snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2025-09-18 10:46:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

Lazily embed, don't fail hybrid search on embedding failure

Browse Source
This commit is contained in:
Louis Dureuil
2024-03-28 11:50:53 +01:00
parent fabc9cf14a
commit 6ebb6b55a6
11 changed files with 237 additions and 203 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
milli/src/search/new/mod.rs
View File

@ -52,7 +52,7 @@ use self::vector_sort::VectorSort;
use crate::error::FieldIdMapMissingEntry;
use crate::score_details::{ScoreDetails, ScoringStrategy};
use crate::search::new::distinct::apply_distinct_rule;
use crate::vector::DistributionShift;
use crate::vector::Embedder;
use crate::{
AscDesc, DocumentId, FieldId, Filter, Index, Member, Result, TermsMatchingStrategy, TimeBudget,
UserError,
@ -298,8 +298,8 @@ fn get_ranking_rules_for_vector<'ctx>(
geo_strategy: geo_sort::Strategy,
limit_plus_offset: usize,
target: &[f32],
distribution_shift: Option<DistributionShift>,
embedder_name: &str,
embedder: &Embedder,
) -> Result<Vec<BoxRankingRule<'ctx, PlaceholderQuery>>> {
// query graph search
@ -325,8 +325,8 @@ fn get_ranking_rules_for_vector<'ctx>(
target.to_vec(),
vector_candidates,
limit_plus_offset,
distribution_shift,
embedder_name,
embedder,
)?;
ranking_rules.push(Box::new(vector_sort));
vector = true;
@ -548,8 +548,8 @@ pub fn execute_vector_search(
geo_strategy: geo_sort::Strategy,
from: usize,
length: usize,
distribution_shift: Option<DistributionShift>,
embedder_name: &str,
embedder: &Embedder,
time_budget: TimeBudget,
) -> Result<PartialSearchResult> {
check_sort_criteria(ctx, sort_criteria.as_ref())?;
@ -562,8 +562,8 @@ pub fn execute_vector_search(
geo_strategy,
from + length,
vector,
distribution_shift,
embedder_name,
embedder,
)?;
let mut placeholder_search_logger = logger::DefaultSearchLogger;

6
milli/src/search/new/vector_sort.rs
View File

@ -5,7 +5,7 @@ use roaring::RoaringBitmap;
use super::ranking_rules::{RankingRule, RankingRuleOutput, RankingRuleQueryTrait};
use crate::score_details::{self, ScoreDetails};
use crate::vector::DistributionShift;
use crate::vector::{DistributionShift, Embedder};
use crate::{DocumentId, Result, SearchContext, SearchLogger};
pub struct VectorSort<Q: RankingRuleQueryTrait> {
@ -24,8 +24,8 @@ impl<Q: RankingRuleQueryTrait> VectorSort<Q> {
target: Vec<f32>,
vector_candidates: RoaringBitmap,
limit: usize,
distribution_shift: Option<DistributionShift>,
embedder_name: &str,
embedder: &Embedder,
) -> Result<Self> {
let embedder_index = ctx
.index
@ -39,7 +39,7 @@ impl<Q: RankingRuleQueryTrait> VectorSort<Q> {
vector_candidates,
cached_sorted_docids: Default::default(),
limit,
distribution_shift,
distribution_shift: embedder.distribution(),
embedder_index,
})
}