Lazily embed, don't fail hybrid search on embedding failure

This commit is contained in:
Louis Dureuil 2024-03-28 11:50:53 +01:00
parent fabc9cf14a
commit 6ebb6b55a6
No known key found for this signature in database
11 changed files with 237 additions and 203 deletions

View file

@ -8,19 +8,19 @@ use meilisearch_types::error::deserr_codes::*;
use meilisearch_types::error::ResponseError;
use meilisearch_types::index_uid::IndexUid;
use meilisearch_types::milli;
use meilisearch_types::milli::vector::DistributionShift;
use meilisearch_types::serde_cs::vec::CS;
use serde_json::Value;
use tracing::{debug, warn};
use tracing::debug;
use crate::analytics::{Analytics, SearchAggregator};
use crate::error::MeilisearchHttpError;
use crate::extractors::authentication::policies::*;
use crate::extractors::authentication::GuardedData;
use crate::extractors::sequential_extractor::SeqHandler;
use crate::metrics::MEILISEARCH_DEGRADED_SEARCH_REQUESTS;
use crate::search::{
add_search_rules, perform_search, HybridQuery, MatchingStrategy, SearchQuery, SemanticRatio,
DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
add_search_rules, perform_search, HybridQuery, MatchingStrategy, 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;
@ -204,11 +204,11 @@ pub async fn search_with_url_query(
let index = index_scheduler.index(&index_uid)?;
let features = index_scheduler.features();
let distribution = embed(&mut query, index_scheduler.get_ref(), &index)?;
let search_kind = search_kind(&query, index_scheduler.get_ref(), &index)?;
let _permit = search_queue.try_get_search_permit().await?;
let search_result =
tokio::task::spawn_blocking(move || perform_search(&index, query, features, distribution))
tokio::task::spawn_blocking(move || perform_search(&index, query, features, search_kind))
.await?;
if let Ok(ref search_result) = search_result {
aggregate.succeed(search_result);
@ -245,11 +245,11 @@ pub async fn search_with_post(
let features = index_scheduler.features();
let distribution = embed(&mut query, index_scheduler.get_ref(), &index)?;
let search_kind = search_kind(&query, index_scheduler.get_ref(), &index)?;
let _permit = search_queue.try_get_search_permit().await?;
let search_result =
tokio::task::spawn_blocking(move || perform_search(&index, query, features, distribution))
tokio::task::spawn_blocking(move || perform_search(&index, query, features, search_kind))
.await?;
if let Ok(ref search_result) = search_result {
aggregate.succeed(search_result);
@ -265,76 +265,49 @@ pub async fn search_with_post(
Ok(HttpResponse::Ok().json(search_result))
}
pub fn embed(
query: &mut SearchQuery,
pub fn search_kind(
query: &SearchQuery,
index_scheduler: &IndexScheduler,
index: &milli::Index,
) -> Result<Option<DistributionShift>, ResponseError> {
match (&query.hybrid, &query.vector, &query.q) {
(Some(HybridQuery { semantic_ratio: _, embedder }), None, Some(q))
if !q.trim().is_empty() =>
{
let embedder_configs = index.embedding_configs(&index.read_txn()?)?;
let embedders = index_scheduler.embedders(embedder_configs)?;
let embedder = if let Some(embedder_name) = embedder {
embedders.get(embedder_name)
} else {
embedders.get_default()
};
let embedder = embedder
.ok_or(milli::UserError::InvalidEmbedder("default".to_owned()))
.map_err(milli::Error::from)?
.0;
let distribution = embedder.distribution();
let embeddings = embedder
.embed(vec![q.to_owned()])
.map_err(milli::vector::Error::from)
.map_err(milli::Error::from)?
.pop()
.expect("No vector returned from embedding");
if embeddings.iter().nth(1).is_some() {
warn!("Ignoring embeddings past the first one in long search query");
query.vector = Some(embeddings.iter().next().unwrap().to_vec());
} else {
query.vector = Some(embeddings.into_inner());
}
Ok(distribution)
) -> Result<SearchKind, ResponseError> {
// regardless of anything, always do a semantic search when we don't have a vector and the query is whitespace or missing
if query.vector.is_none() {
match &query.q {
Some(q) if q.trim().is_empty() => return Ok(SearchKind::KeywordOnly),
None => return Ok(SearchKind::KeywordOnly),
_ => {}
}
(Some(hybrid), vector, _) => {
let embedder_configs = index.embedding_configs(&index.read_txn()?)?;
let embedders = index_scheduler.embedders(embedder_configs)?;
}
let embedder = if let Some(embedder_name) = &hybrid.embedder {
embedders.get(embedder_name)
} else {
embedders.get_default()
};
let embedder = embedder
.ok_or(milli::UserError::InvalidEmbedder("default".to_owned()))
.map_err(milli::Error::from)?
.0;
if let Some(vector) = vector {
if vector.len() != embedder.dimensions() {
return Err(meilisearch_types::milli::Error::UserError(
meilisearch_types::milli::UserError::InvalidVectorDimensions {
expected: embedder.dimensions(),
found: vector.len(),
},
)
.into());
}
}
Ok(embedder.distribution())
match &query.hybrid {
Some(HybridQuery { semantic_ratio, embedder }) if **semantic_ratio == 1.0 => {
Ok(SearchKind::semantic(
index_scheduler,
index,
embedder.as_deref(),
query.vector.as_ref().map(Vec::len),
)?)
}
_ => Ok(None),
Some(HybridQuery { semantic_ratio, embedder: _ }) if **semantic_ratio == 0.0 => {
Ok(SearchKind::KeywordOnly)
}
Some(HybridQuery { semantic_ratio, embedder }) => Ok(SearchKind::hybrid(
index_scheduler,
index,
embedder.as_deref(),
**semantic_ratio,
query.vector.as_ref().map(Vec::len),
)?),
None => match (query.q.as_deref(), query.vector.as_deref()) {
(_query, None) => Ok(SearchKind::KeywordOnly),
(None, Some(_vector)) => Ok(SearchKind::semantic(
index_scheduler,
index,
None,
query.vector.as_ref().map(Vec::len),
)?),
(Some(_), Some(_)) => Err(MeilisearchHttpError::MissingSearchHybrid.into()),
},
}
}