snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2024-11-26 03:55:07 +08:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

forward the embedding config to the extractors

Browse Source
This commit is contained in:
Tamo 2024-05-30 12:16:06 +02:00
parent 9eb6f522ea
commit a73ccc78a6
3 changed files with 15 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
milli/src/update/index_documents/extract/extract_vector_points.rs
View File

@ -14,6 +14,7 @@ use roaring::RoaringBitmap;
use serde_json::Value;
use super::helpers::{create_writer, writer_into_reader, GrenadParameters};
use crate::index::IndexEmbeddingConfig;
use crate::prompt::Prompt;
use crate::update::del_add::{DelAdd, KvReaderDelAdd, KvWriterDelAdd};
use crate::update::settings::InnerIndexSettingsDiff;
@ -96,6 +97,7 @@ struct EmbedderVectorExtractor {
pub fn extract_vector_points<R: io::Read + io::Seek>(
obkv_documents: grenad::Reader<R>,
indexer: GrenadParameters,
embedders_configs: &[IndexEmbeddingConfig],
settings_diff: &InnerIndexSettingsDiff,
) -> Result<Vec<ExtractedVectorPoints>> {
let reindex_vectors = settings_diff.reindex_vectors();

12
milli/src/update/index_documents/extract/mod.rs
View File

@ -30,6 +30,7 @@ use self::extract_word_pair_proximity_docids::extract_word_pair_proximity_docids
use self::extract_word_position_docids::extract_word_position_docids;
use super::helpers::{as_cloneable_grenad, CursorClonableMmap, GrenadParameters};
use super::{helpers, TypedChunk};
use crate::index::IndexEmbeddingConfig;
use crate::update::settings::InnerIndexSettingsDiff;
use crate::{FieldId, Result, ThreadPoolNoAbortBuilder};
@ -43,6 +44,7 @@ pub(crate) fn data_from_obkv_documents(
indexer: GrenadParameters,
lmdb_writer_sx: Sender<Result<TypedChunk>>,
primary_key_id: FieldId,
embedders_configs: Arc<Vec<IndexEmbeddingConfig>>,
settings_diff: Arc<InnerIndexSettingsDiff>,
max_positions_per_attributes: Option<u32>,
) -> Result<()> {
@ -55,6 +57,7 @@ pub(crate) fn data_from_obkv_documents(
original_documents_chunk,
indexer,
lmdb_writer_sx.clone(),
embedders_configs.clone(),
settings_diff.clone(),
)
})
@ -210,6 +213,7 @@ fn send_original_documents_data(
original_documents_chunk: Result<grenad::Reader<BufReader<File>>>,
indexer: GrenadParameters,
lmdb_writer_sx: Sender<Result<TypedChunk>>,
embedders_configs: Arc<Vec<IndexEmbeddingConfig>>,
settings_diff: Arc<InnerIndexSettingsDiff>,
) -> Result<()> {
let original_documents_chunk =
@ -226,11 +230,17 @@ fn send_original_documents_data(
if index_vectors {
let settings_diff = settings_diff.clone();
let embedders_configs = embedders_configs.clone();
let original_documents_chunk = original_documents_chunk.clone();
let lmdb_writer_sx = lmdb_writer_sx.clone();
rayon::spawn(move || {
match extract_vector_points(original_documents_chunk.clone(), indexer, &settings_diff) {
match extract_vector_points(
original_documents_chunk.clone(),
indexer,
&embedders_configs,
&settings_diff,
) {
Ok(extracted_vectors) => {
for ExtractedVectorPoints {
manual_vectors,

2
milli/src/update/index_documents/mod.rs
View File

@ -286,6 +286,7 @@ where
settings_diff.new.recompute_searchables(self.wtxn, self.index)?;
let settings_diff = Arc::new(settings_diff);
let embedders_configs = Arc::new(self.index.embedding_configs(self.wtxn)?);
let backup_pool;
let pool = match self.indexer_config.thread_pool {
@ -399,6 +400,7 @@ where
pool_params,
lmdb_writer_sx.clone(),
primary_key_id,
embedders_configs.clone(),
settings_diff_cloned,
max_positions_per_attributes,
)