searchengines-web/MeiliSearch
searchengines-web/MeiliSearch
1
0
Fork 0
mirror of https://github.com/meilisearch/MeiliSearch synced 2025-07-04 20:37:15 +02:00
Code Issues Releases Wiki Activity

Extract the vectors from the documents

Browse source
This commit is contained in:
Clément Renault 2023-06-08 11:51:55 +02:00
parent 34349faeae
commit 7ac2f1489d
No known key found for this signature in database
GPG key ID: 92ADA4E935E71FA4
3 changed files with 44 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

17
milli/src/update/index_documents/extract/mod.rs
View file

@ -47,6 +47,7 @@ pub(crate) fn data_from_obkv_documents(
faceted_fields: HashSet<FieldId>,
primary_key_id: FieldId,
geo_fields_ids: Option<(FieldId, FieldId)>,
vector_field_id: Option<FieldId>,
stop_words: Option<fst::Set<&[u8]>>,
max_positions_per_attributes: Option<u32>,
exact_attributes: HashSet<FieldId>,
@ -71,6 +72,7 @@ pub(crate) fn data_from_obkv_documents(
&faceted_fields,
primary_key_id,
geo_fields_ids,
vector_field_id,
&stop_words,
max_positions_per_attributes,
)
@ -281,6 +283,7 @@ fn send_and_extract_flattened_documents_data(
faceted_fields: &HashSet<FieldId>,
primary_key_id: FieldId,
geo_fields_ids: Option<(FieldId, FieldId)>,
vector_field_id: Option<FieldId>,
stop_words: &Option<fst::Set<&[u8]>>,
max_positions_per_attributes: Option<u32>,
) -> Result<(
@ -309,6 +312,20 @@ fn send_and_extract_flattened_documents_data(
});
}
if let Some(vector_field_id) = vector_field_id {
let documents_chunk_cloned = flattened_documents_chunk.clone();
let lmdb_writer_sx_cloned = lmdb_writer_sx.clone();
rayon::spawn(move || {
let result = extract_vector_points(documents_chunk_cloned, indexer, vector_field_id);
let _ = match result {
Ok(vector_points) => {
lmdb_writer_sx_cloned.send(Ok(TypedChunk::VectorPoints(vector_points)))
}
Err(error) => lmdb_writer_sx_cloned.send(Err(error)),
};
});
}
let (docid_word_positions_chunk, docid_fid_facet_values_chunks): (Result<_>, Result<_>) =
rayon::join(
|| {