Change retrieveVectors behavior:

- when the feature is disabled, documents are never modified
- when the feature is enabled and `retrieveVectors` is disabled, `_vectors` is removed from documents
- when the feature is enabled and `retrieveVectors` is enabled, vectors from the vectors DB are merged with `_vectors` in documents

Additionally `_vectors` is never displayed when the `displayedAttributes` list does not contain either `*` or `_vectors`

- fixed an issue where `_vectors` was not injected when all vectors in the dataset where always generated
This commit is contained in:
Louis Dureuil 2024-06-13 17:13:36 +02:00
parent e35ef31738
commit b9b938c902
No known key found for this signature in database
5 changed files with 150 additions and 74 deletions

View file

@ -20,9 +20,9 @@ use crate::extractors::sequential_extractor::SeqHandler;
use crate::metrics::MEILISEARCH_DEGRADED_SEARCH_REQUESTS;
use crate::search::{
add_search_rules, perform_search, HybridQuery, MatchingStrategy, RankingScoreThreshold,
SearchKind, SearchQuery, SemanticRatio, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER,
DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT,
DEFAULT_SEARCH_OFFSET, DEFAULT_SEMANTIC_RATIO,
RetrieveVectors, SearchKind, SearchQuery, SemanticRatio, DEFAULT_CROP_LENGTH,
DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG,
DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET, DEFAULT_SEMANTIC_RATIO,
};
use crate::search_queue::SearchQueue;
@ -225,10 +225,12 @@ pub async fn search_with_url_query(
let features = index_scheduler.features();
let search_kind = search_kind(&query, index_scheduler.get_ref(), &index, features)?;
let retrieve_vector = RetrieveVectors::new(query.retrieve_vectors, features)?;
let _permit = search_queue.try_get_search_permit().await?;
let search_result =
tokio::task::spawn_blocking(move || perform_search(&index, query, search_kind)).await?;
let search_result = tokio::task::spawn_blocking(move || {
perform_search(&index, query, search_kind, retrieve_vector)
})
.await?;
if let Ok(ref search_result) = search_result {
aggregate.succeed(search_result);
}
@ -265,10 +267,13 @@ pub async fn search_with_post(
let features = index_scheduler.features();
let search_kind = search_kind(&query, index_scheduler.get_ref(), &index, features)?;
let retrieve_vectors = RetrieveVectors::new(query.retrieve_vectors, features)?;
let _permit = search_queue.try_get_search_permit().await?;
let search_result =
tokio::task::spawn_blocking(move || perform_search(&index, query, search_kind)).await?;
let search_result = tokio::task::spawn_blocking(move || {
perform_search(&index, query, search_kind, retrieve_vectors)
})
.await?;
if let Ok(ref search_result) = search_result {
aggregate.succeed(search_result);
if search_result.degraded {
@ -295,9 +300,6 @@ pub fn search_kind(
if query.hybrid.is_some() {
features.check_vector("Passing `hybrid` as a parameter")?;
}
if query.retrieve_vectors {
features.check_vector("Passing `retrieveVectors` as a parameter")?;
}
// regardless of anything, always do a keyword search when we don't have a vector and the query is whitespace or missing
if query.vector.is_none() {