mirror of
https://github.com/meilisearch/MeiliSearch
synced 2025-07-04 04:17:10 +02:00
Add media
to search
This commit is contained in:
parent
46bceb91f1
commit
d14184f4da
5 changed files with 86 additions and 33 deletions
|
@ -7,6 +7,7 @@ use roaring::RoaringBitmap;
|
|||
use crate::score_details::{ScoreDetails, ScoreValue, ScoringStrategy};
|
||||
use crate::search::new::{distinct_fid, distinct_single_docid};
|
||||
use crate::search::SemanticSearch;
|
||||
use crate::vector::SearchQuery;
|
||||
use crate::{Index, MatchingWords, Result, Search, SearchResult};
|
||||
|
||||
struct ScoreWithRatioResult {
|
||||
|
@ -225,12 +226,9 @@ impl Search<'_> {
|
|||
return Ok(return_keyword_results(self.limit, self.offset, keyword_results));
|
||||
}
|
||||
|
||||
// no vector search against placeholder search
|
||||
let Some(query) = search.query.take() else {
|
||||
return Ok(return_keyword_results(self.limit, self.offset, keyword_results));
|
||||
};
|
||||
// no embedder, no semantic search
|
||||
let Some(SemanticSearch { vector, embedder_name, embedder, quantized }) = semantic else {
|
||||
let Some(SemanticSearch { vector, embedder_name, embedder, quantized, media }) = semantic
|
||||
else {
|
||||
return Ok(return_keyword_results(self.limit, self.offset, keyword_results));
|
||||
};
|
||||
|
||||
|
@ -241,9 +239,17 @@ impl Search<'_> {
|
|||
let span = tracing::trace_span!(target: "search::hybrid", "embed_one");
|
||||
let _entered = span.enter();
|
||||
|
||||
let q = search.query.as_deref();
|
||||
let media = media.as_ref();
|
||||
|
||||
let query = match (q, media) {
|
||||
(Some(text), None) => SearchQuery::Text(text),
|
||||
(q, media) => SearchQuery::Media { q, media },
|
||||
};
|
||||
|
||||
let deadline = std::time::Instant::now() + std::time::Duration::from_secs(3);
|
||||
|
||||
match embedder.embed_search(&query, Some(deadline)) {
|
||||
match embedder.embed_search(query, Some(deadline)) {
|
||||
Ok(embedding) => embedding,
|
||||
Err(error) => {
|
||||
tracing::error!(error=%error, "Embedding failed");
|
||||
|
@ -257,8 +263,13 @@ impl Search<'_> {
|
|||
}
|
||||
};
|
||||
|
||||
search.semantic =
|
||||
Some(SemanticSearch { vector: Some(vector_query), embedder_name, embedder, quantized });
|
||||
search.semantic = Some(SemanticSearch {
|
||||
vector: Some(vector_query),
|
||||
embedder_name,
|
||||
embedder,
|
||||
quantized,
|
||||
media,
|
||||
});
|
||||
|
||||
// TODO: would be better to have two distinct functions at this point
|
||||
let vector_results = search.execute()?;
|
||||
|
|
|
@ -12,7 +12,7 @@ use self::new::{execute_vector_search, PartialSearchResult, VectorStoreStats};
|
|||
use crate::filterable_attributes_rules::{filtered_matching_patterns, matching_features};
|
||||
use crate::index::MatchingStrategy;
|
||||
use crate::score_details::{ScoreDetails, ScoringStrategy};
|
||||
use crate::vector::Embedder;
|
||||
use crate::vector::{Embedder, Embedding};
|
||||
use crate::{
|
||||
execute_search, filtered_universe, AscDesc, DefaultSearchLogger, DocumentId, Error, Index,
|
||||
Result, SearchContext, TimeBudget, UserError,
|
||||
|
@ -32,6 +32,7 @@ pub mod similar;
|
|||
#[derive(Debug, Clone)]
|
||||
pub struct SemanticSearch {
|
||||
vector: Option<Vec<f32>>,
|
||||
media: Option<serde_json::Value>,
|
||||
embedder_name: String,
|
||||
embedder: Arc<Embedder>,
|
||||
quantized: bool,
|
||||
|
@ -93,9 +94,10 @@ impl<'a> Search<'a> {
|
|||
embedder_name: String,
|
||||
embedder: Arc<Embedder>,
|
||||
quantized: bool,
|
||||
vector: Option<Vec<f32>>,
|
||||
vector: Option<Embedding>,
|
||||
media: Option<serde_json::Value>,
|
||||
) -> &mut Search<'a> {
|
||||
self.semantic = Some(SemanticSearch { embedder_name, embedder, quantized, vector });
|
||||
self.semantic = Some(SemanticSearch { embedder_name, embedder, quantized, vector, media });
|
||||
self
|
||||
}
|
||||
|
||||
|
@ -231,24 +233,28 @@ impl<'a> Search<'a> {
|
|||
degraded,
|
||||
used_negative_operator,
|
||||
} = match self.semantic.as_ref() {
|
||||
Some(SemanticSearch { vector: Some(vector), embedder_name, embedder, quantized }) => {
|
||||
execute_vector_search(
|
||||
&mut ctx,
|
||||
vector,
|
||||
self.scoring_strategy,
|
||||
universe,
|
||||
&self.sort_criteria,
|
||||
&self.distinct,
|
||||
self.geo_param,
|
||||
self.offset,
|
||||
self.limit,
|
||||
embedder_name,
|
||||
embedder,
|
||||
*quantized,
|
||||
self.time_budget.clone(),
|
||||
self.ranking_score_threshold,
|
||||
)?
|
||||
}
|
||||
Some(SemanticSearch {
|
||||
vector: Some(vector),
|
||||
embedder_name,
|
||||
embedder,
|
||||
quantized,
|
||||
media: _,
|
||||
}) => execute_vector_search(
|
||||
&mut ctx,
|
||||
vector,
|
||||
self.scoring_strategy,
|
||||
universe,
|
||||
&self.sort_criteria,
|
||||
&self.distinct,
|
||||
self.geo_param,
|
||||
self.offset,
|
||||
self.limit,
|
||||
embedder_name,
|
||||
embedder,
|
||||
*quantized,
|
||||
self.time_budget.clone(),
|
||||
self.ranking_score_threshold,
|
||||
)?,
|
||||
_ => execute_search(
|
||||
&mut ctx,
|
||||
self.query.as_deref(),
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue