searchengines-web/MeiliSearch
searchengines-web/MeiliSearch
1
0
Fork 0
mirror of https://github.com/meilisearch/MeiliSearch synced 2024-11-23 05:14:27 +01:00
Code Issues Releases Wiki Activity

Don't write vectors that weren't autogenerated in document DB

Browse Source
This commit is contained in:
Louis Dureuil 2024-05-14 11:46:04 +02:00
parent 02714ef5ed
commit 2f7a8a4efb
No known key found for this signature in database
1 changed files with 24 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
milli/src/update/index_documents/typed_chunk.rs
View File

@ -193,6 +193,10 @@ pub(crate) fn write_typed_chunk_into_index(
let span = tracing::trace_span!(target: "indexing::write_db", "documents"); let span = tracing::trace_span!(target: "indexing::write_db", "documents");
let _entered = span.enter(); let _entered = span.enter();
let fields_ids_map = index.fields_ids_map(wtxn)?;
let vectors_fid =
fields_ids_map.id(crate::vector::parsed_vectors::RESERVED_VECTORS_FIELD_NAME);
let mut builder = MergerBuilder::new(keep_latest_obkv as MergeFn); let mut builder = MergerBuilder::new(keep_latest_obkv as MergeFn);
for typed_chunk in typed_chunks { for typed_chunk in typed_chunks {
let TypedChunk::Documents(chunk) = typed_chunk else { let TypedChunk::Documents(chunk) = typed_chunk else {
@ -206,6 +210,8 @@ pub(crate) fn write_typed_chunk_into_index(
let mut docids = index.documents_ids(wtxn)?; let mut docids = index.documents_ids(wtxn)?;
let mut iter = merger.into_stream_merger_iter()?; let mut iter = merger.into_stream_merger_iter()?;
let mut vectors_buffer = Vec::new();
while let Some((key, reader)) = iter.next()? { while let Some((key, reader)) = iter.next()? {
let mut writer: KvWriter<_, FieldId> = KvWriter::memory(); let mut writer: KvWriter<_, FieldId> = KvWriter::memory();
let reader: KvReader<FieldId> = KvReader::new(reader); let reader: KvReader<FieldId> = KvReader::new(reader);
@ -219,6 +225,24 @@ pub(crate) fn write_typed_chunk_into_index(
let del_add_reader = KvReaderDelAdd::new(value); let del_add_reader = KvReaderDelAdd::new(value);
if let Some(addition) = del_add_reader.get(DelAdd::Addition) { if let Some(addition) = del_add_reader.get(DelAdd::Addition) {
let addition = match vectors_fid {
// for the "_vectors" field, only keep vectors that are marked as userProvided
Some(vectors_fid) if vectors_fid == field_id => 'vectors: {
vectors_buffer.clear();
let Ok(mut vectors) =
crate::vector::parsed_vectors::ParsedVectors::from_bytes(
addition,
)
else {
break 'vectors addition;
};
vectors.retain_user_provided_vectors();
serde_json::to_writer(&mut vectors_buffer, &vectors.0)
.map_err(InternalError::SerdeJson)?;
&vectors_buffer
}
_ => addition,
};
writer.insert(field_id, addition)?; writer.insert(field_id, addition)?;
} }
} }