-224a183ce7b24ca99b6a9a8da755668a?pvs=25#e4e32195bf0e4195b5daecdbb7a97a17)


Co-authored-by: Louis Dureuil <louis@meilisearch.com>
This commit is contained in:
meili-bors[bot]
2024-06-03 08:42:44 +00:00
committed by GitHub
parent d6bd88ce4f 2b6db6541e
commit fc584f1db3
18 changed files with 804 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
meilisearch/src/analytics/segment_analytics.rs
View File

@ -648,6 +648,7 @@ pub struct SearchAggregator {
// scoring
show_ranking_score: bool,
show_ranking_score_details: bool,
ranking_score_threshold: bool,
}
impl SearchAggregator {
@ -676,6 +677,7 @@ impl SearchAggregator {
matching_strategy,
attributes_to_search_on,
hybrid,
ranking_score_threshold,
} = query;
let mut ret = Self::default();
@ -748,6 +750,7 @@ impl SearchAggregator {
ret.show_ranking_score = *show_ranking_score;
ret.show_ranking_score_details = *show_ranking_score_details;
ret.ranking_score_threshold = ranking_score_threshold.is_some();
if let Some(hybrid) = hybrid {
ret.semantic_ratio = hybrid.semantic_ratio != DEFAULT_SEMANTIC_RATIO();
@ -821,6 +824,7 @@ impl SearchAggregator {
hybrid,
total_degraded,
total_used_negative_operator,
ranking_score_threshold,
} = other;
if self.timestamp.is_none() {
@ -904,6 +908,7 @@ impl SearchAggregator {
// scoring
self.show_ranking_score |= show_ranking_score;
self.show_ranking_score_details |= show_ranking_score_details;
self.ranking_score_threshold |= ranking_score_threshold;
}
pub fn into_event(self, user: &User, event_name: &str) -> Option<Track> {
@ -945,6 +950,7 @@ impl SearchAggregator {
hybrid,
total_degraded,
total_used_negative_operator,
ranking_score_threshold,
} = self;
if total_received == 0 {
@ -1015,6 +1021,7 @@ impl SearchAggregator {
"scoring": {
"show_ranking_score": show_ranking_score,
"show_ranking_score_details": show_ranking_score_details,
"ranking_score_threshold": ranking_score_threshold,
},
});
@ -1087,6 +1094,7 @@ impl MultiSearchAggregator {
matching_strategy: _,
attributes_to_search_on: _,
hybrid: _,
ranking_score_threshold: _,
} = query;
index_uid.as_str()
@ -1234,6 +1242,7 @@ impl FacetSearchAggregator {
matching_strategy,
attributes_to_search_on,
hybrid,
ranking_score_threshold,
} = query;
let mut ret = Self::default();
@ -1248,7 +1257,8 @@ impl FacetSearchAggregator {
|| filter.is_some()
|| *matching_strategy != MatchingStrategy::default()
|| attributes_to_search_on.is_some()
|| hybrid.is_some();
|| hybrid.is_some()
|| ranking_score_threshold.is_some();
ret
}
@ -1624,6 +1634,7 @@ pub struct SimilarAggregator {
// scoring
show_ranking_score: bool,
show_ranking_score_details: bool,
ranking_score_threshold: bool,
}
impl SimilarAggregator {
@ -1638,6 +1649,7 @@ impl SimilarAggregator {
show_ranking_score,
show_ranking_score_details,
filter,
ranking_score_threshold,
} = query;
let mut ret = Self::default();
@ -1675,6 +1687,7 @@ impl SimilarAggregator {
ret.show_ranking_score = *show_ranking_score;
ret.show_ranking_score_details = *show_ranking_score_details;
ret.ranking_score_threshold = ranking_score_threshold.is_some();
ret.embedder = embedder.is_some();
@ -1708,6 +1721,7 @@ impl SimilarAggregator {
show_ranking_score,
show_ranking_score_details,
embedder,
ranking_score_threshold,
} = other;
if self.timestamp.is_none() {
@ -1749,6 +1763,7 @@ impl SimilarAggregator {
// scoring
self.show_ranking_score |= show_ranking_score;
self.show_ranking_score_details |= show_ranking_score_details;
self.ranking_score_threshold |= ranking_score_threshold;
}
pub fn into_event(self, user: &User, event_name: &str) -> Option<Track> {
@ -1769,6 +1784,7 @@ impl SimilarAggregator {
show_ranking_score,
show_ranking_score_details,
embedder,
ranking_score_threshold,
} = self;
if total_received == 0 {
@ -1808,6 +1824,7 @@ impl SimilarAggregator {
"scoring": {
"show_ranking_score": show_ranking_score,
"show_ranking_score_details": show_ranking_score_details,
"ranking_score_threshold": ranking_score_threshold,
},
});

8
meilisearch/src/routes/indexes/facet_search.rs
View File

@ -14,8 +14,8 @@ use crate::extractors::authentication::policies::*;
use crate::extractors::authentication::GuardedData;
use crate::routes::indexes::search::search_kind;
use crate::search::{
add_search_rules, perform_facet_search, HybridQuery, MatchingStrategy, SearchQuery,
DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
add_search_rules, perform_facet_search, HybridQuery, MatchingStrategy, RankingScoreThreshold,
SearchQuery, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET,
};
use crate::search_queue::SearchQueue;
@ -46,6 +46,8 @@ pub struct FacetSearchQuery {
pub matching_strategy: MatchingStrategy,
#[deserr(default, error = DeserrJsonError<InvalidSearchAttributesToSearchOn>, default)]
pub attributes_to_search_on: Option<Vec<String>>,
#[deserr(default, error = DeserrJsonError<InvalidSearchRankingScoreThreshold>, default)]
pub ranking_score_threshold: Option<RankingScoreThreshold>,
}
pub async fn search(
@ -103,6 +105,7 @@ impl From<FacetSearchQuery> for SearchQuery {
matching_strategy,
attributes_to_search_on,
hybrid,
ranking_score_threshold,
} = value;
SearchQuery {
@ -128,6 +131,7 @@ impl From<FacetSearchQuery> for SearchQuery {
vector,
attributes_to_search_on,
hybrid,
ranking_score_threshold,
}
}
}

23
meilisearch/src/routes/indexes/search.rs
View File

@ -19,9 +19,10 @@ use crate::extractors::authentication::GuardedData;
use crate::extractors::sequential_extractor::SeqHandler;
use crate::metrics::MEILISEARCH_DEGRADED_SEARCH_REQUESTS;
use crate::search::{
add_search_rules, perform_search, HybridQuery, MatchingStrategy, SearchKind, SearchQuery,
SemanticRatio, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET, DEFAULT_SEMANTIC_RATIO,
add_search_rules, perform_search, HybridQuery, MatchingStrategy, RankingScoreThreshold,
SearchKind, SearchQuery, SemanticRatio, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER,
DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT,
DEFAULT_SEARCH_OFFSET, DEFAULT_SEMANTIC_RATIO,
};
use crate::search_queue::SearchQueue;
@ -82,6 +83,21 @@ pub struct SearchQueryGet {
pub hybrid_embedder: Option<String>,
#[deserr(default, error = DeserrQueryParamError<InvalidSearchSemanticRatio>)]
pub hybrid_semantic_ratio: Option<SemanticRatioGet>,
#[deserr(default, error = DeserrQueryParamError<InvalidSearchRankingScoreThreshold>)]
pub ranking_score_threshold: Option<RankingScoreThresholdGet>,
}
#[derive(Debug, Clone, Copy, PartialEq, deserr::Deserr)]
#[deserr(try_from(String) = TryFrom::try_from -> InvalidSearchRankingScoreThreshold)]
pub struct RankingScoreThresholdGet(RankingScoreThreshold);
impl std::convert::TryFrom<String> for RankingScoreThresholdGet {
type Error = InvalidSearchRankingScoreThreshold;
fn try_from(s: String) -> Result<Self, Self::Error> {
let f: f64 = s.parse().map_err(|_| InvalidSearchRankingScoreThreshold)?;
Ok(RankingScoreThresholdGet(RankingScoreThreshold::try_from(f)?))
}
}
#[derive(Debug, Clone, Copy, Default, PartialEq, deserr::Deserr)]
@ -152,6 +168,7 @@ impl From<SearchQueryGet> for SearchQuery {
matching_strategy: other.matching_strategy,
attributes_to_search_on: other.attributes_to_search_on.map(|o| o.into_iter().collect()),
hybrid,
ranking_score_threshold: other.ranking_score_threshold.map(|o| o.0),
}
}
}

35
meilisearch/src/routes/indexes/similar.rs
View File

@ -6,8 +6,8 @@ use meilisearch_types::deserr::query_params::Param;
use meilisearch_types::deserr::{DeserrJsonError, DeserrQueryParamError};
use meilisearch_types::error::deserr_codes::{
InvalidEmbedder, InvalidSimilarAttributesToRetrieve, InvalidSimilarFilter, InvalidSimilarId,
InvalidSimilarLimit, InvalidSimilarOffset, InvalidSimilarShowRankingScore,
InvalidSimilarShowRankingScoreDetails,
InvalidSimilarLimit, InvalidSimilarOffset, InvalidSimilarRankingScoreThreshold,
InvalidSimilarShowRankingScore, InvalidSimilarShowRankingScoreDetails,
};
use meilisearch_types::error::{ErrorCode as _, ResponseError};
use meilisearch_types::index_uid::IndexUid;
@ -21,8 +21,8 @@ use crate::analytics::{Analytics, SimilarAggregator};
use crate::extractors::authentication::GuardedData;
use crate::extractors::sequential_extractor::SeqHandler;
use crate::search::{
add_search_rules, perform_similar, SearchKind, SimilarQuery, SimilarResult,
DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET,
add_search_rules, perform_similar, RankingScoreThresholdSimilar, SearchKind, SimilarQuery,
SimilarResult, DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET,
};
pub fn configure(cfg: &mut web::ServiceConfig) {
@ -42,9 +42,7 @@ pub async fn similar_get(
) -> Result<HttpResponse, ResponseError> {
let index_uid = IndexUid::try_from(index_uid.into_inner())?;
let query = params.0.try_into().map_err(|code: InvalidSimilarId| {
ResponseError::from_msg(code.to_string(), code.error_code())
})?;
let query = params.0.try_into()?;
let mut aggregate = SimilarAggregator::from_query(&query, &req);
@ -130,12 +128,27 @@ pub struct SimilarQueryGet {
show_ranking_score: Param<bool>,
#[deserr(default, error = DeserrQueryParamError<InvalidSimilarShowRankingScoreDetails>)]
show_ranking_score_details: Param<bool>,
#[deserr(default, error = DeserrQueryParamError<InvalidSimilarRankingScoreThreshold>, default)]
pub ranking_score_threshold: Option<RankingScoreThresholdGet>,
#[deserr(default, error = DeserrQueryParamError<InvalidEmbedder>)]
pub embedder: Option<String>,
}
#[derive(Debug, Clone, Copy, PartialEq, deserr::Deserr)]
#[deserr(try_from(String) = TryFrom::try_from -> InvalidSimilarRankingScoreThreshold)]
pub struct RankingScoreThresholdGet(RankingScoreThresholdSimilar);
impl std::convert::TryFrom<String> for RankingScoreThresholdGet {
type Error = InvalidSimilarRankingScoreThreshold;
fn try_from(s: String) -> Result<Self, Self::Error> {
let f: f64 = s.parse().map_err(|_| InvalidSimilarRankingScoreThreshold)?;
Ok(RankingScoreThresholdGet(RankingScoreThresholdSimilar::try_from(f)?))
}
}
impl TryFrom<SimilarQueryGet> for SimilarQuery {
type Error = InvalidSimilarId;
type Error = ResponseError;
fn try_from(
SimilarQueryGet {
@ -147,6 +160,7 @@ impl TryFrom<SimilarQueryGet> for SimilarQuery {
show_ranking_score,
show_ranking_score_details,
embedder,
ranking_score_threshold,
}: SimilarQueryGet,
) -> Result<Self, Self::Error> {
let filter = match filter {
@ -158,7 +172,9 @@ impl TryFrom<SimilarQueryGet> for SimilarQuery {
};
Ok(SimilarQuery {
id: id.0.try_into()?,
id: id.0.try_into().map_err(|code: InvalidSimilarId| {
ResponseError::from_msg(code.to_string(), code.error_code())
})?,
offset: offset.0,
limit: limit.0,
filter,
@ -166,6 +182,7 @@ impl TryFrom<SimilarQueryGet> for SimilarQuery {
attributes_to_retrieve: attributes_to_retrieve.map(|o| o.into_iter().collect()),
show_ranking_score: show_ranking_score.0,
show_ranking_score_details: show_ranking_score_details.0,
ranking_score_threshold: ranking_score_threshold.map(|x| x.0),
})
}
}

82
meilisearch/src/search.rs
View File

@ -87,6 +87,44 @@ pub struct SearchQuery {
pub matching_strategy: MatchingStrategy,
#[deserr(default, error = DeserrJsonError<InvalidSearchAttributesToSearchOn>, default)]
pub attributes_to_search_on: Option<Vec<String>>,
#[deserr(default, error = DeserrJsonError<InvalidSearchRankingScoreThreshold>, default)]
pub ranking_score_threshold: Option<RankingScoreThreshold>,
}
#[derive(Debug, Clone, Copy, PartialEq, Deserr)]
#[deserr(try_from(f64) = TryFrom::try_from -> InvalidSearchRankingScoreThreshold)]
pub struct RankingScoreThreshold(f64);
impl std::convert::TryFrom<f64> for RankingScoreThreshold {
type Error = InvalidSearchRankingScoreThreshold;
fn try_from(f: f64) -> Result<Self, Self::Error> {
// the suggested "fix" is: `!(0.0..=1.0).contains(&f)`` which is allegedly less readable
#[allow(clippy::manual_range_contains)]
if f > 1.0 || f < 0.0 {
Err(InvalidSearchRankingScoreThreshold)
} else {
Ok(RankingScoreThreshold(f))
}
}
}
#[derive(Debug, Clone, Copy, PartialEq, Deserr)]
#[deserr(try_from(f64) = TryFrom::try_from -> InvalidSimilarRankingScoreThreshold)]
pub struct RankingScoreThresholdSimilar(f64);
impl std::convert::TryFrom<f64> for RankingScoreThresholdSimilar {
type Error = InvalidSimilarRankingScoreThreshold;
fn try_from(f: f64) -> Result<Self, Self::Error> {
// the suggested "fix" is: `!(0.0..=1.0).contains(&f)`` which is allegedly less readable
#[allow(clippy::manual_range_contains)]
if f > 1.0 || f < 0.0 {
Err(InvalidSimilarRankingScoreThreshold)
} else {
Ok(Self(f))
}
}
}
// Since this structure is logged A LOT we're going to reduce the number of things it logs to the bare minimum.
@ -117,6 +155,7 @@ impl fmt::Debug for SearchQuery {
crop_marker,
matching_strategy,
attributes_to_search_on,
ranking_score_threshold,
} = self;
let mut debug = f.debug_struct("SearchQuery");
@ -188,6 +227,9 @@ impl fmt::Debug for SearchQuery {
debug.field("highlight_pre_tag", &highlight_pre_tag);
debug.field("highlight_post_tag", &highlight_post_tag);
debug.field("crop_marker", &crop_marker);
if let Some(ranking_score_threshold) = ranking_score_threshold {
debug.field("ranking_score_threshold", &ranking_score_threshold);
}
debug.finish()
}
@ -356,6 +398,8 @@ pub struct SearchQueryWithIndex {
pub matching_strategy: MatchingStrategy,
#[deserr(default, error = DeserrJsonError<InvalidSearchAttributesToSearchOn>, default)]
pub attributes_to_search_on: Option<Vec<String>>,
#[deserr(default, error = DeserrJsonError<InvalidSearchRankingScoreThreshold>, default)]
pub ranking_score_threshold: Option<RankingScoreThreshold>,
}
impl SearchQueryWithIndex {
@ -384,6 +428,7 @@ impl SearchQueryWithIndex {
matching_strategy,
attributes_to_search_on,
hybrid,
ranking_score_threshold,
} = self;
(
index_uid,
@ -410,6 +455,7 @@ impl SearchQueryWithIndex {
matching_strategy,
attributes_to_search_on,
hybrid,
ranking_score_threshold,
// do not use ..Default::default() here,
// rather add any missing field from `SearchQuery` to `SearchQueryWithIndex`
},
@ -436,6 +482,8 @@ pub struct SimilarQuery {
pub show_ranking_score: bool,
#[deserr(default, error = DeserrJsonError<InvalidSimilarShowRankingScoreDetails>, default)]
pub show_ranking_score_details: bool,
#[deserr(default, error = DeserrJsonError<InvalidSimilarRankingScoreThreshold>, default)]
pub ranking_score_threshold: Option<RankingScoreThresholdSimilar>,
}
#[derive(Debug, Clone, PartialEq, Deserr)]
@ -664,6 +712,9 @@ fn prepare_search<'t>(
) -> Result<(milli::Search<'t>, bool, usize, usize), MeilisearchHttpError> {
let mut search = index.search(rtxn);
search.time_budget(time_budget);
if let Some(ranking_score_threshold) = query.ranking_score_threshold {
search.ranking_score_threshold(ranking_score_threshold.0);
}
match search_kind {
SearchKind::KeywordOnly => {
@ -705,11 +756,16 @@ fn prepare_search<'t>(
.unwrap_or(DEFAULT_PAGINATION_MAX_TOTAL_HITS);
search.exhaustive_number_hits(is_finite_pagination);
search.scoring_strategy(if query.show_ranking_score || query.show_ranking_score_details {
ScoringStrategy::Detailed
} else {
ScoringStrategy::Skip
});
search.scoring_strategy(
if query.show_ranking_score
|| query.show_ranking_score_details
|| query.ranking_score_threshold.is_some()
{
ScoringStrategy::Detailed
} else {
ScoringStrategy::Skip
},
);
// compute the offset on the limit depending on the pagination mode.
let (offset, limit) = if is_finite_pagination {
@ -787,10 +843,6 @@ pub fn perform_search(
let SearchQuery {
q,
vector: _,
hybrid: _,
// already computed from prepare_search
offset: _,
limit,
page,
hits_per_page,
@ -801,14 +853,19 @@ pub fn perform_search(
show_matches_position,
show_ranking_score,
show_ranking_score_details,
filter: _,
sort,
facets,
highlight_pre_tag,
highlight_post_tag,
crop_marker,
// already used in prepare_search
vector: _,
hybrid: _,
offset: _,
ranking_score_threshold: _,
matching_strategy: _,
attributes_to_search_on: _,
filter: _,
} = query;
let format = AttributesFormat {
@ -1070,6 +1127,7 @@ pub fn perform_similar(
attributes_to_retrieve,
show_ranking_score,
show_ranking_score_details,
ranking_score_threshold,
} = query;
// using let-else rather than `?` so that the borrow checker identifies we're always returning here,
@ -1093,6 +1151,10 @@ pub fn perform_similar(
}
}
if let Some(ranking_score_threshold) = ranking_score_threshold {
similar.ranking_score_threshold(ranking_score_threshold.0);
}
let milli::SearchResult {
documents_ids,
matching_words: _,

34
meilisearch/tests/search/errors.rs
View File

@ -321,6 +321,40 @@ async fn search_bad_facets() {
// Can't make the `attributes_to_highlight` fail with a get search since it'll accept anything as an array of strings.
}
#[actix_rt::test]
async fn search_bad_threshold() {
let server = Server::new().await;
let index = server.index("test");
let (response, code) = index.search_post(json!({"rankingScoreThreshold": "doggo"})).await;
snapshot!(code, @"400 Bad Request");
snapshot!(json_string!(response), @r###"
{
"message": "Invalid value type at `.rankingScoreThreshold`: expected a number, but found a string: `\"doggo\"`",
"code": "invalid_search_ranking_score_threshold",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#invalid_search_ranking_score_threshold"
}
"###);
}
#[actix_rt::test]
async fn search_invalid_threshold() {
let server = Server::new().await;
let index = server.index("test");
let (response, code) = index.search_post(json!({"rankingScoreThreshold": 42})).await;
snapshot!(code, @"400 Bad Request");
snapshot!(json_string!(response), @r###"
{
"message": "Invalid value at `.rankingScoreThreshold`: the value of `rankingScoreThreshold` is invalid, expected a float between `0.0` and `1.0`.",
"code": "invalid_search_ranking_score_threshold",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#invalid_search_ranking_score_threshold"
}
"###);
}
#[actix_rt::test]
async fn search_non_filterable_facets() {
let server = Server::new().await;

232
meilisearch/tests/search/mod.rs
View File

@ -48,6 +48,31 @@ static DOCUMENTS: Lazy<Value> = Lazy::new(|| {
])
});
static SCORE_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
json!([
{
"title": "Batman the dark knight returns: Part 1",
"id": "A",
},
{
"title": "Batman the dark knight returns: Part 2",
"id": "B",
},
{
"title": "Batman Returns",
"id": "C",
},
{
"title": "Batman",
"id": "D",
},
{
"title": "Badman",
"id": "E",
}
])
});
static NESTED_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
json!([
{
@ -960,6 +985,213 @@ async fn test_score_details() {
.await;
}
#[actix_rt::test]
async fn test_score() {
let server = Server::new().await;
let index = server.index("test");
let documents = SCORE_DOCUMENTS.clone();
let res = index.add_documents(json!(documents), None).await;
index.wait_task(res.0.uid()).await;
index
.search(
json!({
"q": "Badman the dark knight returns 1",
"showRankingScore": true,
}),
|response, code| {
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
[
{
"title": "Batman the dark knight returns: Part 1",
"id": "A",
"_rankingScore": 0.9746605609456898
},
{
"title": "Batman the dark knight returns: Part 2",
"id": "B",
"_rankingScore": 0.8055252965383685
},
{
"title": "Badman",
"id": "E",
"_rankingScore": 0.16666666666666666
},
{
"title": "Batman Returns",
"id": "C",
"_rankingScore": 0.07702020202020202
},
{
"title": "Batman",
"id": "D",
"_rankingScore": 0.07702020202020202
}
]
"###);
},
)
.await;
}
#[actix_rt::test]
async fn test_score_threshold() {
let query = "Badman dark returns 1";
let server = Server::new().await;
let index = server.index("test");
let documents = SCORE_DOCUMENTS.clone();
let res = index.add_documents(json!(documents), None).await;
index.wait_task(res.0.uid()).await;
index
.search(
json!({
"q": query,
"showRankingScore": true,
"rankingScoreThreshold": 0.0
}),
|response, code| {
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @"5");
meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
[
{
"title": "Batman the dark knight returns: Part 1",
"id": "A",
"_rankingScore": 0.93430081300813
},
{
"title": "Batman the dark knight returns: Part 2",
"id": "B",
"_rankingScore": 0.6685627880184332
},
{
"title": "Badman",
"id": "E",
"_rankingScore": 0.25
},
{
"title": "Batman Returns",
"id": "C",
"_rankingScore": 0.11553030303030302
},
{
"title": "Batman",
"id": "D",
"_rankingScore": 0.11553030303030302
}
]
"###);
},
)
.await;
index
.search(
json!({
"q": query,
"showRankingScore": true,
"rankingScoreThreshold": 0.2
}),
|response, code| {
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @r###"3"###);
meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
[
{
"title": "Batman the dark knight returns: Part 1",
"id": "A",
"_rankingScore": 0.93430081300813
},
{
"title": "Batman the dark knight returns: Part 2",
"id": "B",
"_rankingScore": 0.6685627880184332
},
{
"title": "Badman",
"id": "E",
"_rankingScore": 0.25
}
]
"###);
},
)
.await;
index
.search(
json!({
"q": query,
"showRankingScore": true,
"rankingScoreThreshold": 0.5
}),
|response, code| {
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @r###"2"###);
meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
[
{
"title": "Batman the dark knight returns: Part 1",
"id": "A",
"_rankingScore": 0.93430081300813
},
{
"title": "Batman the dark knight returns: Part 2",
"id": "B",
"_rankingScore": 0.6685627880184332
}
]
"###);
},
)
.await;
index
.search(
json!({
"q": query,
"showRankingScore": true,
"rankingScoreThreshold": 0.8
}),
|response, code| {
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @r###"1"###);
meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @r###"
[
{
"title": "Batman the dark knight returns: Part 1",
"id": "A",
"_rankingScore": 0.93430081300813
}
]
"###);
},
)
.await;
index
.search(
json!({
"q": query,
"showRankingScore": true,
"rankingScoreThreshold": 1.0
}),
|response, code| {
meili_snap::snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @r###"0"###);
// nobody is perfect
meili_snap::snapshot!(meili_snap::json_string!(response["hits"]), @"[]");
},
)
.await;
}
#[actix_rt::test]
async fn test_degraded_score_details() {
let server = Server::new().await;

62
meilisearch/tests/similar/errors.rs
View File

@ -87,6 +87,68 @@ async fn similar_bad_id() {
"###);
}
#[actix_rt::test]
async fn similar_bad_ranking_score_threshold() {
let server = Server::new().await;
let index = server.index("test");
server.set_features(json!({"vectorStore": true})).await;
let (response, code) = index
.update_settings(json!({
"embedders": {
"manual": {
"source": "userProvided",
"dimensions": 3,
}
},
"filterableAttributes": ["title"]}))
.await;
snapshot!(code, @"202 Accepted");
server.wait_task(response.uid()).await;
let (response, code) = index.similar_post(json!({"rankingScoreThreshold": ["doggo"]})).await;
snapshot!(code, @"400 Bad Request");
snapshot!(json_string!(response), @r###"
{
"message": "Invalid value type at `.rankingScoreThreshold`: expected a number, but found an array: `[\"doggo\"]`",
"code": "invalid_similar_ranking_score_threshold",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#invalid_similar_ranking_score_threshold"
}
"###);
}
#[actix_rt::test]
async fn similar_invalid_ranking_score_threshold() {
let server = Server::new().await;
let index = server.index("test");
server.set_features(json!({"vectorStore": true})).await;
let (response, code) = index
.update_settings(json!({
"embedders": {
"manual": {
"source": "userProvided",
"dimensions": 3,
}
},
"filterableAttributes": ["title"]}))
.await;
snapshot!(code, @"202 Accepted");
server.wait_task(response.uid()).await;
let (response, code) = index.similar_post(json!({"rankingScoreThreshold": 42})).await;
snapshot!(code, @"400 Bad Request");
snapshot!(json_string!(response), @r###"
{
"message": "Invalid value at `.rankingScoreThreshold`: the value of `rankingScoreThreshold` is invalid, expected a float between `0.0` and `1.0`.",
"code": "invalid_similar_ranking_score_threshold",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#invalid_similar_ranking_score_threshold"
}
"###);
}
#[actix_rt::test]
async fn similar_invalid_id() {
let server = Server::new().await;

229
meilisearch/tests/similar/mod.rs
View File

@ -194,6 +194,235 @@ async fn basic() {
.await;
}
#[actix_rt::test]
async fn ranking_score_threshold() {
let server = Server::new().await;
let index = server.index("test");
let (value, code) = server.set_features(json!({"vectorStore": true})).await;
snapshot!(code, @"200 OK");
snapshot!(value, @r###"
{
"vectorStore": true,
"metrics": false,
"logsRoute": false
}
"###);
let (response, code) = index
.update_settings(json!({
"embedders": {
"manual": {
"source": "userProvided",
"dimensions": 3,
}
},
"filterableAttributes": ["title"]}))
.await;
snapshot!(code, @"202 Accepted");
server.wait_task(response.uid()).await;
let documents = DOCUMENTS.clone();
let (value, code) = index.add_documents(documents, None).await;
snapshot!(code, @"202 Accepted");
index.wait_task(value.uid()).await;
index
.similar(
json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0}),
|response, code| {
snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @"4");
snapshot!(json_string!(response["hits"]), @r###"
[
{
"title": "Escape Room",
"release_year": 2019,
"id": "522681",
"_vectors": {
"manual": [
0.1,
0.6,
0.8
]
},
"_rankingScore": 0.890957772731781
},
{
"title": "Captain Marvel",
"release_year": 2019,
"id": "299537",
"_vectors": {
"manual": [
0.6,
0.8,
-0.2
]
},
"_rankingScore": 0.39060014486312866
},
{
"title": "How to Train Your Dragon: The Hidden World",
"release_year": 2019,
"id": "166428",
"_vectors": {
"manual": [
0.7,
0.7,
-0.4
]
},
"_rankingScore": 0.2819308042526245
},
{
"title": "Shazam!",
"release_year": 2019,
"id": "287947",
"_vectors": {
"manual": [
0.8,
0.4,
-0.5
]
},
"_rankingScore": 0.1662663221359253
}
]
"###);
},
)
.await;
index
.similar(
json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0.2}),
|response, code| {
snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @"3");
snapshot!(json_string!(response["hits"]), @r###"
[
{
"title": "Escape Room",
"release_year": 2019,
"id": "522681",
"_vectors": {
"manual": [
0.1,
0.6,
0.8
]
},
"_rankingScore": 0.890957772731781
},
{
"title": "Captain Marvel",
"release_year": 2019,
"id": "299537",
"_vectors": {
"manual": [
0.6,
0.8,
-0.2
]
},
"_rankingScore": 0.39060014486312866
},
{
"title": "How to Train Your Dragon: The Hidden World",
"release_year": 2019,
"id": "166428",
"_vectors": {
"manual": [
0.7,
0.7,
-0.4
]
},
"_rankingScore": 0.2819308042526245
}
]
"###);
},
)
.await;
index
.similar(
json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0.3}),
|response, code| {
snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @"2");
snapshot!(json_string!(response["hits"]), @r###"
[
{
"title": "Escape Room",
"release_year": 2019,
"id": "522681",
"_vectors": {
"manual": [
0.1,
0.6,
0.8
]
},
"_rankingScore": 0.890957772731781
},
{
"title": "Captain Marvel",
"release_year": 2019,
"id": "299537",
"_vectors": {
"manual": [
0.6,
0.8,
-0.2
]
},
"_rankingScore": 0.39060014486312866
}
]
"###);
},
)
.await;
index
.similar(
json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0.6}),
|response, code| {
snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @"1");
snapshot!(json_string!(response["hits"]), @r###"
[
{
"title": "Escape Room",
"release_year": 2019,
"id": "522681",
"_vectors": {
"manual": [
0.1,
0.6,
0.8
]
},
"_rankingScore": 0.890957772731781
}
]
"###);
},
)
.await;
index
.similar(
json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0.9}),
|response, code| {
snapshot!(code, @"200 OK");
snapshot!(json_string!(response["hits"]), @"[]");
},
)
.await;
}
#[actix_rt::test]
async fn filter() {
let server = Server::new().await;