Merge branch 'request-fragments-test' into fragment-filters

crates/meilisearch/tests/common/server.rs

@@ -35,7 +35,7 @@ pub struct Server<State = Owned> {
 pub static TEST_TEMP_DIR: Lazy<TempDir> = Lazy::new(|| TempDir::new().unwrap());
 
 impl Server<Owned> {
-    fn into_shared(self) -> Server<Shared> {
+    pub fn into_shared(self) -> Server<Shared> {
         Server { service: self.service, _dir: self._dir, _marker: PhantomData }
     }
 
@@ -327,7 +327,7 @@ impl<State> Server<State> {
         self.service.get(url).await
     }
 
-    pub(super) fn _index(&self, uid: impl AsRef<str>) -> Index<'_> {
+    pub fn _index(&self, uid: impl AsRef<str>) -> Index<'_> {
         Index {
             uid: uid.as_ref().to_string(),
             service: &self.service,

crates/meilisearch/tests/vector/mod.rs

@@ -1,4 +1,5 @@
 mod binary_quantized;
+mod fragments;
 #[cfg(feature = "test-ollama")]
 mod ollama;
 mod openai;

crates/milli/src/update/settings.rs

@@ -101,6 +101,10 @@ impl<T> Setting<T> {
         matches!(self, Self::NotSet)
     }
 
+    pub const fn is_reset(&self) -> bool {
+        matches!(self, Self::Reset)
+    }
+
     /// If `Self` is `Reset`, then map self to `Set` with the provided `val`.
     pub fn or_reset(self, val: T) -> Self {
         match self {
@@ -1213,6 +1217,10 @@ impl<'a, 't, 'i> Settings<'a, 't, 'i> {
                 // new config
                 EitherOrBoth::Right((name, mut setting)) => {
                     tracing::debug!(embedder = name, "new embedder");
+                    // if we are asked to reset an embedder that doesn't exist, just ignore it
+                    if setting.is_reset() {
+                        continue;
+                    }
                     // apply the default source in case the source was not set so that it gets validated
                     crate::vector::settings::EmbeddingSettings::apply_default_source(&mut setting);
                     crate::vector::settings::EmbeddingSettings::apply_default_openai_model(

crates/milli/src/vector/composite.rs

@@ -59,12 +59,24 @@ pub struct EmbedderOptions {
 
 impl Embedder {
     pub fn new(
-        EmbedderOptions { search, index }: EmbedderOptions,
+        EmbedderOptions { search: search_options, index: index_options }: EmbedderOptions,
         cache_cap: usize,
     ) -> Result<Self, NewEmbedderError> {
-        let search = SubEmbedder::new(search, cache_cap)?;
+        // don't check similarity if one child is a rest embedder with fragments
+        // FIXME: skipping the check isn't ideal but we are unsure how to handle fragments in this context
+        let mut skip_similarity_check = false;
+        for options in [&search_options, &index_options] {
+            if let SubEmbedderOptions::Rest(options) = &options {
+                if !options.search_fragments.is_empty() || !options.indexing_fragments.is_empty() {
+                    skip_similarity_check = true;
+                    break;
+                }
+            }
+        }
+
+        let search = SubEmbedder::new(search_options, cache_cap)?;
         // cache is only used at search
-        let index = SubEmbedder::new(index, 0)?;
+        let index = SubEmbedder::new(index_options, 0)?;
 
         // check dimensions
         if search.dimensions() != index.dimensions() {
@@ -73,7 +85,12 @@ impl Embedder {
                 index.dimensions(),
             ));
         }
+
         // check similarity
+        if skip_similarity_check {
+            return Ok(Self { search, index });
+        }
+
         let search_embeddings = search
             .embed(
                 vec![