snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2024-11-30 00:55:00 +08:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

Implement an ugly deletion of values in the HNSW

Browse Source
This commit is contained in:
Kerollmops 2023-06-14 14:54:28 +02:00 committed by Clément Renault
parent 436a10bef4
commit c2a402f3ae
No known key found for this signature in database
GPG Key ID: 92ADA4E935E71FA4
1 changed files with 27 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
milli/src/update/delete_documents.rs
View File

@ -4,8 +4,10 @@ use std::collections::{BTreeSet, HashMap, HashSet};
use fst::IntoStreamer; use fst::IntoStreamer;
use heed::types::{ByteSlice, DecodeIgnore, Str, UnalignedSlice}; use heed::types::{ByteSlice, DecodeIgnore, Str, UnalignedSlice};
use heed::{BytesDecode, BytesEncode, Database, RwIter}; use heed::{BytesDecode, BytesEncode, Database, RwIter};
use hnsw::Searcher;
use roaring::RoaringBitmap; use roaring::RoaringBitmap;
use serde::{Deserialize, Serialize}; use serde::{Deserialize, Serialize};
use space::KnnPoints;
use time::OffsetDateTime; use time::OffsetDateTime;
use super::facet::delete::FacetsDelete; use super::facet::delete::FacetsDelete;
@ -14,6 +16,7 @@ use crate::error::InternalError;
use crate::facet::FacetType; use crate::facet::FacetType;
use crate::heed_codec::facet::FieldDocIdFacetCodec; use crate::heed_codec::facet::FieldDocIdFacetCodec;
use crate::heed_codec::CboRoaringBitmapCodec; use crate::heed_codec::CboRoaringBitmapCodec;
use crate::index::Hnsw;
use crate::{ use crate::{
ExternalDocumentsIds, FieldId, FieldIdMapMissingEntry, Index, Result, RoaringBitmapCodec, BEU32, ExternalDocumentsIds, FieldId, FieldIdMapMissingEntry, Index, Result, RoaringBitmapCodec, BEU32,
}; };
@ -430,6 +433,30 @@ impl<'t, 'u, 'i> DeleteDocuments<'t, 'u, 'i> {
&self.to_delete_docids, &self.to_delete_docids,
)?; )?;
// 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();
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));
}
}
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)?;
}
self.index.put_vector_hnsw(self.wtxn, &new_hnsw)?;
}
self.index.put_soft_deleted_documents_ids(self.wtxn, &RoaringBitmap::new())?; self.index.put_soft_deleted_documents_ids(self.wtxn, &RoaringBitmap::new())?;
Ok(DetailedDocumentDeletionResult { Ok(DetailedDocumentDeletionResult {