snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2025-09-07 13:16:31 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into fix-threshold-overcounting-bug

Browse Source
This commit is contained in:
Mubelotix
2025-07-07 12:26:37 +02:00
parent 600178c5ab ef4c87accf
commit 70a860a0f0
141 changed files with 6398 additions and 1608 deletions
Download Patch File Download Diff File Expand all files Collapse all files

52
crates/milli/src/search/mod.rs
View File

@ -12,7 +12,7 @@ use self::new::{execute_vector_search, PartialSearchResult, VectorStoreStats};
use crate::filterable_attributes_rules::{filtered_matching_patterns, matching_features};
use crate::index::MatchingStrategy;
use crate::score_details::{ScoreDetails, ScoringStrategy};
use crate::vector::Embedder;
use crate::vector::{Embedder, Embedding};
use crate::{
execute_search, filtered_universe, AscDesc, DefaultSearchLogger, DocumentId, Error, Index,
Result, SearchContext, TimeBudget, UserError,
@ -32,6 +32,7 @@ pub mod similar;
#[derive(Debug, Clone)]
pub struct SemanticSearch {
vector: Option<Vec<f32>>,
media: Option<serde_json::Value>,
embedder_name: String,
embedder: Arc<Embedder>,
quantized: bool,
@ -95,9 +96,10 @@ impl<'a> Search<'a> {
embedder_name: String,
embedder: Arc<Embedder>,
quantized: bool,
vector: Option<Vec<f32>>,
vector: Option<Embedding>,
media: Option<serde_json::Value>,
) -> &mut Search<'a> {
self.semantic = Some(SemanticSearch { embedder_name, embedder, quantized, vector });
self.semantic = Some(SemanticSearch { embedder_name, embedder, quantized, vector, media });
self
}
@ -238,26 +240,30 @@ impl<'a> Search<'a> {
degraded,
used_negative_operator,
} = match self.semantic.as_ref() {
Some(SemanticSearch { vector: Some(vector), embedder_name, embedder, quantized }) => {
execute_vector_search(
&mut ctx,
vector,
self.scoring_strategy,
self.exhaustive_number_hits,
self.max_total_hits,
universe,
&self.sort_criteria,
&self.distinct,
self.geo_param,
self.offset,
self.limit,
embedder_name,
embedder,
*quantized,
self.time_budget.clone(),
self.ranking_score_threshold,
)?
}
Some(SemanticSearch {
vector: Some(vector),
embedder_name,
embedder,
quantized,
media: _,
}) => execute_vector_search(
&mut ctx,
vector,
self.scoring_strategy,
self.exhaustive_number_hits,
self.max_total_hits,
universe,
&self.sort_criteria,
&self.distinct,
self.geo_param,
self.offset,
self.limit,
embedder_name,
embedder,
*quantized,
self.time_budget.clone(),
self.ranking_score_threshold,
)?,
_ => execute_search(
&mut ctx,
self.query.as_deref(),