searchengines-web/MeiliSearch
searchengines-web/MeiliSearch
1
0
Fork 0
mirror of https://github.com/meilisearch/MeiliSearch synced 2025-07-04 12:27:13 +02:00
Code Issues Releases Wiki Activity

Merge #5187

Browse source 
5187: Bring back v1.12.0 of pre-release changes into `main` r=irevoire a=curquiza



Co-authored-by: ManyTheFish <many@meilisearch.com>
Co-authored-by: Louis Dureuil <louis@meilisearch.com>
Co-authored-by: Clément Renault <clement@meilisearch.com>
Co-authored-by: meili-bors[bot] <89034592+meili-bors[bot]@users.noreply.github.com>
Co-authored-by: Many the fish <many@meilisearch.com>
This commit is contained in:
meili-bors[bot] 2024-12-23 10:59:33 +00:00 • committed by GitHub
commit d3491851bc
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
168 changed files with 5778 additions and 2556 deletions
Download patch file Download diff file Expand all files Collapse all files

62
crates/meilisearch/src/search/mod.rs
View file

@ -19,7 +19,9 @@ use meilisearch_types::locales::Locale;
use meilisearch_types::milli::score_details::{ScoreDetails, ScoringStrategy};
use meilisearch_types::milli::vector::parsed_vectors::ExplicitVectors;
use meilisearch_types::milli::vector::Embedder;
use meilisearch_types::milli::{FacetValueHit, OrderBy, SearchForFacetValues, TimeBudget};
use meilisearch_types::milli::{
FacetValueHit, InternalError, OrderBy, SearchForFacetValues, TimeBudget,
};
use meilisearch_types::settings::DEFAULT_PAGINATION_MAX_TOTAL_HITS;
use meilisearch_types::{milli, Document};
use milli::tokenizer::{Language, TokenizerBuilder};
@ -283,35 +285,38 @@ pub enum SearchKind {
impl SearchKind {
pub(crate) fn semantic(
index_scheduler: &index_scheduler::IndexScheduler,
index_uid: String,
index: &Index,
embedder_name: &str,
vector_len: Option<usize>,
) -> Result<Self, ResponseError> {
let (embedder_name, embedder, quantized) =
Self::embedder(index_scheduler, index, embedder_name, vector_len)?;
Self::embedder(index_scheduler, index_uid, index, embedder_name, vector_len)?;
Ok(Self::SemanticOnly { embedder_name, embedder, quantized })
}
pub(crate) fn hybrid(
index_scheduler: &index_scheduler::IndexScheduler,
index_uid: String,
index: &Index,
embedder_name: &str,
semantic_ratio: f32,
vector_len: Option<usize>,
) -> Result<Self, ResponseError> {
let (embedder_name, embedder, quantized) =
Self::embedder(index_scheduler, index, embedder_name, vector_len)?;
Self::embedder(index_scheduler, index_uid, index, embedder_name, vector_len)?;
Ok(Self::Hybrid { embedder_name, embedder, quantized, semantic_ratio })
}
pub(crate) fn embedder(
index_scheduler: &index_scheduler::IndexScheduler,
index_uid: String,
index: &Index,
embedder_name: &str,
vector_len: Option<usize>,
) -> Result<(String, Arc<Embedder>, bool), ResponseError> {
let embedder_configs = index.embedding_configs(&index.read_txn()?)?;
let embedders = index_scheduler.embedders(embedder_configs)?;
let embedders = index_scheduler.embedders(index_uid, embedder_configs)?;
let (embedder, _, quantized) = embedders
.get(embedder_name)
@ -892,6 +897,7 @@ fn prepare_search<'t>(
}
pub fn perform_search(
index_uid: String,
index: &Index,
query: SearchQuery,
search_kind: SearchKind,
@ -918,7 +924,7 @@ pub fn perform_search(
used_negative_operator,
},
semantic_hit_count,
) = search_from_kind(search_kind, search)?;
) = search_from_kind(index_uid, search_kind, search)?;
let SearchQuery {
q,
@ -1071,17 +1077,27 @@ fn compute_facet_distribution_stats<S: AsRef<str>>(
}
pub fn search_from_kind(
index_uid: String,
search_kind: SearchKind,
search: milli::Search<'_>,
) -> Result<(milli::SearchResult, Option<u32>), MeilisearchHttpError> {
let (milli_result, semantic_hit_count) = match &search_kind {
SearchKind::KeywordOnly => (search.execute()?, None),
SearchKind::KeywordOnly => {
let results = search
.execute()
.map_err(|e| MeilisearchHttpError::from_milli(e, Some(index_uid.to_string())))?;
(results, None)
}
SearchKind::SemanticOnly { .. } => {
let results = search.execute()?;
let results = search
.execute()
.map_err(|e| MeilisearchHttpError::from_milli(e, Some(index_uid.to_string())))?;
let semantic_hit_count = results.document_scores.len() as u32;
(results, Some(semantic_hit_count))
}
SearchKind::Hybrid { semantic_ratio, .. } => search.execute_hybrid(*semantic_ratio)?,
SearchKind::Hybrid { semantic_ratio, .. } => search
.execute_hybrid(*semantic_ratio)
.map_err(|e| MeilisearchHttpError::from_milli(e, Some(index_uid)))?,
};
Ok((milli_result, semantic_hit_count))
}
@ -1183,7 +1199,7 @@ impl<'a> HitMaker<'a> {
rtxn: &'a RoTxn<'a>,
format: AttributesFormat,
mut formatter_builder: MatcherBuilder<'a>,
) -> Result<Self, MeilisearchHttpError> {
) -> milli::Result<Self> {
formatter_builder.crop_marker(format.crop_marker);
formatter_builder.highlight_prefix(format.highlight_pre_tag);
formatter_builder.highlight_suffix(format.highlight_post_tag);
@ -1278,11 +1294,7 @@ impl<'a> HitMaker<'a> {
})
}
pub fn make_hit(
&self,
id: u32,
score: &[ScoreDetails],
) -> Result<SearchHit, MeilisearchHttpError> {
pub fn make_hit(&self, id: u32, score: &[ScoreDetails]) -> milli::Result<SearchHit> {
let (_, obkv) =
self.index.iter_documents(self.rtxn, std::iter::once(id))?.next().unwrap()?;
@ -1325,7 +1337,10 @@ impl<'a> HitMaker<'a> {
.is_some_and(|conf| conf.user_provided.contains(id));
let embeddings =
ExplicitVectors { embeddings: Some(vector.into()), regenerate: !user_provided };
vectors.insert(name, serde_json::to_value(embeddings)?);
vectors.insert(
name,
serde_json::to_value(embeddings).map_err(InternalError::SerdeJson)?,
);
}
document.insert("_vectors".into(), vectors.into());
}
@ -1371,7 +1386,7 @@ fn make_hits<'a>(
format: AttributesFormat,
matching_words: milli::MatchingWords,
documents_ids_scores: impl Iterator<Item = (u32, &'a Vec<ScoreDetails>)> + 'a,
) -> Result<Vec<SearchHit>, MeilisearchHttpError> {
) -> milli::Result<Vec<SearchHit>> {
let mut documents = Vec::new();
let dictionary = index.dictionary(rtxn)?;
@ -1409,6 +1424,13 @@ pub fn perform_facet_search(
None => TimeBudget::default(),
};
if !index.facet_search(&rtxn)? {
return Err(ResponseError::from_msg(
"The facet search is disabled for this index".to_string(),
Code::FacetSearchDisabled,
));
}
// In the faceted search context, we want to use the intersection between the locales provided by the user
// and the locales of the facet string.
// If the facet string is not localized, we **ignore** the locales provided by the user because the facet data has no locale.
@ -1692,12 +1714,12 @@ fn make_document(
displayed_attributes: &BTreeSet<FieldId>,
field_ids_map: &FieldsIdsMap,
obkv: &obkv::KvReaderU16,
) -> Result<Document, MeilisearchHttpError> {
) -> milli::Result<Document> {
let mut document = serde_json::Map::new();
// recreate the original json
for (key, value) in obkv.iter() {
let value = serde_json::from_slice(value)?;
let value = serde_json::from_slice(value).map_err(InternalError::SerdeJson)?;
let key = field_ids_map.name(key).expect("Missing field name").to_string();
document.insert(key, value);
@ -1722,7 +1744,7 @@ fn format_fields(
displayable_ids: &BTreeSet<FieldId>,
locales: Option<&[Language]>,
localized_attributes: &[LocalizedAttributesRule],
) -> Result<(Option<MatchesPosition>, Document), MeilisearchHttpError> {
) -> milli::Result<(Option<MatchesPosition>, Document)> {
let mut matches_position = compute_matches.then(BTreeMap::new);
let mut document = document.clone();
@ -1900,5 +1922,5 @@ fn parse_filter_array(arr: &[Value]) -> Result<Option<Filter>, MeilisearchHttpEr
}
}
Ok(Filter::from_array(ands)?)
Filter::from_array(ands).map_err(|e| MeilisearchHttpError::from_milli(e, None))
}