snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2024-11-23 02:27:40 +08:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

Fix the vector query part by using the correct universe

Browse Source
This commit is contained in:
Clément Renault 2023-06-27 12:29:11 +02:00
parent 63bfe1cee2
commit 29d8268c94
No known key found for this signature in database
GPG Key ID: 92ADA4E935E71FA4
1 changed files with 33 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

63
milli/src/search/new/mod.rs
View File

@ -376,8 +376,40 @@ pub fn execute_search(
check_sort_criteria(ctx, sort_criteria.as_ref())?; check_sort_criteria(ctx, sort_criteria.as_ref())?;
let mut located_query_terms = None; if let Some(vector) = vector {
let mut searcher = Searcher::new();
let hnsw = ctx.index.vector_hnsw(ctx.txn)?.unwrap_or_default();
let ef = hnsw.len().min(100);
let mut dest = vec![Neighbor { index: 0, distance: 0 }; ef];
let vector = normalize_vector(vector.clone());
let neighbors = hnsw.nearest(&vector, ef, &mut searcher, &mut dest[..]);
let mut docids = Vec::new();
let mut uniq_docids = RoaringBitmap::new();
for Neighbor { index, distance: _ } in neighbors.iter() {
let index = BEU32::new(*index as u32);
let docid = ctx.index.vector_id_docid.get(ctx.txn, &index)?.unwrap().get();
if universe.contains(docid) && uniq_docids.insert(docid) {
docids.push(docid);
if docids.len() == (from + length) {
break;
}
}
}
// return the nearest documents that are also part of the candidates
// along with a dummy list of scores that are useless in this context.
let docids: Vec<_> = docids.into_iter().skip(from).take(length).collect();
return Ok(PartialSearchResult {
candidates: universe,
document_scores: vec![Vec::new(); docids.len()],
documents_ids: docids,
located_query_terms: None,
});
}
let mut located_query_terms = None;
let query_terms = if let Some(query) = query { let query_terms = if let Some(query) = query {
// We make sure that the analyzer is aware of the stop words // We make sure that the analyzer is aware of the stop words
// this ensures that the query builder is able to properly remove them. // this ensures that the query builder is able to properly remove them.
@ -445,37 +477,8 @@ pub fn execute_search(
}; };
let BucketSortOutput { docids, scores, mut all_candidates } = bucket_sort_output; let BucketSortOutput { docids, scores, mut all_candidates } = bucket_sort_output;
let fields_ids_map = ctx.index.fields_ids_map(ctx.txn)?; let fields_ids_map = ctx.index.fields_ids_map(ctx.txn)?;
let docids = match vector {
Some(vector) => {
// return the nearest documents that are also part of the candidates.
let mut searcher = Searcher::new();
let hnsw = ctx.index.vector_hnsw(ctx.txn)?.unwrap_or_default();
let ef = hnsw.len().min(100);
let mut dest = vec![Neighbor { index: 0, distance: 0 }; ef];
let vector = normalize_vector(vector.clone());
let neighbors = hnsw.nearest(&vector, ef, &mut searcher, &mut dest[..]);
let mut docids = Vec::new();
for Neighbor { index, distance: _ } in neighbors.iter() {
let index = BEU32::new(*index as u32);
let docid = ctx.index.vector_id_docid.get(ctx.txn, &index)?.unwrap().get();
if universe.contains(docid) {
docids.push(docid);
if docids.len() == (from + length) {
break;
}
}
}
docids.into_iter().skip(from).take(length).collect()
}
// return the search docids if the vector field is not specified
None => docids,
};
// The candidates is the universe unless the exhaustive number of hits // The candidates is the universe unless the exhaustive number of hits
// is requested and a distinct attribute is set. // is requested and a distinct attribute is set.
if exhaustive_number_hits { if exhaustive_number_hits {