Add analytics for the negative operator

meilisearch/src/analytics/segment_analytics.rs

@@ -580,6 +580,7 @@ pub struct SearchAggregator {
     total_received: usize,
     total_succeeded: usize,
     total_degraded: usize,
+    total_used_negative_operator: usize,
     time_spent: BinaryHeap<usize>,
 
     // sort
@@ -760,12 +761,16 @@ impl SearchAggregator {
             facet_distribution: _,
             facet_stats: _,
             degraded,
+            used_negative_operator,
         } = result;
 
         self.total_succeeded = self.total_succeeded.saturating_add(1);
         if *degraded {
             self.total_degraded = self.total_degraded.saturating_add(1);
         }
+        if *used_negative_operator {
+            self.total_used_negative_operator = self.total_used_negative_operator.saturating_add(1);
+        }
         self.time_spent.push(*processing_time_ms as usize);
     }
 
@@ -808,6 +813,7 @@ impl SearchAggregator {
             embedder,
             hybrid,
             total_degraded,
+            total_used_negative_operator,
         } = other;
 
         if self.timestamp.is_none() {
@@ -823,6 +829,8 @@ impl SearchAggregator {
         self.total_received = self.total_received.saturating_add(total_received);
         self.total_succeeded = self.total_succeeded.saturating_add(total_succeeded);
         self.total_degraded = self.total_degraded.saturating_add(total_degraded);
+        self.total_used_negative_operator =
+            self.total_used_negative_operator.saturating_add(total_used_negative_operator);
         self.time_spent.append(time_spent);
 
         // sort
@@ -929,6 +937,7 @@ impl SearchAggregator {
             embedder,
             hybrid,
             total_degraded,
+            total_used_negative_operator,
         } = self;
 
         if total_received == 0 {
@@ -949,6 +958,7 @@ impl SearchAggregator {
                     "total_failed": total_received.saturating_sub(total_succeeded), // just to be sure we never panics
                     "total_received": total_received,
                     "total_degraded": total_degraded,
+                    "total_used_negative_operator": total_used_negative_operator,
                 },
                 "sort": {
                     "with_geoPoint": sort_with_geo_point,

meilisearch/src/search.rs

@@ -324,9 +324,11 @@ pub struct SearchResult {
     #[serde(skip_serializing_if = "Option::is_none")]
     pub facet_stats: Option<BTreeMap<String, FacetStats>>,
 
-    // This information is only used for analytics purposes
+    // These fields are only used for analytics purposes
     #[serde(skip)]
     pub degraded: bool,
+    #[serde(skip)]
+    pub used_negative_operator: bool,
 }
 
 #[derive(Serialize, Debug, Clone, PartialEq)]
@@ -512,6 +514,7 @@ pub fn perform_search(
         candidates,
         document_scores,
         degraded,
+        used_negative_operator,
         ..
     } = match &query.hybrid {
         Some(hybrid) => match *hybrid.semantic_ratio {
@@ -717,6 +720,7 @@ pub fn perform_search(
         facet_distribution,
         facet_stats,
         degraded,
+        used_negative_operator,
     };
     Ok(result)
 }

milli/src/search/hybrid.rs

@@ -11,6 +11,7 @@ struct ScoreWithRatioResult {
     candidates: RoaringBitmap,
     document_scores: Vec<(u32, ScoreWithRatio)>,
     degraded: bool,
+    used_negative_operator: bool,
 }
 
 type ScoreWithRatio = (Vec<ScoreDetails>, f32);
@@ -78,6 +79,7 @@ impl ScoreWithRatioResult {
             candidates: results.candidates,
             document_scores,
             degraded: results.degraded,
+            used_negative_operator: results.used_negative_operator,
         }
     }
 
@@ -113,6 +115,7 @@ impl ScoreWithRatioResult {
             documents_ids,
             document_scores,
             degraded: left.degraded | right.degraded,
+            used_negative_operator: left.used_negative_operator | right.used_negative_operator,
         }
     }
 }

milli/src/search/mod.rs

@@ -183,6 +183,7 @@ impl<'a> Search<'a> {
             documents_ids,
             document_scores,
             degraded,
+            used_negative_operator,
         } = match self.vector.as_ref() {
             Some(vector) => execute_vector_search(
                 &mut ctx,
@@ -221,7 +222,14 @@ impl<'a> Search<'a> {
             None => MatchingWords::default(),
         };
 
-        Ok(SearchResult { matching_words, candidates, document_scores, documents_ids, degraded })
+        Ok(SearchResult {
+            matching_words,
+            candidates,
+            document_scores,
+            documents_ids,
+            degraded,
+            used_negative_operator,
+        })
     }
 }
 
@@ -272,6 +280,7 @@ pub struct SearchResult {
     pub documents_ids: Vec<DocumentId>,
     pub document_scores: Vec<Vec<ScoreDetails>>,
     pub degraded: bool,
+    pub used_negative_operator: bool,
 }
 
 #[derive(Debug, Clone, Copy, PartialEq, Eq)]

milli/src/search/new/mod.rs

@@ -571,6 +571,7 @@ pub fn execute_vector_search(
         documents_ids: docids,
         located_query_terms: None,
         degraded,
+        used_negative_operator: false,
     })
 }
 
@@ -594,6 +595,7 @@ pub fn execute_search(
 ) -> Result<PartialSearchResult> {
     check_sort_criteria(ctx, sort_criteria.as_ref())?;
 
+    let mut used_negative_operator = false;
     let mut located_query_terms = None;
     let query_terms = if let Some(query) = query {
         let span = tracing::trace_span!(target: "search::tokens", "tokenizer_builder");
@@ -636,6 +638,7 @@ pub fn execute_search(
 
         let (query_terms, negative_words) =
             located_query_terms_from_tokens(ctx, tokens, words_limit)?;
+        used_negative_operator = !negative_words.is_empty();
 
         let ignored_documents = resolve_negative_words(ctx, &negative_words)?;
         universe -= ignored_documents;
@@ -710,6 +713,7 @@ pub fn execute_search(
         documents_ids: docids,
         located_query_terms,
         degraded,
+        used_negative_operator,
     })
 }
 
@@ -772,4 +776,5 @@ pub struct PartialSearchResult {
     pub document_scores: Vec<Vec<ScoreDetails>>,
 
     pub degraded: bool,
+    pub used_negative_operator: bool,
 }