searchengines-web/MeiliSearch
searchengines-web/MeiliSearch
1
0
Fork 0
mirror of https://github.com/meilisearch/MeiliSearch synced 2024-12-23 21:20:24 +01:00
Code Issues Releases Wiki Activity

Extract the vectors from the non-flattened version of the documents

Browse Source
This commit is contained in:
Kerollmops 2023-09-06 12:20:25 +02:00
parent e02d0064bd
commit 679c0b0f97
No known key found for this signature in database
GPG Key ID: F250A4C4E3AE5F5F
1 changed files with 29 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

51
milli/src/update/index_documents/extract/mod.rs
View File

@ -55,7 +55,13 @@ pub(crate) fn data_from_obkv_documents(
original_obkv_chunks original_obkv_chunks
.par_bridge() .par_bridge()
.map(|original_documents_chunk| { .map(|original_documents_chunk| {
send_original_documents_data(original_documents_chunk, lmdb_writer_sx.clone()) send_original_documents_data(
original_documents_chunk,
indexer,
lmdb_writer_sx.clone(),
vectors_field_id,
primary_key_id,
)
}) })
.collect::<Result<()>>()?; .collect::<Result<()>>()?;
@ -72,7 +78,6 @@ pub(crate) fn data_from_obkv_documents(
&faceted_fields, &faceted_fields,
primary_key_id, primary_key_id,
geo_fields_ids, geo_fields_ids,
vectors_field_id,
&stop_words, &stop_words,
max_positions_per_attributes, max_positions_per_attributes,
) )
@ -257,11 +262,33 @@ fn spawn_extraction_task<FE, FS, M>(
/// - documents /// - documents
fn send_original_documents_data( fn send_original_documents_data(
original_documents_chunk: Result<grenad::Reader<File>>, original_documents_chunk: Result<grenad::Reader<File>>,
indexer: GrenadParameters,
lmdb_writer_sx: Sender<Result<TypedChunk>>, lmdb_writer_sx: Sender<Result<TypedChunk>>,
vectors_field_id: Option<FieldId>,
primary_key_id: FieldId,
) -> Result<()> { ) -> Result<()> {
let original_documents_chunk = let original_documents_chunk =
original_documents_chunk.and_then(|c| unsafe { as_cloneable_grenad(&c) })?; original_documents_chunk.and_then(|c| unsafe { as_cloneable_grenad(&c) })?;
if let Some(vectors_field_id) = vectors_field_id {
let documents_chunk_cloned = original_documents_chunk.clone();
let lmdb_writer_sx_cloned = lmdb_writer_sx.clone();
rayon::spawn(move || {
let result = extract_vector_points(
documents_chunk_cloned,
indexer,
primary_key_id,
vectors_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)),
};
});
}
// TODO: create a custom internal error // TODO: create a custom internal error
lmdb_writer_sx.send(Ok(TypedChunk::Documents(original_documents_chunk))).unwrap(); lmdb_writer_sx.send(Ok(TypedChunk::Documents(original_documents_chunk))).unwrap();
Ok(()) Ok(())
@ -283,7 +310,6 @@ fn send_and_extract_flattened_documents_data(
faceted_fields: &HashSet<FieldId>, faceted_fields: &HashSet<FieldId>,
primary_key_id: FieldId, primary_key_id: FieldId,
geo_fields_ids: Option<(FieldId, FieldId)>, geo_fields_ids: Option<(FieldId, FieldId)>,
vectors_field_id: Option<FieldId>,
stop_words: &Option<fst::Set<&[u8]>>, stop_words: &Option<fst::Set<&[u8]>>,
max_positions_per_attributes: Option<u32>, max_positions_per_attributes: Option<u32>,
) -> Result<( ) -> Result<(
@ -312,25 +338,6 @@ fn send_and_extract_flattened_documents_data(
}); });
} }
if let Some(vectors_field_id) = vectors_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,
primary_key_id,
vectors_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<_>) = let (docid_word_positions_chunk, docid_fid_facet_values_chunks): (Result<_>, Result<_>) =
rayon::join( rayon::join(
|| { || {