searchengines-web/MeiliSearch
searchengines-web/MeiliSearch
1
0
Fork 0
mirror of https://github.com/meilisearch/MeiliSearch synced 2024-06-13 16:19:50 +02:00
Code Issues Releases Wiki Activity

update vector extractor

Browse Source
This commit is contained in:
ManyTheFish 2023-10-31 17:44:42 +01:00
parent 12323d610e
commit 4b64c33aa2
1 changed files with 9 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
milli/src/update/index_documents/extract/extract_vector_points.rs
View File

@ -7,7 +7,8 @@ use serde_json::{from_slice, Value};
use super::helpers::{create_writer, writer_into_reader, GrenadParameters};
use crate::error::UserError;
use crate::{FieldId, InternalError, Result, VectorOrArrayOfVectors};
use crate::update::index_documents::helpers::try_split_at;
use crate::{DocumentId, FieldId, InternalError, Result, VectorOrArrayOfVectors};
/// Extracts the embedding vector contained in each document under the `_vectors` field.
///
@ -28,15 +29,17 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
);
let mut cursor = obkv_documents.into_cursor()?;
while let Some((docid_bytes, value)) = cursor.move_on_next()? {
while let Some((key, value)) = cursor.move_on_next()? {
// this must always be serialized as (docid, external_docid);
let (docid_bytes, external_id_bytes) =
try_split_at(key, std::mem::size_of::<DocumentId>()).unwrap();
debug_assert!(std::str::from_utf8(external_id_bytes).is_ok());
let obkv = obkv::KvReader::new(value);
// since we only needs the primary key when we throw an error we create this getter to
// lazily get it when needed
let document_id = || -> Value {
let document_id = obkv.get(primary_key_id).unwrap();
from_slice(document_id).unwrap()
};
let document_id = || -> Value { std::str::from_utf8(external_id_bytes).unwrap().into() };
// first we retrieve the _vectors field
if let Some(vectors) = obkv.get(vectors_fid) {