From c53841e166a95a3c80e2dc0c3e050aa9e710c722 Mon Sep 17 00:00:00 2001
From: Kerollmops <clement@meilisearch.com>
Date: Mon, 14 Aug 2023 16:03:55 +0200
Subject: [PATCH] Accept the null JSON value as the value of _vectors

---
 meilisearch/src/search.rs                        |  1 +
 milli/src/lib.rs                                 | 12 ++++++------
 .../extract/extract_vector_points.rs             | 16 +++++++++-------
 3 files changed, 16 insertions(+), 13 deletions(-)

diff --git a/meilisearch/src/search.rs b/meilisearch/src/search.rs
index 1a1c7721e..d484cd471 100644
--- a/meilisearch/src/search.rs
+++ b/meilisearch/src/search.rs
@@ -666,6 +666,7 @@ fn compute_semantic_score(query: &[f32], vectors: Value) -> milli::Result<Option
         .map_err(InternalError::SerdeJson)?;
     Ok(vectors
         .into_iter()
+        .flatten()
         .map(|v| OrderedFloat(dot_product_similarity(query, &v)))
         .max()
         .map(OrderedFloat::into_inner))
diff --git a/milli/src/lib.rs b/milli/src/lib.rs
index cd97d6192..cfa438609 100644
--- a/milli/src/lib.rs
+++ b/milli/src/lib.rs
@@ -293,15 +293,15 @@ pub fn normalize_facet(original: &str) -> String {
 #[derive(serde::Serialize, serde::Deserialize, Debug)]
 #[serde(transparent)]
 pub struct VectorOrArrayOfVectors {
-    #[serde(with = "either::serde_untagged")]
-    inner: either::Either<Vec<f32>, Vec<Vec<f32>>>,
+    #[serde(with = "either::serde_untagged_optional")]
+    inner: Option<either::Either<Vec<f32>, Vec<Vec<f32>>>>,
 }
 
 impl VectorOrArrayOfVectors {
-    pub fn into_array_of_vectors(self) -> Vec<Vec<f32>> {
-        match self.inner {
-            either::Either::Left(vector) => vec![vector],
-            either::Either::Right(vectors) => vectors,
+    pub fn into_array_of_vectors(self) -> Option<Vec<Vec<f32>>> {
+        match self.inner? {
+            either::Either::Left(vector) => Some(vec![vector]),
+            either::Either::Right(vectors) => Some(vectors),
         }
     }
 }
diff --git a/milli/src/update/index_documents/extract/extract_vector_points.rs b/milli/src/update/index_documents/extract/extract_vector_points.rs
index 0fad3be07..fdccb515e 100644
--- a/milli/src/update/index_documents/extract/extract_vector_points.rs
+++ b/milli/src/update/index_documents/extract/extract_vector_points.rs
@@ -33,7 +33,7 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
         // lazily get it when needed
         let document_id = || -> Value {
             let document_id = obkv.get(primary_key_id).unwrap();
-            serde_json::from_slice(document_id).unwrap()
+            from_slice(document_id).unwrap()
         };
 
         // first we retrieve the _vectors field
@@ -50,12 +50,14 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
                 }
             };
 
-            for (i, vector) in vectors.into_iter().enumerate().take(u16::MAX as usize) {
-                let index = u16::try_from(i).unwrap();
-                let mut key = docid_bytes.to_vec();
-                key.extend_from_slice(&index.to_be_bytes());
-                let bytes = cast_slice(&vector);
-                writer.insert(key, bytes)?;
+            if let Some(vectors) = vectors {
+                for (i, vector) in vectors.into_iter().enumerate().take(u16::MAX as usize) {
+                    let index = u16::try_from(i).unwrap();
+                    let mut key = docid_bytes.to_vec();
+                    key.extend_from_slice(&index.to_be_bytes());
+                    let bytes = cast_slice(&vector);
+                    writer.insert(key, bytes)?;
+                }
             }
         }
         // else => the `_vectors` object was `null`, there is nothing to do