snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2025-10-11 22:26:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

Replace the hnsw crate by the instant-distance one

Browse Source
This commit is contained in:
Kerollmops
2023-07-25 12:36:01 +02:00
parent 86d8bb3a3e
commit 29ab54b259
7 changed files with 127 additions and 120 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
milli/src/update/delete_documents.rs
View File

@@ -4,10 +4,9 @@ use std::collections::{BTreeSet, HashMap, HashSet};
use fst::IntoStreamer;
use heed::types::{ByteSlice, DecodeIgnore, Str, UnalignedSlice};
use heed::{BytesDecode, BytesEncode, Database, RwIter};
use hnsw::Searcher;
use instant_distance::PointId;
use roaring::RoaringBitmap;
use serde::{Deserialize, Serialize};
use space::KnnPoints;
use time::OffsetDateTime;
use super::facet::delete::FacetsDelete;
@@ -436,24 +435,24 @@ impl<'t, 'u, 'i> DeleteDocuments<'t, 'u, 'i> {
// An ugly and slow way to remove the vectors from the HNSW
// It basically reconstructs the HNSW from scratch without editing the current one.
let current_hnsw = self.index.vector_hnsw(self.wtxn)?.unwrap_or_default();
if !current_hnsw.is_empty() {
let mut new_hnsw = Hnsw::default();
let mut searcher = Searcher::new();
let mut new_vector_id_docids = Vec::new();
if let Some(current_hnsw) = self.index.vector_hnsw(self.wtxn)? {
let mut points = Vec::new();
let mut docids = Vec::new();
for result in vector_id_docid.iter(self.wtxn)? {
let (vector_id, docid) = result?;
if !self.to_delete_docids.contains(docid.get()) {
let vector = current_hnsw.get_point(vector_id.get() as usize).clone();
let vector_id = new_hnsw.insert(vector, &mut searcher);
new_vector_id_docids.push((vector_id as u32, docid));
let pid = PointId::from(vector_id.get());
let vector = current_hnsw[pid].clone();
points.push(vector);
docids.push(docid);
}
}
let (new_hnsw, pids) = Hnsw::builder().build_hnsw(points);
vector_id_docid.clear(self.wtxn)?;
for (vector_id, docid) in new_vector_id_docids {
vector_id_docid.put(self.wtxn, &BEU32::new(vector_id), &docid)?;
for (pid, docid) in pids.into_iter().zip(docids) {
vector_id_docid.put(self.wtxn, &BEU32::new(pid.into_inner()), &docid)?;
}
self.index.put_vector_hnsw(self.wtxn, &new_hnsw)?;
}