improve documentation

Remove risk of command injection

.github/workflows/bench-manual.yml

@@ -18,7 +18,7 @@ jobs:
     timeout-minutes: 180 # 3h
     steps:
       - uses: actions/checkout@v5
-      - uses: dtolnay/rust-toolchain@1.89
+      - uses: dtolnay/rust-toolchain@1.91.1
         with:
           profile: minimal
 

.github/workflows/bench-pr.yml

@@ -66,7 +66,7 @@ jobs:
           fetch-depth: 0 # fetch full history to be able to get main commit sha
           ref: ${{ steps.comment-branch.outputs.head_ref }}
 
-      - uses: dtolnay/rust-toolchain@1.89
+      - uses: dtolnay/rust-toolchain@1.91.1
 
       - name: Run benchmarks on PR ${{ github.event.issue.id }}
         run: |

.github/workflows/bench-push-indexing.yml

@@ -12,7 +12,7 @@ jobs:
     timeout-minutes: 180 # 3h
     steps:
       - uses: actions/checkout@v5
-      - uses: dtolnay/rust-toolchain@1.89
+      - uses: dtolnay/rust-toolchain@1.91.1
 
       # Run benchmarks
       - name: Run benchmarks - Dataset ${BENCH_NAME} - Branch main - Commit ${{ github.sha }}

.github/workflows/benchmarks-manual.yml

@@ -18,7 +18,7 @@ jobs:
     timeout-minutes: 4320 # 72h
     steps:
       - uses: actions/checkout@v5
-      - uses: dtolnay/rust-toolchain@1.89
+      - uses: dtolnay/rust-toolchain@1.91.1
         with:
           profile: minimal
 

.github/workflows/benchmarks-pr.yml

@@ -44,7 +44,7 @@ jobs:
             exit 1
           fi
 
-      - uses: dtolnay/rust-toolchain@1.89
+      - uses: dtolnay/rust-toolchain@1.91.1
         with:
           profile: minimal
 

.github/workflows/benchmarks-push-indexing.yml

@@ -16,7 +16,7 @@ jobs:
     timeout-minutes: 4320 # 72h
     steps:
       - uses: actions/checkout@v5
-      - uses: dtolnay/rust-toolchain@1.89
+      - uses: dtolnay/rust-toolchain@1.91.1
         with:
           profile: minimal
 

.github/workflows/benchmarks-push-search-geo.yml

@@ -15,7 +15,7 @@ jobs:
     runs-on: benchmarks
     steps:
       - uses: actions/checkout@v5
-      - uses: dtolnay/rust-toolchain@1.89
+      - uses: dtolnay/rust-toolchain@1.91.1
         with:
           profile: minimal
 

.github/workflows/benchmarks-push-search-songs.yml

@@ -15,7 +15,7 @@ jobs:
     runs-on: benchmarks
     steps:
       - uses: actions/checkout@v5
-      - uses: dtolnay/rust-toolchain@1.89
+      - uses: dtolnay/rust-toolchain@1.91.1
         with:
           profile: minimal
 

.github/workflows/benchmarks-push-search-wiki.yml

@@ -15,7 +15,7 @@ jobs:
     runs-on: benchmarks
     steps:
       - uses: actions/checkout@v5
-      - uses: dtolnay/rust-toolchain@1.89
+      - uses: dtolnay/rust-toolchain@1.91.1
         with:
           profile: minimal
 

.github/workflows/flaky-tests.yml

@@ -3,7 +3,7 @@ name: Look for flaky tests
 on:
   workflow_dispatch:
   schedule:
-    - cron: '0 4 * * *' # Every day at 4:00AM
+    - cron: "0 4 * * *" # Every day at 4:00AM
 
 jobs:
   flaky:
@@ -23,7 +23,7 @@ jobs:
         run: |
           apt-get update && apt-get install -y curl
           apt-get install build-essential -y
-      - uses: dtolnay/rust-toolchain@1.89
+      - uses: dtolnay/rust-toolchain@1.91.1
       - name: Install cargo-flaky
         run: cargo install cargo-flaky
       - name: Run cargo flaky in the dumps

.github/workflows/fuzzer-indexing.yml

@@ -12,7 +12,7 @@ jobs:
     timeout-minutes: 4320 # 72h
     steps:
       - uses: actions/checkout@v5
-      - uses: dtolnay/rust-toolchain@1.89
+      - uses: dtolnay/rust-toolchain@1.91.1
 
       # Run benchmarks
       - name: Run the fuzzer

.github/workflows/publish-apt-brew-pkg.yml

@@ -31,7 +31,7 @@ jobs:
           sudo rm -rf "/usr/share/dotnet" || true
           sudo rm -rf "/usr/local/lib/android" || true
           sudo rm -rf "/usr/local/share/boost" || true
-      - uses: dtolnay/rust-toolchain@1.89
+      - uses: dtolnay/rust-toolchain@1.91.1
       - name: Install cargo-deb
         run: cargo install cargo-deb
       - uses: actions/checkout@v5

.github/workflows/publish-release-assets.yml

@@ -76,7 +76,7 @@ jobs:
     needs: check-version
     steps:
       - uses: actions/checkout@v5
-      - uses: dtolnay/rust-toolchain@1.89
+      - uses: dtolnay/rust-toolchain@1.91.1
       - name: Build
         run: cargo build --release --locked ${{ matrix.feature-flag }} ${{ matrix.extra-args }}
       # No need to upload binaries for dry run (cron or workflow_dispatch)

.github/workflows/sdks-tests.yml

@@ -25,14 +25,18 @@ jobs:
       - uses: actions/checkout@v5
       - name: Define the Docker image we need to use
         id: define-image
+        env:
+          EVENT_NAME: ${{ github.event_name }}
+          DOCKER_IMAGE_INPUT: ${{ github.event.inputs.docker_image }}
         run: |
-          event=${{ github.event_name }}
           echo "docker-image=nightly" >> $GITHUB_OUTPUT
-          if [[ $event == 'workflow_dispatch' ]]; then
-            echo "docker-image=${{ github.event.inputs.docker_image }}" >> $GITHUB_OUTPUT
+          if [[ "$EVENT_NAME" == 'workflow_dispatch' ]]; then
+            echo "docker-image=$DOCKER_IMAGE_INPUT" >> $GITHUB_OUTPUT
           fi
       - name: Docker image is ${{ steps.define-image.outputs.docker-image }}
-        run: echo "Docker image is ${{ steps.define-image.outputs.docker-image }}"
+        env:
+          DOCKER_IMAGE: ${{ steps.define-image.outputs.docker-image }}
+        run: echo "Docker image is $DOCKER_IMAGE"
 
 ##########
 ## SDKs ##

.github/workflows/test-suite.yml

@@ -34,7 +34,7 @@ jobs:
       - name: check free space after
         run: df -h
       - name: Setup test with Rust stable
-        uses: dtolnay/rust-toolchain@1.89
+        uses: dtolnay/rust-toolchain@1.91.1
       - name: Cache dependencies
         uses: Swatinem/rust-cache@v2.8.0
         with:
@@ -63,7 +63,7 @@ jobs:
       - uses: actions/checkout@v5
       - name: Cache dependencies
         uses: Swatinem/rust-cache@v2.8.0
-      - uses: dtolnay/rust-toolchain@1.89
+      - uses: dtolnay/rust-toolchain@1.91.1
       - name: Run cargo build without any default features
         uses: actions-rs/cargo@v1
         with:
@@ -87,7 +87,7 @@ jobs:
           sudo rm -rf "/usr/share/dotnet" || true
           sudo rm -rf "/usr/local/lib/android" || true
           sudo rm -rf "/usr/local/share/boost" || true
-      - uses: dtolnay/rust-toolchain@1.89
+      - uses: dtolnay/rust-toolchain@1.91.1
       - name: Run cargo build with almost all features
         run: |
           cargo build --workspace --locked --features "$(cargo xtask list-features --exclude-feature cuda,test-ollama)"
@@ -145,7 +145,7 @@ jobs:
           sudo rm -rf "/usr/share/dotnet" || true
           sudo rm -rf "/usr/local/lib/android" || true
           sudo rm -rf "/usr/local/share/boost" || true
-      - uses: dtolnay/rust-toolchain@1.89
+      - uses: dtolnay/rust-toolchain@1.91.1
       - name: Run cargo tree without default features and check lindera is not present
         run: |
           if cargo tree -f '{p} {f}' -e normal --no-default-features | grep -qz lindera; then
@@ -167,7 +167,7 @@ jobs:
           sudo rm -rf "/usr/share/dotnet" || true
           sudo rm -rf "/usr/local/lib/android" || true
           sudo rm -rf "/usr/local/share/boost" || true
-      - uses: dtolnay/rust-toolchain@1.89
+      - uses: dtolnay/rust-toolchain@1.91.1
       - name: Cache dependencies
         uses: Swatinem/rust-cache@v2.8.0
       - name: Build
@@ -187,7 +187,7 @@ jobs:
           sudo rm -rf "/usr/share/dotnet" || true
           sudo rm -rf "/usr/local/lib/android" || true
           sudo rm -rf "/usr/local/share/boost" || true
-      - uses: dtolnay/rust-toolchain@1.89
+      - uses: dtolnay/rust-toolchain@1.91.1
         with:
           components: clippy
       - name: Cache dependencies
@@ -209,7 +209,7 @@ jobs:
           sudo rm -rf "/usr/share/dotnet" || true
           sudo rm -rf "/usr/local/lib/android" || true
           sudo rm -rf "/usr/local/share/boost" || true
-      - uses: dtolnay/rust-toolchain@1.89
+      - uses: dtolnay/rust-toolchain@1.91.1
         with:
           components: rustfmt
       - name: Cache dependencies
@@ -235,7 +235,7 @@ jobs:
           sudo rm -rf "/usr/share/dotnet" || true
           sudo rm -rf "/usr/local/lib/android" || true
           sudo rm -rf "/usr/local/share/boost" || true
-      - uses: dtolnay/rust-toolchain@1.89
+      - uses: dtolnay/rust-toolchain@1.91.1
       - name: Cache dependencies
         uses: Swatinem/rust-cache@v2.8.0
       - name: Run declarative tests

.github/workflows/update-cargo-toml-version.yml

@@ -24,7 +24,7 @@ jobs:
           sudo rm -rf "/usr/share/dotnet" || true
           sudo rm -rf "/usr/local/lib/android" || true
           sudo rm -rf "/usr/local/share/boost" || true
-      - uses: dtolnay/rust-toolchain@1.89
+      - uses: dtolnay/rust-toolchain@1.91.1
       - name: Install sd
         run: cargo install sd
       - name: Update Cargo.toml file

crates/dump/src/reader/v2/settings.rs

@@ -107,19 +107,14 @@ impl Settings<Unchecked> {
     }
 }
 
-#[derive(Debug, Clone, PartialEq)]
+#[derive(Default, Debug, Clone, PartialEq)]
 pub enum Setting<T> {
     Set(T),
     Reset,
+    #[default]
     NotSet,
 }
 
-impl<T> Default for Setting<T> {
-    fn default() -> Self {
-        Self::NotSet
-    }
-}
-
 impl<T> Setting<T> {
     pub const fn is_not_set(&self) -> bool {
         matches!(self, Self::NotSet)

crates/dump/src/reader/v3/settings.rs

@@ -161,19 +161,14 @@ pub struct Facets {
     pub min_level_size: Option<NonZeroUsize>,
 }
 
-#[derive(Debug, Clone, PartialEq, Eq)]
+#[derive(Default, Debug, Clone, PartialEq, Eq)]
 pub enum Setting<T> {
     Set(T),
     Reset,
+    #[default]
     NotSet,
 }
 
-impl<T> Default for Setting<T> {
-    fn default() -> Self {
-        Self::NotSet
-    }
-}
-
 impl<T> Setting<T> {
     pub fn map<U, F>(self, f: F) -> Setting<U>
     where

crates/dump/src/reader/v4/meta.rs

@@ -1,9 +1,7 @@
 use std::fmt::{self, Display, Formatter};
-use std::marker::PhantomData;
 use std::str::FromStr;
 
-use serde::de::Visitor;
-use serde::{Deserialize, Deserializer};
+use serde::Deserialize;
 use uuid::Uuid;
 
 use super::settings::{Settings, Unchecked};
@@ -82,59 +80,3 @@ impl Display for IndexUidFormatError {
 }
 
 impl std::error::Error for IndexUidFormatError {}
-
-/// A type that tries to match either a star (*) or
-/// any other thing that implements `FromStr`.
-#[derive(Debug)]
-#[cfg_attr(test, derive(serde::Serialize))]
-pub enum StarOr<T> {
-    Star,
-    Other(T),
-}
-
-impl<'de, T, E> Deserialize<'de> for StarOr<T>
-where
-    T: FromStr<Err = E>,
-    E: Display,
-{
-    fn deserialize<D>(deserializer: D) -> Result<Self, D::Error>
-    where
-        D: Deserializer<'de>,
-    {
-        /// Serde can't differentiate between `StarOr::Star` and `StarOr::Other` without a tag.
-        /// Simply using `#[serde(untagged)]` + `#[serde(rename="*")]` will lead to attempting to
-        /// deserialize everything as a `StarOr::Other`, including "*".
-        /// [`#[serde(other)]`](https://serde.rs/variant-attrs.html#other) might have helped but is
-        /// not supported on untagged enums.
-        struct StarOrVisitor<T>(PhantomData<T>);
-
-        impl<T, FE> Visitor<'_> for StarOrVisitor<T>
-        where
-            T: FromStr<Err = FE>,
-            FE: Display,
-        {
-            type Value = StarOr<T>;
-
-            fn expecting(&self, formatter: &mut Formatter) -> std::fmt::Result {
-                formatter.write_str("a string")
-            }
-
-            fn visit_str<SE>(self, v: &str) -> Result<Self::Value, SE>
-            where
-                SE: serde::de::Error,
-            {
-                match v {
-                    "*" => Ok(StarOr::Star),
-                    v => {
-                        let other = FromStr::from_str(v).map_err(|e: T::Err| {
-                            SE::custom(format!("Invalid `other` value: {}", e))
-                        })?;
-                        Ok(StarOr::Other(other))
-                    }
-                }
-            }
-        }
-
-        deserializer.deserialize_str(StarOrVisitor(PhantomData))
-    }
-}

crates/dump/src/reader/v4/settings.rs

@@ -192,19 +192,14 @@ pub struct Facets {
     pub min_level_size: Option<NonZeroUsize>,
 }
 
-#[derive(Debug, Clone, PartialEq, Eq, Copy)]
+#[derive(Default, Debug, Clone, PartialEq, Eq, Copy)]
 pub enum Setting<T> {
     Set(T),
     Reset,
+    #[default]
     NotSet,
 }
 
-impl<T> Default for Setting<T> {
-    fn default() -> Self {
-        Self::NotSet
-    }
-}
-
 impl<T> Setting<T> {
     pub fn set(self) -> Option<T> {
         match self {

crates/dump/src/reader/v5/settings.rs

@@ -47,20 +47,15 @@ pub struct Settings<T> {
     pub _kind: PhantomData<T>,
 }
 
-#[derive(Debug, Clone, PartialEq, Eq, Copy)]
+#[derive(Default, Debug, Clone, PartialEq, Eq, Copy)]
 #[cfg_attr(test, derive(serde::Serialize))]
 pub enum Setting<T> {
     Set(T),
     Reset,
+    #[default]
     NotSet,
 }
 
-impl<T> Default for Setting<T> {
-    fn default() -> Self {
-        Self::NotSet
-    }
-}
-
 impl<T> Setting<T> {
     pub fn set(self) -> Option<T> {
         match self {

crates/dump/src/reader/v5/tasks.rs

@@ -322,7 +322,7 @@ impl From<Task> for TaskView {
             _ => None,
         });
 
-        let duration = finished_at.zip(started_at).map(|(tf, ts)| (tf - ts));
+        let duration = finished_at.zip(started_at).map(|(tf, ts)| tf - ts);
 
         Self {
             uid: id,

crates/fuzzers/src/bin/fuzz-indexing.rs

@@ -113,9 +113,9 @@ fn main() {
 
                             for op in &operations {
                                 match op {
-                                    Either::Left(documents) => {
-                                        indexer.replace_documents(documents).unwrap()
-                                    }
+                                    Either::Left(documents) => indexer
+                                        .replace_documents(documents, Default::default())
+                                        .unwrap(),
                                     Either::Right(ids) => indexer.delete_documents(ids),
                                 }
                             }

crates/index-scheduler/src/dump.rs

@@ -164,6 +164,7 @@ impl<'a> Dump<'a> {
                     content_file: content_uuid.ok_or(Error::CorruptedDump)?,
                     documents_count,
                     allow_index_creation,
+                    on_missing_document: Default::default(),
                 },
                 KindDump::DocumentDeletion { documents_ids } => KindWithContent::DocumentDeletion {
                     documents_ids,

crates/index-scheduler/src/scheduler/autobatcher_test.rs

@@ -40,6 +40,7 @@ fn doc_imp(
         content_file: Uuid::new_v4(),
         documents_count: 0,
         allow_index_creation,
+        on_missing_document: Default::default(),
     }
 }
 

crates/index-scheduler/src/scheduler/create_batch.rs

@@ -2,7 +2,7 @@ use std::fmt;
 use std::io::ErrorKind;
 
 use meilisearch_types::heed::RoTxn;
-use meilisearch_types::milli::update::IndexDocumentsMethod;
+use meilisearch_types::milli::update::{IndexDocumentsMethod, MissingDocumentPolicy};
 use meilisearch_types::settings::{Settings, Unchecked};
 use meilisearch_types::tasks::{BatchStopReason, Kind, KindWithContent, Status, Task};
 use roaring::RoaringBitmap;
@@ -63,8 +63,8 @@ pub(crate) enum Batch {
 
 #[derive(Debug)]
 pub(crate) enum DocumentOperation {
-    Replace(Uuid),
-    Update(Uuid),
+    Replace { content_file: Uuid, on_missing_document: MissingDocumentPolicy },
+    Update { content_file: Uuid, on_missing_document: MissingDocumentPolicy },
     Delete(Vec<String>),
 }
 
@@ -293,13 +293,22 @@ impl IndexScheduler {
                 for task in tasks.iter() {
                     match task.kind {
                         KindWithContent::DocumentAdditionOrUpdate {
-                            content_file, method, ..
+                            content_file,
+                            method,
+                            on_missing_document,
+                            ..
                         } => match method {
                             IndexDocumentsMethod::ReplaceDocuments => {
-                                operations.push(DocumentOperation::Replace(content_file))
+                                operations.push(DocumentOperation::Replace {
+                                    content_file,
+                                    on_missing_document,
+                                })
                             }
                             IndexDocumentsMethod::UpdateDocuments => {
-                                operations.push(DocumentOperation::Update(content_file))
+                                operations.push(DocumentOperation::Update {
+                                    content_file,
+                                    on_missing_document,
+                                })
                             }
                             _ => unreachable!("Unknown document merging method"),
                         },

crates/index-scheduler/src/scheduler/process_index_operation.rs

@@ -77,8 +77,8 @@ impl IndexScheduler {
                 let mut content_files = Vec::new();
                 for operation in &operations {
                     match operation {
-                        DocumentOperation::Replace(content_uuid)
-                        | DocumentOperation::Update(content_uuid) => {
+                        DocumentOperation::Replace { content_file: content_uuid, .. }
+                        | DocumentOperation::Update { content_file: content_uuid, .. } => {
                             let content_file = self.queue.file_store.get_update(*content_uuid)?;
                             let mmap = unsafe { memmap2::Mmap::map(&content_file)? };
                             content_files.push(mmap);
@@ -100,16 +100,16 @@ impl IndexScheduler {
                 let embedders = self.embedders(index_uid.clone(), embedders)?;
                 for operation in operations {
                     match operation {
-                        DocumentOperation::Replace(_content_uuid) => {
+                        DocumentOperation::Replace { content_file: _, on_missing_document } => {
                             let mmap = content_files_iter.next().unwrap();
                             indexer
-                                .replace_documents(mmap)
+                                .replace_documents(mmap, on_missing_document)
                                 .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
                         }
-                        DocumentOperation::Update(_content_uuid) => {
+                        DocumentOperation::Update { content_file: _, on_missing_document } => {
                             let mmap = content_files_iter.next().unwrap();
                             indexer
-                                .update_documents(mmap)
+                                .update_documents(mmap, on_missing_document)
                                 .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
                         }
                         DocumentOperation::Delete(document_ids) => {

crates/index-scheduler/src/scheduler/test.rs

@@ -294,6 +294,7 @@ fn document_addition_and_index_deletion() {
                 content_file: uuid,
                 documents_count,
                 allow_index_creation: true,
+                on_missing_document: Default::default(),
             },
             None,
             false,
@@ -482,6 +483,7 @@ fn document_addition_and_index_deletion_on_unexisting_index() {
                 content_file: uuid,
                 documents_count,
                 allow_index_creation: true,
+                on_missing_document: Default::default(),
             },
             None,
             false,

crates/index-scheduler/src/scheduler/test_document_addition.rs

@@ -31,6 +31,7 @@ fn document_addition() {
                 content_file: uuid,
                 documents_count,
                 allow_index_creation: true,
+                on_missing_document: Default::default(),
             },
             None,
             false,
@@ -67,6 +68,7 @@ fn document_addition_and_document_deletion() {
                 content_file: uuid,
                 documents_count,
                 allow_index_creation: true,
+                on_missing_document: Default::default(),
             },
             None,
             false,
@@ -133,6 +135,7 @@ fn document_deletion_and_document_addition() {
                 content_file: uuid,
                 documents_count,
                 allow_index_creation: true,
+                on_missing_document: Default::default(),
             },
             None,
             false,
@@ -185,6 +188,7 @@ fn test_document_replace() {
                     content_file: uuid,
                     documents_count,
                     allow_index_creation: true,
+                    on_missing_document: Default::default(),
                 },
                 None,
                 false,
@@ -236,6 +240,7 @@ fn test_document_update() {
                     content_file: uuid,
                     documents_count,
                     allow_index_creation: true,
+                    on_missing_document: Default::default(),
                 },
                 None,
                 false,
@@ -289,6 +294,7 @@ fn test_mixed_document_addition() {
                     content_file: uuid,
                     documents_count,
                     allow_index_creation: true,
+                    on_missing_document: Default::default(),
                 },
                 None,
                 false,
@@ -340,6 +346,7 @@ fn test_document_replace_without_autobatching() {
                     content_file: uuid,
                     documents_count,
                     allow_index_creation: true,
+                    on_missing_document: Default::default(),
                 },
                 None,
                 false,
@@ -395,6 +402,7 @@ fn test_document_update_without_autobatching() {
                     content_file: uuid,
                     documents_count,
                     allow_index_creation: true,
+                    on_missing_document: Default::default(),
                 },
                 None,
                 false,
@@ -454,6 +462,7 @@ fn test_document_addition_cant_create_index_without_index() {
                     content_file: uuid,
                     documents_count,
                     allow_index_creation: false,
+                    on_missing_document: Default::default(),
                 },
                 None,
                 false,
@@ -506,6 +515,7 @@ fn test_document_addition_cant_create_index_without_index_without_autobatching()
                     content_file: uuid,
                     documents_count,
                     allow_index_creation: false,
+                    on_missing_document: Default::default(),
                 },
                 None,
                 false,
@@ -568,6 +578,7 @@ fn test_document_addition_cant_create_index_with_index() {
                     content_file: uuid,
                     documents_count,
                     allow_index_creation: false,
+                    on_missing_document: Default::default(),
                 },
                 None,
                 false,
@@ -635,6 +646,7 @@ fn test_document_addition_cant_create_index_with_index_without_autobatching() {
                     content_file: uuid,
                     documents_count,
                     allow_index_creation: false,
+                    on_missing_document: Default::default(),
                 },
                 None,
                 false,
@@ -707,6 +719,7 @@ fn test_document_addition_mixed_rights_with_index() {
                     content_file: uuid,
                     documents_count,
                     allow_index_creation,
+                    on_missing_document: Default::default(),
                 },
                 None,
                 false,
@@ -764,6 +777,7 @@ fn test_document_addition_mixed_right_without_index_starts_with_cant_create() {
                     content_file: uuid,
                     documents_count,
                     allow_index_creation,
+                    on_missing_document: Default::default(),
                 },
                 None,
                 false,
@@ -820,6 +834,7 @@ fn test_document_addition_with_multiple_primary_key() {
                     content_file: uuid,
                     documents_count,
                     allow_index_creation: true,
+                    on_missing_document: Default::default(),
                 },
                 None,
                 false,
@@ -883,6 +898,7 @@ fn test_document_addition_with_multiple_primary_key_batch_wrong_key() {
                     content_file: uuid,
                     documents_count,
                     allow_index_creation: true,
+                    on_missing_document: Default::default(),
                 },
                 None,
                 false,
@@ -943,6 +959,7 @@ fn test_document_addition_with_bad_primary_key() {
                     content_file: uuid,
                     documents_count,
                     allow_index_creation: true,
+                    on_missing_document: Default::default(),
                 },
                 None,
                 false,
@@ -1029,6 +1046,7 @@ fn test_document_addition_with_set_and_null_primary_key() {
                     content_file: uuid,
                     documents_count,
                     allow_index_creation: true,
+                    on_missing_document: Default::default(),
                 },
                 None,
                 false,
@@ -1104,6 +1122,7 @@ fn test_document_addition_with_set_and_null_primary_key_inference_works() {
                     content_file: uuid,
                     documents_count,
                     allow_index_creation: true,
+                    on_missing_document: Default::default(),
                 },
                 None,
                 false,

crates/index-scheduler/src/scheduler/test_embedders.rs

@@ -173,6 +173,7 @@ fn import_vectors() {
                 content_file: uuid,
                 documents_count,
                 allow_index_creation: true,
+                on_missing_document: Default::default(),
             },
             None,
             false,
@@ -263,6 +264,7 @@ fn import_vectors() {
                 content_file: uuid,
                 documents_count,
                 allow_index_creation: true,
+                on_missing_document: Default::default(),
             },
             None,
             false,
@@ -399,6 +401,7 @@ fn import_vectors_first_and_embedder_later() {
                 content_file: uuid,
                 documents_count,
                 allow_index_creation: true,
+                on_missing_document: Default::default(),
             },
             None,
             false,
@@ -539,6 +542,7 @@ fn import_vectors_first_and_embedder_later() {
                 content_file: uuid,
                 documents_count,
                 allow_index_creation: true,
+                on_missing_document: Default::default(),
             },
             None,
             false,
@@ -640,6 +644,7 @@ fn delete_document_containing_vector() {
                 content_file: uuid,
                 documents_count,
                 allow_index_creation: false,
+                on_missing_document: Default::default(),
             },
             None,
             false,
@@ -818,6 +823,7 @@ fn delete_embedder_with_user_provided_vectors() {
                 content_file: uuid,
                 documents_count,
                 allow_index_creation: false,
+                on_missing_document: Default::default(),
             },
             None,
             false,

crates/index-scheduler/src/scheduler/test_failure.rs

@@ -52,6 +52,7 @@ fn fail_in_process_batch_for_document_addition() {
                 content_file: uuid,
                 documents_count,
                 allow_index_creation: true,
+                on_missing_document: Default::default(),
             },
             None,
             false,
@@ -94,6 +95,7 @@ fn fail_in_update_task_after_process_batch_success_for_document_addition() {
                 content_file: uuid,
                 documents_count,
                 allow_index_creation: true,
+                on_missing_document: Default::default(),
             },
             None,
             false,
@@ -160,6 +162,7 @@ fn fail_in_process_batch_for_document_deletion() {
                 content_file: uuid,
                 documents_count,
                 allow_index_creation: true,
+                on_missing_document: Default::default(),
             },
             None,
             false,

crates/index-scheduler/src/test_utils.rs

@@ -197,6 +197,7 @@ pub(crate) fn replace_document_import_task(
         content_file: Uuid::from_u128(content_file_uuid),
         documents_count,
         allow_index_creation: true,
+        on_missing_document: Default::default(),
     }
 }
 

crates/meilisearch-types/src/error.rs

@@ -255,6 +255,7 @@ InvalidIndexLimit                              , InvalidRequest       , BAD_REQU
 InvalidIndexOffset                             , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexPrimaryKey                         , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexCustomMetadata                     , InvalidRequest       , BAD_REQUEST ;
+InvalidSkipCreation                            , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexUid                                , InvalidRequest       , BAD_REQUEST ;
 InvalidMultiSearchFacets                       , InvalidRequest       , BAD_REQUEST ;
 InvalidMultiSearchFacetsByIndex                , InvalidRequest       , BAD_REQUEST ;

crates/meilisearch-types/src/tasks.rs

@@ -5,7 +5,7 @@ use std::str::FromStr;
 
 use byte_unit::Byte;
 use enum_iterator::Sequence;
-use milli::update::IndexDocumentsMethod;
+use milli::update::{IndexDocumentsMethod, MissingDocumentPolicy};
 use milli::Object;
 use roaring::RoaringBitmap;
 use serde::{Deserialize, Serialize, Serializer};
@@ -114,6 +114,7 @@ pub enum KindWithContent {
         content_file: Uuid,
         documents_count: u64,
         allow_index_creation: bool,
+        on_missing_document: MissingDocumentPolicy,
     },
     DocumentDeletion {
         index_uid: String,

crates/meilisearch/src/analytics/segment_analytics.rs

@@ -1,7 +1,7 @@
 use std::any::TypeId;
 use std::collections::{HashMap, HashSet};
 use std::fs;
-use std::path::{Path, PathBuf};
+use std::path::Path;
 use std::sync::Arc;
 use std::time::{Duration, Instant};
 
@@ -344,14 +344,14 @@ impl Infos {
             experimental_no_edition_2024_for_dumps,
             experimental_vector_store_setting: vector_store_setting,
             gpu_enabled: meilisearch_types::milli::vector::is_cuda_enabled(),
-            db_path: db_path != PathBuf::from("./data.ms"),
+            db_path: db_path != Path::new("./data.ms"),
             import_dump: import_dump.is_some(),
-            dump_dir: dump_dir != PathBuf::from("dumps/"),
+            dump_dir: dump_dir != Path::new("dumps/"),
             ignore_missing_dump,
             ignore_dump_if_db_exists,
             import_snapshot: import_snapshot.is_some(),
             schedule_snapshot,
-            snapshot_dir: snapshot_dir != PathBuf::from("snapshots/"),
+            snapshot_dir: snapshot_dir != Path::new("snapshots/"),
             uses_s3_snapshots: s3_snapshot_options.is_some(),
             ignore_missing_snapshot,
             ignore_snapshot_if_db_exists,

crates/meilisearch/src/lib.rs

@@ -629,7 +629,7 @@ fn import_dump(
 
             let mmap = unsafe { memmap2::Mmap::map(index_reader.documents_file())? };
 
-            indexer.replace_documents(&mmap)?;
+            indexer.replace_documents(&mmap, Default::default())?;
 
             let indexer_config = index_scheduler.indexer_config();
             let pool = &indexer_config.thread_pool;

crates/meilisearch/src/routes/indexes/documents.rs

@@ -20,7 +20,7 @@ use meilisearch_types::heed::RoTxn;
 use meilisearch_types::index_uid::IndexUid;
 use meilisearch_types::milli::documents::sort::recursive_sort;
 use meilisearch_types::milli::index::EmbeddingsWithMetadata;
-use meilisearch_types::milli::update::IndexDocumentsMethod;
+use meilisearch_types::milli::update::{IndexDocumentsMethod, MissingDocumentPolicy};
 use meilisearch_types::milli::vector::parsed_vectors::ExplicitVectors;
 use meilisearch_types::milli::{AscDesc, DocumentId};
 use meilisearch_types::serde_cs::vec::CS;
@@ -687,6 +687,11 @@ pub struct UpdateDocumentsQuery {
     #[param(example = "custom")]
     #[deserr(default, error = DeserrQueryParamError<InvalidIndexCustomMetadata>)]
     pub custom_metadata: Option<String>,
+
+    #[param(example = "true")]
+    #[deserr(default, try_from(&String) = from_string_skip_creation -> DeserrQueryParamError<InvalidSkipCreation>, error = DeserrQueryParamError<InvalidSkipCreation>)]
+    /// Only update documents if they already exist.
+    pub skip_creation: Option<bool>,
 }
 
 #[derive(Deserialize, Debug, Deserr, IntoParams)]
@@ -711,6 +716,23 @@ fn from_char_csv_delimiter(
     }
 }
 
+fn from_string_skip_creation(
+    s: &String,
+) -> Result<Option<bool>, DeserrQueryParamError<InvalidSkipCreation>> {
+    if s.eq_ignore_ascii_case("true") {
+        return Ok(Some(true));
+    }
+
+    if s.eq_ignore_ascii_case("false") {
+        return Ok(Some(false));
+    }
+
+    Err(DeserrQueryParamError::new(
+        format!("skipCreation must be either `true` or `false`. Found: `{}`", s),
+        Code::InvalidSkipCreation,
+    ))
+}
+
 aggregate_methods!(
     Replaced => "Documents Added",
     Updated => "Documents Updated",
@@ -840,6 +862,7 @@ pub async fn replace_documents(
         params.custom_metadata,
         dry_run,
         allow_index_creation,
+        params.skip_creation,
         &req,
     )
     .await?;
@@ -943,6 +966,7 @@ pub async fn update_documents(
         params.custom_metadata,
         dry_run,
         allow_index_creation,
+        params.skip_creation,
         &req,
     )
     .await?;
@@ -963,6 +987,7 @@ async fn document_addition(
     custom_metadata: Option<String>,
     dry_run: bool,
     allow_index_creation: bool,
+    skip_creation: Option<bool>,
     req: &HttpRequest,
 ) -> Result<SummarizedTaskView, MeilisearchHttpError> {
     let mime_type = extract_mime_type(req)?;
@@ -1083,6 +1108,11 @@ async fn document_addition(
         primary_key,
         allow_index_creation,
         index_uid: index_uid.to_string(),
+        on_missing_document: if matches!(skip_creation, Some(true)) {
+            MissingDocumentPolicy::Skip
+        } else {
+            MissingDocumentPolicy::Create
+        },
     };
 
     let scheduler = index_scheduler.clone();

crates/meilisearch/src/search/mod.rs

@@ -789,11 +789,12 @@ impl TryFrom<Value> for ExternalDocumentId {
     }
 }
 
-#[derive(Debug, Copy, Clone, PartialEq, Eq, Deserr, ToSchema, Serialize)]
+#[derive(Default, Debug, Copy, Clone, PartialEq, Eq, Deserr, ToSchema, Serialize)]
 #[deserr(rename_all = camelCase)]
 #[serde(rename_all = "camelCase")]
 pub enum MatchingStrategy {
     /// Remove query words from last to first
+    #[default]
     Last,
     /// All query words are mandatory
     All,
@@ -801,12 +802,6 @@ pub enum MatchingStrategy {
     Frequency,
 }
 
-impl Default for MatchingStrategy {
-    fn default() -> Self {
-        Self::Last
-    }
-}
-
 impl From<MatchingStrategy> for TermsMatchingStrategy {
     fn from(other: MatchingStrategy) -> Self {
         match other {

crates/meilisearch/tests/auth/tenant_token.rs

@@ -187,7 +187,7 @@ macro_rules! compute_forbidden_search {
 
 #[actix_rt::test]
 async fn search_authorized_simple_token() {
-    let tenant_tokens = vec![
+    let tenant_tokens = [
         hashmap! {
             "searchRules" => json!({"*": {}}),
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
@@ -239,7 +239,7 @@ async fn search_authorized_simple_token() {
 
 #[actix_rt::test]
 async fn search_authorized_filter_token() {
-    let tenant_tokens = vec![
+    let tenant_tokens = [
         hashmap! {
             "searchRules" => json!({"*": {"filter": "color = blue"}}),
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
@@ -292,7 +292,7 @@ async fn search_authorized_filter_token() {
 
 #[actix_rt::test]
 async fn filter_search_authorized_filter_token() {
-    let tenant_tokens = vec![
+    let tenant_tokens = [
         hashmap! {
             "searchRules" => json!({"*": {"filter": "color = blue"}}),
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
@@ -353,7 +353,7 @@ async fn filter_search_authorized_filter_token() {
 /// Tests that those Tenant Token are incompatible with the REFUSED_KEYS defined above.
 #[actix_rt::test]
 async fn error_search_token_forbidden_parent_key() {
-    let tenant_tokens = vec![
+    let tenant_tokens = [
         hashmap! {
             "searchRules" => json!({"*": {}}),
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
@@ -389,7 +389,7 @@ async fn error_search_token_forbidden_parent_key() {
 
 #[actix_rt::test]
 async fn error_search_forbidden_token() {
-    let tenant_tokens = vec![
+    let tenant_tokens = [
         // bad index
         hashmap! {
             "searchRules" => json!({"products": {}}),

crates/meilisearch/tests/auth/tenant_token_multi_search.rs

@@ -680,7 +680,7 @@ async fn multi_search_authorized_simple_token() {
 
 #[actix_rt::test]
 async fn single_search_authorized_filter_token() {
-    let tenant_tokens = vec![
+    let tenant_tokens = [
         hashmap! {
             "searchRules" => json!({"*": {"filter": "color = blue"}}),
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
@@ -733,7 +733,7 @@ async fn single_search_authorized_filter_token() {
 
 #[actix_rt::test]
 async fn multi_search_authorized_filter_token() {
-    let both_tenant_tokens = vec![
+    let both_tenant_tokens = [
         hashmap! {
             "searchRules" => json!({"sales": {"filter": "color = blue"}, "products": {"filter": "doggos.age <= 5"}}),
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
@@ -842,7 +842,7 @@ async fn filter_single_search_authorized_filter_token() {
 
 #[actix_rt::test]
 async fn filter_multi_search_authorized_filter_token() {
-    let tenant_tokens = vec![
+    let tenant_tokens = [
         hashmap! {
             "searchRules" => json!({"sales": {"filter": "color = blue"}, "products": {"filter": "doggos.age <= 5"}}),
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
@@ -900,7 +900,7 @@ async fn filter_multi_search_authorized_filter_token() {
 /// Tests that those Tenant Token are incompatible with the REFUSED_KEYS defined above.
 #[actix_rt::test]
 async fn error_single_search_token_forbidden_parent_key() {
-    let tenant_tokens = vec![
+    let tenant_tokens = [
         hashmap! {
             "searchRules" => json!({"*": {}}),
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())
@@ -941,7 +941,7 @@ async fn error_single_search_token_forbidden_parent_key() {
 /// Tests that those Tenant Token are incompatible with the REFUSED_KEYS defined above.
 #[actix_rt::test]
 async fn error_multi_search_token_forbidden_parent_key() {
-    let tenant_tokens = vec![
+    let tenant_tokens = [
         hashmap! {
             "searchRules" => json!({"*": {}}),
             "exp" => json!((OffsetDateTime::now_utc() + Duration::hours(1)).unix_timestamp())

crates/milli/src/search/mod.rs

@@ -385,9 +385,10 @@ pub struct SearchResult {
     pub query_vector: Option<Embedding>,
 }
 
-#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+#[derive(Default, Debug, Clone, Copy, PartialEq, Eq)]
 pub enum TermsMatchingStrategy {
     // remove last word first
+    #[default]
     Last,
     // all words are mandatory
     All,
@@ -395,12 +396,6 @@ pub enum TermsMatchingStrategy {
     Frequency,
 }
 
-impl Default for TermsMatchingStrategy {
-    fn default() -> Self {
-        Self::Last
-    }
-}
-
 impl From<MatchingStrategy> for TermsMatchingStrategy {
     fn from(other: MatchingStrategy) -> Self {
         match other {

crates/milli/src/search/new/tests/integration.rs

@@ -64,7 +64,7 @@ pub fn setup_search_index_with_criteria(criteria: &[Criterion]) -> Index {
     let payload = unsafe { memmap2::Mmap::map(&file).unwrap() };
 
     // index documents
-    indexer.replace_documents(&payload).unwrap();
+    indexer.replace_documents(&payload, Default::default()).unwrap();
 
     let indexer_alloc = Bump::new();
     let (document_changes, operation_stats, primary_key) = indexer

crates/milli/src/test_index.rs

@@ -70,9 +70,11 @@ impl TempIndex {
         let mut indexer = indexer::DocumentOperation::new();
         match self.index_documents_config.update_method {
             IndexDocumentsMethod::ReplaceDocuments => {
-                indexer.replace_documents(&documents).unwrap()
+                indexer.replace_documents(&documents, Default::default()).unwrap()
+            }
+            IndexDocumentsMethod::UpdateDocuments => {
+                indexer.update_documents(&documents, Default::default()).unwrap()
             }
-            IndexDocumentsMethod::UpdateDocuments => indexer.update_documents(&documents).unwrap(),
         }
 
         let indexer_alloc = Bump::new();
@@ -232,7 +234,7 @@ fn aborting_indexation() {
         { "id": 2, "name": "bob", "age": 20 },
         { "id": 2, "name": "bob", "age": 20 },
     ]);
-    indexer.replace_documents(&payload).unwrap();
+    indexer.replace_documents(&payload, Default::default()).unwrap();
 
     let indexer_alloc = Bump::new();
     let (document_changes, _operation_stats, primary_key) = indexer

crates/milli/src/update/index_documents/helpers/grenad_helpers.rs

@@ -124,7 +124,7 @@ impl GrenadParameters {
     /// This should be called inside of a rayon thread pool,
     /// otherwise, it will take the global number of threads.
     pub fn max_memory_by_thread(&self) -> Option<usize> {
-        self.max_memory.map(|max_memory| (max_memory / rayon::current_num_threads()))
+        self.max_memory.map(|max_memory| max_memory / rayon::current_num_threads())
     }
 }
 

crates/milli/src/update/index_documents/mod.rs

@@ -54,11 +54,12 @@ pub struct DocumentAdditionResult {
     pub number_of_documents: u64,
 }
 
-#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash, Serialize, Deserialize)]
+#[derive(Default, Debug, Clone, Copy, PartialEq, Eq, Hash, Serialize, Deserialize)]
 #[non_exhaustive]
 pub enum IndexDocumentsMethod {
     /// Replace the previous document with the new one,
     /// removing all the already known attributes.
+    #[default]
     ReplaceDocuments,
 
     /// Merge the previous version of the document with the new version,
@@ -66,10 +67,19 @@ pub enum IndexDocumentsMethod {
     UpdateDocuments,
 }
 
-impl Default for IndexDocumentsMethod {
-    fn default() -> Self {
-        Self::ReplaceDocuments
-    }
+/// Controls whether new documents should be created when they don't already exist.
+///
+/// This policy is checked when processing a document whose ID is not found in the index.
+/// It applies to both update and replace operations.
+#[derive(Default, Debug, Clone, Copy, PartialEq, Eq, Hash, Serialize, Deserialize)]
+pub enum MissingDocumentPolicy {
+    /// Create the document if it doesn't exist. This is the default behavior.
+    #[default]
+    Create,
+
+    /// Skip the document silently if it doesn't exist. No error is returned, the document is simply
+    /// not indexed.
+    Skip,
 }
 
 pub struct IndexDocuments<'t, 'i, 'a, FP, FA> {
@@ -1976,10 +1986,10 @@ mod tests {
         let mut new_fields_ids_map = db_fields_ids_map.clone();
 
         let mut indexer = indexer::DocumentOperation::new();
-        indexer.replace_documents(&doc1).unwrap();
-        indexer.replace_documents(&doc2).unwrap();
-        indexer.replace_documents(&doc3).unwrap();
-        indexer.replace_documents(&doc4).unwrap();
+        indexer.replace_documents(&doc1, Default::default()).unwrap();
+        indexer.replace_documents(&doc2, Default::default()).unwrap();
+        indexer.replace_documents(&doc3, Default::default()).unwrap();
+        indexer.replace_documents(&doc4, Default::default()).unwrap();
 
         let indexer_alloc = Bump::new();
         let (_document_changes, operation_stats, _primary_key) = indexer
@@ -2029,10 +2039,10 @@ mod tests {
         let mut new_fields_ids_map = db_fields_ids_map.clone();
 
         let mut indexer = indexer::DocumentOperation::new();
-        indexer.replace_documents(&doc1).unwrap();
-        indexer.update_documents(&doc2).unwrap();
-        indexer.update_documents(&doc3).unwrap();
-        indexer.update_documents(&doc4).unwrap();
+        indexer.replace_documents(&doc1, Default::default()).unwrap();
+        indexer.update_documents(&doc2, Default::default()).unwrap();
+        indexer.update_documents(&doc3, Default::default()).unwrap();
+        indexer.update_documents(&doc4, Default::default()).unwrap();
 
         let indexer_alloc = Bump::new();
         let (document_changes, operation_stats, primary_key) = indexer
@@ -2117,11 +2127,11 @@ mod tests {
         let mut new_fields_ids_map = db_fields_ids_map.clone();
 
         let mut indexer = indexer::DocumentOperation::new();
-        indexer.replace_documents(&doc1).unwrap();
-        indexer.update_documents(&doc2).unwrap();
-        indexer.update_documents(&doc3).unwrap();
-        indexer.replace_documents(&doc4).unwrap();
-        indexer.update_documents(&doc5).unwrap();
+        indexer.replace_documents(&doc1, Default::default()).unwrap();
+        indexer.update_documents(&doc2, Default::default()).unwrap();
+        indexer.update_documents(&doc3, Default::default()).unwrap();
+        indexer.replace_documents(&doc4, Default::default()).unwrap();
+        indexer.update_documents(&doc5, Default::default()).unwrap();
 
         let indexer_alloc = Bump::new();
         let (document_changes, operation_stats, primary_key) = indexer
@@ -2312,7 +2322,7 @@ mod tests {
         let indexer_alloc = Bump::new();
         let embedders = RuntimeEmbedders::default();
         let mut indexer = indexer::DocumentOperation::new();
-        indexer.replace_documents(&documents).unwrap();
+        indexer.replace_documents(&documents, Default::default()).unwrap();
         indexer.delete_documents(&["2"]);
         let (document_changes, _operation_stats, primary_key) = indexer
             .into_changes(
@@ -2367,13 +2377,13 @@ mod tests {
             { "id": 3, "name": "jean", "age": 25 },
         ]);
         let mut indexer = indexer::DocumentOperation::new();
-        indexer.update_documents(&documents).unwrap();
+        indexer.update_documents(&documents, Default::default()).unwrap();
 
         let documents = documents!([
             { "id": 2, "catto": "jorts" },
             { "id": 3, "legs": 4 },
         ]);
-        indexer.update_documents(&documents).unwrap();
+        indexer.update_documents(&documents, Default::default()).unwrap();
         indexer.delete_documents(&["1", "2"]);
 
         let indexer_alloc = Bump::new();
@@ -2431,7 +2441,7 @@ mod tests {
         let indexer_alloc = Bump::new();
         let embedders = RuntimeEmbedders::default();
         let mut indexer = indexer::DocumentOperation::new();
-        indexer.update_documents(&documents).unwrap();
+        indexer.update_documents(&documents, Default::default()).unwrap();
 
         let (document_changes, _operation_stats, primary_key) = indexer
             .into_changes(
@@ -2484,7 +2494,7 @@ mod tests {
         let indexer_alloc = Bump::new();
         let embedders = RuntimeEmbedders::default();
         let mut indexer = indexer::DocumentOperation::new();
-        indexer.update_documents(&documents).unwrap();
+        indexer.update_documents(&documents, Default::default()).unwrap();
         indexer.delete_documents(&["1", "2"]);
 
         let (document_changes, _operation_stats, primary_key) = indexer
@@ -2541,7 +2551,7 @@ mod tests {
             { "id": 2, "doggo": { "name": "jean", "age": 20 } },
             { "id": 3, "name": "bob", "age": 25 },
         ]);
-        indexer.update_documents(&documents).unwrap();
+        indexer.update_documents(&documents, Default::default()).unwrap();
 
         let (document_changes, _operation_stats, primary_key) = indexer
             .into_changes(
@@ -2600,7 +2610,7 @@ mod tests {
             { "id": 2, "doggo": { "name": "jean", "age": 20 } },
             { "id": 3, "name": "bob", "age": 25 },
         ]);
-        indexer.update_documents(&documents).unwrap();
+        indexer.update_documents(&documents, Default::default()).unwrap();
 
         indexer.delete_documents(&["1", "2", "1", "2"]);
 
@@ -2656,7 +2666,7 @@ mod tests {
         let documents = documents!([
             { "id": 1, "doggo": "kevin" },
         ]);
-        indexer.update_documents(&documents).unwrap();
+        indexer.update_documents(&documents, Default::default()).unwrap();
 
         let (document_changes, _operation_stats, primary_key) = indexer
             .into_changes(
@@ -2710,7 +2720,7 @@ mod tests {
             { "id": 1, "catto": "jorts" },
         ]);
 
-        indexer.replace_documents(&documents).unwrap();
+        indexer.replace_documents(&documents, Default::default()).unwrap();
 
         let (document_changes, _operation_stats, primary_key) = indexer
             .into_changes(
@@ -2921,7 +2931,7 @@ mod tests {
         let documents = documents!([
             { "id": 1, "doggo": "bernese" },
         ]);
-        indexer.replace_documents(&documents).unwrap();
+        indexer.replace_documents(&documents, Default::default()).unwrap();
 
         // FINISHING
         let (document_changes, _operation_stats, primary_key) = indexer
@@ -2983,7 +2993,7 @@ mod tests {
         let documents = documents!([
             { "id": 0, "catto": "jorts" },
         ]);
-        indexer.replace_documents(&documents).unwrap();
+        indexer.replace_documents(&documents, Default::default()).unwrap();
 
         let (document_changes, _operation_stats, primary_key) = indexer
             .into_changes(
@@ -3041,7 +3051,7 @@ mod tests {
         let documents = documents!([
             { "id": 1, "catto": "jorts" },
         ]);
-        indexer.replace_documents(&documents).unwrap();
+        indexer.replace_documents(&documents, Default::default()).unwrap();
 
         let (document_changes, _operation_stats, primary_key) = indexer
             .into_changes(

crates/milli/src/update/new/indexer/document_operation.rs

@@ -21,7 +21,7 @@ use crate::update::new::indexer::current_edition::sharding::Shards;
 use crate::update::new::steps::IndexingStep;
 use crate::update::new::thread_local::MostlySend;
 use crate::update::new::{DocumentIdentifiers, Insertion, Update};
-use crate::update::{AvailableIds, IndexDocumentsMethod};
+use crate::update::{AvailableIds, IndexDocumentsMethod, MissingDocumentPolicy};
 use crate::{DocumentId, Error, FieldsIdsMap, Index, InternalError, Result, UserError};
 
 #[derive(Default)]
@@ -37,20 +37,28 @@ impl<'pl> DocumentOperation<'pl> {
     /// Append a replacement of documents.
     ///
     /// The payload is expected to be in the NDJSON format
-    pub fn replace_documents(&mut self, payload: &'pl Mmap) -> Result<()> {
+    pub fn replace_documents(
+        &mut self,
+        payload: &'pl Mmap,
+        on_missing_document: MissingDocumentPolicy,
+    ) -> Result<()> {
         #[cfg(unix)]
         payload.advise(memmap2::Advice::Sequential)?;
-        self.operations.push(Payload::Replace(&payload[..]));
+        self.operations.push(Payload::Replace { payload: &payload[..], on_missing_document });
         Ok(())
     }
 
     /// Append an update of documents.
     ///
     /// The payload is expected to be in the NDJSON format
-    pub fn update_documents(&mut self, payload: &'pl Mmap) -> Result<()> {
+    pub fn update_documents(
+        &mut self,
+        payload: &'pl Mmap,
+        on_missing_document: MissingDocumentPolicy,
+    ) -> Result<()> {
         #[cfg(unix)]
         payload.advise(memmap2::Advice::Sequential)?;
-        self.operations.push(Payload::Update(&payload[..]));
+        self.operations.push(Payload::Update { payload: &payload[..], on_missing_document });
         Ok(())
     }
 
@@ -98,34 +106,40 @@ impl<'pl> DocumentOperation<'pl> {
 
             let mut bytes = 0;
             let result = match operation {
-                Payload::Replace(payload) => extract_addition_payload_changes(
-                    indexer,
-                    index,
-                    rtxn,
-                    primary_key_from_op,
-                    &mut primary_key,
-                    new_fields_ids_map,
-                    &mut available_docids,
-                    &mut bytes,
-                    &docids_version_offsets,
-                    IndexDocumentsMethod::ReplaceDocuments,
-                    shards,
-                    payload,
-                ),
-                Payload::Update(payload) => extract_addition_payload_changes(
-                    indexer,
-                    index,
-                    rtxn,
-                    primary_key_from_op,
-                    &mut primary_key,
-                    new_fields_ids_map,
-                    &mut available_docids,
-                    &mut bytes,
-                    &docids_version_offsets,
-                    IndexDocumentsMethod::UpdateDocuments,
-                    shards,
-                    payload,
-                ),
+                Payload::Replace { payload, on_missing_document } => {
+                    extract_addition_payload_changes(
+                        indexer,
+                        index,
+                        rtxn,
+                        primary_key_from_op,
+                        &mut primary_key,
+                        new_fields_ids_map,
+                        &mut available_docids,
+                        &mut bytes,
+                        &docids_version_offsets,
+                        IndexDocumentsMethod::ReplaceDocuments,
+                        shards,
+                        payload,
+                        on_missing_document,
+                    )
+                }
+                Payload::Update { payload, on_missing_document } => {
+                    extract_addition_payload_changes(
+                        indexer,
+                        index,
+                        rtxn,
+                        primary_key_from_op,
+                        &mut primary_key,
+                        new_fields_ids_map,
+                        &mut available_docids,
+                        &mut bytes,
+                        &docids_version_offsets,
+                        IndexDocumentsMethod::UpdateDocuments,
+                        shards,
+                        payload,
+                        on_missing_document,
+                    )
+                }
                 Payload::Deletion(to_delete) => extract_deletion_payload_changes(
                     index,
                     rtxn,
@@ -180,6 +194,7 @@ fn extract_addition_payload_changes<'r, 'pl: 'r>(
     method: IndexDocumentsMethod,
     shards: Option<&Shards>,
     payload: &'pl [u8],
+    on_missing_document: MissingDocumentPolicy,
 ) -> Result<hashbrown::HashMap<&'pl str, PayloadOperations<'pl>>> {
     use IndexDocumentsMethod::{ReplaceDocuments, UpdateDocuments};
 
@@ -271,6 +286,10 @@ fn extract_addition_payload_changes<'r, 'pl: 'r>(
 
                             match method {
                                 ReplaceDocuments => {
+                                    if matches!(on_missing_document, MissingDocumentPolicy::Skip) {
+                                        continue;
+                                    }
+
                                     entry.insert(PayloadOperations::new_replacement(
                                         docid,
                                         true, // is new
@@ -278,6 +297,10 @@ fn extract_addition_payload_changes<'r, 'pl: 'r>(
                                     ));
                                 }
                                 UpdateDocuments => {
+                                    if matches!(on_missing_document, MissingDocumentPolicy::Skip) {
+                                        continue;
+                                    }
+
                                     entry.insert(PayloadOperations::new_update(
                                         docid,
                                         true, // is new
@@ -297,6 +320,12 @@ fn extract_addition_payload_changes<'r, 'pl: 'r>(
                 },
                 Entry::Vacant(entry) => match method {
                     ReplaceDocuments => {
+                        if payload_operations.is_new
+                            && matches!(on_missing_document, MissingDocumentPolicy::Skip)
+                        {
+                            continue;
+                        }
+
                         entry.insert(PayloadOperations::new_replacement(
                             payload_operations.docid,
                             payload_operations.is_new,
@@ -304,6 +333,12 @@ fn extract_addition_payload_changes<'r, 'pl: 'r>(
                         ));
                     }
                     UpdateDocuments => {
+                        if payload_operations.is_new
+                            && matches!(on_missing_document, MissingDocumentPolicy::Skip)
+                        {
+                            continue;
+                        }
+
                         entry.insert(PayloadOperations::new_update(
                             payload_operations.docid,
                             payload_operations.is_new,
@@ -448,8 +483,8 @@ pub struct DocumentOperationChanges<'pl> {
 }
 
 pub enum Payload<'pl> {
-    Replace(&'pl [u8]),
-    Update(&'pl [u8]),
+    Replace { payload: &'pl [u8], on_missing_document: MissingDocumentPolicy },
+    Update { payload: &'pl [u8], on_missing_document: MissingDocumentPolicy },
     Deletion(&'pl [&'pl str]),
 }
 

crates/milli/src/update/settings.rs

@@ -48,10 +48,11 @@ use crate::{
     ChannelCongestion, FieldId, FilterableAttributesRule, Index, LocalizedAttributesRule, Result,
 };
 
-#[derive(Debug, Clone, PartialEq, Eq, Copy)]
+#[derive(Default, Debug, Clone, PartialEq, Eq, Copy)]
 pub enum Setting<T> {
     Set(T),
     Reset,
+    #[default]
     NotSet,
 }
 
@@ -71,12 +72,6 @@ where
     }
 }
 
-impl<T> Default for Setting<T> {
-    fn default() -> Self {
-        Self::NotSet
-    }
-}
-
 impl<T> Setting<T> {
     pub fn set(self) -> Option<T> {
         match self {

crates/milli/src/vector/embeddings.rs

@@ -67,7 +67,7 @@ impl<F> Embeddings<F> {
     ///
     /// If `embeddings.len() % self.dimension != 0`, then the append operation fails.
     pub fn append(&mut self, mut embeddings: Vec<F>) -> Result<(), Vec<F>> {
-        if embeddings.len() % self.dimension != 0 {
+        if !embeddings.len().is_multiple_of(self.dimension) {
             return Err(embeddings);
         }
         self.data.append(&mut embeddings);

crates/milli/tests/search/facet_distribution.rs

@@ -47,7 +47,7 @@ fn test_facet_distribution_with_no_facet_values() {
     let documents = mmap_from_objects(vec![doc1, doc2]);
 
     // index documents
-    indexer.replace_documents(&documents).unwrap();
+    indexer.replace_documents(&documents, Default::default()).unwrap();
 
     let indexer_alloc = Bump::new();
     let (document_changes, _operation_stats, primary_key) = indexer

crates/milli/tests/search/mod.rs

@@ -85,7 +85,7 @@ pub fn setup_search_index_with_criteria(criteria: &[Criterion]) -> Index {
     let payload = unsafe { memmap2::Mmap::map(&file).unwrap() };
 
     // index documents
-    indexer.replace_documents(&payload).unwrap();
+    indexer.replace_documents(&payload, Default::default()).unwrap();
 
     let indexer_alloc = Bump::new();
     let (document_changes, operation_stats, primary_key) = indexer

crates/milli/tests/search/query_criteria.rs

@@ -319,7 +319,7 @@ fn criteria_ascdesc() {
     file.sync_all().unwrap();
 
     let payload = unsafe { memmap2::Mmap::map(&file).unwrap() };
-    indexer.replace_documents(&payload).unwrap();
+    indexer.replace_documents(&payload, Default::default()).unwrap();
     let (document_changes, _operation_stats, primary_key) = indexer
         .into_changes(
             &indexer_alloc,

crates/milli/tests/search/typo_tolerance.rs

@@ -126,7 +126,7 @@ fn test_typo_disabled_on_word() {
     let embedders = RuntimeEmbedders::default();
     let mut indexer = indexer::DocumentOperation::new();
 
-    indexer.replace_documents(&documents).unwrap();
+    indexer.replace_documents(&documents, Default::default()).unwrap();
 
     let indexer_alloc = Bump::new();
     let (document_changes, _operation_stats, primary_key) = indexer

crates/xtask/src/common/instance/release.rs

@@ -178,6 +178,7 @@ pub fn get_arch() -> anyhow::Result<&'static str> {
     #[cfg(not(all(target_os = "linux", target_arch = "aarch64")))]
     #[cfg(not(all(target_os = "linux", target_arch = "x86_64")))]
     #[cfg(not(all(target_os = "macos", target_arch = "aarch64")))]
+    #[cfg(not(all(target_os = "macos", target_arch = "x86_64")))]
     anyhow::bail!("unsupported platform")
 }
 

rust-toolchain.toml

@@ -1,3 +1,3 @@
 [toolchain]
-channel = "1.89.0"
+channel = "1.91.1"
 components = ["clippy"]