Merge branch 'main' into cellulite

crates/benchmarks/Cargo.toml

@@ -14,7 +14,7 @@ license.workspace = true
 anyhow = "1.0.98"
 bumpalo = "3.18.1"
 csv = "1.3.1"
-memmap2 = "0.9.5"
+memmap2 = "0.9.7"
 milli = { path = "../milli" }
 mimalloc = { version = "0.1.47", default-features = false }
 serde_json = { version = "1.0.140", features = ["preserve_order"] }
@@ -51,3 +51,11 @@ harness = false
 [[bench]]
 name = "indexing"
 harness = false
+
+[[bench]]
+name = "sort"
+harness = false
+
+[[bench]]
+name = "filter_starts_with"
+harness = false

crates/benchmarks/benches/filter_starts_with.rs

@@ -0,0 +1,66 @@
+mod datasets_paths;
+mod utils;
+
+use criterion::{criterion_group, criterion_main};
+use milli::update::Settings;
+use milli::FilterableAttributesRule;
+use utils::Conf;
+
+#[cfg(not(windows))]
+#[global_allocator]
+static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;
+
+fn base_conf(builder: &mut Settings) {
+    let displayed_fields = ["geonameid", "name"].iter().map(|s| s.to_string()).collect();
+    builder.set_displayed_fields(displayed_fields);
+
+    let filterable_fields =
+        ["name"].iter().map(|s| FilterableAttributesRule::Field(s.to_string())).collect();
+    builder.set_filterable_fields(filterable_fields);
+}
+
+#[rustfmt::skip]
+const BASE_CONF: Conf = Conf {
+    dataset: datasets_paths::SMOL_ALL_COUNTRIES,
+    dataset_format: "jsonl",
+    queries: &[
+        "",
+    ],
+    configure: base_conf,
+    primary_key: Some("geonameid"),
+    ..Conf::BASE
+};
+
+fn filter_starts_with(c: &mut criterion::Criterion) {
+    #[rustfmt::skip]
+    let confs = &[
+        utils::Conf {
+            group_name: "1 letter",
+            filter: Some("name STARTS WITH e"),
+            ..BASE_CONF
+        },
+
+        utils::Conf {
+            group_name: "2 letters",
+            filter: Some("name STARTS WITH es"),
+            ..BASE_CONF
+        },
+
+        utils::Conf {
+            group_name: "3 letters",
+            filter: Some("name STARTS WITH est"),
+            ..BASE_CONF
+        },
+
+        utils::Conf {
+            group_name: "6 letters",
+            filter: Some("name STARTS WITH estoni"),
+            ..BASE_CONF
+        }
+    ];
+
+    utils::run_benches(c, confs);
+}
+
+criterion_group!(benches, filter_starts_with);
+criterion_main!(benches);

crates/benchmarks/benches/sort.rs

@@ -0,0 +1,114 @@
+//! This benchmark module is used to compare the performance of sorting documents in /search VS /documents
+//!
+//! The tests/benchmarks were designed in the context of a query returning only 20 documents.
+
+mod datasets_paths;
+mod utils;
+
+use criterion::{criterion_group, criterion_main};
+use milli::update::Settings;
+use utils::Conf;
+
+#[cfg(not(windows))]
+#[global_allocator]
+static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;
+
+fn base_conf(builder: &mut Settings) {
+    let displayed_fields =
+        ["geonameid", "name", "asciiname", "alternatenames", "_geo", "population"]
+            .iter()
+            .map(|s| s.to_string())
+            .collect();
+    builder.set_displayed_fields(displayed_fields);
+
+    let sortable_fields =
+        ["_geo", "name", "population", "elevation", "timezone", "modification-date"]
+            .iter()
+            .map(|s| s.to_string())
+            .collect();
+    builder.set_sortable_fields(sortable_fields);
+}
+
+#[rustfmt::skip]
+const BASE_CONF: Conf = Conf {
+    dataset: datasets_paths::SMOL_ALL_COUNTRIES,
+    dataset_format: "jsonl",
+    configure: base_conf,
+    primary_key: Some("geonameid"),
+    queries: &[""],
+    offsets: &[
+        Some((0, 20)), // The most common query in the real world
+        Some((0, 500)), // A query that ranges over many documents
+        Some((980, 20)), // The worst query that could happen in the real world
+        Some((800_000, 20)) // The worst query
+    ],
+    get_documents: true,
+    ..Conf::BASE
+};
+
+fn bench_sort(c: &mut criterion::Criterion) {
+    #[rustfmt::skip]
+    let confs = &[
+        utils::Conf {
+            group_name: "without sort",
+            sort: None,
+            ..BASE_CONF
+        },
+
+        utils::Conf {
+            group_name: "sort on many different values",
+            sort: Some(vec!["name:asc"]),
+            ..BASE_CONF
+        },
+
+        utils::Conf {
+            group_name: "sort on many similar values",
+            sort: Some(vec!["timezone:desc"]),
+            ..BASE_CONF
+        },
+
+        utils::Conf {
+            group_name: "sort on many similar then different values",
+            sort: Some(vec!["timezone:desc", "name:asc"]),
+            ..BASE_CONF
+        },
+
+        utils::Conf {
+            group_name: "sort on many different then similar values",
+            sort: Some(vec!["timezone:desc", "name:asc"]),
+            ..BASE_CONF
+        },
+
+        utils::Conf {
+            group_name: "geo sort",
+            sample_size: Some(10),
+            sort: Some(vec!["_geoPoint(45.4777599, 9.1967508):asc"]),
+            ..BASE_CONF
+        },
+
+        utils::Conf {
+            group_name: "sort on many similar values then geo sort",
+            sample_size: Some(50),
+            sort: Some(vec!["timezone:desc", "_geoPoint(45.4777599, 9.1967508):asc"]),
+            ..BASE_CONF
+        },
+
+        utils::Conf {
+            group_name: "sort on many different values then geo sort",
+            sample_size: Some(50),
+            sort: Some(vec!["name:desc", "_geoPoint(45.4777599, 9.1967508):asc"]),
+            ..BASE_CONF
+        },
+
+        utils::Conf {
+            group_name: "sort on many fields",
+            sort: Some(vec!["population:asc", "name:asc", "elevation:asc", "timezone:asc"]),
+            ..BASE_CONF
+        },
+    ];
+
+    utils::run_benches(c, confs);
+}
+
+criterion_group!(benches, bench_sort);
+criterion_main!(benches);

crates/benchmarks/benches/utils.rs

@@ -9,6 +9,7 @@ use anyhow::Context;
 use bumpalo::Bump;
 use criterion::BenchmarkId;
 use memmap2::Mmap;
+use milli::documents::sort::recursive_sort;
 use milli::heed::EnvOpenOptions;
 use milli::progress::Progress;
 use milli::update::new::indexer;
@@ -35,6 +36,12 @@ pub struct Conf<'a> {
     pub configure: fn(&mut Settings),
     pub filter: Option<&'a str>,
     pub sort: Option<Vec<&'a str>>,
+    /// set to skip documents (offset, limit)
+    pub offsets: &'a [Option<(usize, usize)>],
+    /// enable if you want to bench getting documents without querying
+    pub get_documents: bool,
+    /// configure the benchmark sample size
+    pub sample_size: Option<usize>,
     /// enable or disable the optional words on the query
     pub optional_words: bool,
     /// primary key, if there is None we'll auto-generate docids for every documents
@@ -52,6 +59,9 @@ impl Conf<'_> {
         configure: |_| (),
         filter: None,
         sort: None,
+        offsets: &[None],
+        get_documents: false,
+        sample_size: None,
         optional_words: true,
         primary_key: None,
     };
@@ -145,25 +155,79 @@ pub fn run_benches(c: &mut criterion::Criterion, confs: &[Conf]) {
         let file_name = Path::new(conf.dataset).file_name().and_then(|f| f.to_str()).unwrap();
         let name = format!("{}: {}", file_name, conf.group_name);
         let mut group = c.benchmark_group(&name);
+        if let Some(sample_size) = conf.sample_size {
+            group.sample_size(sample_size);
+        }
 
         for &query in conf.queries {
-            group.bench_with_input(BenchmarkId::from_parameter(query), &query, |b, &query| {
-                b.iter(|| {
-                    let rtxn = index.read_txn().unwrap();
-                    let mut search = index.search(&rtxn);
-                    search.query(query).terms_matching_strategy(TermsMatchingStrategy::default());
-                    if let Some(filter) = conf.filter {
-                        let filter = Filter::from_str(filter).unwrap().unwrap();
-                        search.filter(filter);
-                    }
-                    if let Some(sort) = &conf.sort {
-                        let sort = sort.iter().map(|sort| sort.parse().unwrap()).collect();
-                        search.sort_criteria(sort);
-                    }
-                    let _ids = search.execute().unwrap();
-                });
-            });
+            for offset in conf.offsets {
+                let parameter = match offset {
+                    None => query.to_string(),
+                    Some((offset, limit)) => format!("{query}[{offset}:{limit}]"),
+                };
+                group.bench_with_input(
+                    BenchmarkId::from_parameter(parameter),
+                    &query,
+                    |b, &query| {
+                        b.iter(|| {
+                            let rtxn = index.read_txn().unwrap();
+                            let mut search = index.search(&rtxn);
+                            search
+                                .query(query)
+                                .terms_matching_strategy(TermsMatchingStrategy::default());
+                            if let Some(filter) = conf.filter {
+                                let filter = Filter::from_str(filter).unwrap().unwrap();
+                                search.filter(filter);
+                            }
+                            if let Some(sort) = &conf.sort {
+                                let sort = sort.iter().map(|sort| sort.parse().unwrap()).collect();
+                                search.sort_criteria(sort);
+                            }
+                            if let Some((offset, limit)) = offset {
+                                search.offset(*offset).limit(*limit);
+                            }
+
+                            let _ids = search.execute().unwrap();
+                        });
+                    },
+                );
+            }
         }
+
+        if conf.get_documents {
+            for offset in conf.offsets {
+                let parameter = match offset {
+                    None => String::from("get_documents"),
+                    Some((offset, limit)) => format!("get_documents[{offset}:{limit}]"),
+                };
+                group.bench_with_input(BenchmarkId::from_parameter(parameter), &(), |b, &()| {
+                    b.iter(|| {
+                        let rtxn = index.read_txn().unwrap();
+                        if let Some(sort) = &conf.sort {
+                            let sort = sort.iter().map(|sort| sort.parse().unwrap()).collect();
+                            let all_docs = index.documents_ids(&rtxn).unwrap();
+                            let facet_sort =
+                                recursive_sort(&index, &rtxn, sort, &all_docs).unwrap();
+                            let iter = facet_sort.iter().unwrap();
+                            if let Some((offset, limit)) = offset {
+                                let _results = iter.skip(*offset).take(*limit).collect::<Vec<_>>();
+                            } else {
+                                let _results = iter.collect::<Vec<_>>();
+                            }
+                        } else {
+                            let all_docs = index.documents_ids(&rtxn).unwrap();
+                            if let Some((offset, limit)) = offset {
+                                let _results =
+                                    all_docs.iter().skip(*offset).take(*limit).collect::<Vec<_>>();
+                            } else {
+                                let _results = all_docs.iter().collect::<Vec<_>>();
+                            }
+                        }
+                    });
+                });
+            }
+        }
+
         group.finish();
 
         index.prepare_for_closing().wait();

crates/dump/src/reader/compat/v1_to_v2.rs

@@ -1,3 +1,4 @@
+use std::fs::File;
 use std::str::FromStr;
 
 use super::v2_to_v3::CompatV2ToV3;
@@ -94,6 +95,10 @@ impl CompatIndexV1ToV2 {
         self.from.documents().map(|it| Box::new(it) as Box<dyn Iterator<Item = _>>)
     }
 
+    pub fn documents_file(&self) -> &File {
+        self.from.documents_file()
+    }
+
     pub fn settings(&mut self) -> Result<v2::settings::Settings<v2::settings::Checked>> {
         Ok(v2::settings::Settings::<v2::settings::Unchecked>::from(self.from.settings()?).check())
     }

crates/dump/src/reader/compat/v2_to_v3.rs

@@ -1,3 +1,4 @@
+use std::fs::File;
 use std::str::FromStr;
 
 use time::OffsetDateTime;
@@ -122,6 +123,13 @@ impl CompatIndexV2ToV3 {
         }
     }
 
+    pub fn documents_file(&self) -> &File {
+        match self {
+            CompatIndexV2ToV3::V2(v2) => v2.documents_file(),
+            CompatIndexV2ToV3::Compat(compat) => compat.documents_file(),
+        }
+    }
+
     pub fn settings(&mut self) -> Result<v3::Settings<v3::Checked>> {
         let settings = match self {
             CompatIndexV2ToV3::V2(from) => from.settings()?,

crates/dump/src/reader/compat/v3_to_v4.rs

@@ -1,3 +1,5 @@
+use std::fs::File;
+
 use super::v2_to_v3::{CompatIndexV2ToV3, CompatV2ToV3};
 use super::v4_to_v5::CompatV4ToV5;
 use crate::reader::{v3, v4, UpdateFile};
@@ -252,6 +254,13 @@ impl CompatIndexV3ToV4 {
         }
     }
 
+    pub fn documents_file(&self) -> &File {
+        match self {
+            CompatIndexV3ToV4::V3(v3) => v3.documents_file(),
+            CompatIndexV3ToV4::Compat(compat) => compat.documents_file(),
+        }
+    }
+
     pub fn settings(&mut self) -> Result<v4::Settings<v4::Checked>> {
         Ok(match self {
             CompatIndexV3ToV4::V3(v3) => {

crates/dump/src/reader/compat/v4_to_v5.rs

@@ -1,3 +1,5 @@
+use std::fs::File;
+
 use super::v3_to_v4::{CompatIndexV3ToV4, CompatV3ToV4};
 use super::v5_to_v6::CompatV5ToV6;
 use crate::reader::{v4, v5, Document};
@@ -241,6 +243,13 @@ impl CompatIndexV4ToV5 {
         }
     }
 
+    pub fn documents_file(&self) -> &File {
+        match self {
+            CompatIndexV4ToV5::V4(v4) => v4.documents_file(),
+            CompatIndexV4ToV5::Compat(compat) => compat.documents_file(),
+        }
+    }
+
     pub fn settings(&mut self) -> Result<v5::Settings<v5::Checked>> {
         match self {
             CompatIndexV4ToV5::V4(v4) => Ok(v5::Settings::from(v4.settings()?).check()),

crates/dump/src/reader/compat/v5_to_v6.rs

@@ -1,3 +1,4 @@
+use std::fs::File;
 use std::num::NonZeroUsize;
 use std::str::FromStr;
 
@@ -201,6 +202,10 @@ impl CompatV5ToV6 {
     pub fn network(&self) -> Result<Option<&v6::Network>> {
         Ok(None)
     }
+
+    pub fn webhooks(&self) -> Option<&v6::Webhooks> {
+        None
+    }
 }
 
 pub enum CompatIndexV5ToV6 {
@@ -243,6 +248,13 @@ impl CompatIndexV5ToV6 {
         }
     }
 
+    pub fn documents_file(&self) -> &File {
+        match self {
+            CompatIndexV5ToV6::V5(v5) => v5.documents_file(),
+            CompatIndexV5ToV6::Compat(compat) => compat.documents_file(),
+        }
+    }
+
     pub fn settings(&mut self) -> Result<v6::Settings<v6::Checked>> {
         match self {
             CompatIndexV5ToV6::V5(v5) => Ok(v6::Settings::from(v5.settings()?).check()),

crates/dump/src/reader/mod.rs

@@ -138,6 +138,13 @@ impl DumpReader {
             DumpReader::Compat(compat) => compat.network(),
         }
     }
+
+    pub fn webhooks(&self) -> Option<&v6::Webhooks> {
+        match self {
+            DumpReader::Current(current) => current.webhooks(),
+            DumpReader::Compat(compat) => compat.webhooks(),
+        }
+    }
 }
 
 impl From<V6Reader> for DumpReader {
@@ -192,6 +199,14 @@ impl DumpIndexReader {
         }
     }
 
+    /// A reference to a file in the NDJSON format containing all the documents of the index
+    pub fn documents_file(&self) -> &File {
+        match self {
+            DumpIndexReader::Current(v6) => v6.documents_file(),
+            DumpIndexReader::Compat(compat) => compat.documents_file(),
+        }
+    }
+
     pub fn settings(&mut self) -> Result<v6::Settings<v6::Checked>> {
         match self {
             DumpIndexReader::Current(v6) => v6.settings(),
@@ -357,6 +372,7 @@ pub(crate) mod test {
 
         assert_eq!(dump.features().unwrap().unwrap(), RuntimeTogglableFeatures::default());
         assert_eq!(dump.network().unwrap(), None);
+        assert_eq!(dump.webhooks(), None);
     }
 
     #[test]
@@ -427,6 +443,43 @@ pub(crate) mod test {
         insta::assert_snapshot!(network.remotes.get("ms-2").as_ref().unwrap().search_api_key.as_ref().unwrap(), @"foo");
     }
 
+    #[test]
+    fn import_dump_v6_webhooks() {
+        let dump = File::open("tests/assets/v6-with-webhooks.dump").unwrap();
+        let dump = DumpReader::open(dump).unwrap();
+
+        // top level infos
+        insta::assert_snapshot!(dump.date().unwrap(), @"2025-07-31 9:21:30.479544 +00:00:00");
+        insta::assert_debug_snapshot!(dump.instance_uid().unwrap(), @r"
+        Some(
+            cb887dcc-34b3-48d1-addd-9815ae721a81,
+        )
+        ");
+
+        // webhooks
+        let webhooks = dump.webhooks().unwrap();
+        insta::assert_json_snapshot!(webhooks, @r#"
+        {
+          "webhooks": {
+            "627ea538-733d-4545-8d2d-03526eb381ce": {
+              "url": "https://example.com/authorization-less",
+              "headers": {}
+            },
+            "771b0a28-ef28-4082-b984-536f82958c65": {
+              "url": "https://example.com/hook",
+              "headers": {
+                "authorization": "TOKEN"
+              }
+            },
+            "f3583083-f8a7-4cbf-a5e7-fb3f1e28a7e9": {
+              "url": "https://third.com",
+              "headers": {}
+            }
+          }
+        }
+        "#);
+    }
+
     #[test]
     fn import_dump_v5() {
         let dump = File::open("tests/assets/v5.dump").unwrap();

crates/dump/src/reader/v1/mod.rs

@@ -72,6 +72,10 @@ impl V1IndexReader {
             .map(|line| -> Result<_> { Ok(serde_json::from_str(&line?)?) }))
     }
 
+    pub fn documents_file(&self) -> &File {
+        self.documents.get_ref()
+    }
+
     pub fn settings(&mut self) -> Result<self::settings::Settings> {
         Ok(serde_json::from_reader(&mut self.settings)?)
     }

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

@@ -203,6 +203,10 @@ impl V2IndexReader {
             .map(|line| -> Result<_> { Ok(serde_json::from_str(&line?)?) }))
     }
 
+    pub fn documents_file(&self) -> &File {
+        self.documents.get_ref()
+    }
+
     pub fn settings(&mut self) -> Result<Settings<Checked>> {
         Ok(self.settings.clone())
     }

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

@@ -215,6 +215,10 @@ impl V3IndexReader {
             .map(|line| -> Result<_> { Ok(serde_json::from_str(&line?)?) }))
     }
 
+    pub fn documents_file(&self) -> &File {
+        self.documents.get_ref()
+    }
+
     pub fn settings(&mut self) -> Result<Settings<Checked>> {
         Ok(self.settings.clone())
     }

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

@@ -210,6 +210,10 @@ impl V4IndexReader {
             .map(|line| -> Result<_> { Ok(serde_json::from_str(&line?)?) }))
     }
 
+    pub fn documents_file(&self) -> &File {
+        self.documents.get_ref()
+    }
+
     pub fn settings(&mut self) -> Result<Settings<Checked>> {
         Ok(self.settings.clone())
     }

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

@@ -247,6 +247,10 @@ impl V5IndexReader {
             .map(|line| -> Result<_> { Ok(serde_json::from_str(&line?)?) }))
     }
 
+    pub fn documents_file(&self) -> &File {
+        self.documents.get_ref()
+    }
+
     pub fn settings(&mut self) -> Result<Settings<Checked>> {
         Ok(self.settings.clone())
     }

crates/dump/src/reader/v6/mod.rs

@@ -25,6 +25,7 @@ pub type Key = meilisearch_types::keys::Key;
 pub type ChatCompletionSettings = meilisearch_types::features::ChatCompletionSettings;
 pub type RuntimeTogglableFeatures = meilisearch_types::features::RuntimeTogglableFeatures;
 pub type Network = meilisearch_types::features::Network;
+pub type Webhooks = meilisearch_types::webhooks::WebhooksDumpView;
 
 // ===== Other types to clarify the code of the compat module
 // everything related to the tasks
@@ -59,6 +60,7 @@ pub struct V6Reader {
     keys: BufReader<File>,
     features: Option<RuntimeTogglableFeatures>,
     network: Option<Network>,
+    webhooks: Option<Webhooks>,
 }
 
 impl V6Reader {
@@ -93,8 +95,8 @@ impl V6Reader {
             Err(e) => return Err(e.into()),
         };
 
-        let network_file = match fs::read(dump.path().join("network.json")) {
-            Ok(network_file) => Some(network_file),
+        let network = match fs::read(dump.path().join("network.json")) {
+            Ok(network_file) => Some(serde_json::from_reader(&*network_file)?),
             Err(error) => match error.kind() {
                 // Allows the file to be missing, this will only result in all experimental features disabled.
                 ErrorKind::NotFound => {
@@ -104,10 +106,16 @@ impl V6Reader {
                 _ => return Err(error.into()),
             },
         };
-        let network = if let Some(network_file) = network_file {
-            Some(serde_json::from_reader(&*network_file)?)
-        } else {
-            None
+
+        let webhooks = match fs::read(dump.path().join("webhooks.json")) {
+            Ok(webhooks_file) => Some(serde_json::from_reader(&*webhooks_file)?),
+            Err(error) => match error.kind() {
+                ErrorKind::NotFound => {
+                    debug!("`webhooks.json` not found in dump");
+                    None
+                }
+                _ => return Err(error.into()),
+            },
         };
 
         Ok(V6Reader {
@@ -119,6 +127,7 @@ impl V6Reader {
             features,
             network,
             dump,
+            webhooks,
         })
     }
 
@@ -229,6 +238,10 @@ impl V6Reader {
     pub fn network(&self) -> Option<&Network> {
         self.network.as_ref()
     }
+
+    pub fn webhooks(&self) -> Option<&Webhooks> {
+        self.webhooks.as_ref()
+    }
 }
 
 pub struct UpdateFile {
@@ -284,6 +297,10 @@ impl V6IndexReader {
             .map(|line| -> Result<_> { Ok(serde_json::from_str(&line?)?) }))
     }
 
+    pub fn documents_file(&self) -> &File {
+        self.documents.get_ref()
+    }
+
     pub fn settings(&mut self) -> Result<Settings<Checked>> {
         let mut settings: Settings<Unchecked> = serde_json::from_reader(&mut self.settings)?;
         patch_embedders(&mut settings);

crates/dump/src/writer.rs

@@ -8,6 +8,7 @@ use meilisearch_types::batches::Batch;
 use meilisearch_types::features::{ChatCompletionSettings, Network, RuntimeTogglableFeatures};
 use meilisearch_types::keys::Key;
 use meilisearch_types::settings::{Checked, Settings};
+use meilisearch_types::webhooks::WebhooksDumpView;
 use serde_json::{Map, Value};
 use tempfile::TempDir;
 use time::OffsetDateTime;
@@ -74,6 +75,13 @@ impl DumpWriter {
         Ok(std::fs::write(self.dir.path().join("network.json"), serde_json::to_string(&network)?)?)
     }
 
+    pub fn create_webhooks(&self, webhooks: WebhooksDumpView) -> Result<()> {
+        Ok(std::fs::write(
+            self.dir.path().join("webhooks.json"),
+            serde_json::to_string(&webhooks)?,
+        )?)
+    }
+
     pub fn persist_to(self, mut writer: impl Write) -> Result<()> {
         let gz_encoder = GzEncoder::new(&mut writer, Compression::default());
         let mut tar_encoder = tar::Builder::new(gz_encoder);

crates/filter-parser/Cargo.toml

@@ -15,6 +15,7 @@ license.workspace = true
 nom = "7.1.3"
 nom_locate = "4.2.0"
 unescaper = "0.1.6"
+levenshtein_automata = { version = "0.2.1", features = ["fst_automaton"] }
 
 [dev-dependencies]
 # fixed version due to format breakages in v1.40

crates/filter-parser/src/condition.rs

@@ -7,11 +7,22 @@
 
 use nom::branch::alt;
 use nom::bytes::complete::tag;
+use nom::character::complete::char;
+use nom::character::complete::multispace0;
 use nom::character::complete::multispace1;
 use nom::combinator::cut;
+use nom::combinator::map;
+use nom::combinator::value;
+use nom::sequence::preceded;
 use nom::sequence::{terminated, tuple};
 use Condition::*;
 
+use crate::error::IResultExt;
+use crate::value::parse_vector_value;
+use crate::value::parse_vector_value_cut;
+use crate::Error;
+use crate::ErrorKind;
+use crate::VectorFilter;
 use crate::{parse_value, FilterCondition, IResult, Span, Token};
 
 #[derive(Debug, Clone, PartialEq, Eq)]
@@ -113,6 +124,83 @@ pub fn parse_not_exists(input: Span) -> IResult<FilterCondition> {
     Ok((input, FilterCondition::Not(Box::new(FilterCondition::Condition { fid: key, op: Exists }))))
 }
 
+fn parse_vectors(input: Span) -> IResult<(Token, Option<Token>, VectorFilter<'_>)> {
+    let (input, _) = multispace0(input)?;
+    let (input, fid) = tag("_vectors")(input)?;
+
+    if let Ok((input, _)) = multispace1::<_, crate::Error>(input) {
+        return Ok((input, (Token::from(fid), None, VectorFilter::None)));
+    }
+
+    let (input, _) = char('.')(input)?;
+
+    // From this point, we are certain this is a vector filter, so our errors must be final.
+    // We could use nom's `cut` but it's better to be explicit about the errors
+
+    if let Ok((_, space)) = tag::<_, _, ()>(" ")(input) {
+        return Err(crate::Error::failure_from_kind(space, ErrorKind::VectorFilterMissingEmbedder));
+    }
+
+    let (input, embedder_name) =
+        parse_vector_value_cut(input, ErrorKind::VectorFilterInvalidEmbedder)?;
+
+    let (input, filter) = alt((
+        map(
+            preceded(tag(".fragments"), |input| {
+                let (input, _) = tag(".")(input).map_cut(ErrorKind::VectorFilterMissingFragment)?;
+                parse_vector_value_cut(input, ErrorKind::VectorFilterInvalidFragment)
+            }),
+            VectorFilter::Fragment,
+        ),
+        value(VectorFilter::UserProvided, tag(".userProvided")),
+        value(VectorFilter::DocumentTemplate, tag(".documentTemplate")),
+        value(VectorFilter::Regenerate, tag(".regenerate")),
+        value(VectorFilter::None, nom::combinator::success("")),
+    ))(input)?;
+
+    if let Ok((input, point)) = tag::<_, _, ()>(".")(input) {
+        let opt_value = parse_vector_value(input).ok().map(|(_, v)| v);
+        let value =
+            opt_value.as_ref().map(|v| v.value().to_owned()).unwrap_or_else(|| point.to_string());
+        let context = opt_value.map(|v| v.original_span()).unwrap_or(point);
+        let previous_kind = match filter {
+            VectorFilter::Fragment(_) => Some("fragments"),
+            VectorFilter::DocumentTemplate => Some("documentTemplate"),
+            VectorFilter::UserProvided => Some("userProvided"),
+            VectorFilter::Regenerate => Some("regenerate"),
+            VectorFilter::None => None,
+        };
+        return Err(Error::failure_from_kind(
+            context,
+            ErrorKind::VectorFilterUnknownSuffix(previous_kind, value),
+        ));
+    }
+
+    let (input, _) = multispace1(input).map_cut(ErrorKind::VectorFilterLeftover)?;
+
+    Ok((input, (Token::from(fid), Some(embedder_name), filter)))
+}
+
+/// vectors_exists          = vectors ("EXISTS" | ("NOT" WS+ "EXISTS"))
+pub fn parse_vectors_exists(input: Span) -> IResult<FilterCondition> {
+    let (input, (fid, embedder, filter)) = parse_vectors(input)?;
+
+    // Try parsing "EXISTS" first
+    if let Ok((input, _)) = tag::<_, _, ()>("EXISTS")(input) {
+        return Ok((input, FilterCondition::VectorExists { fid, embedder, filter }));
+    }
+
+    // Try parsing "NOT EXISTS"
+    if let Ok((input, _)) = tuple::<_, _, (), _>((tag("NOT"), multispace1, tag("EXISTS")))(input) {
+        return Ok((
+            input,
+            FilterCondition::Not(Box::new(FilterCondition::VectorExists { fid, embedder, filter })),
+        ));
+    }
+
+    Err(crate::Error::failure_from_kind(input, ErrorKind::VectorFilterOperation))
+}
+
 /// contains        = value "CONTAINS" value
 pub fn parse_contains(input: Span) -> IResult<FilterCondition> {
     let (input, (fid, contains, value)) =

crates/filter-parser/src/error.rs

@@ -42,6 +42,23 @@ pub fn cut_with_err<'a, O>(
     }
 }
 
+pub trait IResultExt<'a> {
+    fn map_cut(self, kind: ErrorKind<'a>) -> Self;
+}
+
+impl<'a, T> IResultExt<'a> for IResult<'a, T> {
+    fn map_cut(self, kind: ErrorKind<'a>) -> Self {
+        self.map_err(move |e: nom::Err<Error<'a>>| {
+            let input = match e {
+                nom::Err::Incomplete(_) => return e,
+                nom::Err::Error(e) => *e.context(),
+                nom::Err::Failure(e) => *e.context(),
+            };
+            Error::failure_from_kind(input, kind)
+        })
+    }
+}
+
 #[derive(Debug)]
 pub struct Error<'a> {
     context: Span<'a>,
@@ -61,6 +78,14 @@ pub enum ErrorKind<'a> {
     GeoBoundingBox,
     MisusedGeoRadius,
     MisusedGeoBoundingBox,
+    VectorFilterLeftover,
+    VectorFilterInvalidQuotes,
+    VectorFilterMissingEmbedder,
+    VectorFilterInvalidEmbedder,
+    VectorFilterMissingFragment,
+    VectorFilterInvalidFragment,
+    VectorFilterUnknownSuffix(Option<&'static str>, String),
+    VectorFilterOperation,
     InvalidPrimary,
     InvalidEscapedNumber,
     ExpectedEof,
@@ -91,6 +116,10 @@ impl<'a> Error<'a> {
         Self { context, kind }
     }
 
+    pub fn failure_from_kind(context: Span<'a>, kind: ErrorKind<'a>) -> nom::Err<Self> {
+        nom::Err::Failure(Self::new_from_kind(context, kind))
+    }
+
     pub fn new_from_external(context: Span<'a>, error: impl std::error::Error) -> Self {
         Self::new_from_kind(context, ErrorKind::External(error.to_string()))
     }
@@ -128,6 +157,20 @@ impl Display for Error<'_> {
         // first line being the diagnostic and the second line being the incriminated filter.
         let escaped_input = input.escape_debug();
 
+        fn key_suggestion<'a>(key: &str, keys: &[&'a str]) -> Option<&'a str> {
+            let typos =
+                levenshtein_automata::LevenshteinAutomatonBuilder::new(2, true).build_dfa(key);
+            for key in keys.iter() {
+                match typos.eval(key) {
+                    levenshtein_automata::Distance::Exact(_) => {
+                        return Some(key);
+                    }
+                    levenshtein_automata::Distance::AtLeast(_) => continue,
+                }
+            }
+            None
+        }
+
         match &self.kind {
             ErrorKind::ExpectedValue(_) if input.trim().is_empty() => {
                 writeln!(f, "Was expecting a value but instead got nothing.")?
@@ -169,6 +212,44 @@ impl Display for Error<'_> {
             ErrorKind::MisusedGeoBoundingBox => {
                 writeln!(f, "The `_geoBoundingBox` filter is an operation and can't be used as a value.")?
             }
+            ErrorKind::VectorFilterLeftover => {
+                writeln!(f, "The vector filter has leftover tokens.")?
+            }
+            ErrorKind::VectorFilterUnknownSuffix(_, value) if value.as_str() == "." => {
+                writeln!(f, "Was expecting one of `.fragments`, `.userProvided`, `.documentTemplate`, `.regenerate` or nothing, but instead found a point without a valid value.")?;
+            }
+            ErrorKind::VectorFilterUnknownSuffix(None, value) if ["fragments", "userProvided", "documentTemplate", "regenerate"].contains(&value.as_str()) => {
+                // This will happen with "_vectors.rest.\"userProvided\"" for instance
+                writeln!(f, "Was expecting this part to be unquoted.")?
+            }
+            ErrorKind::VectorFilterUnknownSuffix(None, value) => {
+                if let Some(suggestion) = key_suggestion(value, &["fragments", "userProvided", "documentTemplate", "regenerate"]) {
+                    writeln!(f, "Was expecting one of `fragments`, `userProvided`, `documentTemplate`, `regenerate` or nothing, but instead found `{value}`. Did you mean `{suggestion}`?")?;
+                } else {
+                    writeln!(f, "Was expecting one of `fragments`, `userProvided`, `documentTemplate`, `regenerate` or nothing, but instead found `{value}`.")?;
+                }
+            }
+            ErrorKind::VectorFilterUnknownSuffix(Some(previous_filter_kind), value) => {
+                writeln!(f, "Vector filter can only accept one of `fragments`, `userProvided`, `documentTemplate` or `regenerate`, but found both `{previous_filter_kind}` and `{value}`.")?
+            },
+            ErrorKind::VectorFilterInvalidFragment => {
+                writeln!(f, "The vector filter's fragment name is invalid.")?
+            }
+            ErrorKind::VectorFilterMissingFragment => {
+                writeln!(f, "The vector filter is missing a fragment name.")?
+            }
+            ErrorKind::VectorFilterMissingEmbedder => {
+                writeln!(f, "Was expecting embedder name but found nothing.")?
+            }
+            ErrorKind::VectorFilterInvalidEmbedder => {
+                writeln!(f, "The vector filter's embedder name is invalid.")?
+            }
+            ErrorKind::VectorFilterOperation => {
+                writeln!(f, "Was expecting an operation like `EXISTS` or `NOT EXISTS` after the vector filter.")?
+            }
+            ErrorKind::VectorFilterInvalidQuotes => {
+                writeln!(f, "The quotes in one of the values are inconsistent.")?
+            }
             ErrorKind::ReservedKeyword(word) => {
                 writeln!(f, "`{word}` is a reserved keyword and thus cannot be used as a field name unless it is put inside quotes. Use \"{word}\" or \'{word}\' instead.")?
             }

crates/filter-parser/src/lib.rs

@@ -66,6 +66,9 @@ use nom_locate::LocatedSpan;
 pub(crate) use value::parse_value;
 use value::word_exact;
 
+use crate::condition::parse_vectors_exists;
+use crate::error::IResultExt;
+
 pub type Span<'a> = LocatedSpan<&'a str, &'a str>;
 
 type IResult<'a, Ret> = nom::IResult<Span<'a>, Ret, Error<'a>>;
@@ -137,6 +140,15 @@ impl<'a> From<&'a str> for Token<'a> {
     }
 }
 
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub enum VectorFilter<'a> {
+    Fragment(Token<'a>),
+    DocumentTemplate,
+    UserProvided,
+    Regenerate,
+    None,
+}
+
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub enum FilterCondition<'a> {
     Not(Box<Self>),
@@ -144,6 +156,7 @@ pub enum FilterCondition<'a> {
     In { fid: Token<'a>, els: Vec<Token<'a>> },
     Or(Vec<Self>),
     And(Vec<Self>),
+    VectorExists { fid: Token<'a>, embedder: Option<Token<'a>>, filter: VectorFilter<'a> },
     GeoLowerThan { point: [Token<'a>; 2], radius: Token<'a> },
     GeoBoundingBox { top_right_point: [Token<'a>; 2], bottom_left_point: [Token<'a>; 2] },
     GeoPolygon { points: Vec<[Token<'a>; 2]> },
@@ -167,18 +180,34 @@ impl<'a> FilterCondition<'a> {
                 | Condition::Exists
                 | Condition::LowerThan(_)
                 | Condition::LowerThanOrEqual(_)
-                | Condition::Between { .. } => None,
-                Condition::Contains { keyword, word: _ }
-                | Condition::StartsWith { keyword, word: _ } => Some(keyword),
+                | Condition::Between { .. }
+                | Condition::StartsWith { .. } => None,
+                Condition::Contains { keyword, word: _ } => Some(keyword),
             },
             FilterCondition::Not(this) => this.use_contains_operator(),
             FilterCondition::Or(seq) | FilterCondition::And(seq) => {
                 seq.iter().find_map(|filter| filter.use_contains_operator())
             }
+            FilterCondition::VectorExists { .. }
+            | FilterCondition::GeoLowerThan { .. }
+            | FilterCondition::GeoBoundingBox { .. }
+            | FilterCondition::GeoPolygon { .. }
+            | FilterCondition::In { .. } => None,
+        }
+    }
+
+    pub fn use_vector_filter(&self) -> Option<&Token> {
+        match self {
+            FilterCondition::Condition { .. } => None,
+            FilterCondition::Not(this) => this.use_vector_filter(),
+            FilterCondition::Or(seq) | FilterCondition::And(seq) => {
+                seq.iter().find_map(|filter| filter.use_vector_filter())
+            }
             FilterCondition::GeoLowerThan { .. }
             | FilterCondition::GeoBoundingBox { .. }
             | FilterCondition::GeoPolygon { .. }
             | FilterCondition::In { .. } => None,
+            FilterCondition::VectorExists { fid, .. } => Some(fid),
         }
     }
 
@@ -266,10 +295,7 @@ fn parse_in_body(input: Span) -> IResult<Vec<Token>> {
     let (input, _) = ws(word_exact("IN"))(input)?;
 
     // everything after `IN` can be a failure
-    let (input, _) =
-        cut_with_err(tag("["), |_| Error::new_from_kind(input, ErrorKind::InOpeningBracket))(
-            input,
-        )?;
+    let (input, _) = tag("[")(input).map_cut(ErrorKind::InOpeningBracket)?;
 
     let (input, content) = cut(parse_value_list)(input)?;
 
@@ -415,7 +441,7 @@ fn parse_geo_bounding_box(input: Span) -> IResult<FilterCondition> {
     let (input, args) = parsed?;
 
     if args.len() != 2 || args[0].len() != 2 || args[1].len() != 2 {
-        return Err(nom::Err::Failure(Error::new_from_kind(input, ErrorKind::GeoBoundingBox)));
+        return Err(Error::failure_from_kind(input, ErrorKind::GeoBoundingBox));
     }
 
     let res = FilterCondition::GeoBoundingBox {
@@ -468,7 +494,7 @@ fn parse_geo_point(input: Span) -> IResult<FilterCondition> {
     ))(input)
     .map_err(|e| e.map(|_| Error::new_from_kind(input, ErrorKind::ReservedGeo("_geoPoint"))))?;
     // if we succeeded we still return a `Failure` because geoPoints are not allowed
-    Err(nom::Err::Failure(Error::new_from_kind(input, ErrorKind::ReservedGeo("_geoPoint"))))
+    Err(Error::failure_from_kind(input, ErrorKind::ReservedGeo("_geoPoint")))
 }
 
 /// geoPoint      = WS* "_geoDistance(float WS* "," WS* float WS* "," WS* float)
@@ -482,7 +508,7 @@ fn parse_geo_distance(input: Span) -> IResult<FilterCondition> {
     ))(input)
     .map_err(|e| e.map(|_| Error::new_from_kind(input, ErrorKind::ReservedGeo("_geoDistance"))))?;
     // if we succeeded we still return a `Failure` because `geoDistance` filters are not allowed
-    Err(nom::Err::Failure(Error::new_from_kind(input, ErrorKind::ReservedGeo("_geoDistance"))))
+    Err(Error::failure_from_kind(input, ErrorKind::ReservedGeo("_geoDistance")))
 }
 
 /// geo      = WS* "_geo(float WS* "," WS* float WS* "," WS* float)
@@ -496,7 +522,7 @@ fn parse_geo(input: Span) -> IResult<FilterCondition> {
     ))(input)
     .map_err(|e| e.map(|_| Error::new_from_kind(input, ErrorKind::ReservedGeo("_geo"))))?;
     // if we succeeded we still return a `Failure` because `_geo` filter is not allowed
-    Err(nom::Err::Failure(Error::new_from_kind(input, ErrorKind::ReservedGeo("_geo"))))
+    Err(Error::failure_from_kind(input, ErrorKind::ReservedGeo("_geo")))
 }
 
 fn parse_error_reserved_keyword(input: Span) -> IResult<FilterCondition> {
@@ -535,8 +561,7 @@ fn parse_primary(input: Span, depth: usize) -> IResult<FilterCondition> {
         parse_is_not_null,
         parse_is_empty,
         parse_is_not_empty,
-        parse_exists,
-        parse_not_exists,
+        alt((parse_vectors_exists, parse_exists, parse_not_exists)),
         parse_to,
         parse_contains,
         parse_not_contains,
@@ -592,6 +617,22 @@ impl std::fmt::Display for FilterCondition<'_> {
                 }
                 write!(f, "]")
             }
+            FilterCondition::VectorExists { fid: _, embedder, filter: inner } => {
+                write!(f, "_vectors")?;
+                if let Some(embedder) = embedder {
+                    write!(f, ".{:?}", embedder.value())?;
+                }
+                match inner {
+                    VectorFilter::Fragment(fragment) => {
+                        write!(f, ".fragments.{:?}", fragment.value())?
+                    }
+                    VectorFilter::DocumentTemplate => write!(f, ".documentTemplate")?,
+                    VectorFilter::UserProvided => write!(f, ".userProvided")?,
+                    VectorFilter::Regenerate => write!(f, ".regenerate")?,
+                    VectorFilter::None => (),
+                }
+                write!(f, " EXISTS")
+            }
             FilterCondition::GeoLowerThan { point, radius } => {
                 write!(f, "_geoRadius({}, {}, {})", point[0], point[1], radius)
             }
@@ -672,6 +713,9 @@ pub mod tests {
         insta::assert_snapshot!(p(r"title = 'foo\\\\\\\\'"), @r#"{title} = {foo\\\\}"#);
         // but it also works with other sequences
         insta::assert_snapshot!(p(r#"title = 'foo\x20\n\t\"\'"'"#), @"{title} = {foo \n\t\"\'\"}");
+
+        insta::assert_snapshot!(p(r#"_vectors." valid.name  ".fragments."also.. valid! " EXISTS"#), @r#"_vectors." valid.name  ".fragments."also.. valid! " EXISTS"#);
+        insta::assert_snapshot!(p("_vectors.\"\n\t\r\\\"\" EXISTS"), @r#"_vectors."\n\t\r\"" EXISTS"#);
     }
 
     #[test]
@@ -734,6 +778,18 @@ pub mod tests {
         insta::assert_snapshot!(p("NOT subscribers IS NOT EMPTY"), @"{subscribers} IS EMPTY");
         insta::assert_snapshot!(p("subscribers  IS   NOT   EMPTY"), @"NOT ({subscribers} IS EMPTY)");
 
+        // Test _vectors EXISTS + _vectors NOT EXITS
+        insta::assert_snapshot!(p("_vectors EXISTS"), @"_vectors EXISTS");
+        insta::assert_snapshot!(p("_vectors.embedderName EXISTS"), @r#"_vectors."embedderName" EXISTS"#);
+        insta::assert_snapshot!(p("_vectors.embedderName.documentTemplate EXISTS"), @r#"_vectors."embedderName".documentTemplate EXISTS"#);
+        insta::assert_snapshot!(p("_vectors.embedderName.regenerate EXISTS"), @r#"_vectors."embedderName".regenerate EXISTS"#);
+        insta::assert_snapshot!(p("_vectors.embedderName.regenerate EXISTS"), @r#"_vectors."embedderName".regenerate EXISTS"#);
+        insta::assert_snapshot!(p("_vectors.embedderName.fragments.fragmentName EXISTS"), @r#"_vectors."embedderName".fragments."fragmentName" EXISTS"#);
+        insta::assert_snapshot!(p("  _vectors.embedderName.fragments.fragmentName   EXISTS"), @r#"_vectors."embedderName".fragments."fragmentName" EXISTS"#);
+        insta::assert_snapshot!(p("NOT _vectors EXISTS"), @"NOT (_vectors EXISTS)");
+        insta::assert_snapshot!(p(" NOT  _vectors   EXISTS"), @"NOT (_vectors EXISTS)");
+        insta::assert_snapshot!(p("  _vectors  NOT  EXISTS"), @"NOT (_vectors EXISTS)");
+
         // Test EXISTS + NOT EXITS
         insta::assert_snapshot!(p("subscribers EXISTS"), @"{subscribers} EXISTS");
         insta::assert_snapshot!(p("NOT subscribers EXISTS"), @"NOT ({subscribers} EXISTS)");
@@ -988,6 +1044,71 @@ pub mod tests {
         "###
         );
 
+        insta::assert_snapshot!(p(r#"_vectors _vectors EXISTS"#), @r"
+        Was expecting an operation like `EXISTS` or `NOT EXISTS` after the vector filter.
+        10:25 _vectors _vectors EXISTS
+        ");
+        insta::assert_snapshot!(p(r#"_vectors. embedderName EXISTS"#), @r"
+        Was expecting embedder name but found nothing.
+        10:11 _vectors. embedderName EXISTS
+        ");
+        insta::assert_snapshot!(p(r#"_vectors .embedderName EXISTS"#), @r"
+        Was expecting an operation like `EXISTS` or `NOT EXISTS` after the vector filter.
+        10:30 _vectors .embedderName EXISTS
+        ");
+        insta::assert_snapshot!(p(r#"_vectors.embedderName. EXISTS"#), @r"
+        Was expecting one of `.fragments`, `.userProvided`, `.documentTemplate`, `.regenerate` or nothing, but instead found a point without a valid value.
+        22:23 _vectors.embedderName. EXISTS
+        ");
+        insta::assert_snapshot!(p(r#"_vectors."embedderName EXISTS"#), @r#"
+        The quotes in one of the values are inconsistent.
+        10:30 _vectors."embedderName EXISTS
+        "#);
+        insta::assert_snapshot!(p(r#"_vectors."embedderNam"e EXISTS"#), @r#"
+        The vector filter has leftover tokens.
+        23:31 _vectors."embedderNam"e EXISTS
+        "#);
+        insta::assert_snapshot!(p(r#"_vectors.embedderName.documentTemplate. EXISTS"#), @r"
+        Was expecting one of `.fragments`, `.userProvided`, `.documentTemplate`, `.regenerate` or nothing, but instead found a point without a valid value.
+        39:40 _vectors.embedderName.documentTemplate. EXISTS
+        ");
+        insta::assert_snapshot!(p(r#"_vectors.embedderName.fragments EXISTS"#), @r"
+        The vector filter is missing a fragment name.
+        32:39 _vectors.embedderName.fragments EXISTS
+        ");
+        insta::assert_snapshot!(p(r#"_vectors.embedderName.fragments. EXISTS"#), @r"
+        The vector filter's fragment name is invalid.
+        33:40 _vectors.embedderName.fragments. EXISTS
+        ");
+        insta::assert_snapshot!(p(r#"_vectors.embedderName.fragments.test test EXISTS"#), @r"
+        Was expecting an operation like `EXISTS` or `NOT EXISTS` after the vector filter.
+        38:49 _vectors.embedderName.fragments.test test EXISTS
+        ");
+        insta::assert_snapshot!(p(r#"_vectors.embedderName.fragments. test EXISTS"#), @r"
+        The vector filter's fragment name is invalid.
+        33:45 _vectors.embedderName.fragments. test EXISTS
+        ");
+        insta::assert_snapshot!(p(r#"_vectors.embedderName .fragments. test EXISTS"#), @r"
+        Was expecting an operation like `EXISTS` or `NOT EXISTS` after the vector filter.
+        23:46 _vectors.embedderName .fragments. test EXISTS
+        ");
+        insta::assert_snapshot!(p(r#"_vectors.embedderName .fragments.test EXISTS"#), @r"
+        Was expecting an operation like `EXISTS` or `NOT EXISTS` after the vector filter.
+        23:45 _vectors.embedderName .fragments.test EXISTS
+        ");
+        insta::assert_snapshot!(p(r#"_vectors.embedderName.fargments.test EXISTS"#), @r"
+        Was expecting one of `fragments`, `userProvided`, `documentTemplate`, `regenerate` or nothing, but instead found `fargments`. Did you mean `fragments`?
+        23:32 _vectors.embedderName.fargments.test EXISTS
+        ");
+        insta::assert_snapshot!(p(r#"_vectors.embedderName."userProvided" EXISTS"#), @r#"
+        Was expecting this part to be unquoted.
+        24:36 _vectors.embedderName."userProvided" EXISTS
+        "#);
+        insta::assert_snapshot!(p(r#"_vectors.embedderName.userProvided.fragments.test EXISTS"#), @r"
+        Vector filter can only accept one of `fragments`, `userProvided`, `documentTemplate` or `regenerate`, but found both `userProvided` and `fragments`.
+        36:45 _vectors.embedderName.userProvided.fragments.test EXISTS
+        ");
+
         insta::assert_snapshot!(p(r#"NOT OR EXISTS AND EXISTS NOT EXISTS"#), @r###"
         Was expecting a value but instead got `OR`, which is a reserved keyword. To use `OR` as a field name or a value, surround it by quotes.
         5:7 NOT OR EXISTS AND EXISTS NOT EXISTS

crates/filter-parser/src/value.rs

@@ -80,6 +80,51 @@ pub fn word_exact<'a, 'b: 'a>(tag: &'b str) -> impl Fn(Span<'a>) -> IResult<'a,
     }
 }
 
+/// vector_value          = ( non_dot_word | singleQuoted | doubleQuoted)
+pub fn parse_vector_value(input: Span) -> IResult<Token> {
+    pub fn non_dot_word(input: Span) -> IResult<Token> {
+        let (input, word) = take_while1(|c| is_value_component(c) && c != '.')(input)?;
+        Ok((input, word.into()))
+    }
+
+    let (input, value) = alt((
+        delimited(char('\''), cut(|input| quoted_by('\'', input)), cut(char('\''))),
+        delimited(char('"'), cut(|input| quoted_by('"', input)), cut(char('"'))),
+        non_dot_word,
+    ))(input)?;
+
+    match unescaper::unescape(value.value()) {
+        Ok(content) => {
+            if content.len() != value.value().len() {
+                Ok((input, Token::new(value.original_span(), Some(content))))
+            } else {
+                Ok((input, value))
+            }
+        }
+        Err(unescaper::Error::IncompleteStr(_)) => Err(nom::Err::Incomplete(nom::Needed::Unknown)),
+        Err(unescaper::Error::ParseIntError { .. }) => Err(nom::Err::Error(Error::new_from_kind(
+            value.original_span(),
+            ErrorKind::InvalidEscapedNumber,
+        ))),
+        Err(unescaper::Error::InvalidChar { .. }) => Err(nom::Err::Error(Error::new_from_kind(
+            value.original_span(),
+            ErrorKind::MalformedValue,
+        ))),
+    }
+}
+
+pub fn parse_vector_value_cut<'a>(input: Span<'a>, kind: ErrorKind<'a>) -> IResult<'a, Token<'a>> {
+    parse_vector_value(input).map_err(|e| match e {
+        nom::Err::Failure(e) => match e.kind() {
+            ErrorKind::Char(c) if *c == '"' || *c == '\'' => {
+                crate::Error::failure_from_kind(input, ErrorKind::VectorFilterInvalidQuotes)
+            }
+            _ => crate::Error::failure_from_kind(input, kind),
+        },
+        _ => crate::Error::failure_from_kind(input, kind),
+    })
+}
+
 /// value          = WS* ( word | singleQuoted | doubleQuoted) WS+
 pub fn parse_value(input: Span) -> IResult<Token> {
     // to get better diagnostic message we are going to strip the left whitespaces from the input right now
@@ -99,31 +144,21 @@ pub fn parse_value(input: Span) -> IResult<Token> {
     }
 
     match parse_geo_radius(input) {
-        Ok(_) => {
-            return Err(nom::Err::Failure(Error::new_from_kind(input, ErrorKind::MisusedGeoRadius)))
-        }
+        Ok(_) => return Err(Error::failure_from_kind(input, ErrorKind::MisusedGeoRadius)),
         // if we encountered a failure it means the user badly wrote a _geoRadius filter.
         // But instead of showing them how to fix his syntax we are going to tell them they should not use this filter as a value.
         Err(e) if e.is_failure() => {
-            return Err(nom::Err::Failure(Error::new_from_kind(input, ErrorKind::MisusedGeoRadius)))
+            return Err(Error::failure_from_kind(input, ErrorKind::MisusedGeoRadius))
         }
         _ => (),
     }
 
     match parse_geo_bounding_box(input) {
-        Ok(_) => {
-            return Err(nom::Err::Failure(Error::new_from_kind(
-                input,
-                ErrorKind::MisusedGeoBoundingBox,
-            )))
-        }
+        Ok(_) => return Err(Error::failure_from_kind(input, ErrorKind::MisusedGeoBoundingBox)),
         // if we encountered a failure it means the user badly wrote a _geoBoundingBox filter.
         // But instead of showing them how to fix his syntax we are going to tell them they should not use this filter as a value.
         Err(e) if e.is_failure() => {
-            return Err(nom::Err::Failure(Error::new_from_kind(
-                input,
-                ErrorKind::MisusedGeoBoundingBox,
-            )))
+            return Err(Error::failure_from_kind(input, ErrorKind::MisusedGeoBoundingBox))
         }
         _ => (),
     }

crates/index-scheduler/Cargo.toml

@@ -26,7 +26,7 @@ flate2 = "1.1.2"
 indexmap = "2.9.0"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
-memmap2 = "0.9.5"
+memmap2 = "0.9.7"
 page_size = "0.6.0"
 rayon = "1.10.0"
 roaring = { version = "0.10.12", features = ["serde"] }

crates/index-scheduler/src/features.rs

@@ -85,7 +85,7 @@ impl RoFeatures {
             Ok(())
         } else {
             Err(FeatureNotEnabledError {
-                disabled_action: "Using `CONTAINS` or `STARTS WITH` in a filter",
+                disabled_action: "Using `CONTAINS` in a filter",
                 feature: "contains filter",
                 issue_link: "https://github.com/orgs/meilisearch/discussions/763",
             }
@@ -182,6 +182,7 @@ impl FeatureData {
             ..persisted_features
         }));
 
+        // Once this is stabilized, network should be stored along with webhooks in index-scheduler's persisted database
         let network_db = runtime_features_db.remap_data_type::<SerdeJson<Network>>();
         let network: Network = network_db.get(wtxn, db_keys::NETWORK)?.unwrap_or_default();
 

crates/index-scheduler/src/index_mapper/mod.rs

@@ -71,7 +71,7 @@ pub struct IndexMapper {
     /// Path to the folder where the LMDB environments of each index are.
     base_path: PathBuf,
     /// The map size an index is opened with on the first time.
-    index_base_map_size: usize,
+    pub(crate) index_base_map_size: usize,
     /// The quantity by which the map size of an index is incremented upon reopening, in bytes.
     index_growth_amount: usize,
     /// Whether we open a meilisearch index with the MDB_WRITEMAP option or not.

crates/index-scheduler/src/insta_snapshot.rs

@@ -20,16 +20,17 @@ pub fn snapshot_index_scheduler(scheduler: &IndexScheduler) -> String {
 
     let IndexScheduler {
         cleanup_enabled: _,
+        experimental_no_edition_2024_for_dumps: _,
         processing_tasks,
         env,
         version,
         queue,
         scheduler,
+        persisted,
 
         index_mapper,
         features: _,
-        webhook_url: _,
-        webhook_authorization_header: _,
+        webhooks: _,
         test_breakpoint_sdr: _,
         planned_failures: _,
         run_loop_iteration: _,
@@ -61,6 +62,13 @@ pub fn snapshot_index_scheduler(scheduler: &IndexScheduler) -> String {
     }
     snap.push_str("\n----------------------------------------------------------------------\n");
 
+    let persisted_db_snapshot = snapshot_persisted_db(&rtxn, persisted);
+    if !persisted_db_snapshot.is_empty() {
+        snap.push_str("### Persisted:\n");
+        snap.push_str(&persisted_db_snapshot);
+        snap.push_str("----------------------------------------------------------------------\n");
+    }
+
     snap.push_str("### All Tasks:\n");
     snap.push_str(&snapshot_all_tasks(&rtxn, queue.tasks.all_tasks));
     snap.push_str("----------------------------------------------------------------------\n");
@@ -199,6 +207,16 @@ pub fn snapshot_date_db(rtxn: &RoTxn, db: Database<BEI128, CboRoaringBitmapCodec
     snap
 }
 
+pub fn snapshot_persisted_db(rtxn: &RoTxn, db: &Database<Str, Str>) -> String {
+    let mut snap = String::new();
+    let iter = db.iter(rtxn).unwrap();
+    for next in iter {
+        let (key, value) = next.unwrap();
+        snap.push_str(&format!("{key}: {value}\n"));
+    }
+    snap
+}
+
 pub fn snapshot_task(task: &Task) -> String {
     let mut snap = String::new();
     let Task {
@@ -310,6 +328,7 @@ pub fn snapshot_status(
     }
     snap
 }
+
 pub fn snapshot_kind(rtxn: &RoTxn, db: Database<SerdeBincode<Kind>, RoaringBitmapCodec>) -> String {
     let mut snap = String::new();
     let iter = db.iter(rtxn).unwrap();
@@ -330,6 +349,7 @@ pub fn snapshot_index_tasks(rtxn: &RoTxn, db: Database<Str, RoaringBitmapCodec>)
     }
     snap
 }
+
 pub fn snapshot_canceled_by(rtxn: &RoTxn, db: Database<BEU32, RoaringBitmapCodec>) -> String {
     let mut snap = String::new();
     let iter = db.iter(rtxn).unwrap();

crates/index-scheduler/src/lib.rs

@@ -65,13 +65,16 @@ use meilisearch_types::milli::vector::{
 use meilisearch_types::milli::{self, Index};
 use meilisearch_types::task_view::TaskView;
 use meilisearch_types::tasks::{KindWithContent, Task};
+use meilisearch_types::webhooks::{Webhook, WebhooksDumpView, WebhooksView};
 use milli::vector::db::IndexEmbeddingConfig;
 use processing::ProcessingTasks;
 pub use queue::Query;
 use queue::Queue;
 use roaring::RoaringBitmap;
 use scheduler::Scheduler;
+use serde::{Deserialize, Serialize};
 use time::OffsetDateTime;
+use uuid::Uuid;
 use versioning::Versioning;
 
 use crate::index_mapper::IndexMapper;
@@ -80,7 +83,15 @@ use crate::utils::clamp_to_page_size;
 pub(crate) type BEI128 = I128<BE>;
 
 const TASK_SCHEDULER_SIZE_THRESHOLD_PERCENT_INT: u64 = 40;
-const CHAT_SETTINGS_DB_NAME: &str = "chat-settings";
+
+mod db_name {
+    pub const CHAT_SETTINGS: &str = "chat-settings";
+    pub const PERSISTED: &str = "persisted";
+}
+
+mod db_keys {
+    pub const WEBHOOKS: &str = "webhooks";
+}
 
 #[derive(Debug)]
 pub struct IndexSchedulerOptions {
@@ -98,10 +109,10 @@ pub struct IndexSchedulerOptions {
     pub snapshots_path: PathBuf,
     /// The path to the folder containing the dumps.
     pub dumps_path: PathBuf,
-    /// The URL on which we must send the tasks statuses
-    pub webhook_url: Option<String>,
-    /// The value we will send into the Authorization HTTP header on the webhook URL
-    pub webhook_authorization_header: Option<String>,
+    /// The webhook url that was set by the CLI.
+    pub cli_webhook_url: Option<String>,
+    /// The Authorization header to send to the webhook URL that was set by the CLI.
+    pub cli_webhook_authorization: Option<String>,
     /// The maximum size, in bytes, of the task index.
     pub task_db_size: usize,
     /// The size, in bytes, with which a meilisearch index is opened the first time of each meilisearch index.
@@ -168,10 +179,14 @@ pub struct IndexScheduler {
     /// Whether we should automatically cleanup the task queue or not.
     pub(crate) cleanup_enabled: bool,
 
-    /// The webhook url we should send tasks to after processing every batches.
-    pub(crate) webhook_url: Option<String>,
-    /// The Authorization header to send to the webhook URL.
-    pub(crate) webhook_authorization_header: Option<String>,
+    /// Whether we should use the old document indexer or the new one.
+    pub(crate) experimental_no_edition_2024_for_dumps: bool,
+
+    /// A database to store single-keyed data that is persisted across restarts.
+    persisted: Database<Str, Str>,
+
+    /// Webhook, loaded and stored in the `persisted` database
+    webhooks: Arc<Webhooks>,
 
     /// A map to retrieve the runtime representation of an embedder depending on its configuration.
     ///
@@ -210,8 +225,10 @@ impl IndexScheduler {
 
             index_mapper: self.index_mapper.clone(),
             cleanup_enabled: self.cleanup_enabled,
-            webhook_url: self.webhook_url.clone(),
-            webhook_authorization_header: self.webhook_authorization_header.clone(),
+            experimental_no_edition_2024_for_dumps: self.experimental_no_edition_2024_for_dumps,
+            persisted: self.persisted,
+
+            webhooks: self.webhooks.clone(),
             embedders: self.embedders.clone(),
             #[cfg(test)]
             test_breakpoint_sdr: self.test_breakpoint_sdr.clone(),
@@ -230,6 +247,7 @@ impl IndexScheduler {
             + IndexMapper::nb_db()
             + features::FeatureData::nb_db()
             + 1 // chat-prompts
+            + 1 // persisted
     }
 
     /// Create an index scheduler and start its run loop.
@@ -280,10 +298,18 @@ impl IndexScheduler {
         let version = versioning::Versioning::new(&env, from_db_version)?;
 
         let mut wtxn = env.write_txn()?;
+
         let features = features::FeatureData::new(&env, &mut wtxn, options.instance_features)?;
         let queue = Queue::new(&env, &mut wtxn, &options)?;
         let index_mapper = IndexMapper::new(&env, &mut wtxn, &options, budget)?;
-        let chat_settings = env.create_database(&mut wtxn, Some(CHAT_SETTINGS_DB_NAME))?;
+        let chat_settings = env.create_database(&mut wtxn, Some(db_name::CHAT_SETTINGS))?;
+
+        let persisted = env.create_database(&mut wtxn, Some(db_name::PERSISTED))?;
+        let webhooks_db = persisted.remap_data_type::<SerdeJson<Webhooks>>();
+        let mut webhooks = webhooks_db.get(&wtxn, db_keys::WEBHOOKS)?.unwrap_or_default();
+        webhooks
+            .with_cli(options.cli_webhook_url.clone(), options.cli_webhook_authorization.clone());
+
         wtxn.commit()?;
 
         // allow unreachable_code to get rids of the warning in the case of a test build.
@@ -296,8 +322,11 @@ impl IndexScheduler {
             index_mapper,
             env,
             cleanup_enabled: options.cleanup_enabled,
-            webhook_url: options.webhook_url,
-            webhook_authorization_header: options.webhook_authorization_header,
+            experimental_no_edition_2024_for_dumps: options
+                .indexer_config
+                .experimental_no_edition_2024_for_dumps,
+            persisted,
+            webhooks: Arc::new(webhooks),
             embedders: Default::default(),
 
             #[cfg(test)]
@@ -594,6 +623,11 @@ impl IndexScheduler {
         Ok(nbr_index_processing_tasks > 0)
     }
 
+    /// Whether the index should use the old document indexer.
+    pub fn no_edition_2024_for_dumps(&self) -> bool {
+        self.experimental_no_edition_2024_for_dumps
+    }
+
     /// Return the tasks matching the query from the user's point of view along
     /// with the total number of tasks matching the query, ignoring from and limit.
     ///
@@ -740,86 +774,92 @@ impl IndexScheduler {
         Ok(())
     }
 
-    /// Once the tasks changes have been committed we must send all the tasks that were updated to our webhook if there is one.
-    fn notify_webhook(&self, updated: &RoaringBitmap) -> Result<()> {
-        if let Some(ref url) = self.webhook_url {
-            struct TaskReader<'a, 'b> {
-                rtxn: &'a RoTxn<'a>,
-                index_scheduler: &'a IndexScheduler,
-                tasks: &'b mut roaring::bitmap::Iter<'b>,
-                buffer: Vec<u8>,
-                written: usize,
-            }
+    /// Once the tasks changes have been committed we must send all the tasks that were updated to our webhooks
+    fn notify_webhooks(&self, updated: RoaringBitmap) {
+        struct TaskReader<'a, 'b> {
+            rtxn: &'a RoTxn<'a>,
+            index_scheduler: &'a IndexScheduler,
+            tasks: &'b mut roaring::bitmap::Iter<'b>,
+            buffer: Vec<u8>,
+            written: usize,
+        }
 
-            impl Read for TaskReader<'_, '_> {
-                fn read(&mut self, mut buf: &mut [u8]) -> std::io::Result<usize> {
-                    if self.buffer.is_empty() {
-                        match self.tasks.next() {
-                            None => return Ok(0),
-                            Some(task_id) => {
-                                let task = self
-                                    .index_scheduler
-                                    .queue
-                                    .tasks
-                                    .get_task(self.rtxn, task_id)
-                                    .map_err(|err| io::Error::new(io::ErrorKind::Other, err))?
-                                    .ok_or_else(|| {
-                                        io::Error::new(
-                                            io::ErrorKind::Other,
-                                            Error::CorruptedTaskQueue,
-                                        )
-                                    })?;
+        impl Read for TaskReader<'_, '_> {
+            fn read(&mut self, mut buf: &mut [u8]) -> std::io::Result<usize> {
+                if self.buffer.is_empty() {
+                    match self.tasks.next() {
+                        None => return Ok(0),
+                        Some(task_id) => {
+                            let task = self
+                                .index_scheduler
+                                .queue
+                                .tasks
+                                .get_task(self.rtxn, task_id)
+                                .map_err(|err| io::Error::new(io::ErrorKind::Other, err))?
+                                .ok_or_else(|| {
+                                    io::Error::new(io::ErrorKind::Other, Error::CorruptedTaskQueue)
+                                })?;
 
-                                serde_json::to_writer(
-                                    &mut self.buffer,
-                                    &TaskView::from_task(&task),
-                                )?;
-                                self.buffer.push(b'\n');
-                            }
+                            serde_json::to_writer(&mut self.buffer, &TaskView::from_task(&task))?;
+                            self.buffer.push(b'\n');
                         }
                     }
-
-                    let mut to_write = &self.buffer[self.written..];
-                    let wrote = io::copy(&mut to_write, &mut buf)?;
-                    self.written += wrote as usize;
-
-                    // we wrote everything and must refresh our buffer on the next call
-                    if self.written == self.buffer.len() {
-                        self.written = 0;
-                        self.buffer.clear();
-                    }
-
-                    Ok(wrote as usize)
                 }
-            }
 
-            let rtxn = self.env.read_txn()?;
+                let mut to_write = &self.buffer[self.written..];
+                let wrote = io::copy(&mut to_write, &mut buf)?;
+                self.written += wrote as usize;
 
-            let task_reader = TaskReader {
-                rtxn: &rtxn,
-                index_scheduler: self,
-                tasks: &mut updated.into_iter(),
-                buffer: Vec::with_capacity(50), // on average a task is around ~100 bytes
-                written: 0,
-            };
+                // we wrote everything and must refresh our buffer on the next call
+                if self.written == self.buffer.len() {
+                    self.written = 0;
+                    self.buffer.clear();
+                }
 
-            // let reader = GzEncoder::new(BufReader::new(task_reader), Compression::default());
-            let reader = GzEncoder::new(BufReader::new(task_reader), Compression::default());
-            let request = ureq::post(url)
-                .timeout(Duration::from_secs(30))
-                .set("Content-Encoding", "gzip")
-                .set("Content-Type", "application/x-ndjson");
-            let request = match &self.webhook_authorization_header {
-                Some(header) => request.set("Authorization", header),
-                None => request,
-            };
-
-            if let Err(e) = request.send(reader) {
-                tracing::error!("While sending data to the webhook: {e}");
+                Ok(wrote as usize)
             }
         }
 
-        Ok(())
+        let webhooks = self.webhooks.get_all();
+        if webhooks.is_empty() {
+            return;
+        }
+        let this = self.private_clone();
+        // We must take the RoTxn before entering the thread::spawn otherwise another batch may be
+        // processed before we had the time to take our txn.
+        let rtxn = match self.env.clone().static_read_txn() {
+            Ok(rtxn) => rtxn,
+            Err(e) => {
+                tracing::error!("Couldn't get an rtxn to notify the webhook: {e}");
+                return;
+            }
+        };
+
+        std::thread::spawn(move || {
+            for (uuid, Webhook { url, headers }) in webhooks.iter() {
+                let task_reader = TaskReader {
+                    rtxn: &rtxn,
+                    index_scheduler: &this,
+                    tasks: &mut updated.iter(),
+                    buffer: Vec::with_capacity(page_size::get()),
+                    written: 0,
+                };
+
+                let reader = GzEncoder::new(BufReader::new(task_reader), Compression::default());
+
+                let mut request = ureq::post(url)
+                    .timeout(Duration::from_secs(30))
+                    .set("Content-Encoding", "gzip")
+                    .set("Content-Type", "application/x-ndjson");
+                for (header_name, header_value) in headers.iter() {
+                    request = request.set(header_name, header_value);
+                }
+
+                if let Err(e) = request.send(reader) {
+                    tracing::error!("While sending data to the webhook {uuid}: {e}");
+                }
+            }
+        });
     }
 
     pub fn index_stats(&self, index_uid: &str) -> Result<IndexStats> {
@@ -850,6 +890,29 @@ impl IndexScheduler {
         self.features.network()
     }
 
+    pub fn update_runtime_webhooks(&self, runtime: RuntimeWebhooks) -> Result<()> {
+        let webhooks = Webhooks::from_runtime(runtime);
+        let mut wtxn = self.env.write_txn()?;
+        let webhooks_db = self.persisted.remap_data_type::<SerdeJson<Webhooks>>();
+        webhooks_db.put(&mut wtxn, db_keys::WEBHOOKS, &webhooks)?;
+        wtxn.commit()?;
+        self.webhooks.update_runtime(webhooks.into_runtime());
+        Ok(())
+    }
+
+    pub fn webhooks_dump_view(&self) -> WebhooksDumpView {
+        // We must not dump the cli api key
+        WebhooksDumpView { webhooks: self.webhooks.get_runtime() }
+    }
+
+    pub fn webhooks_view(&self) -> WebhooksView {
+        WebhooksView { webhooks: self.webhooks.get_all() }
+    }
+
+    pub fn retrieve_runtime_webhooks(&self) -> RuntimeWebhooks {
+        self.webhooks.get_runtime()
+    }
+
     pub fn embedders(
         &self,
         index_uid: String,
@@ -978,3 +1041,72 @@ pub struct IndexStats {
     /// Internal stats computed from the index.
     pub inner_stats: index_mapper::IndexStats,
 }
+
+/// These structure are not meant to be exposed to the end user, if needed, use the meilisearch-types::webhooks structure instead.
+/// /!\ Everytime you deserialize this structure you should fill the cli_webhook later on with the `with_cli` method. /!\
+#[derive(Debug, Serialize, Deserialize, Default)]
+#[serde(rename_all = "camelCase")]
+struct Webhooks {
+    // The cli webhook should *never* be stored in a database.
+    // It represent a state that only exists for this execution of meilisearch
+    #[serde(skip)]
+    pub cli: Option<CliWebhook>,
+
+    #[serde(default)]
+    pub runtime: RwLock<RuntimeWebhooks>,
+}
+
+type RuntimeWebhooks = BTreeMap<Uuid, Webhook>;
+
+impl Webhooks {
+    pub fn with_cli(&mut self, url: Option<String>, auth: Option<String>) {
+        if let Some(url) = url {
+            let webhook = CliWebhook { url, auth };
+            self.cli = Some(webhook);
+        }
+    }
+
+    pub fn from_runtime(webhooks: RuntimeWebhooks) -> Self {
+        Self { cli: None, runtime: RwLock::new(webhooks) }
+    }
+
+    pub fn into_runtime(self) -> RuntimeWebhooks {
+        // safe because we own self and it cannot be cloned
+        self.runtime.into_inner().unwrap()
+    }
+
+    pub fn update_runtime(&self, webhooks: RuntimeWebhooks) {
+        *self.runtime.write().unwrap() = webhooks;
+    }
+
+    /// Returns all the webhooks in an unified view. The cli webhook is represented with an uuid set to 0
+    pub fn get_all(&self) -> BTreeMap<Uuid, Webhook> {
+        self.cli
+            .as_ref()
+            .map(|wh| (Uuid::nil(), Webhook::from(wh)))
+            .into_iter()
+            .chain(self.runtime.read().unwrap().iter().map(|(uuid, wh)| (*uuid, wh.clone())))
+            .collect()
+    }
+
+    /// Returns all the runtime webhooks.
+    pub fn get_runtime(&self) -> BTreeMap<Uuid, Webhook> {
+        self.runtime.read().unwrap().iter().map(|(uuid, wh)| (*uuid, wh.clone())).collect()
+    }
+}
+
+#[derive(Debug, Serialize, Deserialize, Default, Clone, PartialEq)]
+struct CliWebhook {
+    pub url: String,
+    pub auth: Option<String>,
+}
+
+impl From<&CliWebhook> for Webhook {
+    fn from(webhook: &CliWebhook) -> Self {
+        let mut headers = BTreeMap::new();
+        if let Some(ref auth) = webhook.auth {
+            headers.insert("Authorization".to_string(), auth.to_string());
+        }
+        Self { url: webhook.url.to_string(), headers }
+    }
+}

crates/index-scheduler/src/processing.rs

@@ -108,6 +108,7 @@ make_enum_progress! {
         DumpTheBatches,
         DumpTheIndexes,
         DumpTheExperimentalFeatures,
+        DumpTheWebhooks,
         CompressTheDump,
     }
 }

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

@@ -446,8 +446,7 @@ impl IndexScheduler {
             Ok(())
         })?;
 
-        // We shouldn't crash the tick function if we can't send data to the webhook.
-        let _ = self.notify_webhook(&ids);
+        self.notify_webhooks(ids);
 
         #[cfg(test)]
         self.breakpoint(crate::test_utils::Breakpoint::AfterProcessing);

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

@@ -5,6 +5,7 @@ use std::sync::atomic::Ordering;
 
 use dump::IndexMetadata;
 use meilisearch_types::milli::constants::RESERVED_VECTORS_FIELD_NAME;
+use meilisearch_types::milli::index::EmbeddingsWithMetadata;
 use meilisearch_types::milli::progress::{Progress, VariableNameStep};
 use meilisearch_types::milli::vector::parsed_vectors::{ExplicitVectors, VectorOrArrayOfVectors};
 use meilisearch_types::milli::{self};
@@ -227,12 +228,21 @@ impl IndexScheduler {
                         return Err(Error::from_milli(user_err, Some(uid.to_string())));
                     };
 
-                    for (embedder_name, (embeddings, regenerate)) in embeddings {
+                    for (
+                        embedder_name,
+                        EmbeddingsWithMetadata { embeddings, regenerate, has_fragments },
+                    ) in embeddings
+                    {
                         let embeddings = ExplicitVectors {
                             embeddings: Some(VectorOrArrayOfVectors::from_array_of_vectors(
                                 embeddings,
                             )),
-                            regenerate,
+                            regenerate: regenerate &&
+                            // Meilisearch does not handle well dumps with fragments, because as the fragments
+                            // are marked as user-provided,
+                            // all embeddings would be regenerated on any settings change or document update.
+                            // To prevent this, we mark embeddings has non regenerate in this case.
+                            !has_fragments,
                         };
                         vectors.insert(embedder_name, serde_json::to_value(embeddings).unwrap());
                     }
@@ -260,6 +270,11 @@ impl IndexScheduler {
         let network = self.network();
         dump.create_network(network)?;
 
+        // 7. Dump the webhooks
+        progress.update_progress(DumpCreationProgress::DumpTheWebhooks);
+        let webhooks = self.webhooks_dump_view();
+        dump.create_webhooks(webhooks)?;
+
         let dump_uid = started_at.format(format_description!(
                     "[year repr:full][month repr:numerical][day padding:zero]-[hour padding:zero][minute padding:zero][second padding:zero][subsecond digits:3]"
                 )).unwrap();

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

@@ -9,6 +9,7 @@ use flate2::write::GzEncoder;
 use flate2::Compression;
 use meilisearch_types::index_uid_pattern::IndexUidPattern;
 use meilisearch_types::milli::constants::RESERVED_VECTORS_FIELD_NAME;
+use meilisearch_types::milli::index::EmbeddingsWithMetadata;
 use meilisearch_types::milli::progress::{Progress, VariableNameStep};
 use meilisearch_types::milli::update::{request_threads, Setting};
 use meilisearch_types::milli::vector::parsed_vectors::{ExplicitVectors, VectorOrArrayOfVectors};
@@ -62,13 +63,14 @@ impl IndexScheduler {
             let ExportIndexSettings { filter, override_settings } = export_settings;
             let index = self.index(uid)?;
             let index_rtxn = index.read_txn()?;
+            let bearer = api_key.map(|api_key| format!("Bearer {api_key}"));
 
             // First, check if the index already exists
             let url = format!("{base_url}/indexes/{uid}");
             let response = retry(&must_stop_processing, || {
                 let mut request = agent.get(&url);
-                if let Some(api_key) = api_key {
-                    request = request.set("Authorization", &format!("Bearer {api_key}"));
+                if let Some(bearer) = &bearer {
+                    request = request.set("Authorization", bearer);
                 }
 
                 request.send_bytes(Default::default()).map_err(into_backoff_error)
@@ -90,8 +92,8 @@ impl IndexScheduler {
                 let url = format!("{base_url}/indexes");
                 retry(&must_stop_processing, || {
                     let mut request = agent.post(&url);
-                    if let Some(api_key) = api_key {
-                        request = request.set("Authorization", &format!("Bearer {api_key}"));
+                    if let Some(bearer) = &bearer {
+                        request = request.set("Authorization", bearer);
                     }
                     let index_param = json!({ "uid": uid, "primaryKey": primary_key });
                     request.send_json(&index_param).map_err(into_backoff_error)
@@ -103,8 +105,8 @@ impl IndexScheduler {
                 let url = format!("{base_url}/indexes/{uid}");
                 retry(&must_stop_processing, || {
                     let mut request = agent.patch(&url);
-                    if let Some(api_key) = api_key {
-                        request = request.set("Authorization", &format!("Bearer {api_key}"));
+                    if let Some(bearer) = &bearer {
+                        request = request.set("Authorization", bearer);
                     }
                     let index_param = json!({ "primaryKey": primary_key });
                     request.send_json(&index_param).map_err(into_backoff_error)
@@ -122,7 +124,6 @@ impl IndexScheduler {
                 }
                 // Retry logic for sending settings
                 let url = format!("{base_url}/indexes/{uid}/settings");
-                let bearer = api_key.map(|api_key| format!("Bearer {api_key}"));
                 retry(&must_stop_processing, || {
                     let mut request = agent.patch(&url);
                     if let Some(bearer) = bearer.as_ref() {
@@ -167,10 +168,10 @@ impl IndexScheduler {
                 },
             );
 
-            let limit = payload_size.map(|ps| ps.as_u64() as usize).unwrap_or(50 * 1024 * 1024); // defaults to 50 MiB
+            let limit = payload_size.map(|ps| ps.as_u64() as usize).unwrap_or(20 * 1024 * 1024); // defaults to 20 MiB
             let documents_url = format!("{base_url}/indexes/{uid}/documents");
 
-            request_threads()
+            let results = request_threads()
                 .broadcast(|ctx| {
                     let index_rtxn = index
                         .read_txn()
@@ -229,12 +230,21 @@ impl IndexScheduler {
                                 ));
                             };
 
-                            for (embedder_name, (embeddings, regenerate)) in embeddings {
+                            for (
+                                embedder_name,
+                                EmbeddingsWithMetadata { embeddings, regenerate, has_fragments },
+                            ) in embeddings
+                            {
                                 let embeddings = ExplicitVectors {
                                     embeddings: Some(
                                         VectorOrArrayOfVectors::from_array_of_vectors(embeddings),
                                     ),
-                                    regenerate,
+                                    regenerate: regenerate &&
+                                    // Meilisearch does not handle well dumps with fragments, because as the fragments
+                                    // are marked as user-provided,
+                                    // all embeddings would be regenerated on any settings change or document update.
+                                    // To prevent this, we mark embeddings has non regenerate in this case.
+                                    !has_fragments,
                                 };
                                 vectors.insert(
                                     embedder_name,
@@ -265,9 +275,8 @@ impl IndexScheduler {
                                 let mut request = agent.post(&documents_url);
                                 request = request.set("Content-Type", "application/x-ndjson");
                                 request = request.set("Content-Encoding", "gzip");
-                                if let Some(api_key) = api_key {
-                                    request = request
-                                        .set("Authorization", &(format!("Bearer {api_key}")));
+                                if let Some(bearer) = &bearer {
+                                    request = request.set("Authorization", bearer);
                                 }
                                 request.send_bytes(&compressed_buffer).map_err(into_backoff_error)
                             })?;
@@ -276,7 +285,7 @@ impl IndexScheduler {
                         }
                         buffer.extend_from_slice(&tmp_buffer);
 
-                        if i % 100 == 0 {
+                        if i > 0 && i % 100 == 0 {
                             step.fetch_add(100, atomic::Ordering::Relaxed);
                         }
                     }
@@ -284,8 +293,8 @@ impl IndexScheduler {
                     retry(&must_stop_processing, || {
                         let mut request = agent.post(&documents_url);
                         request = request.set("Content-Type", "application/x-ndjson");
-                        if let Some(api_key) = api_key {
-                            request = request.set("Authorization", &(format!("Bearer {api_key}")));
+                        if let Some(bearer) = &bearer {
+                            request = request.set("Authorization", bearer);
                         }
                         request.send_bytes(&buffer).map_err(into_backoff_error)
                     })?;
@@ -298,6 +307,9 @@ impl IndexScheduler {
                         Some(uid.to_string()),
                     )
                 })?;
+            for result in results {
+                result?;
+            }
 
             step.store(total_documents, atomic::Ordering::Relaxed);
         }

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

@@ -7,9 +7,73 @@ use meilisearch_types::milli::progress::{Progress, VariableNameStep};
 use meilisearch_types::tasks::{Status, Task};
 use meilisearch_types::{compression, VERSION_FILE_NAME};
 
+use crate::heed::EnvOpenOptions;
 use crate::processing::{AtomicUpdateFileStep, SnapshotCreationProgress};
+use crate::queue::TaskQueue;
 use crate::{Error, IndexScheduler, Result};
 
+/// # Safety
+///
+/// See [`EnvOpenOptions::open`].
+unsafe fn remove_tasks(
+    tasks: &[Task],
+    dst: &std::path::Path,
+    index_base_map_size: usize,
+) -> Result<()> {
+    let env_options = EnvOpenOptions::new();
+    let mut env_options = env_options.read_txn_without_tls();
+    let env = env_options.max_dbs(TaskQueue::nb_db()).map_size(index_base_map_size).open(dst)?;
+    let mut wtxn = env.write_txn()?;
+    let task_queue = TaskQueue::new(&env, &mut wtxn)?;
+
+    // Destructuring to ensure the code below gets updated if a database gets added in the future.
+    let TaskQueue {
+        all_tasks,
+        status,
+        kind,
+        index_tasks: _, // snapshot creation tasks are not index tasks
+        canceled_by,
+        enqueued_at,
+        started_at,
+        finished_at,
+    } = task_queue;
+
+    for task in tasks {
+        all_tasks.delete(&mut wtxn, &task.uid)?;
+
+        let mut tasks = status.get(&wtxn, &task.status)?.unwrap_or_default();
+        tasks.remove(task.uid);
+        status.put(&mut wtxn, &task.status, &tasks)?;
+
+        let mut tasks = kind.get(&wtxn, &task.kind.as_kind())?.unwrap_or_default();
+        tasks.remove(task.uid);
+        kind.put(&mut wtxn, &task.kind.as_kind(), &tasks)?;
+
+        canceled_by.delete(&mut wtxn, &task.uid)?;
+
+        let timestamp = task.enqueued_at.unix_timestamp_nanos();
+        let mut tasks = enqueued_at.get(&wtxn, &timestamp)?.unwrap_or_default();
+        tasks.remove(task.uid);
+        enqueued_at.put(&mut wtxn, &timestamp, &tasks)?;
+
+        if let Some(task_started_at) = task.started_at {
+            let timestamp = task_started_at.unix_timestamp_nanos();
+            let mut tasks = started_at.get(&wtxn, &timestamp)?.unwrap_or_default();
+            tasks.remove(task.uid);
+            started_at.put(&mut wtxn, &timestamp, &tasks)?;
+        }
+
+        if let Some(task_finished_at) = task.finished_at {
+            let timestamp = task_finished_at.unix_timestamp_nanos();
+            let mut tasks = finished_at.get(&wtxn, &timestamp)?.unwrap_or_default();
+            tasks.remove(task.uid);
+            finished_at.put(&mut wtxn, &timestamp, &tasks)?;
+        }
+    }
+    wtxn.commit()?;
+    Ok(())
+}
+
 impl IndexScheduler {
     pub(super) fn process_snapshot(
         &self,
@@ -48,14 +112,26 @@ impl IndexScheduler {
         };
         self.env.copy_to_path(dst.join("data.mdb"), compaction_option)?;
 
-        // 2.2 Create a read transaction on the index-scheduler
+        // 2.2 Remove the current snapshot tasks
+        //
+        // This is done to ensure that the tasks are not processed again when the snapshot is imported
+        //
+        // # Safety
+        //
+        // This is safe because we open the env file we just created in a temporary directory.
+        // We are sure it's not being used by any other process nor thread.
+        unsafe {
+            remove_tasks(&tasks, &dst, self.index_mapper.index_base_map_size)?;
+        }
+
+        // 2.3 Create a read transaction on the index-scheduler
         let rtxn = self.env.read_txn()?;
 
-        // 2.3 Create the update files directory
+        // 2.4 Create the update files directory
         let update_files_dir = temp_snapshot_dir.path().join("update_files");
         fs::create_dir_all(&update_files_dir)?;
 
-        // 2.4 Only copy the update files of the enqueued tasks
+        // 2.5 Only copy the update files of the enqueued tasks
         progress.update_progress(SnapshotCreationProgress::SnapshotTheUpdateFiles);
         let enqueued = self.queue.tasks.get_status(&rtxn, Status::Enqueued)?;
         let (atomic, update_file_progress) = AtomicUpdateFileStep::new(enqueued.len() as u32);

crates/index-scheduler/src/scheduler/snapshots/test_failure.rs/upgrade_failure/after_processing_everything.snap

@@ -6,7 +6,7 @@ source: crates/index-scheduler/src/scheduler/test_failure.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_uid: 0, status: succeeded, details: { from: (1, 12, 0), to: (1, 16, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
+0 {uid: 0, batch_uid: 0, status: succeeded, details: { from: (1, 12, 0), to: (1, 17, 1) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
 1 {uid: 1, batch_uid: 1, status: succeeded, details: { primary_key: Some("mouse") }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
 2 {uid: 2, batch_uid: 2, status: succeeded, details: { primary_key: Some("bone") }, kind: IndexCreation { index_uid: "doggo", primary_key: Some("bone") }}
 3 {uid: 3, batch_uid: 3, status: failed, error: ResponseError { code: 200, message: "Index `doggo` already exists.", error_code: "index_already_exists", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#index_already_exists" }, details: { primary_key: Some("bone") }, kind: IndexCreation { index_uid: "doggo", primary_key: Some("bone") }}
@@ -57,7 +57,7 @@ girafo: { number_of_documents: 0, field_distribution: {} }
 [timestamp] [4,]
 ----------------------------------------------------------------------
 ### All Batches:
-0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.16.0"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
+0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.17.1"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
 1 {uid: 1, details: {"primaryKey":"mouse"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"catto":1}}, stop reason: "created batch containing only task with id 1 of type `indexCreation` that cannot be batched with any other task.", }
 2 {uid: 2, details: {"primaryKey":"bone"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"doggo":1}}, stop reason: "created batch containing only task with id 2 of type `indexCreation` that cannot be batched with any other task.", }
 3 {uid: 3, details: {"primaryKey":"bone"}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"indexCreation":1},"indexUids":{"doggo":1}}, stop reason: "created batch containing only task with id 3 of type `indexCreation` that cannot be batched with any other task.", }

crates/index-scheduler/src/scheduler/snapshots/test_failure.rs/upgrade_failure/register_automatic_upgrade_task.snap

@@ -6,7 +6,7 @@ source: crates/index-scheduler/src/scheduler/test_failure.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, status: enqueued, details: { from: (1, 12, 0), to: (1, 16, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
+0 {uid: 0, status: enqueued, details: { from: (1, 12, 0), to: (1, 17, 1) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued [0,]

crates/index-scheduler/src/scheduler/snapshots/test_failure.rs/upgrade_failure/registered_a_task_while_the_upgrade_task_is_enqueued.snap

@@ -6,7 +6,7 @@ source: crates/index-scheduler/src/scheduler/test_failure.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, status: enqueued, details: { from: (1, 12, 0), to: (1, 16, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
+0 {uid: 0, status: enqueued, details: { from: (1, 12, 0), to: (1, 17, 1) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
 1 {uid: 1, status: enqueued, details: { primary_key: Some("mouse") }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
 ----------------------------------------------------------------------
 ### Status:

crates/index-scheduler/src/scheduler/snapshots/test_failure.rs/upgrade_failure/upgrade_task_failed.snap

@@ -6,7 +6,7 @@ source: crates/index-scheduler/src/scheduler/test_failure.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_uid: 0, status: failed, error: ResponseError { code: 200, message: "Planned failure for tests.", error_code: "internal", error_type: "internal", error_link: "https://docs.meilisearch.com/errors#internal" }, details: { from: (1, 12, 0), to: (1, 16, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
+0 {uid: 0, batch_uid: 0, status: failed, error: ResponseError { code: 200, message: "Planned failure for tests.", error_code: "internal", error_type: "internal", error_link: "https://docs.meilisearch.com/errors#internal" }, details: { from: (1, 12, 0), to: (1, 17, 1) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
 1 {uid: 1, status: enqueued, details: { primary_key: Some("mouse") }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
 ----------------------------------------------------------------------
 ### Status:
@@ -37,7 +37,7 @@ catto [1,]
 [timestamp] [0,]
 ----------------------------------------------------------------------
 ### All Batches:
-0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.16.0"}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
+0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.17.1"}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

crates/index-scheduler/src/scheduler/snapshots/test_failure.rs/upgrade_failure/upgrade_task_failed_again.snap

@@ -6,7 +6,7 @@ source: crates/index-scheduler/src/scheduler/test_failure.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_uid: 0, status: failed, error: ResponseError { code: 200, message: "Planned failure for tests.", error_code: "internal", error_type: "internal", error_link: "https://docs.meilisearch.com/errors#internal" }, details: { from: (1, 12, 0), to: (1, 16, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
+0 {uid: 0, batch_uid: 0, status: failed, error: ResponseError { code: 200, message: "Planned failure for tests.", error_code: "internal", error_type: "internal", error_link: "https://docs.meilisearch.com/errors#internal" }, details: { from: (1, 12, 0), to: (1, 17, 1) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
 1 {uid: 1, status: enqueued, details: { primary_key: Some("mouse") }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
 2 {uid: 2, status: enqueued, details: { primary_key: Some("bone") }, kind: IndexCreation { index_uid: "doggo", primary_key: Some("bone") }}
 ----------------------------------------------------------------------
@@ -40,7 +40,7 @@ doggo [2,]
 [timestamp] [0,]
 ----------------------------------------------------------------------
 ### All Batches:
-0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.16.0"}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
+0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.17.1"}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

crates/index-scheduler/src/scheduler/snapshots/test_failure.rs/upgrade_failure/upgrade_task_succeeded.snap

@@ -6,7 +6,7 @@ source: crates/index-scheduler/src/scheduler/test_failure.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, batch_uid: 0, status: succeeded, details: { from: (1, 12, 0), to: (1, 16, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
+0 {uid: 0, batch_uid: 0, status: succeeded, details: { from: (1, 12, 0), to: (1, 17, 1) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
 1 {uid: 1, status: enqueued, details: { primary_key: Some("mouse") }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
 2 {uid: 2, status: enqueued, details: { primary_key: Some("bone") }, kind: IndexCreation { index_uid: "doggo", primary_key: Some("bone") }}
 3 {uid: 3, status: enqueued, details: { primary_key: Some("bone") }, kind: IndexCreation { index_uid: "doggo", primary_key: Some("bone") }}
@@ -43,7 +43,7 @@ doggo [2,3,]
 [timestamp] [0,]
 ----------------------------------------------------------------------
 ### All Batches:
-0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.16.0"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
+0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.17.1"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

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

@@ -736,7 +736,7 @@ fn test_document_addition_mixed_rights_with_index() {
 #[test]
 fn test_document_addition_mixed_right_without_index_starts_with_cant_create() {
     // We're going to autobatch multiple document addition.
-    // - The index does not exists
+    // - The index does not exist
     // - The first document addition don't have the right to create an index
     // - The second do. They should not batch together.
     // - The second should batch with everything else as it's going to create an index.

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

@@ -3,6 +3,7 @@ use std::collections::BTreeMap;
 use big_s::S;
 use insta::assert_json_snapshot;
 use meili_snap::{json_string, snapshot};
+use meilisearch_types::milli::index::EmbeddingsWithMetadata;
 use meilisearch_types::milli::update::Setting;
 use meilisearch_types::milli::vector::settings::EmbeddingSettings;
 use meilisearch_types::milli::vector::SearchQuery;
@@ -220,8 +221,8 @@ fn import_vectors() {
 
         let embeddings = index.embeddings(&rtxn, 0).unwrap();
 
-        assert_json_snapshot!(embeddings[&simple_hf_name].0[0] == lab_embed, @"true");
-        assert_json_snapshot!(embeddings[&fakerest_name].0[0] == beagle_embed, @"true");
+        assert_json_snapshot!(embeddings[&simple_hf_name].embeddings[0] == lab_embed, @"true");
+        assert_json_snapshot!(embeddings[&fakerest_name].embeddings[0] == beagle_embed, @"true");
 
         let doc = index.documents(&rtxn, std::iter::once(0)).unwrap()[0].1;
         let fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
@@ -311,9 +312,9 @@ fn import_vectors() {
             let embeddings = index.embeddings(&rtxn, 0).unwrap();
 
             // automatically changed to patou because set to regenerate
-            assert_json_snapshot!(embeddings[&simple_hf_name].0[0] == patou_embed, @"true");
+            assert_json_snapshot!(embeddings[&simple_hf_name].embeddings[0] == patou_embed, @"true");
             // remained beagle
-            assert_json_snapshot!(embeddings[&fakerest_name].0[0] == beagle_embed, @"true");
+            assert_json_snapshot!(embeddings[&fakerest_name].embeddings[0] == beagle_embed, @"true");
 
             let doc = index.documents(&rtxn, std::iter::once(0)).unwrap()[0].1;
             let fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
@@ -497,13 +498,13 @@ fn import_vectors_first_and_embedder_later() {
 
     let docid = index.external_documents_ids.get(&rtxn, "0").unwrap().unwrap();
     let embeddings = index.embeddings(&rtxn, docid).unwrap();
-    let (embedding, _) = &embeddings["my_doggo_embedder"];
-    assert!(!embedding.is_empty(), "{embedding:?}");
+    let EmbeddingsWithMetadata { embeddings, .. } = &embeddings["my_doggo_embedder"];
+    assert!(!embeddings.is_empty(), "{embeddings:?}");
 
     // the document with the id 3 should keep its original embedding
     let docid = index.external_documents_ids.get(&rtxn, "3").unwrap().unwrap();
     let embeddings = index.embeddings(&rtxn, docid).unwrap();
-    let (embeddings, _) = &embeddings["my_doggo_embedder"];
+    let EmbeddingsWithMetadata { embeddings, .. } = &embeddings["my_doggo_embedder"];
 
     snapshot!(embeddings.len(), @"1");
     assert!(embeddings[0].iter().all(|i| *i == 3.0), "{:?}", embeddings[0]);
@@ -558,7 +559,7 @@ fn import_vectors_first_and_embedder_later() {
         "###);
 
     let embeddings = index.embeddings(&rtxn, docid).unwrap();
-    let (embedding, _) = &embeddings["my_doggo_embedder"];
+    let EmbeddingsWithMetadata { embeddings: embedding, .. } = &embeddings["my_doggo_embedder"];
 
     assert!(!embedding.is_empty());
     assert!(!embedding[0].iter().all(|i| *i == 3.0), "{:?}", embedding[0]);
@@ -566,7 +567,7 @@ fn import_vectors_first_and_embedder_later() {
     // the document with the id 4 should generate an embedding
     let docid = index.external_documents_ids.get(&rtxn, "4").unwrap().unwrap();
     let embeddings = index.embeddings(&rtxn, docid).unwrap();
-    let (embedding, _) = &embeddings["my_doggo_embedder"];
+    let EmbeddingsWithMetadata { embeddings: embedding, .. } = &embeddings["my_doggo_embedder"];
 
     assert!(!embedding.is_empty());
 }
@@ -696,7 +697,7 @@ fn delete_document_containing_vector() {
     "###);
     let docid = index.external_documents_ids.get(&rtxn, "0").unwrap().unwrap();
     let embeddings = index.embeddings(&rtxn, docid).unwrap();
-    let (embedding, _) = &embeddings["manual"];
+    let EmbeddingsWithMetadata { embeddings: embedding, .. } = &embeddings["manual"];
     assert!(!embedding.is_empty(), "{embedding:?}");
 
     index_scheduler

crates/index-scheduler/src/test_utils.rs

@@ -98,8 +98,8 @@ impl IndexScheduler {
             indexes_path: tempdir.path().join("indexes"),
             snapshots_path: tempdir.path().join("snapshots"),
             dumps_path: tempdir.path().join("dumps"),
-            webhook_url: None,
-            webhook_authorization_header: None,
+            cli_webhook_url: None,
+            cli_webhook_authorization: None,
             task_db_size: 1000 * 1000 * 10, // 10 MB, we don't use MiB on purpose.
             index_base_map_size: 1000 * 1000, // 1 MB, we don't use MiB on purpose.
             enable_mdb_writemap: false,

crates/index-scheduler/src/upgrade/mod.rs

@@ -39,6 +39,7 @@ pub fn upgrade_index_scheduler(
         (1, 13, _) => 0,
         (1, 14, _) => 0,
         (1, 15, _) => 0,
+        (1, 16, _) => 0,
         (major, minor, patch) => {
             if major > current_major
                 || (major == current_major && minor > current_minor)

crates/meilisearch-auth/src/lib.rs

@@ -158,7 +158,7 @@ impl AuthController {
         self.store.delete_all_keys()
     }
 
-    /// Delete all the keys in the DB.
+    /// Insert a key directly into the store.
     pub fn raw_insert_key(&mut self, key: Key) -> Result<()> {
         self.store.put_api_key(key)?;
         Ok(())
@@ -351,6 +351,7 @@ pub struct IndexSearchRules {
 
 fn generate_default_keys(store: &HeedAuthStore) -> Result<()> {
     store.put_api_key(Key::default_chat())?;
+    store.put_api_key(Key::default_read_only_admin())?;
     store.put_api_key(Key::default_admin())?;
     store.put_api_key(Key::default_search())?;
 

crates/meilisearch-auth/src/store.rs

@@ -88,7 +88,13 @@ impl HeedAuthStore {
         let mut actions = HashSet::new();
         for action in &key.actions {
             match action {
-                Action::All => actions.extend(enum_iterator::all::<Action>()),
+                Action::All => {
+                    actions.extend(enum_iterator::all::<Action>());
+                    actions.remove(&Action::AllGet);
+                }
+                Action::AllGet => {
+                    actions.extend(enum_iterator::all::<Action>().filter(|a| a.is_read()))
+                }
                 Action::DocumentsAll => {
                     actions.extend(
                         [Action::DocumentsGet, Action::DocumentsDelete, Action::DocumentsAdd]
@@ -131,6 +137,14 @@ impl HeedAuthStore {
                 Action::ChatsSettingsAll => {
                     actions.extend([Action::ChatsSettingsGet, Action::ChatsSettingsUpdate]);
                 }
+                Action::WebhooksAll => {
+                    actions.extend([
+                        Action::WebhooksGet,
+                        Action::WebhooksUpdate,
+                        Action::WebhooksDelete,
+                        Action::WebhooksCreate,
+                    ]);
+                }
                 other => {
                     actions.insert(*other);
                 }

crates/meilisearch-types/Cargo.toml

@@ -24,7 +24,7 @@ enum-iterator = "2.1.0"
 file-store = { path = "../file-store" }
 flate2 = "1.1.2"
 fst = "0.4.7"
-memmap2 = "0.9.5"
+memmap2 = "0.9.7"
 milli = { path = "../milli" }
 roaring = { version = "0.10.12", features = ["serde"] }
 rustc-hash = "2.1.1"

crates/meilisearch-types/src/error.rs

@@ -237,6 +237,7 @@ InvalidDocumentRetrieveVectors                 , InvalidRequest       , BAD_REQU
 MissingDocumentFilter                          , InvalidRequest       , BAD_REQUEST ;
 MissingDocumentEditionFunction                 , InvalidRequest       , BAD_REQUEST ;
 InvalidDocumentFilter                          , InvalidRequest       , BAD_REQUEST ;
+InvalidDocumentSort                            , InvalidRequest       , BAD_REQUEST ;
 InvalidDocumentGeoField                        , InvalidRequest       , BAD_REQUEST ;
 InvalidVectorDimensions                        , InvalidRequest       , BAD_REQUEST ;
 InvalidVectorsType                             , InvalidRequest       , BAD_REQUEST ;
@@ -415,8 +416,18 @@ InvalidChatCompletionPrompts                   , InvalidRequest       , BAD_REQU
 InvalidChatCompletionSystemPrompt              , InvalidRequest       , BAD_REQUEST ;
 InvalidChatCompletionSearchDescriptionPrompt   , InvalidRequest       , BAD_REQUEST ;
 InvalidChatCompletionSearchQueryParamPrompt    , InvalidRequest       , BAD_REQUEST ;
+InvalidChatCompletionSearchFilterParamPrompt   , InvalidRequest       , BAD_REQUEST ;
 InvalidChatCompletionSearchIndexUidParamPrompt , InvalidRequest       , BAD_REQUEST ;
-InvalidChatCompletionPreQueryPrompt            , InvalidRequest       , BAD_REQUEST
+InvalidChatCompletionPreQueryPrompt            , InvalidRequest       , BAD_REQUEST ;
+// Webhooks
+InvalidWebhooks                                , InvalidRequest       , BAD_REQUEST ;
+InvalidWebhookUrl                              , InvalidRequest       , BAD_REQUEST ;
+InvalidWebhookHeaders                          , InvalidRequest       , BAD_REQUEST ;
+ImmutableWebhook                               , InvalidRequest       , BAD_REQUEST ;
+InvalidWebhookUuid                             , InvalidRequest       , BAD_REQUEST ;
+WebhookNotFound                                , InvalidRequest       , NOT_FOUND ;
+ImmutableWebhookUuid                           , InvalidRequest       , BAD_REQUEST ;
+ImmutableWebhookIsEditable                     , InvalidRequest       , BAD_REQUEST
 }
 
 impl ErrorCode for JoinError {
@@ -476,7 +487,8 @@ impl ErrorCode for milli::Error {
                     UserError::InvalidDistinctAttribute { .. } => Code::InvalidSearchDistinct,
                     UserError::SortRankingRuleMissing => Code::InvalidSearchSort,
                     UserError::InvalidFacetsDistribution { .. } => Code::InvalidSearchFacets,
-                    UserError::InvalidSortableAttribute { .. } => Code::InvalidSearchSort,
+                    UserError::InvalidSearchSortableAttribute { .. } => Code::InvalidSearchSort,
+                    UserError::InvalidDocumentSortableAttribute { .. } => Code::InvalidDocumentSort,
                     UserError::InvalidSearchableAttribute { .. } => {
                         Code::InvalidSearchAttributesToSearchOn
                     }
@@ -494,7 +506,8 @@ impl ErrorCode for milli::Error {
                     UserError::InvalidVectorsMapType { .. }
                     | UserError::InvalidVectorsEmbedderConf { .. } => Code::InvalidVectorsType,
                     UserError::TooManyVectors(_, _) => Code::TooManyVectors,
-                    UserError::SortError(_) => Code::InvalidSearchSort,
+                    UserError::SortError { search: true, .. } => Code::InvalidSearchSort,
+                    UserError::SortError { search: false, .. } => Code::InvalidDocumentSort,
                     UserError::InvalidMinTypoWordLenSetting(_, _) => {
                         Code::InvalidSettingsTypoTolerance
                     }

crates/meilisearch-types/src/features.rs

@@ -4,10 +4,11 @@ use serde::{Deserialize, Serialize};
 
 use crate::error::{Code, ResponseError};
 
-pub const DEFAULT_CHAT_SYSTEM_PROMPT: &str = "You are a highly capable research assistant with access to powerful search tools. IMPORTANT INSTRUCTIONS:1. When answering questions, you MUST make multiple tool calls (at least 2-3) to gather comprehensive information.2. Use different search queries for each tool call - vary keywords, rephrase questions, and explore different semantic angles to ensure broad coverage.3. Always explicitly announce BEFORE making each tool call by saying: \"I'll search for [specific information] now.\"4. Combine information from ALL tool calls to provide complete, nuanced answers rather than relying on a single source.5. For complex topics, break down your research into multiple targeted queries rather than using a single generic search.";
+pub const DEFAULT_CHAT_SYSTEM_PROMPT: &str = "You are a highly capable research assistant with access to powerful search tools. IMPORTANT INSTRUCTIONS:1. When answering questions, you MUST make multiple tool calls (at least 2-3) to gather comprehensive information.2. Use different search queries for each tool call - vary keywords, rephrase questions, and explore different semantic angles to ensure broad coverage.3. Always explicitly announce BEFORE making each tool call by saying: \"I'll search for [specific information] now.\"4. Combine information from ALL tool calls to provide complete, nuanced answers rather than relying on a single source.5. For complex topics, break down your research into multiple targeted queries rather than using a single generic search. Meilisearch doesn't use the colon (:) syntax to filter but rather the equal (=) one. Separate filters from query and keep the q parameter empty if needed. Same for the filter parameter: keep it empty if need be. If you need to find documents that CONTAINS keywords simply put the keywords in the q parameter do no use a filter for this purpose. Whenever you get an error, read the error message and fix your error. ";
 pub const DEFAULT_CHAT_SEARCH_DESCRIPTION_PROMPT: &str =
-    "Search the database for relevant JSON documents using an optional query.";
+    "Query: 'best story about Rust before 2018' with year: 2018, 2020, 2021\nlabel: analysis, golang, javascript\ntype: story, link\nvote: 300, 298, 278\n: {\"q\": \"\", \"filter\": \"category = Rust AND type = story AND year < 2018 AND vote > 100\"}\nQuery: 'A black or green car that can go fast with red brakes' with maxspeed_kmh: 200, 150, 130\ncolor: black, grey, red, green\nbrand: Toyota, Renault, Jeep, Ferrari\n: {\"q\": \"red brakes\", \"filter\": \"maxspeed_kmh > 150 AND color IN ['black', green]\"}\nQuery: 'Superman movie released in 2018 or after' with year: 2018, 2020, 2021\ngenres: Drama, Comedy, Adventure, Fiction\n: {\"q\":\"Superman\",\"filter\":\"genres IN [Adventure, Fiction] AND year >= 2018\"}";
 pub const DEFAULT_CHAT_SEARCH_Q_PARAM_PROMPT: &str = "The search query string used to find relevant documents in the index. This should contain keywords or phrases that best represent what the user is looking for. More specific queries will yield more precise results.";
+pub const DEFAULT_CHAT_SEARCH_FILTER_PARAM_PROMPT: &str = "The search filter string used to find relevant documents in the index. It supports parentheses, `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox`. Here is an example: \"price > 100 AND category = 'electronics'\". The following is a list of fields that can be filtered on: ";
 pub const DEFAULT_CHAT_SEARCH_INDEX_UID_PARAM_PROMPT: &str = "The name of the index to search within. An index is a collection of documents organized for search. Selecting the right index ensures the most relevant results for the user query.";
 
 #[derive(Serialize, Deserialize, Debug, Clone, Copy, Default, PartialEq, Eq)]
@@ -161,18 +162,31 @@ impl ChatCompletionSource {
 #[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq)]
 #[serde(rename_all = "camelCase")]
 pub struct ChatCompletionPrompts {
+    #[serde(default)]
     pub system: String,
+    #[serde(default)]
     pub search_description: String,
+    #[serde(default)]
     pub search_q_param: String,
+    #[serde(default = "default_search_filter_param")]
+    pub search_filter_param: String,
+    #[serde(default)]
     pub search_index_uid_param: String,
 }
 
+/// This function is used for when the search_filter_param is
+/// not provided and this can happen when the database is in v1.15.
+fn default_search_filter_param() -> String {
+    DEFAULT_CHAT_SEARCH_FILTER_PARAM_PROMPT.to_string()
+}
+
 impl Default for ChatCompletionPrompts {
     fn default() -> Self {
         Self {
             system: DEFAULT_CHAT_SYSTEM_PROMPT.to_string(),
             search_description: DEFAULT_CHAT_SEARCH_DESCRIPTION_PROMPT.to_string(),
             search_q_param: DEFAULT_CHAT_SEARCH_Q_PARAM_PROMPT.to_string(),
+            search_filter_param: DEFAULT_CHAT_SEARCH_FILTER_PARAM_PROMPT.to_string(),
             search_index_uid_param: DEFAULT_CHAT_SEARCH_INDEX_UID_PARAM_PROMPT.to_string(),
         }
     }

crates/meilisearch-types/src/keys.rs

@@ -144,6 +144,21 @@ impl Key {
         }
     }
 
+    pub fn default_read_only_admin() -> Self {
+        let now = OffsetDateTime::now_utc();
+        let uid = Uuid::new_v4();
+        Self {
+            name: Some("Default Read-Only Admin API Key".to_string()),
+            description: Some("Use it to read information across the whole database. Caution! Do not expose this key on a public frontend".to_string()),
+            uid,
+            actions: vec![Action::AllGet, Action::KeysGet],
+            indexes: vec![IndexUidPattern::all()],
+            expires_at: None,
+            created_at: now,
+            updated_at: now,
+        }
+    }
+
     pub fn default_search() -> Self {
         let now = OffsetDateTime::now_utc();
         let uid = Uuid::new_v4();
@@ -347,6 +362,24 @@ pub enum Action {
     #[serde(rename = "chatsSettings.update")]
     #[deserr(rename = "chatsSettings.update")]
     ChatsSettingsUpdate,
+    #[serde(rename = "*.get")]
+    #[deserr(rename = "*.get")]
+    AllGet,
+    #[serde(rename = "webhooks.get")]
+    #[deserr(rename = "webhooks.get")]
+    WebhooksGet,
+    #[serde(rename = "webhooks.update")]
+    #[deserr(rename = "webhooks.update")]
+    WebhooksUpdate,
+    #[serde(rename = "webhooks.delete")]
+    #[deserr(rename = "webhooks.delete")]
+    WebhooksDelete,
+    #[serde(rename = "webhooks.create")]
+    #[deserr(rename = "webhooks.create")]
+    WebhooksCreate,
+    #[serde(rename = "webhooks.*")]
+    #[deserr(rename = "webhooks.*")]
+    WebhooksAll,
 }
 
 impl Action {
@@ -385,6 +418,7 @@ impl Action {
             METRICS_GET => Some(Self::MetricsGet),
             DUMPS_ALL => Some(Self::DumpsAll),
             DUMPS_CREATE => Some(Self::DumpsCreate),
+            SNAPSHOTS_ALL => Some(Self::SnapshotsAll),
             SNAPSHOTS_CREATE => Some(Self::SnapshotsCreate),
             VERSION => Some(Self::Version),
             KEYS_CREATE => Some(Self::KeysAdd),
@@ -393,12 +427,71 @@ impl Action {
             KEYS_DELETE => Some(Self::KeysDelete),
             EXPERIMENTAL_FEATURES_GET => Some(Self::ExperimentalFeaturesGet),
             EXPERIMENTAL_FEATURES_UPDATE => Some(Self::ExperimentalFeaturesUpdate),
+            EXPORT => Some(Self::Export),
             NETWORK_GET => Some(Self::NetworkGet),
             NETWORK_UPDATE => Some(Self::NetworkUpdate),
+            ALL_GET => Some(Self::AllGet),
+            WEBHOOKS_GET => Some(Self::WebhooksGet),
+            WEBHOOKS_UPDATE => Some(Self::WebhooksUpdate),
+            WEBHOOKS_DELETE => Some(Self::WebhooksDelete),
+            WEBHOOKS_CREATE => Some(Self::WebhooksCreate),
+            WEBHOOKS_ALL => Some(Self::WebhooksAll),
             _otherwise => None,
         }
     }
 
+    /// Whether the action should be included in [Action::AllRead].
+    pub fn is_read(&self) -> bool {
+        use Action::*;
+
+        // It's using an exhaustive match to force the addition of new actions.
+        match self {
+            // Any action that expands to others must return false, as it wouldn't be able to expand recursively.
+            All | AllGet | DocumentsAll | IndexesAll | ChatsAll | TasksAll | SettingsAll
+            | StatsAll | MetricsAll | DumpsAll | SnapshotsAll | ChatsSettingsAll | WebhooksAll => {
+                false
+            }
+
+            Search => true,
+            DocumentsAdd => false,
+            DocumentsGet => true,
+            DocumentsDelete => false,
+            Export => true,
+            IndexesAdd => false,
+            IndexesGet => true,
+            IndexesUpdate => false,
+            IndexesDelete => false,
+            IndexesSwap => false,
+            TasksCancel => false,
+            TasksDelete => false,
+            TasksGet => true,
+            SettingsGet => true,
+            SettingsUpdate => false,
+            StatsGet => true,
+            MetricsGet => true,
+            DumpsCreate => false,
+            SnapshotsCreate => false,
+            Version => true,
+            KeysAdd => false,
+            KeysGet => false, // Disabled in order to prevent privilege escalation
+            KeysUpdate => false,
+            KeysDelete => false,
+            ExperimentalFeaturesGet => true,
+            ExperimentalFeaturesUpdate => false,
+            NetworkGet => true,
+            NetworkUpdate => false,
+            ChatCompletions => false, // Disabled because it might trigger generation of new chats
+            ChatsGet => true,
+            ChatsDelete => false,
+            ChatsSettingsGet => true,
+            ChatsSettingsUpdate => false,
+            WebhooksGet => true,
+            WebhooksUpdate => false,
+            WebhooksDelete => false,
+            WebhooksCreate => false,
+        }
+    }
+
     pub const fn repr(&self) -> u8 {
         *self as u8
     }
@@ -408,6 +501,7 @@ pub mod actions {
     use super::Action::*;
 
     pub(crate) const ALL: u8 = All.repr();
+    pub const ALL_GET: u8 = AllGet.repr();
     pub const SEARCH: u8 = Search.repr();
     pub const DOCUMENTS_ALL: u8 = DocumentsAll.repr();
     pub const DOCUMENTS_ADD: u8 = DocumentsAdd.repr();
@@ -432,6 +526,7 @@ pub mod actions {
     pub const METRICS_GET: u8 = MetricsGet.repr();
     pub const DUMPS_ALL: u8 = DumpsAll.repr();
     pub const DUMPS_CREATE: u8 = DumpsCreate.repr();
+    pub const SNAPSHOTS_ALL: u8 = SnapshotsAll.repr();
     pub const SNAPSHOTS_CREATE: u8 = SnapshotsCreate.repr();
     pub const VERSION: u8 = Version.repr();
     pub const KEYS_CREATE: u8 = KeysAdd.repr();
@@ -453,4 +548,80 @@ pub mod actions {
     pub const CHATS_SETTINGS_ALL: u8 = ChatsSettingsAll.repr();
     pub const CHATS_SETTINGS_GET: u8 = ChatsSettingsGet.repr();
     pub const CHATS_SETTINGS_UPDATE: u8 = ChatsSettingsUpdate.repr();
+
+    pub const WEBHOOKS_GET: u8 = WebhooksGet.repr();
+    pub const WEBHOOKS_UPDATE: u8 = WebhooksUpdate.repr();
+    pub const WEBHOOKS_DELETE: u8 = WebhooksDelete.repr();
+    pub const WEBHOOKS_CREATE: u8 = WebhooksCreate.repr();
+    pub const WEBHOOKS_ALL: u8 = WebhooksAll.repr();
+}
+
+#[cfg(test)]
+pub(crate) mod test {
+    use super::actions::*;
+    use super::Action::*;
+    use super::*;
+
+    #[test]
+    fn test_action_repr_and_constants() {
+        assert!(All.repr() == 0 && ALL == 0);
+        assert!(Search.repr() == 1 && SEARCH == 1);
+        assert!(DocumentsAll.repr() == 2 && DOCUMENTS_ALL == 2);
+        assert!(DocumentsAdd.repr() == 3 && DOCUMENTS_ADD == 3);
+        assert!(DocumentsGet.repr() == 4 && DOCUMENTS_GET == 4);
+        assert!(DocumentsDelete.repr() == 5 && DOCUMENTS_DELETE == 5);
+        assert!(IndexesAll.repr() == 6 && INDEXES_ALL == 6);
+        assert!(IndexesAdd.repr() == 7 && INDEXES_CREATE == 7);
+        assert!(IndexesGet.repr() == 8 && INDEXES_GET == 8);
+        assert!(IndexesUpdate.repr() == 9 && INDEXES_UPDATE == 9);
+        assert!(IndexesDelete.repr() == 10 && INDEXES_DELETE == 10);
+        assert!(IndexesSwap.repr() == 11 && INDEXES_SWAP == 11);
+        assert!(TasksAll.repr() == 12 && TASKS_ALL == 12);
+        assert!(TasksCancel.repr() == 13 && TASKS_CANCEL == 13);
+        assert!(TasksDelete.repr() == 14 && TASKS_DELETE == 14);
+        assert!(TasksGet.repr() == 15 && TASKS_GET == 15);
+        assert!(SettingsAll.repr() == 16 && SETTINGS_ALL == 16);
+        assert!(SettingsGet.repr() == 17 && SETTINGS_GET == 17);
+        assert!(SettingsUpdate.repr() == 18 && SETTINGS_UPDATE == 18);
+        assert!(StatsAll.repr() == 19 && STATS_ALL == 19);
+        assert!(StatsGet.repr() == 20 && STATS_GET == 20);
+        assert!(MetricsAll.repr() == 21 && METRICS_ALL == 21);
+        assert!(MetricsGet.repr() == 22 && METRICS_GET == 22);
+        assert!(DumpsAll.repr() == 23 && DUMPS_ALL == 23);
+        assert!(DumpsCreate.repr() == 24 && DUMPS_CREATE == 24);
+        assert!(SnapshotsAll.repr() == 25 && SNAPSHOTS_ALL == 25);
+        assert!(SnapshotsCreate.repr() == 26 && SNAPSHOTS_CREATE == 26);
+        assert!(Version.repr() == 27 && VERSION == 27);
+        assert!(KeysAdd.repr() == 28 && KEYS_CREATE == 28);
+        assert!(KeysGet.repr() == 29 && KEYS_GET == 29);
+        assert!(KeysUpdate.repr() == 30 && KEYS_UPDATE == 30);
+        assert!(KeysDelete.repr() == 31 && KEYS_DELETE == 31);
+        assert!(ExperimentalFeaturesGet.repr() == 32 && EXPERIMENTAL_FEATURES_GET == 32);
+        assert!(ExperimentalFeaturesUpdate.repr() == 33 && EXPERIMENTAL_FEATURES_UPDATE == 33);
+        assert!(Export.repr() == 34 && EXPORT == 34);
+        assert!(NetworkGet.repr() == 35 && NETWORK_GET == 35);
+        assert!(NetworkUpdate.repr() == 36 && NETWORK_UPDATE == 36);
+        assert!(ChatCompletions.repr() == 37 && CHAT_COMPLETIONS == 37);
+        assert!(ChatsAll.repr() == 38 && CHATS_ALL == 38);
+        assert!(ChatsGet.repr() == 39 && CHATS_GET == 39);
+        assert!(ChatsDelete.repr() == 40 && CHATS_DELETE == 40);
+        assert!(ChatsSettingsAll.repr() == 41 && CHATS_SETTINGS_ALL == 41);
+        assert!(ChatsSettingsGet.repr() == 42 && CHATS_SETTINGS_GET == 42);
+        assert!(ChatsSettingsUpdate.repr() == 43 && CHATS_SETTINGS_UPDATE == 43);
+        assert!(AllGet.repr() == 44 && ALL_GET == 44);
+        assert!(WebhooksGet.repr() == 45 && WEBHOOKS_GET == 45);
+        assert!(WebhooksUpdate.repr() == 46 && WEBHOOKS_UPDATE == 46);
+        assert!(WebhooksDelete.repr() == 47 && WEBHOOKS_DELETE == 47);
+        assert!(WebhooksCreate.repr() == 48 && WEBHOOKS_CREATE == 48);
+        assert!(WebhooksAll.repr() == 49 && WEBHOOKS_ALL == 49);
+    }
+
+    #[test]
+    fn test_from_repr() {
+        for action in enum_iterator::all::<Action>() {
+            let repr = action.repr();
+            let action_from_repr = Action::from_repr(repr);
+            assert_eq!(Some(action), action_from_repr, "Failed for action: {:?}", action);
+        }
+    }
 }

crates/meilisearch-types/src/lib.rs

@@ -15,6 +15,7 @@ pub mod star_or;
 pub mod task_view;
 pub mod tasks;
 pub mod versioning;
+pub mod webhooks;
 pub use milli::{heed, Index};
 use uuid::Uuid;
 pub use versioning::VERSION_FILE_NAME;

crates/meilisearch-types/src/webhooks.rs

@@ -0,0 +1,28 @@
+use std::collections::BTreeMap;
+
+use serde::{Deserialize, Serialize};
+use uuid::Uuid;
+
+#[derive(Debug, Serialize, Deserialize, Clone, PartialEq)]
+#[serde(rename_all = "camelCase")]
+pub struct Webhook {
+    pub url: String,
+    #[serde(default)]
+    pub headers: BTreeMap<String, String>,
+}
+
+#[derive(Debug, Serialize, Default, Clone, PartialEq)]
+#[serde(rename_all = "camelCase")]
+pub struct WebhooksView {
+    #[serde(default)]
+    pub webhooks: BTreeMap<Uuid, Webhook>,
+}
+
+// Same as the WebhooksView instead it should never contains the CLI webhooks.
+// It's the right structure to use in the dump
+#[derive(Debug, Deserialize, Serialize, Default, Clone, PartialEq)]
+#[serde(rename_all = "camelCase")]
+pub struct WebhooksDumpView {
+    #[serde(default)]
+    pub webhooks: BTreeMap<Uuid, Webhook>,
+}

crates/meilisearch/Cargo.toml

@@ -50,6 +50,7 @@ jsonwebtoken = "9.3.1"
 lazy_static = "1.5.0"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
+memmap2 = "0.9.7"
 mimalloc = { version = "0.1.47", default-features = false }
 mime = "0.3.17"
 num_cpus = "1.17.0"
@@ -169,5 +170,5 @@ german = ["meilisearch-types/german"]
 turkish = ["meilisearch-types/turkish"]
 
 [package.metadata.mini-dashboard]
-assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.20/build.zip"
-sha1 = "82a7ddd7bf14bb5323c3d235d2b62892a98b6a59"
+assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.22/build.zip"
+sha1 = "b70b2036b5f167da9ea0b637da8b320c7ea88254"

crates/meilisearch/src/analytics/mock_analytics.rs

@@ -104,6 +104,4 @@ impl Analytics for MockAnalytics {
         _request: &HttpRequest,
     ) {
     }
-    fn get_fetch_documents(&self, _documents_query: &DocumentFetchKind, _request: &HttpRequest) {}
-    fn post_fetch_documents(&self, _documents_query: &DocumentFetchKind, _request: &HttpRequest) {}
 }

crates/meilisearch/src/analytics/mod.rs

@@ -73,12 +73,6 @@ pub enum DocumentDeletionKind {
     PerFilter,
 }
 
-#[derive(Copy, Clone, Debug, PartialEq, Eq)]
-pub enum DocumentFetchKind {
-    PerDocumentId { retrieve_vectors: bool },
-    Normal { with_filter: bool, limit: usize, offset: usize, retrieve_vectors: bool },
-}
-
 /// To send an event to segment, your event must be able to aggregate itself with another event of the same type.
 pub trait Aggregate: 'static + mopa::Any + Send {
     /// The name of the event that will be sent to segment.

crates/meilisearch/src/analytics/segment_analytics.rs

@@ -203,6 +203,7 @@ struct Infos {
     experimental_composite_embedders: bool,
     experimental_embedding_cache_entries: usize,
     experimental_no_snapshot_compaction: bool,
+    experimental_no_edition_2024_for_dumps: bool,
     experimental_no_edition_2024_for_settings: bool,
     gpu_enabled: bool,
     db_path: bool,
@@ -293,6 +294,7 @@ impl Infos {
             max_indexing_threads,
             skip_index_budget: _,
             experimental_no_edition_2024_for_settings,
+            experimental_no_edition_2024_for_dumps,
         } = indexer_options;
 
         let RuntimeTogglableFeatures {
@@ -329,6 +331,7 @@ impl Infos {
             experimental_composite_embedders: composite_embedders,
             experimental_embedding_cache_entries,
             experimental_no_snapshot_compaction,
+            experimental_no_edition_2024_for_dumps,
             gpu_enabled: meilisearch_types::milli::vector::is_cuda_enabled(),
             db_path: db_path != PathBuf::from("./data.ms"),
             import_dump: import_dump.is_some(),

crates/meilisearch/src/error.rs

@@ -49,7 +49,7 @@ pub enum MeilisearchHttpError {
     TooManySearchRequests(usize),
     #[error("Internal error: Search limiter is down.")]
     SearchLimiterIsDown,
-    #[error("The provided payload reached the size limit. The maximum accepted payload size is {}.",  Byte::from_u64(*.0 as u64).get_appropriate_unit(UnitType::Binary))]
+    #[error("The provided payload reached the size limit. The maximum accepted payload size is {}.", Byte::from_u64(*.0 as u64).get_appropriate_unit(if *.0 % 1024 == 0 { UnitType::Binary } else { UnitType::Decimal }))]
     PayloadTooLarge(usize),
     #[error("Two indexes must be given for each swap. The list `[{}]` contains {} indexes.",
         .0.iter().map(|uid| format!("\"{uid}\"")).collect::<Vec<_>>().join(", "), .0.len()

crates/meilisearch/src/lib.rs

@@ -30,6 +30,7 @@ use actix_web::web::Data;
 use actix_web::{web, HttpRequest};
 use analytics::Analytics;
 use anyhow::bail;
+use bumpalo::Bump;
 use error::PayloadError;
 use extractors::payload::PayloadConfig;
 use index_scheduler::versioning::Versioning;
@@ -38,6 +39,7 @@ use meilisearch_auth::{open_auth_store_env, AuthController};
 use meilisearch_types::milli::constants::VERSION_MAJOR;
 use meilisearch_types::milli::documents::{DocumentsBatchBuilder, DocumentsBatchReader};
 use meilisearch_types::milli::progress::{EmbedderStats, Progress};
+use meilisearch_types::milli::update::new::indexer;
 use meilisearch_types::milli::update::{
     default_thread_pool_and_threads, IndexDocumentsConfig, IndexDocumentsMethod, IndexerConfig,
 };
@@ -221,8 +223,8 @@ pub fn setup_meilisearch(opt: &Opt) -> anyhow::Result<(Arc<IndexScheduler>, Arc<
         indexes_path: opt.db_path.join("indexes"),
         snapshots_path: opt.snapshot_dir.clone(),
         dumps_path: opt.dump_dir.clone(),
-        webhook_url: opt.task_webhook_url.as_ref().map(|url| url.to_string()),
-        webhook_authorization_header: opt.task_webhook_authorization_header.clone(),
+        cli_webhook_url: opt.task_webhook_url.as_ref().map(|url| url.to_string()),
+        cli_webhook_authorization: opt.task_webhook_authorization_header.clone(),
         task_db_size: opt.max_task_db_size.as_u64() as usize,
         index_base_map_size: opt.max_index_size.as_u64() as usize,
         enable_mdb_writemap: opt.experimental_reduce_indexing_memory_usage,
@@ -489,7 +491,12 @@ fn import_dump(
         let _ = std::fs::write(db_path.join("instance-uid"), instance_uid.to_string().as_bytes());
     };
 
-    // 2. Import the `Key`s.
+    // 2. Import the webhooks
+    if let Some(webhooks) = dump_reader.webhooks() {
+        index_scheduler.update_runtime_webhooks(webhooks.webhooks.clone())?;
+    }
+
+    // 3. Import the `Key`s.
     let mut keys = Vec::new();
     auth.raw_delete_all_keys()?;
     for key in dump_reader.keys()? {
@@ -498,20 +505,20 @@ fn import_dump(
         keys.push(key);
     }
 
-    // 3. Import the `ChatCompletionSettings`s.
+    // 4. Import the `ChatCompletionSettings`s.
     for result in dump_reader.chat_completions_settings()? {
         let (name, settings) = result?;
         index_scheduler.put_chat_settings(&name, &settings)?;
     }
 
-    // 4. Import the runtime features and network
+    // 5. Import the runtime features and network
     let features = dump_reader.features()?.unwrap_or_default();
     index_scheduler.put_runtime_features(features)?;
 
     let network = dump_reader.network()?.cloned().unwrap_or_default();
     index_scheduler.put_network(network)?;
 
-    // 4.1 Use all cpus to process dump if `max_indexing_threads` not configured
+    // 5.1 Use all cpus to process dump if `max_indexing_threads` not configured
     let backup_config;
     let base_config = index_scheduler.indexer_config();
 
@@ -528,12 +535,12 @@ fn import_dump(
     // /!\ The tasks must be imported AFTER importing the indexes or else the scheduler might
     // try to process tasks while we're trying to import the indexes.
 
-    // 5. Import the indexes.
+    // 6. Import the indexes.
     for index_reader in dump_reader.indexes()? {
         let mut index_reader = index_reader?;
         let metadata = index_reader.metadata();
         let uid = metadata.uid.clone();
-        tracing::info!("Importing index `{}`.", metadata.uid);
+        tracing::info!("Importing index `{uid}`.");
 
         let date = Some((metadata.created_at, metadata.updated_at));
         let index = index_scheduler.create_raw_index(&metadata.uid, date)?;
@@ -541,71 +548,123 @@ fn import_dump(
         let mut wtxn = index.write_txn()?;
 
         let mut builder = milli::update::Settings::new(&mut wtxn, &index, indexer_config);
-        // 5.1 Import the primary key if there is one.
+        // 6.1 Import the primary key if there is one.
         if let Some(ref primary_key) = metadata.primary_key {
             builder.set_primary_key(primary_key.to_string());
         }
 
-        // 5.2 Import the settings.
+        // 6.2 Import the settings.
         tracing::info!("Importing the settings.");
         let settings = index_reader.settings()?;
         apply_settings_to_builder(&settings, &mut builder);
         let embedder_stats: Arc<EmbedderStats> = Default::default();
         builder.execute(&|| false, &progress, embedder_stats.clone())?;
+        wtxn.commit()?;
 
-        // 5.3 Import the documents.
-        // 5.3.1 We need to recreate the grenad+obkv format accepted by the index.
-        tracing::info!("Importing the documents.");
-        let file = tempfile::tempfile()?;
-        let mut builder = DocumentsBatchBuilder::new(BufWriter::new(file));
-        for document in index_reader.documents()? {
-            builder.append_json_object(&document?)?;
+        let mut wtxn = index.write_txn()?;
+        let rtxn = index.read_txn()?;
+
+        if index_scheduler.no_edition_2024_for_dumps() {
+            // 6.3 Import the documents.
+            // 6.3.1 We need to recreate the grenad+obkv format accepted by the index.
+            tracing::info!("Importing the documents.");
+            let file = tempfile::tempfile()?;
+            let mut builder = DocumentsBatchBuilder::new(BufWriter::new(file));
+            for document in index_reader.documents()? {
+                builder.append_json_object(&document?)?;
+            }
+
+            // This flush the content of the batch builder.
+            let file = builder.into_inner()?.into_inner()?;
+
+            // 6.3.2 We feed it to the milli index.
+            let reader = BufReader::new(file);
+            let reader = DocumentsBatchReader::from_reader(reader)?;
+
+            let embedder_configs = index.embedding_configs().embedding_configs(&wtxn)?;
+            let embedders = index_scheduler.embedders(uid.to_string(), embedder_configs)?;
+
+            let builder = milli::update::IndexDocuments::new(
+                &mut wtxn,
+                &index,
+                indexer_config,
+                IndexDocumentsConfig {
+                    update_method: IndexDocumentsMethod::ReplaceDocuments,
+                    ..Default::default()
+                },
+                |indexing_step| tracing::trace!("update: {:?}", indexing_step),
+                || false,
+                &embedder_stats,
+            )?;
+
+            let builder = builder.with_embedders(embedders);
+
+            let (builder, user_result) = builder.add_documents(reader)?;
+            let user_result = user_result?;
+            tracing::info!(documents_found = user_result, "{} documents found.", user_result);
+            builder.execute()?;
+        } else {
+            let db_fields_ids_map = index.fields_ids_map(&rtxn)?;
+            let primary_key = index.primary_key(&rtxn)?;
+            let mut new_fields_ids_map = db_fields_ids_map.clone();
+
+            let mut indexer = indexer::DocumentOperation::new();
+            let embedders = index.embedding_configs().embedding_configs(&rtxn)?;
+            let embedders = index_scheduler.embedders(uid.clone(), embedders)?;
+
+            let mmap = unsafe { memmap2::Mmap::map(index_reader.documents_file())? };
+
+            indexer.replace_documents(&mmap)?;
+
+            let indexer_config = index_scheduler.indexer_config();
+            let pool = &indexer_config.thread_pool;
+
+            let indexer_alloc = Bump::new();
+            let (document_changes, mut operation_stats, primary_key) = indexer.into_changes(
+                &indexer_alloc,
+                &index,
+                &rtxn,
+                primary_key,
+                &mut new_fields_ids_map,
+                &|| false, // never stop processing a dump
+                progress.clone(),
+            )?;
+
+            let operation_stats = operation_stats.pop().unwrap();
+            if let Some(error) = operation_stats.error {
+                return Err(error.into());
+            }
+
+            let _congestion = indexer::index(
+                &mut wtxn,
+                &index,
+                pool,
+                indexer_config.grenad_parameters(),
+                &db_fields_ids_map,
+                new_fields_ids_map,
+                primary_key,
+                &document_changes,
+                embedders,
+                &|| false, // never stop processing a dump
+                &progress,
+                &embedder_stats,
+            )?;
         }
 
-        // This flush the content of the batch builder.
-        let file = builder.into_inner()?.into_inner()?;
-
-        // 5.3.2 We feed it to the milli index.
-        let reader = BufReader::new(file);
-        let reader = DocumentsBatchReader::from_reader(reader)?;
-
-        let embedder_configs = index.embedding_configs().embedding_configs(&wtxn)?;
-        let embedders = index_scheduler.embedders(uid.to_string(), embedder_configs)?;
-
-        let builder = milli::update::IndexDocuments::new(
-            &mut wtxn,
-            &index,
-            indexer_config,
-            IndexDocumentsConfig {
-                update_method: IndexDocumentsMethod::ReplaceDocuments,
-                ..Default::default()
-            },
-            |indexing_step| tracing::trace!("update: {:?}", indexing_step),
-            || false,
-            &embedder_stats,
-        )?;
-
-        let builder = builder.with_embedders(embedders);
-
-        let (builder, user_result) = builder.add_documents(reader)?;
-        let user_result = user_result?;
-        tracing::info!(documents_found = user_result, "{} documents found.", user_result);
-        builder.execute()?;
         wtxn.commit()?;
         tracing::info!("All documents successfully imported.");
-
         index_scheduler.refresh_index_stats(&uid)?;
     }
 
-    // 6. Import the queue
+    // 7. Import the queue
     let mut index_scheduler_dump = index_scheduler.register_dumped_task()?;
-    // 6.1. Import the batches
+    // 7.1. Import the batches
     for ret in dump_reader.batches()? {
         let batch = ret?;
         index_scheduler_dump.register_dumped_batch(batch)?;
     }
 
-    // 6.2. Import the tasks
+    // 7.2. Import the tasks
     for ret in dump_reader.tasks()? {
         let (task, file) = ret?;
         index_scheduler_dump.register_dumped_task(task, file)?;

crates/meilisearch/src/metrics.rs

@@ -15,30 +15,33 @@ lazy_static! {
         "Meilisearch number of degraded search requests"
     ))
     .expect("Can't create a metric");
-    pub static ref MEILISEARCH_CHAT_SEARCH_REQUESTS: IntCounterVec = register_int_counter_vec!(
+    pub static ref MEILISEARCH_CHAT_SEARCHES_TOTAL: IntCounterVec = register_int_counter_vec!(
         opts!(
-            "meilisearch_chat_search_requests",
-            "Meilisearch number of search requests performed by the chat route itself"
+            "meilisearch_chat_searches_total",
+            "Total number of searches performed by the chat route"
         ),
         &["type"]
     )
     .expect("Can't create a metric");
-    pub static ref MEILISEARCH_CHAT_PROMPT_TOKENS_USAGE: IntCounterVec = register_int_counter_vec!(
-        opts!("meilisearch_chat_prompt_tokens_usage", "Meilisearch Chat Prompt Tokens Usage"),
+    pub static ref MEILISEARCH_CHAT_PROMPT_TOKENS_TOTAL: IntCounterVec = register_int_counter_vec!(
+        opts!("meilisearch_chat_prompt_tokens_total", "Total number of prompt tokens consumed"),
         &["workspace", "model"]
     )
     .expect("Can't create a metric");
-    pub static ref MEILISEARCH_CHAT_COMPLETION_TOKENS_USAGE: IntCounterVec =
+    pub static ref MEILISEARCH_CHAT_COMPLETION_TOKENS_TOTAL: IntCounterVec =
         register_int_counter_vec!(
             opts!(
-                "meilisearch_chat_completion_tokens_usage",
-                "Meilisearch Chat Completion Tokens Usage"
+                "meilisearch_chat_completion_tokens_total",
+                "Total number of completion tokens consumed"
             ),
             &["workspace", "model"]
         )
         .expect("Can't create a metric");
-    pub static ref MEILISEARCH_CHAT_TOTAL_TOKENS_USAGE: IntCounterVec = register_int_counter_vec!(
-        opts!("meilisearch_chat_total_tokens_usage", "Meilisearch Chat Total Tokens Usage"),
+    pub static ref MEILISEARCH_CHAT_TOKENS_TOTAL: IntCounterVec = register_int_counter_vec!(
+        opts!(
+            "meilisearch_chat_tokens_total",
+            "Total number of tokens consumed (prompt + completion)"
+        ),
         &["workspace", "model"]
     )
     .expect("Can't create a metric");

crates/meilisearch/src/option.rs

@@ -68,6 +68,8 @@ const MEILI_EXPERIMENTAL_LIMIT_BATCHED_TASKS_TOTAL_SIZE: &str =
 const MEILI_EXPERIMENTAL_EMBEDDING_CACHE_ENTRIES: &str =
     "MEILI_EXPERIMENTAL_EMBEDDING_CACHE_ENTRIES";
 const MEILI_EXPERIMENTAL_NO_SNAPSHOT_COMPACTION: &str = "MEILI_EXPERIMENTAL_NO_SNAPSHOT_COMPACTION";
+const MEILI_EXPERIMENTAL_NO_EDITION_2024_FOR_DUMPS: &str =
+    "MEILI_EXPERIMENTAL_NO_EDITION_2024_FOR_DUMPS";
 const DEFAULT_CONFIG_FILE_PATH: &str = "./config.toml";
 const DEFAULT_DB_PATH: &str = "./data.ms";
 const DEFAULT_HTTP_ADDR: &str = "localhost:7700";
@@ -204,11 +206,13 @@ pub struct Opt {
     pub env: String,
 
     /// Called whenever a task finishes so a third party can be notified.
+    /// See also the dedicated API `/webhooks`.
     #[clap(long, env = MEILI_TASK_WEBHOOK_URL)]
     pub task_webhook_url: Option<Url>,
 
     /// The Authorization header to send on the webhook URL whenever
     /// a task finishes so a third party can be notified.
+    /// See also the dedicated API `/webhooks`.
     #[clap(long, env = MEILI_TASK_WEBHOOK_AUTHORIZATION_HEADER)]
     pub task_webhook_authorization_header: Option<String>,
 
@@ -759,6 +763,15 @@ pub struct IndexerOpts {
     #[clap(long, env = MEILI_EXPERIMENTAL_NO_EDITION_2024_FOR_SETTINGS)]
     #[serde(default)]
     pub experimental_no_edition_2024_for_settings: bool,
+
+    /// Experimental make dump imports use the old document indexer.
+    ///
+    /// When enabled, Meilisearch will use the old document indexer when importing dumps.
+    ///
+    /// For more information, see <https://github.com/orgs/meilisearch/discussions/851>.
+    #[clap(long, env = MEILI_EXPERIMENTAL_NO_EDITION_2024_FOR_DUMPS)]
+    #[serde(default)]
+    pub experimental_no_edition_2024_for_dumps: bool,
 }
 
 impl IndexerOpts {
@@ -769,6 +782,7 @@ impl IndexerOpts {
             max_indexing_threads,
             skip_index_budget: _,
             experimental_no_edition_2024_for_settings,
+            experimental_no_edition_2024_for_dumps,
         } = self;
         if let Some(max_indexing_memory) = max_indexing_memory.0 {
             export_to_env_if_not_present(
@@ -788,6 +802,12 @@ impl IndexerOpts {
                 experimental_no_edition_2024_for_settings.to_string(),
             );
         }
+        if experimental_no_edition_2024_for_dumps {
+            export_to_env_if_not_present(
+                MEILI_EXPERIMENTAL_NO_EDITION_2024_FOR_DUMPS,
+                experimental_no_edition_2024_for_dumps.to_string(),
+            );
+        }
     }
 }
 
@@ -808,6 +828,7 @@ impl TryFrom<&IndexerOpts> for IndexerConfig {
             skip_index_budget: other.skip_index_budget,
             experimental_no_edition_2024_for_settings: other
                 .experimental_no_edition_2024_for_settings,
+            experimental_no_edition_2024_for_dumps: other.experimental_no_edition_2024_for_dumps,
             chunk_compression_type: Default::default(),
             chunk_compression_level: Default::default(),
             documents_chunk_size: Default::default(),

crates/meilisearch/src/routes/chats/chat_completions.rs

@@ -27,9 +27,10 @@ use meilisearch_types::features::{
     ChatCompletionPrompts as DbChatCompletionPrompts,
     ChatCompletionSource as DbChatCompletionSource, SystemRole,
 };
+use meilisearch_types::heed::RoTxn;
 use meilisearch_types::keys::actions;
 use meilisearch_types::milli::index::ChatConfig;
-use meilisearch_types::milli::{all_obkv_to_json, obkv_to_json, TimeBudget};
+use meilisearch_types::milli::{all_obkv_to_json, obkv_to_json, OrderBy, PatternMatch, TimeBudget};
 use meilisearch_types::{Document, Index};
 use serde::Deserialize;
 use serde_json::json;
@@ -49,8 +50,8 @@ use crate::error::MeilisearchHttpError;
 use crate::extractors::authentication::policies::ActionPolicy;
 use crate::extractors::authentication::{extract_token_from_request, GuardedData, Policy as _};
 use crate::metrics::{
-    MEILISEARCH_CHAT_COMPLETION_TOKENS_USAGE, MEILISEARCH_CHAT_PROMPT_TOKENS_USAGE,
-    MEILISEARCH_CHAT_SEARCH_REQUESTS, MEILISEARCH_CHAT_TOTAL_TOKENS_USAGE,
+    MEILISEARCH_CHAT_COMPLETION_TOKENS_TOTAL, MEILISEARCH_CHAT_PROMPT_TOKENS_TOTAL,
+    MEILISEARCH_CHAT_SEARCHES_TOTAL, MEILISEARCH_CHAT_TOKENS_TOTAL,
     MEILISEARCH_DEGRADED_SEARCH_REQUESTS,
 };
 use crate::routes::chats::utils::SseEventSender;
@@ -169,6 +170,7 @@ fn setup_search_tool(
 
     let mut index_uids = Vec::new();
     let mut function_description = prompts.search_description.clone();
+    let mut filter_description = prompts.search_filter_param.clone();
     index_scheduler.try_for_each_index::<_, ()>(|name, index| {
         // Make sure to skip unauthorized indexes
         if !filters.is_index_authorized(name) {
@@ -180,16 +182,22 @@ fn setup_search_tool(
         let index_description = chat_config.description;
         let _ = writeln!(&mut function_description, "\n\n - {name}: {index_description}\n");
         index_uids.push(name.to_string());
+        let facet_distributions = format_facet_distributions(index, &rtxn, 10).unwrap(); // TODO do not unwrap
+        let _ = writeln!(&mut filter_description, "\n## Facet distributions of the {name} index");
+        let _ = writeln!(&mut filter_description, "{facet_distributions}");
 
         Ok(())
     })?;
 
+    tracing::debug!("LLM function description: {function_description}");
+    tracing::debug!("LLM filter description: {filter_description}");
+
     let tool = ChatCompletionToolArgs::default()
         .r#type(ChatCompletionToolType::Function)
         .function(
             FunctionObjectArgs::default()
                 .name(MEILI_SEARCH_IN_INDEX_FUNCTION_NAME)
-                .description(&function_description)
+                .description(function_description)
                 .parameters(json!({
                     "type": "object",
                     "properties": {
@@ -203,9 +211,13 @@ fn setup_search_tool(
                             // "type": ["string", "null"],
                             "type": "string",
                             "description": prompts.search_q_param,
+                        },
+                        "filter": {
+                            "type": "string",
+                            "description": filter_description,
                         }
                     },
-                    "required": ["index_uid", "q"],
+                    "required": ["index_uid", "q", "filter"],
                     "additionalProperties": false,
                 }))
                 .strict(true)
@@ -247,11 +259,19 @@ async fn process_search_request(
     auth_token: &str,
     index_uid: String,
     q: Option<String>,
+    filter: Option<String>,
 ) -> Result<(Index, Vec<Document>, String), ResponseError> {
     let index = index_scheduler.index(&index_uid)?;
     let rtxn = index.static_read_txn()?;
     let ChatConfig { description: _, prompt: _, search_parameters } = index.chat_config(&rtxn)?;
-    let mut query = SearchQuery { q, ..SearchQuery::from(search_parameters) };
+    let mut query = SearchQuery {
+        q,
+        filter: filter.map(serde_json::Value::from),
+        ..SearchQuery::from(search_parameters)
+    };
+
+    tracing::debug!("LLM query: {:?}", query);
+
     let auth_filter = ActionPolicy::<{ actions::SEARCH }>::authenticate(
         auth_ctrl,
         auth_token,
@@ -280,17 +300,26 @@ async fn process_search_request(
         let (search, _is_finite_pagination, _max_total_hits, _offset) =
             prepare_search(&index_cloned, &rtxn, &query, &search_kind, time_budget, features)?;
 
-        search_from_kind(index_uid, search_kind, search)
-            .map(|(search_results, _)| (rtxn, search_results))
-            .map_err(ResponseError::from)
+        match search_from_kind(index_uid, search_kind, search) {
+            Ok((search_results, _)) => Ok((rtxn, Ok(search_results))),
+            Err(MeilisearchHttpError::Milli {
+                error: meilisearch_types::milli::Error::UserError(user_error),
+                index_name: _,
+            }) => Ok((rtxn, Err(user_error))),
+            Err(err) => Err(ResponseError::from(err)),
+        }
     })
     .await;
     permit.drop().await;
 
-    let output = output?;
+    let output = match output? {
+        Ok((rtxn, Ok(search_results))) => Ok((rtxn, search_results)),
+        Ok((_rtxn, Err(error))) => return Ok((index, Vec::new(), error.to_string())),
+        Err(err) => Err(err),
+    };
     let mut documents = Vec::new();
     if let Ok((ref rtxn, ref search_result)) = output {
-        MEILISEARCH_CHAT_SEARCH_REQUESTS.with_label_values(&["internal"]).inc();
+        MEILISEARCH_CHAT_SEARCHES_TOTAL.with_label_values(&["internal"]).inc();
         if search_result.degraded {
             MEILISEARCH_DEGRADED_SEARCH_REQUESTS.inc();
         }
@@ -395,16 +424,19 @@ async fn non_streamed_chat(
 
                 for call in meili_calls {
                     let result = match serde_json::from_str(&call.function.arguments) {
-                        Ok(SearchInIndexParameters { index_uid, q }) => process_search_request(
-                            &index_scheduler,
-                            auth_ctrl.clone(),
-                            &search_queue,
-                            auth_token,
-                            index_uid,
-                            q,
-                        )
-                        .await
-                        .map_err(|e| e.to_string()),
+                        Ok(SearchInIndexParameters { index_uid, q, filter }) => {
+                            process_search_request(
+                                &index_scheduler,
+                                auth_ctrl.clone(),
+                                &search_queue,
+                                auth_token,
+                                index_uid,
+                                q,
+                                filter,
+                            )
+                            .await
+                            .map_err(|e| e.to_string())
+                        }
                         Err(err) => Err(err.to_string()),
                     };
 
@@ -564,13 +596,13 @@ async fn run_conversation<C: async_openai::config::Config>(
         match result {
             Ok(resp) => {
                 if let Some(usage) = resp.usage.as_ref() {
-                    MEILISEARCH_CHAT_PROMPT_TOKENS_USAGE
+                    MEILISEARCH_CHAT_PROMPT_TOKENS_TOTAL
                         .with_label_values(&[workspace_uid, &chat_completion.model])
                         .inc_by(usage.prompt_tokens as u64);
-                    MEILISEARCH_CHAT_COMPLETION_TOKENS_USAGE
+                    MEILISEARCH_CHAT_COMPLETION_TOKENS_TOTAL
                         .with_label_values(&[workspace_uid, &chat_completion.model])
                         .inc_by(usage.completion_tokens as u64);
-                    MEILISEARCH_CHAT_TOTAL_TOKENS_USAGE
+                    MEILISEARCH_CHAT_TOKENS_TOTAL
                         .with_label_values(&[workspace_uid, &chat_completion.model])
                         .inc_by(usage.total_tokens as u64);
                 }
@@ -719,13 +751,14 @@ async fn handle_meili_tools(
         let mut error = None;
 
         let result = match serde_json::from_str(&call.function.arguments) {
-            Ok(SearchInIndexParameters { index_uid, q }) => match process_search_request(
+            Ok(SearchInIndexParameters { index_uid, q, filter }) => match process_search_request(
                 index_scheduler,
                 auth_ctrl.clone(),
                 search_queue,
                 auth_token,
                 index_uid,
                 q,
+                filter,
             )
             .await
             {
@@ -801,4 +834,42 @@ struct SearchInIndexParameters {
     index_uid: String,
     /// The query parameter to use.
     q: Option<String>,
+    /// The filter parameter to use.
+    filter: Option<String>,
+}
+
+fn format_facet_distributions(
+    index: &Index,
+    rtxn: &RoTxn,
+    max_values_per_facet: usize,
+) -> meilisearch_types::milli::Result<String> {
+    let universe = index.documents_ids(rtxn)?;
+    let rules = index.filterable_attributes_rules(rtxn)?;
+    let fields_ids_map = index.fields_ids_map(rtxn)?;
+    let filterable_attributes = fields_ids_map
+        .names()
+        .filter(|name| rules.iter().any(|rule| matches!(rule.match_str(name), PatternMatch::Match)))
+        .map(|name| (name, OrderBy::Count));
+    let facets_distribution = index
+        .facets_distribution(rtxn)
+        .max_values_per_facet(max_values_per_facet)
+        .candidates(universe)
+        .facets(filterable_attributes)
+        .execute()?;
+
+    let mut output = String::new();
+    for (facet_name, entries) in facets_distribution {
+        let _ = write!(&mut output, "{}: ", facet_name);
+        let total_entries = entries.len();
+        for (i, (value, _count)) in entries.into_iter().enumerate() {
+            let _ = if total_entries.saturating_sub(1) == i {
+                write!(&mut output, "{value}.")
+            } else {
+                write!(&mut output, "{value}, ")
+            };
+        }
+        let _ = writeln!(&mut output);
+    }
+
+    Ok(output)
 }

crates/meilisearch/src/routes/chats/settings.rs

@@ -8,8 +8,8 @@ use meilisearch_types::error::{Code, ResponseError};
 use meilisearch_types::features::{
     ChatCompletionPrompts as DbChatCompletionPrompts, ChatCompletionSettings,
     ChatCompletionSource as DbChatCompletionSource, DEFAULT_CHAT_SEARCH_DESCRIPTION_PROMPT,
-    DEFAULT_CHAT_SEARCH_INDEX_UID_PARAM_PROMPT, DEFAULT_CHAT_SEARCH_Q_PARAM_PROMPT,
-    DEFAULT_CHAT_SYSTEM_PROMPT,
+    DEFAULT_CHAT_SEARCH_FILTER_PARAM_PROMPT, DEFAULT_CHAT_SEARCH_INDEX_UID_PARAM_PROMPT,
+    DEFAULT_CHAT_SEARCH_Q_PARAM_PROMPT, DEFAULT_CHAT_SYSTEM_PROMPT,
 };
 use meilisearch_types::keys::actions;
 use meilisearch_types::milli::update::Setting;
@@ -84,6 +84,11 @@ async fn patch_settings(
                 Setting::Reset => DEFAULT_CHAT_SEARCH_Q_PARAM_PROMPT.to_string(),
                 Setting::NotSet => old_settings.prompts.search_q_param,
             },
+            search_filter_param: match new_prompts.search_filter_param {
+                Setting::Set(new_description) => new_description,
+                Setting::Reset => DEFAULT_CHAT_SEARCH_FILTER_PARAM_PROMPT.to_string(),
+                Setting::NotSet => old_settings.prompts.search_filter_param,
+            },
             search_index_uid_param: match new_prompts.search_index_uid_param {
                 Setting::Set(new_description) => new_description,
                 Setting::Reset => DEFAULT_CHAT_SEARCH_INDEX_UID_PARAM_PROMPT.to_string(),
@@ -252,6 +257,10 @@ pub struct ChatPrompts {
     #[schema(value_type = Option<String>, example = json!("This is query parameter..."))]
     pub search_q_param: Setting<String>,
     #[serde(default)]
+    #[deserr(default, error = DeserrJsonError<InvalidChatCompletionSearchFilterParamPrompt>)]
+    #[schema(value_type = Option<String>, example = json!("This is filter parameter..."))]
+    pub search_filter_param: Setting<String>,
+    #[serde(default)]
     #[deserr(default, error = DeserrJsonError<InvalidChatCompletionSearchIndexUidParamPrompt>)]
     #[schema(value_type = Option<String>, example = json!("This is index you want to search in..."))]
     pub search_index_uid_param: Setting<String>,

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

@@ -1,6 +1,7 @@
 use std::collections::HashSet;
 use std::io::{ErrorKind, Seek as _};
 use std::marker::PhantomData;
+use std::str::FromStr;
 
 use actix_web::http::header::CONTENT_TYPE;
 use actix_web::web::Data;
@@ -17,9 +18,11 @@ use meilisearch_types::error::deserr_codes::*;
 use meilisearch_types::error::{Code, ResponseError};
 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::vector::parsed_vectors::ExplicitVectors;
-use meilisearch_types::milli::DocumentId;
+use meilisearch_types::milli::{AscDesc, DocumentId};
 use meilisearch_types::serde_cs::vec::CS;
 use meilisearch_types::star_or::OptionStarOrList;
 use meilisearch_types::tasks::KindWithContent;
@@ -42,6 +45,7 @@ use crate::extractors::authentication::policies::*;
 use crate::extractors::authentication::GuardedData;
 use crate::extractors::payload::Payload;
 use crate::extractors::sequential_extractor::SeqHandler;
+use crate::routes::indexes::search::fix_sort_query_parameters;
 use crate::routes::{
     get_task_id, is_dry_run, PaginationView, SummarizedTaskView, PAGINATION_DEFAULT_LIMIT,
 };
@@ -135,6 +139,10 @@ pub struct DocumentsFetchAggregator<Method: AggregateMethod> {
     per_document_id: bool,
     // if a filter was used
     per_filter: bool,
+    with_vector_filter: bool,
+
+    // if documents were sorted
+    sort: bool,
 
     #[serde(rename = "vector.retrieve_vectors")]
     retrieve_vectors: bool,
@@ -151,39 +159,6 @@ pub struct DocumentsFetchAggregator<Method: AggregateMethod> {
     marker: std::marker::PhantomData<Method>,
 }
 
-#[derive(Copy, Clone, Debug, PartialEq, Eq)]
-pub enum DocumentFetchKind {
-    PerDocumentId { retrieve_vectors: bool },
-    Normal { with_filter: bool, limit: usize, offset: usize, retrieve_vectors: bool, ids: usize },
-}
-
-impl<Method: AggregateMethod> DocumentsFetchAggregator<Method> {
-    pub fn from_query(query: &DocumentFetchKind) -> Self {
-        let (limit, offset, retrieve_vectors) = match query {
-            DocumentFetchKind::PerDocumentId { retrieve_vectors } => (1, 0, *retrieve_vectors),
-            DocumentFetchKind::Normal { limit, offset, retrieve_vectors, .. } => {
-                (*limit, *offset, *retrieve_vectors)
-            }
-        };
-
-        let ids = match query {
-            DocumentFetchKind::Normal { ids, .. } => *ids,
-            DocumentFetchKind::PerDocumentId { .. } => 0,
-        };
-
-        Self {
-            per_document_id: matches!(query, DocumentFetchKind::PerDocumentId { .. }),
-            per_filter: matches!(query, DocumentFetchKind::Normal { with_filter, .. } if *with_filter),
-            max_limit: limit,
-            max_offset: offset,
-            retrieve_vectors,
-            max_document_ids: ids,
-
-            marker: PhantomData,
-        }
-    }
-}
-
 impl<Method: AggregateMethod> Aggregate for DocumentsFetchAggregator<Method> {
     fn event_name(&self) -> &'static str {
         Method::event_name()
@@ -193,6 +168,8 @@ impl<Method: AggregateMethod> Aggregate for DocumentsFetchAggregator<Method> {
         Box::new(Self {
             per_document_id: self.per_document_id | new.per_document_id,
             per_filter: self.per_filter | new.per_filter,
+            with_vector_filter: self.with_vector_filter | new.with_vector_filter,
+            sort: self.sort | new.sort,
             retrieve_vectors: self.retrieve_vectors | new.retrieve_vectors,
             max_limit: self.max_limit.max(new.max_limit),
             max_offset: self.max_offset.max(new.max_offset),
@@ -276,6 +253,8 @@ pub async fn get_document(
             retrieve_vectors: param_retrieve_vectors.0,
             per_document_id: true,
             per_filter: false,
+            with_vector_filter: false,
+            sort: false,
             max_limit: 0,
             max_offset: 0,
             max_document_ids: 0,
@@ -406,6 +385,8 @@ pub struct BrowseQueryGet {
     #[param(default, value_type = Option<String>, example = "popularity > 1000")]
     #[deserr(default, error = DeserrQueryParamError<InvalidDocumentFilter>)]
     filter: Option<String>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidDocumentSort>)]
+    sort: Option<String>,
 }
 
 #[derive(Debug, Deserr, ToSchema)]
@@ -430,6 +411,9 @@ pub struct BrowseQuery {
     #[schema(default, value_type = Option<Value>, example = "popularity > 1000")]
     #[deserr(default, error = DeserrJsonError<InvalidDocumentFilter>)]
     filter: Option<Value>,
+    #[schema(default, value_type = Option<Vec<String>>, example = json!(["title:asc", "rating:desc"]))]
+    #[deserr(default, error = DeserrJsonError<InvalidDocumentSort>)]
+    sort: Option<Vec<String>>,
 }
 
 /// Get documents with POST
@@ -495,6 +479,11 @@ pub async fn documents_by_query_post(
     analytics.publish(
         DocumentsFetchAggregator::<DocumentsPOST> {
             per_filter: body.filter.is_some(),
+            with_vector_filter: body
+                .filter
+                .as_ref()
+                .is_some_and(|f| f.to_string().contains("_vectors")),
+            sort: body.sort.is_some(),
             retrieve_vectors: body.retrieve_vectors,
             max_limit: body.limit,
             max_offset: body.offset,
@@ -571,7 +560,7 @@ pub async fn get_documents(
 ) -> Result<HttpResponse, ResponseError> {
     debug!(parameters = ?params, "Get documents GET");
 
-    let BrowseQueryGet { limit, offset, fields, retrieve_vectors, filter, ids } =
+    let BrowseQueryGet { limit, offset, fields, retrieve_vectors, filter, ids, sort } =
         params.into_inner();
 
     let filter = match filter {
@@ -582,20 +571,24 @@ pub async fn get_documents(
         None => None,
     };
 
-    let ids = ids.map(|ids| ids.into_iter().map(Into::into).collect());
-
     let query = BrowseQuery {
         offset: offset.0,
         limit: limit.0,
         fields: fields.merge_star_and_none(),
         retrieve_vectors: retrieve_vectors.0,
         filter,
-        ids,
+        ids: ids.map(|ids| ids.into_iter().map(Into::into).collect()),
+        sort: sort.map(|attr| fix_sort_query_parameters(&attr)),
     };
 
     analytics.publish(
         DocumentsFetchAggregator::<DocumentsGET> {
             per_filter: query.filter.is_some(),
+            with_vector_filter: query
+                .filter
+                .as_ref()
+                .is_some_and(|f| f.to_string().contains("_vectors")),
+            sort: query.sort.is_some(),
             retrieve_vectors: query.retrieve_vectors,
             max_limit: query.limit,
             max_offset: query.offset,
@@ -615,7 +608,7 @@ fn documents_by_query(
     query: BrowseQuery,
 ) -> Result<HttpResponse, ResponseError> {
     let index_uid = IndexUid::try_from(index_uid.into_inner())?;
-    let BrowseQuery { offset, limit, fields, retrieve_vectors, filter, ids } = query;
+    let BrowseQuery { offset, limit, fields, retrieve_vectors, filter, ids, sort } = query;
 
     let retrieve_vectors = RetrieveVectors::new(retrieve_vectors);
 
@@ -633,6 +626,18 @@ fn documents_by_query(
         None
     };
 
+    let sort_criteria = if let Some(sort) = &sort {
+        let sorts: Vec<_> = match sort.iter().map(|s| milli::AscDesc::from_str(s)).collect() {
+            Ok(sorts) => sorts,
+            Err(asc_desc_error) => {
+                return Err(milli::SortError::from(asc_desc_error).into_document_error().into())
+            }
+        };
+        Some(sorts)
+    } else {
+        None
+    };
+
     let index = index_scheduler.index(&index_uid)?;
     let (total, documents) = retrieve_documents(
         &index,
@@ -643,6 +648,7 @@ fn documents_by_query(
         fields,
         retrieve_vectors,
         index_scheduler.features(),
+        sort_criteria,
     )?;
 
     let ret = PaginationView::new(offset, limit, total as usize, documents);
@@ -1461,15 +1467,17 @@ fn some_documents<'a, 't: 'a>(
                     document.remove("_vectors");
                 }
                 RetrieveVectors::Retrieve => {
-                    // Clippy is simply wrong
-                    #[allow(clippy::manual_unwrap_or_default)]
                     let mut vectors = match document.remove("_vectors") {
                         Some(Value::Object(map)) => map,
                         _ => Default::default(),
                     };
-                    for (name, (vector, regenerate)) in index.embeddings(rtxn, key)? {
+                    for (
+                        name,
+                        EmbeddingsWithMetadata { embeddings, regenerate, has_fragments: _ },
+                    ) in index.embeddings(rtxn, key)?
+                    {
                         let embeddings =
-                            ExplicitVectors { embeddings: Some(vector.into()), regenerate };
+                            ExplicitVectors { embeddings: Some(embeddings.into()), regenerate };
                         vectors.insert(
                             name,
                             serde_json::to_value(embeddings).map_err(MeilisearchHttpError::from)?,
@@ -1494,6 +1502,7 @@ fn retrieve_documents<S: AsRef<str>>(
     attributes_to_retrieve: Option<Vec<S>>,
     retrieve_vectors: RetrieveVectors,
     features: RoFeatures,
+    sort_criteria: Option<Vec<AscDesc>>,
 ) -> Result<(u64, Vec<Document>), ResponseError> {
     let rtxn = index.read_txn()?;
     let filter = &filter;
@@ -1526,15 +1535,32 @@ fn retrieve_documents<S: AsRef<str>>(
         })?
     }
 
-    let (it, number_of_documents) = {
+    let (it, number_of_documents) = if let Some(sort) = sort_criteria {
+        let number_of_documents = candidates.len();
+        let facet_sort = recursive_sort(index, &rtxn, sort, &candidates)?;
+        let iter = facet_sort.iter()?;
+        let mut documents = Vec::with_capacity(limit);
+        for result in iter.skip(offset).take(limit) {
+            documents.push(result?);
+        }
+        (
+            itertools::Either::Left(some_documents(
+                index,
+                &rtxn,
+                documents.into_iter(),
+                retrieve_vectors,
+            )?),
+            number_of_documents,
+        )
+    } else {
         let number_of_documents = candidates.len();
         (
-            some_documents(
+            itertools::Either::Right(some_documents(
                 index,
                 &rtxn,
                 candidates.into_iter().skip(offset).take(limit),
                 retrieve_vectors,
-            )?,
+            )?),
             number_of_documents,
         )
     };

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

@@ -40,6 +40,7 @@ pub struct SearchAggregator<Method: AggregateMethod> {
     // filter
     filter_with_geo_radius: bool,
     filter_with_geo_bounding_box: bool,
+    filter_on_vectors: bool,
     // every time a request has a filter, this field must be incremented by the number of terms it contains
     filter_sum_of_criteria_terms: usize,
     // every time a request has a filter, this field must be incremented by one
@@ -163,6 +164,7 @@ impl<Method: AggregateMethod> SearchAggregator<Method> {
             let stringified_filters = filter.to_string();
             ret.filter_with_geo_radius = stringified_filters.contains("_geoRadius(");
             ret.filter_with_geo_bounding_box = stringified_filters.contains("_geoBoundingBox(");
+            ret.filter_on_vectors = stringified_filters.contains("_vectors");
             ret.filter_sum_of_criteria_terms = RE.split(&stringified_filters).count();
         }
 
@@ -224,6 +226,7 @@ impl<Method: AggregateMethod> SearchAggregator<Method> {
         let SearchResult {
             hits: _,
             query: _,
+            query_vector: _,
             processing_time_ms,
             hits_info: _,
             semantic_hit_count: _,
@@ -260,6 +263,7 @@ impl<Method: AggregateMethod> Aggregate for SearchAggregator<Method> {
             distinct,
             filter_with_geo_radius,
             filter_with_geo_bounding_box,
+            filter_on_vectors,
             filter_sum_of_criteria_terms,
             filter_total_number_of_criteria,
             used_syntax,
@@ -314,6 +318,7 @@ impl<Method: AggregateMethod> Aggregate for SearchAggregator<Method> {
         // filter
         self.filter_with_geo_radius |= filter_with_geo_radius;
         self.filter_with_geo_bounding_box |= filter_with_geo_bounding_box;
+        self.filter_on_vectors |= filter_on_vectors;
         self.filter_sum_of_criteria_terms =
             self.filter_sum_of_criteria_terms.saturating_add(filter_sum_of_criteria_terms);
         self.filter_total_number_of_criteria =
@@ -388,6 +393,7 @@ impl<Method: AggregateMethod> Aggregate for SearchAggregator<Method> {
             distinct,
             filter_with_geo_radius,
             filter_with_geo_bounding_box,
+            filter_on_vectors,
             filter_sum_of_criteria_terms,
             filter_total_number_of_criteria,
             used_syntax,
@@ -445,6 +451,7 @@ impl<Method: AggregateMethod> Aggregate for SearchAggregator<Method> {
             "filter": {
                "with_geoRadius": filter_with_geo_radius,
                "with_geoBoundingBox": filter_with_geo_bounding_box,
+               "on_vectors": filter_on_vectors,
                "avg_criteria_number": format!("{:.2}", filter_sum_of_criteria_terms as f64 / filter_total_number_of_criteria as f64),
                "most_used_syntax": used_syntax.iter().max_by_key(|(_, v)| *v).map(|(k, _)| json!(k)).unwrap_or_else(|| json!(null)),
             },

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

@@ -511,7 +511,7 @@ make_setting_routes!(
     },
     {
         route: "/chat",
-        update_verb: put,
+        update_verb: patch,
         value_type: ChatSettings,
         err_type: meilisearch_types::deserr::DeserrJsonError<
             meilisearch_types::error::deserr_codes::InvalidSettingsIndexChat,

crates/meilisearch/src/routes/mod.rs

@@ -41,6 +41,7 @@ use crate::routes::indexes::IndexView;
 use crate::routes::multi_search::SearchResults;
 use crate::routes::network::{Network, Remote};
 use crate::routes::swap_indexes::SwapIndexesPayload;
+use crate::routes::webhooks::{WebhookResults, WebhookSettings, WebhookWithMetadata};
 use crate::search::{
     FederatedSearch, FederatedSearchResult, Federation, FederationOptions, MergeFacets,
     SearchQueryWithIndex, SearchResultWithIndex, SimilarQuery, SimilarResult,
@@ -70,6 +71,7 @@ mod swap_indexes;
 pub mod tasks;
 #[cfg(test)]
 mod tasks_test;
+mod webhooks;
 
 #[derive(OpenApi)]
 #[openapi(
@@ -89,6 +91,7 @@ mod tasks_test;
         (path = "/experimental-features", api = features::ExperimentalFeaturesApi),
         (path = "/export", api = export::ExportApi),
         (path = "/network", api = network::NetworkApi),
+        (path = "/webhooks", api = webhooks::WebhooksApi),
     ),
     paths(get_health, get_version, get_stats),
     tags(
@@ -99,7 +102,7 @@ mod tasks_test;
         url = "/",
         description = "Local server",
     )),
-    components(schemas(PaginationView<KeyView>, PaginationView<IndexView>, IndexView, DocumentDeletionByFilter, AllBatches, BatchStats, ProgressStepView, ProgressView, BatchView, RuntimeTogglableFeatures, SwapIndexesPayload, DocumentEditionByFunction, MergeFacets, FederationOptions, SearchQueryWithIndex, Federation, FederatedSearch, FederatedSearchResult, SearchResults, SearchResultWithIndex, SimilarQuery, SimilarResult, PaginationView<serde_json::Value>, BrowseQuery, UpdateIndexRequest, IndexUid, IndexCreateRequest, KeyView, Action, CreateApiKey, UpdateStderrLogs, LogMode, GetLogs, IndexStats, Stats, HealthStatus, HealthResponse, VersionResponse, Code, ErrorType, AllTasks, TaskView, Status, DetailsView, ResponseError, Settings<Unchecked>, Settings<Checked>, TypoSettings, MinWordSizeTyposSetting, FacetingSettings, PaginationSettings, SummarizedTaskView, Kind, Network, Remote, FilterableAttributesRule, FilterableAttributesPatterns, AttributePatterns, FilterableAttributesFeatures, FilterFeatures, Export))
+    components(schemas(PaginationView<KeyView>, PaginationView<IndexView>, IndexView, DocumentDeletionByFilter, AllBatches, BatchStats, ProgressStepView, ProgressView, BatchView, RuntimeTogglableFeatures, SwapIndexesPayload, DocumentEditionByFunction, MergeFacets, FederationOptions, SearchQueryWithIndex, Federation, FederatedSearch, FederatedSearchResult, SearchResults, SearchResultWithIndex, SimilarQuery, SimilarResult, PaginationView<serde_json::Value>, BrowseQuery, UpdateIndexRequest, IndexUid, IndexCreateRequest, KeyView, Action, CreateApiKey, UpdateStderrLogs, LogMode, GetLogs, IndexStats, Stats, HealthStatus, HealthResponse, VersionResponse, Code, ErrorType, AllTasks, TaskView, Status, DetailsView, ResponseError, Settings<Unchecked>, Settings<Checked>, TypoSettings, MinWordSizeTyposSetting, FacetingSettings, PaginationSettings, SummarizedTaskView, Kind, Network, Remote, FilterableAttributesRule, FilterableAttributesPatterns, AttributePatterns, FilterableAttributesFeatures, FilterFeatures, Export, WebhookSettings, WebhookResults, WebhookWithMetadata))
 )]
 pub struct MeilisearchApi;
 
@@ -120,7 +123,8 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
         .service(web::scope("/experimental-features").configure(features::configure))
         .service(web::scope("/network").configure(network::configure))
         .service(web::scope("/export").configure(export::configure))
-        .service(web::scope("/chats").configure(chats::configure));
+        .service(web::scope("/chats").configure(chats::configure))
+        .service(web::scope("/webhooks").configure(webhooks::configure));
 
     #[cfg(feature = "swagger")]
     {

crates/meilisearch/src/routes/network.rs

@@ -51,7 +51,7 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
     get,
     path = "",
     tag = "Network",
-    security(("Bearer" = ["network.get", "network.*", "*"])),
+    security(("Bearer" = ["network.get", "*"])),
     responses(
         (status = OK, description = "Known nodes are returned", body = Network, content_type = "application/json", example = json!(
             {
@@ -168,7 +168,7 @@ impl Aggregate for PatchNetworkAnalytics {
     path = "",
     tag = "Network",
     request_body = Network,
-    security(("Bearer" = ["network.update", "network.*", "*"])),
+    security(("Bearer" = ["network.update", "*"])),
     responses(
         (status = OK, description = "New network state is returned",  body = Network, content_type = "application/json", example = json!(
             {

crates/meilisearch/src/routes/tasks.rs

@@ -336,7 +336,7 @@ impl<Method: AggregateMethod + 'static> Aggregate for TaskFilterAnalytics<Method
                 "link": "https://docs.meilisearch.com/errors#missing_authorization_header"
             }
         )),
-        (status = 404, description = "The task uid does not exists", body = ResponseError, content_type = "application/json", example = json!(
+        (status = 404, description = "The task uid does not exist", body = ResponseError, content_type = "application/json", example = json!(
             {
                 "message": "Task :taskUid not found.",
                 "code": "task_not_found",
@@ -430,7 +430,7 @@ async fn cancel_tasks(
                 "link": "https://docs.meilisearch.com/errors#missing_authorization_header"
             }
         )),
-        (status = 404, description = "The task uid does not exists", body = ResponseError, content_type = "application/json", example = json!(
+        (status = 404, description = "The task uid does not exist", body = ResponseError, content_type = "application/json", example = json!(
             {
                 "message": "Task :taskUid not found.",
                 "code": "task_not_found",
@@ -611,7 +611,7 @@ async fn get_tasks(
                 "link": "https://docs.meilisearch.com/errors#missing_authorization_header"
             }
         )),
-        (status = 404, description = "The task uid does not exists", body = ResponseError, content_type = "application/json", example = json!(
+        (status = 404, description = "The task uid does not exist", body = ResponseError, content_type = "application/json", example = json!(
             {
                 "message": "Task :taskUid not found.",
                 "code": "task_not_found",
@@ -665,7 +665,7 @@ async fn get_task(
                 "link": "https://docs.meilisearch.com/errors#missing_authorization_header"
             }
         )),
-        (status = 404, description = "The task uid does not exists", body = ResponseError, content_type = "application/json", example = json!(
+        (status = 404, description = "The task uid does not exist", body = ResponseError, content_type = "application/json", example = json!(
             {
                 "message": "Task :taskUid not found.",
                 "code": "task_not_found",

crates/meilisearch/src/routes/webhooks.rs

@@ -0,0 +1,474 @@
+use std::collections::BTreeMap;
+use std::str::FromStr;
+
+use actix_http::header::{
+    HeaderName, HeaderValue, InvalidHeaderName as ActixInvalidHeaderName,
+    InvalidHeaderValue as ActixInvalidHeaderValue,
+};
+use actix_web::web::{self, Data, Path};
+use actix_web::{HttpRequest, HttpResponse};
+use core::convert::Infallible;
+use deserr::actix_web::AwebJson;
+use deserr::{DeserializeError, Deserr, ValuePointerRef};
+use index_scheduler::IndexScheduler;
+use meilisearch_types::deserr::{immutable_field_error, DeserrJsonError};
+use meilisearch_types::error::deserr_codes::{
+    BadRequest, InvalidWebhookHeaders, InvalidWebhookUrl,
+};
+use meilisearch_types::error::{Code, ErrorCode, ResponseError};
+use meilisearch_types::keys::actions;
+use meilisearch_types::milli::update::Setting;
+use meilisearch_types::webhooks::Webhook;
+use serde::Serialize;
+use tracing::debug;
+use url::Url;
+use utoipa::{OpenApi, ToSchema};
+use uuid::Uuid;
+
+use crate::analytics::{Aggregate, Analytics};
+use crate::extractors::authentication::policies::ActionPolicy;
+use crate::extractors::authentication::GuardedData;
+use crate::extractors::sequential_extractor::SeqHandler;
+use WebhooksError::*;
+
+#[derive(OpenApi)]
+#[openapi(
+    paths(get_webhooks, get_webhook, post_webhook, patch_webhook, delete_webhook),
+    tags((
+        name = "Webhooks",
+        description = "The `/webhooks` route allows you to register endpoints to be called once tasks are processed.",
+        external_docs(url = "https://www.meilisearch.com/docs/reference/api/webhooks"),
+    )),
+)]
+pub struct WebhooksApi;
+
+pub fn configure(cfg: &mut web::ServiceConfig) {
+    cfg.service(
+        web::resource("")
+            .route(web::get().to(get_webhooks))
+            .route(web::post().to(SeqHandler(post_webhook))),
+    )
+    .service(
+        web::resource("/{uuid}")
+            .route(web::get().to(get_webhook))
+            .route(web::patch().to(SeqHandler(patch_webhook)))
+            .route(web::delete().to(SeqHandler(delete_webhook))),
+    );
+}
+
+#[derive(Debug, Deserr, ToSchema)]
+#[deserr(error = DeserrJsonError, rename_all = camelCase, deny_unknown_fields = deny_immutable_fields_webhook)]
+#[serde(rename_all = "camelCase")]
+#[schema(rename_all = "camelCase")]
+pub(super) struct WebhookSettings {
+    #[schema(value_type = Option<String>, example = "https://your.site/on-tasks-completed")]
+    #[deserr(default, error = DeserrJsonError<InvalidWebhookUrl>)]
+    #[serde(default)]
+    url: Setting<String>,
+    #[schema(value_type = Option<BTreeMap<String, String>>, example = json!({"Authorization":"Bearer a-secret-token"}))]
+    #[deserr(default, error = DeserrJsonError<InvalidWebhookHeaders>)]
+    #[serde(default)]
+    headers: Setting<BTreeMap<String, Setting<String>>>,
+}
+
+fn deny_immutable_fields_webhook(
+    field: &str,
+    accepted: &[&str],
+    location: ValuePointerRef,
+) -> DeserrJsonError {
+    match field {
+        "uuid" => immutable_field_error(field, accepted, Code::ImmutableWebhookUuid),
+        "isEditable" => immutable_field_error(field, accepted, Code::ImmutableWebhookIsEditable),
+        _ => deserr::take_cf_content(DeserrJsonError::<BadRequest>::error::<Infallible>(
+            None,
+            deserr::ErrorKind::UnknownKey { key: field, accepted },
+            location,
+        )),
+    }
+}
+
+#[derive(Debug, Serialize, ToSchema)]
+#[serde(rename_all = "camelCase")]
+#[schema(rename_all = "camelCase")]
+pub(super) struct WebhookWithMetadata {
+    uuid: Uuid,
+    is_editable: bool,
+    #[schema(value_type = WebhookSettings)]
+    #[serde(flatten)]
+    webhook: Webhook,
+}
+
+impl WebhookWithMetadata {
+    pub fn from(uuid: Uuid, webhook: Webhook) -> Self {
+        Self { uuid, is_editable: uuid != Uuid::nil(), webhook }
+    }
+}
+
+#[derive(Debug, Serialize, ToSchema)]
+#[serde(rename_all = "camelCase")]
+pub(super) struct WebhookResults {
+    results: Vec<WebhookWithMetadata>,
+}
+
+#[utoipa::path(
+    get,
+    path = "",
+    tag = "Webhooks",
+    security(("Bearer" = ["webhooks.get", "webhooks.*", "*.get", "*"])),
+    responses(
+        (status = OK, description = "Webhooks are returned", body = WebhookResults, content_type = "application/json", example = json!({
+            "results": [
+                {
+                    "uuid": "550e8400-e29b-41d4-a716-446655440000",
+                    "url": "https://your.site/on-tasks-completed",
+                    "headers": {
+                        "Authorization": "Bearer a-secret-token"
+                    },
+                    "isEditable": true
+                },
+                {
+                    "uuid": "550e8400-e29b-41d4-a716-446655440001",
+                    "url": "https://another.site/on-tasks-completed",
+                    "isEditable": true
+                }
+            ]
+        })),
+        (status = 401, description = "The authorization header is missing", body = ResponseError, content_type = "application/json", example = json!(
+            {
+                "message": "The Authorization header is missing. It must use the bearer authorization method.",
+                "code": "missing_authorization_header",
+                "type": "auth",
+                "link": "https://docs.meilisearch.com/errors#missing_authorization_header"
+            }
+        )),
+    )
+)]
+async fn get_webhooks(
+    index_scheduler: GuardedData<ActionPolicy<{ actions::WEBHOOKS_GET }>, Data<IndexScheduler>>,
+) -> Result<HttpResponse, ResponseError> {
+    let webhooks = index_scheduler.webhooks_view();
+    let results = webhooks
+        .webhooks
+        .into_iter()
+        .map(|(uuid, webhook)| WebhookWithMetadata::from(uuid, webhook))
+        .collect::<Vec<_>>();
+    let results = WebhookResults { results };
+
+    debug!(returns = ?results, "Get webhooks");
+    Ok(HttpResponse::Ok().json(results))
+}
+
+#[derive(Serialize, Default)]
+pub struct PatchWebhooksAnalytics;
+
+impl Aggregate for PatchWebhooksAnalytics {
+    fn event_name(&self) -> &'static str {
+        "Webhooks Updated"
+    }
+
+    fn aggregate(self: Box<Self>, _new: Box<Self>) -> Box<Self> {
+        self
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        serde_json::to_value(*self).unwrap_or_default()
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct PostWebhooksAnalytics;
+
+impl Aggregate for PostWebhooksAnalytics {
+    fn event_name(&self) -> &'static str {
+        "Webhooks Created"
+    }
+
+    fn aggregate(self: Box<Self>, _new: Box<Self>) -> Box<Self> {
+        self
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        serde_json::to_value(*self).unwrap_or_default()
+    }
+}
+
+#[derive(Debug, thiserror::Error)]
+enum WebhooksError {
+    #[error("The URL for the webhook `{0}` is missing.")]
+    MissingUrl(Uuid),
+    #[error("Defining too many webhooks would crush the server. Please limit the number of webhooks to 20. You may use a third-party proxy server to dispatch events to more than 20 endpoints.")]
+    TooManyWebhooks,
+    #[error("Too many headers for the webhook `{0}`. Please limit the number of headers to 200. Hint: To remove an already defined header set its value to `null`")]
+    TooManyHeaders(Uuid),
+    #[error("Webhook `{0}` is immutable. The webhook defined from the command line cannot be modified using the API.")]
+    ImmutableWebhook(Uuid),
+    #[error("Webhook `{0}` not found.")]
+    WebhookNotFound(Uuid),
+    #[error("Invalid header name `{0}`: {1}")]
+    InvalidHeaderName(String, ActixInvalidHeaderName),
+    #[error("Invalid header value `{0}`: {1}")]
+    InvalidHeaderValue(String, ActixInvalidHeaderValue),
+    #[error("Invalid URL `{0}`: {1}")]
+    InvalidUrl(String, url::ParseError),
+    #[error("Invalid UUID: {0}")]
+    InvalidUuid(uuid::Error),
+}
+
+impl ErrorCode for WebhooksError {
+    fn error_code(&self) -> meilisearch_types::error::Code {
+        match self {
+            MissingUrl(_) => meilisearch_types::error::Code::InvalidWebhookUrl,
+            TooManyWebhooks => meilisearch_types::error::Code::InvalidWebhooks,
+            TooManyHeaders(_) => meilisearch_types::error::Code::InvalidWebhookHeaders,
+            ImmutableWebhook(_) => meilisearch_types::error::Code::ImmutableWebhook,
+            WebhookNotFound(_) => meilisearch_types::error::Code::WebhookNotFound,
+            InvalidHeaderName(_, _) => meilisearch_types::error::Code::InvalidWebhookHeaders,
+            InvalidHeaderValue(_, _) => meilisearch_types::error::Code::InvalidWebhookHeaders,
+            InvalidUrl(_, _) => meilisearch_types::error::Code::InvalidWebhookUrl,
+            InvalidUuid(_) => meilisearch_types::error::Code::InvalidWebhookUuid,
+        }
+    }
+}
+
+fn patch_webhook_inner(
+    uuid: &Uuid,
+    old_webhook: Webhook,
+    new_webhook: WebhookSettings,
+) -> Result<Webhook, WebhooksError> {
+    let Webhook { url: old_url, mut headers } = old_webhook;
+
+    let url = match new_webhook.url {
+        Setting::Set(url) => url,
+        Setting::NotSet => old_url,
+        Setting::Reset => return Err(MissingUrl(uuid.to_owned())),
+    };
+
+    match new_webhook.headers {
+        Setting::Set(new_headers) => {
+            for (name, value) in new_headers {
+                match value {
+                    Setting::Set(value) => {
+                        headers.insert(name, value);
+                    }
+                    Setting::NotSet => continue,
+                    Setting::Reset => {
+                        headers.remove(&name);
+                        continue;
+                    }
+                }
+            }
+        }
+        Setting::Reset => headers.clear(),
+        Setting::NotSet => (),
+    };
+
+    if headers.len() > 200 {
+        return Err(TooManyHeaders(uuid.to_owned()));
+    }
+
+    Ok(Webhook { url, headers })
+}
+
+fn check_changed(uuid: Uuid, webhook: &Webhook) -> Result<(), WebhooksError> {
+    if uuid.is_nil() {
+        return Err(ImmutableWebhook(uuid));
+    }
+
+    if webhook.url.is_empty() {
+        return Err(MissingUrl(uuid));
+    }
+
+    if webhook.headers.len() > 200 {
+        return Err(TooManyHeaders(uuid));
+    }
+
+    for (header, value) in &webhook.headers {
+        HeaderName::from_bytes(header.as_bytes())
+            .map_err(|e| InvalidHeaderName(header.to_owned(), e))?;
+        HeaderValue::from_str(value).map_err(|e| InvalidHeaderValue(header.to_owned(), e))?;
+    }
+
+    if let Err(e) = Url::parse(&webhook.url) {
+        return Err(InvalidUrl(webhook.url.to_owned(), e));
+    }
+
+    Ok(())
+}
+
+#[utoipa::path(
+    get,
+    path = "/{uuid}",
+    tag = "Webhooks",
+    security(("Bearer" = ["webhooks.get", "webhooks.*", "*.get", "*"])),
+    responses(
+        (status = 200, description = "Webhook found", body = WebhookWithMetadata, content_type = "application/json", example = json!({
+            "uuid": "550e8400-e29b-41d4-a716-446655440000",
+            "url": "https://your.site/on-tasks-completed",
+            "headers": {
+                "Authorization": "Bearer a-secret"
+            },
+            "isEditable": true
+        })),
+        (status = 404, description = "Webhook not found", body = ResponseError, content_type = "application/json"),
+        (status = 401, description = "The authorization header is missing", body = ResponseError, content_type = "application/json"),
+    ),
+    params(
+        ("uuid" = Uuid, Path, description = "The universally unique identifier of the webhook")
+    )
+)]
+async fn get_webhook(
+    index_scheduler: GuardedData<ActionPolicy<{ actions::WEBHOOKS_GET }>, Data<IndexScheduler>>,
+    uuid: Path<String>,
+) -> Result<HttpResponse, ResponseError> {
+    let uuid = Uuid::from_str(&uuid.into_inner()).map_err(InvalidUuid)?;
+    let mut webhooks = index_scheduler.webhooks_view();
+
+    let webhook = webhooks.webhooks.remove(&uuid).ok_or(WebhookNotFound(uuid))?;
+    let webhook = WebhookWithMetadata::from(uuid, webhook);
+
+    debug!(returns = ?webhook, "Get webhook");
+    Ok(HttpResponse::Ok().json(webhook))
+}
+
+#[utoipa::path(
+    post,
+    path = "",
+    tag = "Webhooks",
+    request_body = WebhookSettings,
+    security(("Bearer" = ["webhooks.create", "webhooks.*", "*"])),
+    responses(
+        (status = 201, description = "Webhook created successfully", body = WebhookWithMetadata, content_type = "application/json", example = json!({
+            "uuid": "550e8400-e29b-41d4-a716-446655440000",
+            "url": "https://your.site/on-tasks-completed",
+            "headers": {
+                "Authorization": "Bearer a-secret-token"
+            },
+            "isEditable": true
+        })),
+        (status = 401, description = "The authorization header is missing", body = ResponseError, content_type = "application/json"),
+        (status = 400, description = "Bad request", body = ResponseError, content_type = "application/json"),
+    )
+)]
+async fn post_webhook(
+    index_scheduler: GuardedData<ActionPolicy<{ actions::WEBHOOKS_CREATE }>, Data<IndexScheduler>>,
+    webhook_settings: AwebJson<WebhookSettings, DeserrJsonError>,
+    req: HttpRequest,
+    analytics: Data<Analytics>,
+) -> Result<HttpResponse, ResponseError> {
+    let webhook_settings = webhook_settings.into_inner();
+    debug!(parameters = ?webhook_settings, "Post webhook");
+
+    let uuid = Uuid::new_v4();
+    if webhook_settings.headers.as_ref().set().is_some_and(|h| h.len() > 200) {
+        return Err(TooManyHeaders(uuid).into());
+    }
+
+    let mut webhooks = index_scheduler.retrieve_runtime_webhooks();
+    if webhooks.len() >= 20 {
+        return Err(TooManyWebhooks.into());
+    }
+
+    let webhook = Webhook {
+        url: webhook_settings.url.set().ok_or(MissingUrl(uuid))?,
+        headers: webhook_settings
+            .headers
+            .set()
+            .map(|h| h.into_iter().map(|(k, v)| (k, v.set().unwrap_or_default())).collect())
+            .unwrap_or_default(),
+    };
+
+    check_changed(uuid, &webhook)?;
+    webhooks.insert(uuid, webhook.clone());
+    index_scheduler.update_runtime_webhooks(webhooks)?;
+
+    analytics.publish(PostWebhooksAnalytics, &req);
+
+    let response = WebhookWithMetadata::from(uuid, webhook);
+    debug!(returns = ?response, "Post webhook");
+    Ok(HttpResponse::Created().json(response))
+}
+
+#[utoipa::path(
+    patch,
+    path = "/{uuid}",
+    tag = "Webhooks",
+    request_body = WebhookSettings,
+    security(("Bearer" = ["webhooks.update", "webhooks.*", "*"])),
+    responses(
+        (status = 200, description = "Webhook updated successfully", body = WebhookWithMetadata, content_type = "application/json", example = json!({
+            "uuid": "550e8400-e29b-41d4-a716-446655440000",
+            "url": "https://your.site/on-tasks-completed",
+            "headers": {
+                "Authorization": "Bearer a-secret-token"
+            },
+            "isEditable": true
+        })),
+        (status = 401, description = "The authorization header is missing", body = ResponseError, content_type = "application/json"),
+        (status = 400, description = "Bad request", body = ResponseError, content_type = "application/json"),
+    ),
+    params(
+        ("uuid" = Uuid, Path, description = "The universally unique identifier of the webhook")
+    )
+)]
+async fn patch_webhook(
+    index_scheduler: GuardedData<ActionPolicy<{ actions::WEBHOOKS_UPDATE }>, Data<IndexScheduler>>,
+    uuid: Path<String>,
+    webhook_settings: AwebJson<WebhookSettings, DeserrJsonError>,
+    req: HttpRequest,
+    analytics: Data<Analytics>,
+) -> Result<HttpResponse, ResponseError> {
+    let uuid = Uuid::from_str(&uuid.into_inner()).map_err(InvalidUuid)?;
+    let webhook_settings = webhook_settings.into_inner();
+    debug!(parameters = ?(uuid, &webhook_settings), "Patch webhook");
+
+    if uuid.is_nil() {
+        return Err(ImmutableWebhook(uuid).into());
+    }
+
+    let mut webhooks = index_scheduler.retrieve_runtime_webhooks();
+    let old_webhook = webhooks.remove(&uuid).ok_or(WebhookNotFound(uuid))?;
+    let webhook = patch_webhook_inner(&uuid, old_webhook, webhook_settings)?;
+
+    check_changed(uuid, &webhook)?;
+    webhooks.insert(uuid, webhook.clone());
+    index_scheduler.update_runtime_webhooks(webhooks)?;
+
+    analytics.publish(PatchWebhooksAnalytics, &req);
+
+    let response = WebhookWithMetadata::from(uuid, webhook);
+    debug!(returns = ?response, "Patch webhook");
+    Ok(HttpResponse::Ok().json(response))
+}
+
+#[utoipa::path(
+    delete,
+    path = "/{uuid}",
+    tag = "Webhooks",
+    security(("Bearer" = ["webhooks.delete", "webhooks.*", "*"])),
+    responses(
+        (status = 204, description = "Webhook deleted successfully"),
+        (status = 404, description = "Webhook not found", body = ResponseError, content_type = "application/json"),
+        (status = 401, description = "The authorization header is missing", body = ResponseError, content_type = "application/json"),
+    ),
+    params(
+        ("uuid" = Uuid, Path, description = "The universally unique identifier of the webhook")
+    )
+)]
+async fn delete_webhook(
+    index_scheduler: GuardedData<ActionPolicy<{ actions::WEBHOOKS_DELETE }>, Data<IndexScheduler>>,
+    uuid: Path<String>,
+) -> Result<HttpResponse, ResponseError> {
+    let uuid = Uuid::from_str(&uuid.into_inner()).map_err(InvalidUuid)?;
+    debug!(parameters = ?uuid, "Delete webhook");
+
+    if uuid.is_nil() {
+        return Err(ImmutableWebhook(uuid).into());
+    }
+
+    let mut webhooks = index_scheduler.retrieve_runtime_webhooks();
+    webhooks.remove(&uuid).ok_or(WebhookNotFound(uuid))?;
+    index_scheduler.update_runtime_webhooks(webhooks)?;
+
+    debug!(returns = "No Content", "Delete webhook");
+    Ok(HttpResponse::NoContent().finish())
+}

crates/meilisearch/src/search/federated/perform.rs

@@ -13,6 +13,7 @@ use meilisearch_types::error::ResponseError;
 use meilisearch_types::features::{Network, Remote};
 use meilisearch_types::milli::order_by_map::OrderByMap;
 use meilisearch_types::milli::score_details::{ScoreDetails, WeightedScoreValue};
+use meilisearch_types::milli::vector::Embedding;
 use meilisearch_types::milli::{self, DocumentId, OrderBy, TimeBudget, DEFAULT_VALUES_PER_FACET};
 use roaring::RoaringBitmap;
 use tokio::task::JoinHandle;
@@ -46,6 +47,7 @@ pub async fn perform_federated_search(
     let deadline = before_search + std::time::Duration::from_secs(9);
 
     let required_hit_count = federation.limit + federation.offset;
+    let retrieve_vectors = queries.iter().any(|q| q.retrieve_vectors);
 
     let network = index_scheduler.network();
 
@@ -91,6 +93,7 @@ pub async fn perform_federated_search(
         federation,
         mut semantic_hit_count,
         mut results_by_index,
+        mut query_vectors,
         previous_query_data: _,
         facet_order,
     } = search_by_index;
@@ -122,7 +125,26 @@ pub async fn perform_federated_search(
         .map(|hit| hit.hit())
         .collect();
 
-    // 3.3. merge facets
+    // 3.3. merge query vectors
+    let query_vectors = if retrieve_vectors {
+        for remote_results in remote_results.iter_mut() {
+            if let Some(remote_vectors) = remote_results.query_vectors.take() {
+                for (key, value) in remote_vectors.into_iter() {
+                    debug_assert!(
+                        !query_vectors.contains_key(&key),
+                        "Query vector for query {key} already exists"
+                    );
+                    query_vectors.insert(key, value);
+                }
+            }
+        }
+
+        Some(query_vectors)
+    } else {
+        None
+    };
+
+    // 3.4. merge facets
     let (facet_distribution, facet_stats, facets_by_index) =
         facet_order.merge(federation.merge_facets, remote_results, facets);
 
@@ -140,6 +162,7 @@ pub async fn perform_federated_search(
             offset: federation.offset,
             estimated_total_hits,
         },
+        query_vectors,
         semantic_hit_count,
         degraded,
         used_negative_operator,
@@ -408,6 +431,7 @@ fn merge_metadata(
         hits: _,
         processing_time_ms,
         hits_info,
+        query_vectors: _,
         semantic_hit_count: _,
         facet_distribution: _,
         facet_stats: _,
@@ -657,6 +681,7 @@ struct SearchByIndex {
     // Then when merging, we'll update its value if there is any semantic hit
     semantic_hit_count: Option<u32>,
     results_by_index: Vec<SearchResultByIndex>,
+    query_vectors: BTreeMap<usize, Embedding>,
     previous_query_data: Option<(RankingRules, usize, String)>,
     // remember the order and name of first index for each facet when merging with index settings
     // to detect if the order is inconsistent for a facet.
@@ -674,6 +699,7 @@ impl SearchByIndex {
             federation,
             semantic_hit_count: None,
             results_by_index: Vec::with_capacity(index_count),
+            query_vectors: BTreeMap::new(),
             previous_query_data: None,
         }
     }
@@ -745,10 +771,9 @@ impl SearchByIndex {
                         match sort.iter().map(|s| milli::AscDesc::from_str(s)).collect() {
                             Ok(sorts) => sorts,
                             Err(asc_desc_error) => {
-                                return Err(milli::Error::from(milli::SortError::from(
-                                    asc_desc_error,
-                                ))
-                                .into())
+                                return Err(milli::SortError::from(asc_desc_error)
+                                    .into_search_error()
+                                    .into())
                             }
                         };
                     Some(sorts)
@@ -838,8 +863,19 @@ impl SearchByIndex {
                     document_scores,
                     degraded: query_degraded,
                     used_negative_operator: query_used_negative_operator,
+                    query_vector,
                 } = result;
 
+                if query.retrieve_vectors {
+                    if let Some(query_vector) = query_vector {
+                        debug_assert!(
+                            !self.query_vectors.contains_key(&query_index),
+                            "Query vector for query {query_index} already exists"
+                        );
+                        self.query_vectors.insert(query_index, query_vector);
+                    }
+                }
+
                 candidates |= query_candidates;
                 degraded |= query_degraded;
                 used_negative_operator |= query_used_negative_operator;

crates/meilisearch/src/search/federated/types.rs

@@ -18,6 +18,7 @@ use serde::{Deserialize, Serialize};
 use utoipa::ToSchema;
 
 use super::super::{ComputedFacets, FacetStats, HitsInfo, SearchHit, SearchQueryWithIndex};
+use crate::milli::vector::Embedding;
 
 pub const DEFAULT_FEDERATED_WEIGHT: f64 = 1.0;
 
@@ -117,6 +118,9 @@ pub struct FederatedSearchResult {
     #[serde(flatten)]
     pub hits_info: HitsInfo,
 
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub query_vectors: Option<BTreeMap<usize, Embedding>>,
+
     #[serde(default, skip_serializing_if = "Option::is_none")]
     pub semantic_hit_count: Option<u32>,
 
@@ -144,6 +148,7 @@ impl fmt::Debug for FederatedSearchResult {
             hits,
             processing_time_ms,
             hits_info,
+            query_vectors,
             semantic_hit_count,
             degraded,
             used_negative_operator,
@@ -158,6 +163,10 @@ impl fmt::Debug for FederatedSearchResult {
         debug.field("processing_time_ms", &processing_time_ms);
         debug.field("hits", &format!("[{} hits returned]", hits.len()));
         debug.field("hits_info", &hits_info);
+        if let Some(query_vectors) = query_vectors {
+            let known = query_vectors.len();
+            debug.field("query_vectors", &format!("[{known} known vectors]"));
+        }
         if *used_negative_operator {
             debug.field("used_negative_operator", used_negative_operator);
         }

crates/meilisearch/src/search/mod.rs

@@ -16,7 +16,7 @@ use meilisearch_types::error::{Code, ResponseError};
 use meilisearch_types::heed::RoTxn;
 use meilisearch_types::index_uid::IndexUid;
 use meilisearch_types::locales::Locale;
-use meilisearch_types::milli::index::{self, SearchParameters};
+use meilisearch_types::milli::index::{self, EmbeddingsWithMetadata, SearchParameters};
 use meilisearch_types::milli::score_details::{ScoreDetails, ScoringStrategy};
 use meilisearch_types::milli::vector::parsed_vectors::ExplicitVectors;
 use meilisearch_types::milli::vector::Embedder;
@@ -841,6 +841,8 @@ pub struct SearchHit {
 pub struct SearchResult {
     pub hits: Vec<SearchHit>,
     pub query: String,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub query_vector: Option<Vec<f32>>,
     pub processing_time_ms: u128,
     #[serde(flatten)]
     pub hits_info: HitsInfo,
@@ -865,6 +867,7 @@ impl fmt::Debug for SearchResult {
         let SearchResult {
             hits,
             query,
+            query_vector,
             processing_time_ms,
             hits_info,
             facet_distribution,
@@ -879,6 +882,9 @@ impl fmt::Debug for SearchResult {
         debug.field("processing_time_ms", &processing_time_ms);
         debug.field("hits", &format!("[{} hits returned]", hits.len()));
         debug.field("query", &query);
+        if query_vector.is_some() {
+            debug.field("query_vector", &"[...]");
+        }
         debug.field("hits_info", &hits_info);
         if *used_negative_operator {
             debug.field("used_negative_operator", used_negative_operator);
@@ -1050,7 +1056,9 @@ pub fn prepare_search<'t>(
         .map(|x| x as usize)
         .unwrap_or(DEFAULT_PAGINATION_MAX_TOTAL_HITS);
 
+    search.retrieve_vectors(query.retrieve_vectors);
     search.exhaustive_number_hits(is_finite_pagination);
+    search.max_total_hits(Some(max_total_hits));
     search.scoring_strategy(
         if query.show_ranking_score
             || query.show_ranking_score_details
@@ -1091,7 +1099,7 @@ pub fn prepare_search<'t>(
         let sort = match sort.iter().map(|s| AscDesc::from_str(s)).collect() {
             Ok(sorts) => sorts,
             Err(asc_desc_error) => {
-                return Err(milli::Error::from(SortError::from(asc_desc_error)).into())
+                return Err(SortError::from(asc_desc_error).into_search_error().into())
             }
         };
 
@@ -1131,6 +1139,7 @@ pub fn perform_search(
             document_scores,
             degraded,
             used_negative_operator,
+            query_vector,
         },
         semantic_hit_count,
     ) = search_from_kind(index_uid, search_kind, search)?;
@@ -1221,6 +1230,7 @@ pub fn perform_search(
         hits: documents,
         hits_info,
         query: q.unwrap_or_default(),
+        query_vector,
         processing_time_ms: before_search.elapsed().as_millis(),
         facet_distribution,
         facet_stats,
@@ -1527,8 +1537,11 @@ impl<'a> HitMaker<'a> {
                 Some(Value::Object(map)) => map,
                 _ => Default::default(),
             };
-            for (name, (vector, regenerate)) in self.index.embeddings(self.rtxn, id)? {
-                let embeddings = ExplicitVectors { embeddings: Some(vector.into()), regenerate };
+            for (name, EmbeddingsWithMetadata { embeddings, regenerate, has_fragments: _ }) in
+                self.index.embeddings(self.rtxn, id)?
+            {
+                let embeddings =
+                    ExplicitVectors { embeddings: Some(embeddings.into()), regenerate };
                 vectors.insert(
                     name,
                     serde_json::to_value(embeddings).map_err(InternalError::SerdeJson)?,
@@ -1730,6 +1743,7 @@ pub fn perform_similar(
         document_scores,
         degraded: _,
         used_negative_operator: _,
+        query_vector: _,
     } = similar.execute().map_err(|err| match err {
         milli::Error::UserError(milli::UserError::InvalidFilter(_)) => {
             ResponseError::from_msg(err.to_string(), Code::InvalidSimilarFilter)
@@ -2077,7 +2091,7 @@ pub(crate) fn parse_filter(
     })?;
 
     if let Some(ref filter) = filter {
-        // If the contains operator is used while the contains filter features is not enabled, errors out
+        // If the contains operator is used while the contains filter feature is not enabled, errors out
         if let Some((token, error)) =
             filter.use_contains_operator().zip(features.check_contains_filter().err())
         {
@@ -2088,6 +2102,18 @@ pub(crate) fn parse_filter(
         }
     }
 
+    if let Some(ref filter) = filter {
+        // If a vector filter is used while the multi modal feature is not enabled, errors out
+        if let Some((token, error)) =
+            filter.use_vector_filter().zip(features.check_multimodal("using a vector filter").err())
+        {
+            return Err(ResponseError::from_msg(
+                token.as_external_error(error).to_string(),
+                Code::FeatureNotEnabled,
+            ));
+        }
+    }
+
     Ok(filter)
 }
 

crates/meilisearch/tests/auth/api_keys.rs

@@ -419,14 +419,14 @@ async fn error_add_api_key_invalid_parameters_actions() {
     let (response, code) = server.add_api_key(content).await;
 
     meili_snap::snapshot!(code, @"400 Bad Request");
-    meili_snap::snapshot!(meili_snap::json_string!(response, { ".createdAt" => "[ignored]", ".updatedAt" => "[ignored]" }), @r###"
+    meili_snap::snapshot!(meili_snap::json_string!(response, { ".createdAt" => "[ignored]", ".updatedAt" => "[ignored]" }), @r#"
     {
-      "message": "Unknown value `doc.add` at `.actions[0]`: expected one of `*`, `search`, `documents.*`, `documents.add`, `documents.get`, `documents.delete`, `indexes.*`, `indexes.create`, `indexes.get`, `indexes.update`, `indexes.delete`, `indexes.swap`, `tasks.*`, `tasks.cancel`, `tasks.delete`, `tasks.get`, `settings.*`, `settings.get`, `settings.update`, `stats.*`, `stats.get`, `metrics.*`, `metrics.get`, `dumps.*`, `dumps.create`, `snapshots.*`, `snapshots.create`, `version`, `keys.create`, `keys.get`, `keys.update`, `keys.delete`, `experimental.get`, `experimental.update`, `export`, `network.get`, `network.update`, `chatCompletions`, `chats.*`, `chats.get`, `chats.delete`, `chatsSettings.*`, `chatsSettings.get`, `chatsSettings.update`",
+      "message": "Unknown value `doc.add` at `.actions[0]`: expected one of `*`, `search`, `documents.*`, `documents.add`, `documents.get`, `documents.delete`, `indexes.*`, `indexes.create`, `indexes.get`, `indexes.update`, `indexes.delete`, `indexes.swap`, `tasks.*`, `tasks.cancel`, `tasks.delete`, `tasks.get`, `settings.*`, `settings.get`, `settings.update`, `stats.*`, `stats.get`, `metrics.*`, `metrics.get`, `dumps.*`, `dumps.create`, `snapshots.*`, `snapshots.create`, `version`, `keys.create`, `keys.get`, `keys.update`, `keys.delete`, `experimental.get`, `experimental.update`, `export`, `network.get`, `network.update`, `chatCompletions`, `chats.*`, `chats.get`, `chats.delete`, `chatsSettings.*`, `chatsSettings.get`, `chatsSettings.update`, `*.get`, `webhooks.get`, `webhooks.update`, `webhooks.delete`, `webhooks.create`, `webhooks.*`",
       "code": "invalid_api_key_actions",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_api_key_actions"
     }
-    "###);
+    "#);
 }
 
 #[actix_rt::test]
@@ -790,7 +790,7 @@ async fn list_api_keys() {
     meili_snap::snapshot!(code, @"201 Created");
 
     let (response, code) = server.list_api_keys("").await;
-    meili_snap::snapshot!(meili_snap::json_string!(response, { ".results[].createdAt" => "[ignored]", ".results[].updatedAt" => "[ignored]", ".results[].uid" => "[ignored]", ".results[].key" => "[ignored]" }), @r###"
+    meili_snap::snapshot!(meili_snap::json_string!(response, { ".results[].createdAt" => "[ignored]", ".results[].updatedAt" => "[ignored]", ".results[].uid" => "[ignored]", ".results[].key" => "[ignored]" }), @r#"
     {
       "results": [
         {
@@ -850,6 +850,22 @@ async fn list_api_keys() {
           "createdAt": "[ignored]",
           "updatedAt": "[ignored]"
         },
+        {
+          "name": "Default Read-Only Admin API Key",
+          "description": "Use it to read information across the whole database. Caution! Do not expose this key on a public frontend",
+          "key": "[ignored]",
+          "uid": "[ignored]",
+          "actions": [
+            "*.get",
+            "keys.get"
+          ],
+          "indexes": [
+            "*"
+          ],
+          "expiresAt": null,
+          "createdAt": "[ignored]",
+          "updatedAt": "[ignored]"
+        },
         {
           "name": "Default Chat API Key",
           "description": "Use it to chat and search from the frontend",
@@ -869,9 +885,9 @@ async fn list_api_keys() {
       ],
       "offset": 0,
       "limit": 20,
-      "total": 4
+      "total": 5
     }
-    "###);
+    "#);
     meili_snap::snapshot!(code, @"200 OK");
 }
 

crates/meilisearch/tests/auth/errors.rs

@@ -91,14 +91,14 @@ async fn create_api_key_bad_actions() {
     // can't parse
     let (response, code) = server.add_api_key(json!({ "actions": ["doggo"] })).await;
     snapshot!(code, @"400 Bad Request");
-    snapshot!(json_string!(response), @r###"
+    snapshot!(json_string!(response), @r#"
     {
-      "message": "Unknown value `doggo` at `.actions[0]`: expected one of `*`, `search`, `documents.*`, `documents.add`, `documents.get`, `documents.delete`, `indexes.*`, `indexes.create`, `indexes.get`, `indexes.update`, `indexes.delete`, `indexes.swap`, `tasks.*`, `tasks.cancel`, `tasks.delete`, `tasks.get`, `settings.*`, `settings.get`, `settings.update`, `stats.*`, `stats.get`, `metrics.*`, `metrics.get`, `dumps.*`, `dumps.create`, `snapshots.*`, `snapshots.create`, `version`, `keys.create`, `keys.get`, `keys.update`, `keys.delete`, `experimental.get`, `experimental.update`, `export`, `network.get`, `network.update`, `chatCompletions`, `chats.*`, `chats.get`, `chats.delete`, `chatsSettings.*`, `chatsSettings.get`, `chatsSettings.update`",
+      "message": "Unknown value `doggo` at `.actions[0]`: expected one of `*`, `search`, `documents.*`, `documents.add`, `documents.get`, `documents.delete`, `indexes.*`, `indexes.create`, `indexes.get`, `indexes.update`, `indexes.delete`, `indexes.swap`, `tasks.*`, `tasks.cancel`, `tasks.delete`, `tasks.get`, `settings.*`, `settings.get`, `settings.update`, `stats.*`, `stats.get`, `metrics.*`, `metrics.get`, `dumps.*`, `dumps.create`, `snapshots.*`, `snapshots.create`, `version`, `keys.create`, `keys.get`, `keys.update`, `keys.delete`, `experimental.get`, `experimental.update`, `export`, `network.get`, `network.update`, `chatCompletions`, `chats.*`, `chats.get`, `chats.delete`, `chatsSettings.*`, `chatsSettings.get`, `chatsSettings.update`, `*.get`, `webhooks.get`, `webhooks.update`, `webhooks.delete`, `webhooks.create`, `webhooks.*`",
       "code": "invalid_api_key_actions",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_api_key_actions"
     }
-    "###);
+    "#);
 }
 
 #[actix_rt::test]

crates/meilisearch/tests/common/index.rs

@@ -249,6 +249,11 @@ impl<'a> Index<'a, Owned> {
         self.service.put_encoded(url, settings, self.encoder).await
     }
 
+    pub async fn update_settings_chat(&self, settings: Value) -> (Value, StatusCode) {
+        let url = format!("/indexes/{}/settings/chat", urlencode(self.uid.as_ref()));
+        self.service.patch_encoded(url, settings, self.encoder).await
+    }
+
     pub async fn delete_settings(&self) -> (Value, StatusCode) {
         let url = format!("/indexes/{}/settings", urlencode(self.uid.as_ref()));
         self.service.delete(url).await
@@ -551,5 +556,7 @@ pub struct GetAllDocumentsOptions {
     pub offset: Option<usize>,
     #[serde(skip_serializing_if = "Option::is_none")]
     pub fields: Option<Vec<&'static str>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub sort: Option<Vec<&'static str>>,
     pub retrieve_vectors: bool,
 }

crates/meilisearch/tests/common/mod.rs

@@ -3,8 +3,10 @@ pub mod index;
 pub mod server;
 pub mod service;
 
+use std::collections::BTreeMap;
 use std::fmt::{self, Display};
 
+use actix_http::StatusCode;
 #[allow(unused)]
 pub use index::GetAllDocumentsOptions;
 use meili_snap::json_string;
@@ -13,6 +15,8 @@ use serde::{Deserialize, Serialize};
 #[allow(unused)]
 pub use server::{default_settings, Server};
 use tokio::sync::OnceCell;
+use wiremock::matchers::{method, path};
+use wiremock::{Mock, MockServer, Request, ResponseTemplate};
 
 use crate::common::index::Index;
 
@@ -38,6 +42,15 @@ impl Value {
         self["uid"].as_u64().is_some() || self["taskUid"].as_u64().is_some()
     }
 
+    #[track_caller]
+    pub fn batch_uid(&self) -> u32 {
+        if let Some(batch_uid) = self["batchUid"].as_u64() {
+            batch_uid as u32
+        } else {
+            panic!("Didn't find `batchUid` in: {self}");
+        }
+    }
+
     /// Return `true` if the `status` field is set to `succeeded`.
     /// Panic if the `status` field doesn't exists.
     #[track_caller]
@@ -508,3 +521,166 @@ pub async fn shared_index_with_geo_documents() -> &'static Index<'static, Shared
         })
         .await
 }
+
+pub async fn shared_index_for_fragments() -> Index<'static, Shared> {
+    static INDEX: OnceCell<(Server<Shared>, String)> = OnceCell::const_new();
+    let (server, uid) = INDEX
+        .get_or_init(|| async {
+            let (server, uid, _) = init_fragments_index().await;
+            (server.into_shared(), uid)
+        })
+        .await;
+    server._index(uid).to_shared()
+}
+
+async fn fragment_mock_server() -> String {
+    let text_to_embedding: BTreeMap<_, _> = vec![
+        ("kefir", [0.5, -0.5, 0.0]),
+        ("intel", [1.0, 1.0, 0.0]),
+        ("dustin", [-0.5, 0.5, 0.0]),
+        ("bulldog", [0.0, 0.0, 1.0]),
+        ("labrador", [0.0, 0.0, -1.0]),
+        ("{{ doc.", [-9999.0, -9999.0, -9999.0]), // If a template didn't render
+    ]
+    .into_iter()
+    .collect();
+
+    let mock_server = Box::leak(Box::new(MockServer::start().await));
+
+    Mock::given(method("POST"))
+        .and(path("/"))
+        .respond_with(move |req: &Request| {
+            let text = String::from_utf8_lossy(&req.body).to_string();
+
+            let mut data = [0.0, 0.0, 0.0];
+            for (inner_text, inner_data) in &text_to_embedding {
+                if text.contains(inner_text) {
+                    for (i, &value) in inner_data.iter().enumerate() {
+                        data[i] += value;
+                    }
+                }
+            }
+            ResponseTemplate::new(200).set_body_json(json!({ "data": data }))
+        })
+        .mount(mock_server)
+        .await;
+
+    mock_server.uri()
+}
+
+pub async fn init_fragments_index() -> (Server<Owned>, String, crate::common::Value) {
+    let url = fragment_mock_server().await;
+    let server = Server::new().await;
+    let index = server.unique_index();
+
+    let (_response, code) = server.set_features(json!({"multimodal": true})).await;
+    assert_eq!(code, StatusCode::OK);
+
+    // Configure the index to use our mock embedder
+    let settings = json!({
+        "embedders": {
+            "rest": {
+                "source": "rest",
+                "url": url,
+                "dimensions": 3,
+                "request": "{{fragment}}",
+                "response": {
+                    "data": "{{embedding}}"
+                },
+                "indexingFragments": {
+                    "withBreed": {"value": "{{ doc.name }} is a {{ doc.breed }}"},
+                    "basic": {"value": "{{ doc.name }} is a dog"},
+                },
+                "searchFragments": {
+                    "justBreed": {"value": "It's a {{ media.breed }}"},
+                    "justName": {"value": "{{ media.name }} is a dog"},
+                    "query": {"value": "Some pre-prompt for query {{ q }}"},
+                }
+            },
+        },
+    });
+    let (response, code) = index.update_settings(settings.clone()).await;
+    assert_eq!(code, StatusCode::ACCEPTED);
+
+    server.wait_task(response.uid()).await.succeeded();
+
+    // Send documents
+    let documents = json!([
+        {"id": 0, "name": "kefir"},
+        {"id": 1, "name": "echo", "_vectors": { "rest": [1, 1, 1] }},
+        {"id": 2, "name": "intel", "breed": "labrador"},
+        {"id": 3, "name": "dustin", "breed": "bulldog"},
+    ]);
+    let (value, code) = index.add_documents(documents, None).await;
+    assert_eq!(code, StatusCode::ACCEPTED);
+
+    let _task = server.wait_task(value.uid()).await.succeeded();
+
+    let uid = index.uid.clone();
+    (server, uid, settings)
+}
+
+pub async fn init_fragments_index_composite() -> (Server<Owned>, String, crate::common::Value) {
+    let url = fragment_mock_server().await;
+    let server = Server::new().await;
+    let index = server.unique_index();
+
+    let (_response, code) = server.set_features(json!({"multimodal": true})).await;
+    assert_eq!(code, StatusCode::OK);
+
+    let (_response, code) = server.set_features(json!({"compositeEmbedders": true})).await;
+    assert_eq!(code, StatusCode::OK);
+
+    // Configure the index to use our mock embedder
+    let settings = json!({
+        "embedders": {
+            "rest": {
+                "source": "composite",
+                "searchEmbedder": {
+                    "source": "rest",
+                    "url": url,
+                    "dimensions": 3,
+                    "request": "{{fragment}}",
+                    "response": {
+                        "data": "{{embedding}}"
+                    },
+                    "searchFragments": {
+                        "query": {"value": "Some pre-prompt for query {{ q }}"},
+                    }
+                },
+                "indexingEmbedder": {
+                    "source": "rest",
+                    "url": url,
+                    "dimensions": 3,
+                    "request": "{{fragment}}",
+                    "response": {
+                        "data": "{{embedding}}"
+                    },
+                    "indexingFragments": {
+                        "withBreed": {"value": "{{ doc.name }} is a {{ doc.breed }}"},
+                        "basic": {"value": "{{ doc.name }} is a dog"},
+                    }
+                },
+            },
+        },
+    });
+    let (response, code) = index.update_settings(settings.clone()).await;
+    assert_eq!(code, StatusCode::ACCEPTED);
+
+    server.wait_task(response.uid()).await.succeeded();
+
+    // Send documents
+    let documents = json!([
+        {"id": 0, "name": "kefir"},
+        {"id": 1, "name": "echo", "_vectors": { "rest": [1, 1, 1] }},
+        {"id": 2, "name": "intel", "breed": "labrador"},
+        {"id": 3, "name": "dustin", "breed": "bulldog"},
+    ]);
+    let (value, code) = index.add_documents(documents, None).await;
+    assert_eq!(code, StatusCode::ACCEPTED);
+
+    server.wait_task(value.uid()).await.succeeded();
+
+    let uid = index.uid.clone();
+    (server, uid, settings)
+}

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(super) fn into_shared(self) -> Server<Shared> {
         Server { service: self.service, _dir: self._dir, _marker: PhantomData }
     }
 
@@ -97,6 +97,7 @@ impl Server<Owned> {
         self.use_api_key(master_key);
         let (response, code) = self.list_api_keys("").await;
         assert_eq!(200, code, "{:?}", response);
+        // TODO: relying on the order of keys is not ideal, we should use the name instead
         let admin_key = &response["results"][1]["key"];
         self.use_api_key(admin_key.as_str().unwrap());
     }
@@ -181,6 +182,25 @@ impl Server<Owned> {
         self.service.patch("/network", value).await
     }
 
+    pub async fn create_webhook(&self, value: Value) -> (Value, StatusCode) {
+        self.service.post("/webhooks", value).await
+    }
+
+    pub async fn get_webhook(&self, uuid: impl AsRef<str>) -> (Value, StatusCode) {
+        let url = format!("/webhooks/{}", uuid.as_ref());
+        self.service.get(url).await
+    }
+
+    pub async fn delete_webhook(&self, uuid: impl AsRef<str>) -> (Value, StatusCode) {
+        let url = format!("/webhooks/{}", uuid.as_ref());
+        self.service.delete(url).await
+    }
+
+    pub async fn patch_webhook(&self, uuid: impl AsRef<str>, value: Value) -> (Value, StatusCode) {
+        let url = format!("/webhooks/{}", uuid.as_ref());
+        self.service.patch(url, value).await
+    }
+
     pub async fn get_metrics(&self) -> (Value, StatusCode) {
         self.service.get("/metrics").await
     }
@@ -446,6 +466,10 @@ impl<State> Server<State> {
     pub async fn get_network(&self) -> (Value, StatusCode) {
         self.service.get("/network").await
     }
+
+    pub async fn get_webhooks(&self) -> (Value, StatusCode) {
+        self.service.get("/webhooks").await
+    }
 }
 
 pub fn default_settings(dir: impl AsRef<Path>) -> Opt {
@@ -465,6 +489,7 @@ pub fn default_settings(dir: impl AsRef<Path>) -> Opt {
             // Having 2 threads makes the tests way faster
             max_indexing_threads: MaxThreads::from_str("2").unwrap(),
             experimental_no_edition_2024_for_settings: false,
+            experimental_no_edition_2024_for_dumps: false,
         },
         experimental_enable_metrics: false,
         ..Parser::parse_from(None as Option<&str>)

crates/meilisearch/tests/documents/errors.rs

@@ -557,7 +557,7 @@ async fn delete_document_by_filter() {
     "###);
 
     let index = shared_does_not_exists_index().await;
-    // index does not exists
+    // index does not exist
     let (response, _code) =
         index.delete_document_by_filter_fail(json!({ "filter": "doggo = bernese"}), server).await;
     snapshot!(response, @r###"

crates/meilisearch/tests/documents/get_documents.rs

@@ -5,8 +5,8 @@ use urlencoding::encode as urlencode;
 
 use crate::common::encoder::Encoder;
 use crate::common::{
-    shared_does_not_exists_index, shared_empty_index, shared_index_with_test_set,
-    GetAllDocumentsOptions, Server, Value,
+    shared_does_not_exists_index, shared_empty_index, shared_index_with_geo_documents,
+    shared_index_with_test_set, GetAllDocumentsOptions, Server, Value,
 };
 use crate::json;
 
@@ -83,6 +83,311 @@ async fn get_document() {
     );
 }
 
+#[actix_rt::test]
+async fn get_document_sorted() {
+    let server = Server::new_shared();
+    let index = server.unique_index();
+    index.load_test_set(server).await;
+
+    let (task, _status_code) =
+        index.update_settings_sortable_attributes(json!(["age", "email", "gender", "name"])).await;
+    server.wait_task(task.uid()).await.succeeded();
+
+    let (response, _code) = index
+        .get_all_documents(GetAllDocumentsOptions {
+            fields: Some(vec!["id", "age", "email"]),
+            sort: Some(vec!["age:asc", "email:desc"]),
+            ..Default::default()
+        })
+        .await;
+    let results = response["results"].as_array().unwrap();
+    snapshot!(json_string!(results), @r#"
+    [
+      {
+        "id": 5,
+        "age": 20,
+        "email": "warrenwatson@chorizon.com"
+      },
+      {
+        "id": 6,
+        "age": 20,
+        "email": "sheliaberry@chorizon.com"
+      },
+      {
+        "id": 57,
+        "age": 20,
+        "email": "kaitlinconner@chorizon.com"
+      },
+      {
+        "id": 45,
+        "age": 20,
+        "email": "irenebennett@chorizon.com"
+      },
+      {
+        "id": 40,
+        "age": 21,
+        "email": "staffordemerson@chorizon.com"
+      },
+      {
+        "id": 41,
+        "age": 21,
+        "email": "salinasgamble@chorizon.com"
+      },
+      {
+        "id": 63,
+        "age": 21,
+        "email": "knowleshebert@chorizon.com"
+      },
+      {
+        "id": 50,
+        "age": 21,
+        "email": "guerramcintyre@chorizon.com"
+      },
+      {
+        "id": 44,
+        "age": 22,
+        "email": "jonispears@chorizon.com"
+      },
+      {
+        "id": 56,
+        "age": 23,
+        "email": "tuckerbarry@chorizon.com"
+      },
+      {
+        "id": 51,
+        "age": 23,
+        "email": "keycervantes@chorizon.com"
+      },
+      {
+        "id": 60,
+        "age": 23,
+        "email": "jodyherrera@chorizon.com"
+      },
+      {
+        "id": 70,
+        "age": 23,
+        "email": "glassperkins@chorizon.com"
+      },
+      {
+        "id": 75,
+        "age": 24,
+        "email": "emmajacobs@chorizon.com"
+      },
+      {
+        "id": 68,
+        "age": 24,
+        "email": "angelinadyer@chorizon.com"
+      },
+      {
+        "id": 17,
+        "age": 25,
+        "email": "ortegabrennan@chorizon.com"
+      },
+      {
+        "id": 76,
+        "age": 25,
+        "email": "claricegardner@chorizon.com"
+      },
+      {
+        "id": 43,
+        "age": 25,
+        "email": "arnoldbender@chorizon.com"
+      },
+      {
+        "id": 12,
+        "age": 25,
+        "email": "aidakirby@chorizon.com"
+      },
+      {
+        "id": 9,
+        "age": 26,
+        "email": "kellimendez@chorizon.com"
+      }
+    ]
+    "#);
+
+    let (response, _code) = index
+        .get_all_documents(GetAllDocumentsOptions {
+            fields: Some(vec!["id", "gender", "name"]),
+            sort: Some(vec!["gender:asc", "name:asc"]),
+            ..Default::default()
+        })
+        .await;
+    let results = response["results"].as_array().unwrap();
+    snapshot!(json_string!(results), @r#"
+    [
+      {
+        "id": 3,
+        "name": "Adeline Flynn",
+        "gender": "female"
+      },
+      {
+        "id": 12,
+        "name": "Aida Kirby",
+        "gender": "female"
+      },
+      {
+        "id": 68,
+        "name": "Angelina Dyer",
+        "gender": "female"
+      },
+      {
+        "id": 15,
+        "name": "Aurelia Contreras",
+        "gender": "female"
+      },
+      {
+        "id": 36,
+        "name": "Barbra Valenzuela",
+        "gender": "female"
+      },
+      {
+        "id": 23,
+        "name": "Blanca Mcclain",
+        "gender": "female"
+      },
+      {
+        "id": 53,
+        "name": "Caitlin Burnett",
+        "gender": "female"
+      },
+      {
+        "id": 71,
+        "name": "Candace Sawyer",
+        "gender": "female"
+      },
+      {
+        "id": 65,
+        "name": "Carole Rowland",
+        "gender": "female"
+      },
+      {
+        "id": 33,
+        "name": "Cecilia Greer",
+        "gender": "female"
+      },
+      {
+        "id": 1,
+        "name": "Cherry Orr",
+        "gender": "female"
+      },
+      {
+        "id": 38,
+        "name": "Christina Short",
+        "gender": "female"
+      },
+      {
+        "id": 7,
+        "name": "Chrystal Boyd",
+        "gender": "female"
+      },
+      {
+        "id": 76,
+        "name": "Clarice Gardner",
+        "gender": "female"
+      },
+      {
+        "id": 73,
+        "name": "Eleanor Shepherd",
+        "gender": "female"
+      },
+      {
+        "id": 75,
+        "name": "Emma Jacobs",
+        "gender": "female"
+      },
+      {
+        "id": 16,
+        "name": "Estella Bass",
+        "gender": "female"
+      },
+      {
+        "id": 62,
+        "name": "Estelle Ramirez",
+        "gender": "female"
+      },
+      {
+        "id": 20,
+        "name": "Florence Long",
+        "gender": "female"
+      },
+      {
+        "id": 42,
+        "name": "Graciela Russell",
+        "gender": "female"
+      }
+    ]
+    "#);
+}
+
+#[actix_rt::test]
+async fn get_document_geosorted() {
+    let index = shared_index_with_geo_documents().await;
+
+    let (response, _code) = index
+        .get_all_documents(GetAllDocumentsOptions {
+            sort: Some(vec!["_geoPoint(45.4777599, 9.1967508):asc"]),
+            ..Default::default()
+        })
+        .await;
+    let results = response["results"].as_array().unwrap();
+    snapshot!(json_string!(results), @r#"
+    [
+      {
+        "id": 2,
+        "name": "La Bella Italia",
+        "address": "456 Elm Street, Townsville",
+        "type": "Italian",
+        "rating": 9,
+        "_geo": {
+          "lat": "45.4777599",
+          "lng": "9.1967508"
+        }
+      },
+      {
+        "id": 1,
+        "name": "Taco Truck",
+        "address": "444 Salsa Street, Burritoville",
+        "type": "Mexican",
+        "rating": 9,
+        "_geo": {
+          "lat": 34.0522,
+          "lng": -118.2437
+        }
+      },
+      {
+        "id": 3,
+        "name": "Crêpe Truck",
+        "address": "2 Billig Avenue, Rouenville",
+        "type": "French",
+        "rating": 10
+      }
+    ]
+    "#);
+}
+
+#[actix_rt::test]
+async fn get_document_sort_the_unsortable() {
+    let index = shared_index_with_test_set().await;
+
+    let (response, _code) = index
+        .get_all_documents(GetAllDocumentsOptions {
+            fields: Some(vec!["id", "name"]),
+            sort: Some(vec!["name:asc"]),
+            ..Default::default()
+        })
+        .await;
+
+    snapshot!(json_string!(response), @r#"
+    {
+      "message": "Attribute `name` is not sortable. This index does not have configured sortable attributes.",
+      "code": "invalid_document_sort",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#invalid_document_sort"
+    }
+    "#);
+}
+
 #[actix_rt::test]
 async fn error_get_unexisting_index_all_documents() {
     let index = shared_does_not_exists_index().await;

crates/meilisearch/tests/index/stats.rs

@@ -1,5 +1,4 @@
 use crate::common::{shared_does_not_exists_index, Server};
-
 use crate::json;
 
 #[actix_rt::test]

crates/meilisearch/tests/search/errors.rs

@@ -304,7 +304,7 @@ async fn search_bad_filter() {
     let server = Server::new_shared();
     let index = server.unique_index();
     // Also, to trigger the error message we need to effectively create the index or else it'll throw an
-    // index does not exists error.
+    // index does not exist error.
     let (response, _code) = index.create(None).await;
     server.wait_task(response.uid()).await.succeeded();
 
@@ -1263,34 +1263,34 @@ async fn search_with_contains_without_enabling_the_feature() {
     let server = Server::new_shared();
     let index = server.unique_index();
     // Also, to trigger the error message we need to effectively create the index or else it'll throw an
-    // index does not exists error.
+    // index does not exist error.
     let (task, _code) = index.create(None).await;
     server.wait_task(task.uid()).await.succeeded();
 
     index
         .search(json!({ "filter": "doggo CONTAINS kefir" }), |response, code| {
             snapshot!(code, @"400 Bad Request");
-            snapshot!(json_string!(response), @r###"
+            snapshot!(json_string!(response), @r#"
             {
-              "message": "Using `CONTAINS` or `STARTS WITH` in a filter requires enabling the `contains filter` experimental feature. See https://github.com/orgs/meilisearch/discussions/763\n7:15 doggo CONTAINS kefir",
+              "message": "Using `CONTAINS` in a filter requires enabling the `contains filter` experimental feature. See https://github.com/orgs/meilisearch/discussions/763\n7:15 doggo CONTAINS kefir",
               "code": "feature_not_enabled",
               "type": "invalid_request",
               "link": "https://docs.meilisearch.com/errors#feature_not_enabled"
             }
-            "###);
+            "#);
         })
         .await;
     index
         .search(json!({ "filter": "doggo != echo AND doggo CONTAINS kefir" }), |response, code| {
             snapshot!(code, @"400 Bad Request");
-            snapshot!(json_string!(response), @r###"
+            snapshot!(json_string!(response), @r#"
             {
-              "message": "Using `CONTAINS` or `STARTS WITH` in a filter requires enabling the `contains filter` experimental feature. See https://github.com/orgs/meilisearch/discussions/763\n25:33 doggo != echo AND doggo CONTAINS kefir",
+              "message": "Using `CONTAINS` in a filter requires enabling the `contains filter` experimental feature. See https://github.com/orgs/meilisearch/discussions/763\n25:33 doggo != echo AND doggo CONTAINS kefir",
               "code": "feature_not_enabled",
               "type": "invalid_request",
               "link": "https://docs.meilisearch.com/errors#feature_not_enabled"
             }
-            "###);
+            "#);
         })
         .await;
 
@@ -1299,24 +1299,24 @@ async fn search_with_contains_without_enabling_the_feature() {
         index.search_post(json!({ "filter": ["doggo != echo", "doggo CONTAINS kefir"] })).await;
 
     snapshot!(code, @"400 Bad Request");
-    snapshot!(json_string!(response), @r###"
+    snapshot!(json_string!(response), @r#"
     {
-      "message": "Using `CONTAINS` or `STARTS WITH` in a filter requires enabling the `contains filter` experimental feature. See https://github.com/orgs/meilisearch/discussions/763\n7:15 doggo CONTAINS kefir",
+      "message": "Using `CONTAINS` in a filter requires enabling the `contains filter` experimental feature. See https://github.com/orgs/meilisearch/discussions/763\n7:15 doggo CONTAINS kefir",
       "code": "feature_not_enabled",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#feature_not_enabled"
     }
-    "###);
+    "#);
     let (response, code) =
         index.search_post(json!({ "filter": ["doggo != echo", ["doggo CONTAINS kefir"]] })).await;
 
     snapshot!(code, @"400 Bad Request");
-    snapshot!(json_string!(response), @r###"
+    snapshot!(json_string!(response), @r#"
     {
-      "message": "Using `CONTAINS` or `STARTS WITH` in a filter requires enabling the `contains filter` experimental feature. See https://github.com/orgs/meilisearch/discussions/763\n7:15 doggo CONTAINS kefir",
+      "message": "Using `CONTAINS` in a filter requires enabling the `contains filter` experimental feature. See https://github.com/orgs/meilisearch/discussions/763\n7:15 doggo CONTAINS kefir",
       "code": "feature_not_enabled",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#feature_not_enabled"
     }
-    "###);
+    "#);
 }

crates/meilisearch/tests/search/filters.rs

@@ -4,8 +4,8 @@ use tempfile::TempDir;
 
 use super::test_settings_documents_indexing_swapping_and_search;
 use crate::common::{
-    default_settings, shared_index_with_documents, shared_index_with_nested_documents, Server,
-    DOCUMENTS, NESTED_DOCUMENTS,
+    default_settings, shared_index_for_fragments, shared_index_with_documents,
+    shared_index_with_nested_documents, Server, DOCUMENTS, NESTED_DOCUMENTS,
 };
 use crate::json;
 
@@ -731,3 +731,432 @@ async fn test_filterable_attributes_priority() {
     )
     .await;
 }
+
+#[actix_rt::test]
+async fn vector_filter_all_embedders() {
+    let index = shared_index_for_fragments().await;
+
+    let (value, _code) = index
+        .search_post(json!({
+            "filter": "_vectors EXISTS",
+            "attributesToRetrieve": ["name"]
+        }))
+        .await;
+    snapshot!(value, @r#"
+    {
+      "hits": [
+        {
+          "name": "kefir"
+        },
+        {
+          "name": "echo"
+        },
+        {
+          "name": "intel"
+        },
+        {
+          "name": "dustin"
+        }
+      ],
+      "query": "",
+      "processingTimeMs": "[duration]",
+      "limit": 20,
+      "offset": 0,
+      "estimatedTotalHits": 4
+    }
+    "#);
+}
+
+#[actix_rt::test]
+async fn vector_filter_missing_fragment() {
+    let index = shared_index_for_fragments().await;
+
+    let (value, _code) = index
+        .search_post(json!({
+            "filter": "_vectors.rest.fragments EXISTS",
+            "attributesToRetrieve": ["name"]
+        }))
+        .await;
+    snapshot!(value, @r#"
+    {
+      "message": "The vector filter is missing a fragment name.\n24:31 _vectors.rest.fragments EXISTS",
+      "code": "invalid_search_filter",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#invalid_search_filter"
+    }
+    "#);
+}
+
+#[actix_rt::test]
+async fn vector_filter_nonexistent_embedder() {
+    let index = shared_index_for_fragments().await;
+
+    let (value, _code) = index
+        .search_post(json!({
+            "filter": "_vectors.other EXISTS",
+            "attributesToRetrieve": ["name"]
+        }))
+        .await;
+    snapshot!(value, @r#"
+    {
+      "message": "Index `[uuid]`: The embedder `other` does not exist. Available embedders are: `rest`.\n10:15 _vectors.other EXISTS",
+      "code": "invalid_search_filter",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#invalid_search_filter"
+    }
+    "#);
+}
+
+#[actix_rt::test]
+async fn vector_filter_all_embedders_user_provided() {
+    let index = shared_index_for_fragments().await;
+
+    // This one is counterintuitive, but it is the same as the previous one.
+    // It's because userProvided is interpreted as an embedder name
+    let (value, _code) = index
+        .search_post(json!({
+            "filter": "_vectors.userProvided EXISTS",
+            "attributesToRetrieve": ["name"]
+        }))
+        .await;
+    snapshot!(value, @r#"
+    {
+      "message": "Index `[uuid]`: The embedder `userProvided` does not exist. Available embedders are: `rest`.\n10:22 _vectors.userProvided EXISTS",
+      "code": "invalid_search_filter",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#invalid_search_filter"
+    }
+    "#);
+}
+
+#[actix_rt::test]
+async fn vector_filter_specific_embedder() {
+    let index = shared_index_for_fragments().await;
+
+    let (value, _code) = index
+        .search_post(json!({
+            "filter": "_vectors.rest EXISTS",
+            "attributesToRetrieve": ["name"]
+        }))
+        .await;
+    snapshot!(value, @r#"
+    {
+      "hits": [
+        {
+          "name": "kefir"
+        },
+        {
+          "name": "echo"
+        },
+        {
+          "name": "intel"
+        },
+        {
+          "name": "dustin"
+        }
+      ],
+      "query": "",
+      "processingTimeMs": "[duration]",
+      "limit": 20,
+      "offset": 0,
+      "estimatedTotalHits": 4
+    }
+    "#);
+}
+
+#[actix_rt::test]
+async fn vector_filter_user_provided() {
+    let index = shared_index_for_fragments().await;
+
+    let (value, _code) = index
+        .search_post(json!({
+            "filter": "_vectors.rest.userProvided EXISTS",
+            "attributesToRetrieve": ["name"]
+        }))
+        .await;
+    snapshot!(value, @r#"
+    {
+      "hits": [
+        {
+          "name": "echo"
+        }
+      ],
+      "query": "",
+      "processingTimeMs": "[duration]",
+      "limit": 20,
+      "offset": 0,
+      "estimatedTotalHits": 1
+    }
+    "#);
+}
+
+#[actix_rt::test]
+async fn vector_filter_specific_fragment() {
+    let index = shared_index_for_fragments().await;
+
+    let (value, _code) = index
+        .search_post(json!({
+            "filter": "_vectors.rest.fragments.withBreed EXISTS",
+            "attributesToRetrieve": ["name"]
+        }))
+        .await;
+    snapshot!(value, @r#"
+    {
+      "hits": [
+        {
+          "name": "intel"
+        },
+        {
+          "name": "dustin"
+        }
+      ],
+      "query": "",
+      "processingTimeMs": "[duration]",
+      "limit": 20,
+      "offset": 0,
+      "estimatedTotalHits": 2
+    }
+    "#);
+
+    let (value, _code) = index
+        .search_post(json!({
+            "filter": "_vectors.rest.fragments.basic EXISTS",
+            "attributesToRetrieve": ["name"]
+        }))
+        .await;
+    snapshot!(value, @r#"
+    {
+      "hits": [
+        {
+          "name": "kefir"
+        },
+        {
+          "name": "intel"
+        },
+        {
+          "name": "dustin"
+        }
+      ],
+      "query": "",
+      "processingTimeMs": "[duration]",
+      "limit": 20,
+      "offset": 0,
+      "estimatedTotalHits": 3
+    }
+    "#);
+}
+
+#[actix_rt::test]
+async fn vector_filter_non_existant_fragment() {
+    let index = shared_index_for_fragments().await;
+
+    let (value, _code) = index
+        .search_post(json!({
+            "filter": "_vectors.rest.fragments.withBred EXISTS",
+            "attributesToRetrieve": ["name"]
+        }))
+        .await;
+    snapshot!(value, @r#"
+    {
+      "message": "Index `[uuid]`: The fragment `withBred` does not exist on embedder `rest`. Available fragments on this embedder are: `basic`, `withBreed`. Did you mean `withBreed`?\n25:33 _vectors.rest.fragments.withBred EXISTS",
+      "code": "invalid_search_filter",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#invalid_search_filter"
+    }
+    "#);
+}
+
+#[actix_rt::test]
+async fn vector_filter_document_template_but_fragments_used() {
+    let index = shared_index_for_fragments().await;
+
+    let (value, _code) = index
+        .search_post(json!({
+            "filter": "_vectors.rest.documentTemplate EXISTS",
+            "attributesToRetrieve": ["name"]
+        }))
+        .await;
+    snapshot!(value, @r#"
+    {
+      "hits": [],
+      "query": "",
+      "processingTimeMs": "[duration]",
+      "limit": 20,
+      "offset": 0,
+      "estimatedTotalHits": 0
+    }
+    "#);
+}
+
+#[actix_rt::test]
+async fn vector_filter_document_template() {
+    let (_mock, setting) = crate::vector::create_mock().await;
+    let server = crate::vector::get_server_vector().await;
+    let index = server.index("doggo");
+
+    let (_response, code) = server.set_features(json!({"multimodal": true})).await;
+    snapshot!(code, @"200 OK");
+
+    let (response, code) = index
+        .update_settings(json!({
+            "embedders": {
+                "rest": setting,
+            },
+        }))
+        .await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(response.uid()).await.succeeded();
+
+    let documents = json!([
+        {"id": 0, "name": "kefir"},
+        {"id": 1, "name": "echo", "_vectors": { "rest": [1, 1, 1] }},
+        {"id": 2, "name": "intel"},
+        {"id": 3, "name": "iko" }
+    ]);
+    let (value, code) = index.add_documents(documents, None).await;
+    snapshot!(code, @"202 Accepted");
+    server.wait_task(value.uid()).await.succeeded();
+
+    let (value, _code) = index
+        .search_post(json!({
+            "filter": "_vectors.rest.documentTemplate EXISTS",
+            "attributesToRetrieve": ["name"]
+        }))
+        .await;
+    snapshot!(value, @r#"
+    {
+      "hits": [
+        {
+          "name": "kefir"
+        },
+        {
+          "name": "intel"
+        },
+        {
+          "name": "iko"
+        }
+      ],
+      "query": "",
+      "processingTimeMs": "[duration]",
+      "limit": 20,
+      "offset": 0,
+      "estimatedTotalHits": 3
+    }
+    "#);
+}
+
+#[actix_rt::test]
+async fn vector_filter_feature_gate() {
+    let index = shared_index_with_documents().await;
+
+    let (value, _code) = index
+        .search_post(json!({
+            "filter": "_vectors EXISTS",
+            "attributesToRetrieve": ["name"]
+        }))
+        .await;
+    snapshot!(value, @r#"
+    {
+      "message": "using a vector filter requires enabling the `multimodal` experimental feature. See https://github.com/orgs/meilisearch/discussions/846\n1:9 _vectors EXISTS",
+      "code": "feature_not_enabled",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#feature_not_enabled"
+    }
+    "#);
+}
+
+#[actix_rt::test]
+async fn vector_filter_negation() {
+    let index = shared_index_for_fragments().await;
+
+    let (value, _code) = index
+        .search_post(json!({
+            "filter": "_vectors.rest.userProvided NOT EXISTS",
+            "attributesToRetrieve": ["name"]
+        }))
+        .await;
+    snapshot!(value, @r#"
+    {
+      "hits": [
+        {
+          "name": "kefir"
+        },
+        {
+          "name": "intel"
+        },
+        {
+          "name": "dustin"
+        }
+      ],
+      "query": "",
+      "processingTimeMs": "[duration]",
+      "limit": 20,
+      "offset": 0,
+      "estimatedTotalHits": 3
+    }
+    "#);
+}
+
+#[actix_rt::test]
+async fn vector_filter_or_combination() {
+    let index = shared_index_for_fragments().await;
+
+    let (value, _code) = index
+        .search_post(json!({
+            "filter": "_vectors.rest.fragments.withBreed EXISTS OR _vectors.rest.userProvided EXISTS",
+            "attributesToRetrieve": ["name"]
+        }))
+        .await;
+    snapshot!(value, @r#"
+    {
+      "hits": [
+        {
+          "name": "echo"
+        },
+        {
+          "name": "intel"
+        },
+        {
+          "name": "dustin"
+        }
+      ],
+      "query": "",
+      "processingTimeMs": "[duration]",
+      "limit": 20,
+      "offset": 0,
+      "estimatedTotalHits": 3
+    }
+    "#);
+}
+
+#[actix_rt::test]
+async fn vector_filter_regenerate() {
+    let index = shared_index_for_fragments().await;
+
+    let (value, _code) = index
+        .search_post(json!({
+            "filter": format!("_vectors.rest.regenerate EXISTS"),
+            "attributesToRetrieve": ["name"]
+        }))
+        .await;
+    snapshot!(value, @r#"
+    {
+      "hits": [
+        {
+          "name": "kefir"
+        },
+        {
+          "name": "intel"
+        },
+        {
+          "name": "dustin"
+        }
+      ],
+      "query": "",
+      "processingTimeMs": "[duration]",
+      "limit": 20,
+      "offset": 0,
+      "estimatedTotalHits": 3
+    }
+    "#);
+}

crates/meilisearch/tests/search/hybrid.rs

@@ -148,7 +148,70 @@ async fn simple_search() {
         )
         .await;
     snapshot!(code, @"200 OK");
-    snapshot!(response["hits"], @r###"[{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":{"embeddings":[[1.0,2.0]],"regenerate":false}}},{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":{"embeddings":[[2.0,3.0]],"regenerate":false}}},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}}}]"###);
+    snapshot!(response, @r#"
+    {
+      "hits": [
+        {
+          "title": "Captain Planet",
+          "desc": "He's not part of the Marvel Cinematic Universe",
+          "id": "2",
+          "_vectors": {
+            "default": {
+              "embeddings": [
+                [
+                  1.0,
+                  2.0
+                ]
+              ],
+              "regenerate": false
+            }
+          }
+        },
+        {
+          "title": "Captain Marvel",
+          "desc": "a Shazam ersatz",
+          "id": "3",
+          "_vectors": {
+            "default": {
+              "embeddings": [
+                [
+                  2.0,
+                  3.0
+                ]
+              ],
+              "regenerate": false
+            }
+          }
+        },
+        {
+          "title": "Shazam!",
+          "desc": "a Captain Marvel ersatz",
+          "id": "1",
+          "_vectors": {
+            "default": {
+              "embeddings": [
+                [
+                  1.0,
+                  3.0
+                ]
+              ],
+              "regenerate": false
+            }
+          }
+        }
+      ],
+      "query": "Captain",
+      "queryVector": [
+        1.0,
+        1.0
+      ],
+      "processingTimeMs": "[duration]",
+      "limit": 20,
+      "offset": 0,
+      "estimatedTotalHits": 3,
+      "semanticHitCount": 0
+    }
+    "#);
     snapshot!(response["semanticHitCount"], @"0");
 
     let (response, code) = index
@@ -157,7 +220,73 @@ async fn simple_search() {
         )
         .await;
     snapshot!(code, @"200 OK");
-    snapshot!(response["hits"], @r###"[{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":{"embeddings":[[2.0,3.0]],"regenerate":false}},"_rankingScore":0.990290343761444},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":{"embeddings":[[1.0,2.0]],"regenerate":false}},"_rankingScore":0.9848484848484848},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}},"_rankingScore":0.9472135901451112}]"###);
+    snapshot!(response, @r#"
+    {
+      "hits": [
+        {
+          "title": "Captain Marvel",
+          "desc": "a Shazam ersatz",
+          "id": "3",
+          "_vectors": {
+            "default": {
+              "embeddings": [
+                [
+                  2.0,
+                  3.0
+                ]
+              ],
+              "regenerate": false
+            }
+          },
+          "_rankingScore": 0.990290343761444
+        },
+        {
+          "title": "Captain Planet",
+          "desc": "He's not part of the Marvel Cinematic Universe",
+          "id": "2",
+          "_vectors": {
+            "default": {
+              "embeddings": [
+                [
+                  1.0,
+                  2.0
+                ]
+              ],
+              "regenerate": false
+            }
+          },
+          "_rankingScore": 0.9848484848484848
+        },
+        {
+          "title": "Shazam!",
+          "desc": "a Captain Marvel ersatz",
+          "id": "1",
+          "_vectors": {
+            "default": {
+              "embeddings": [
+                [
+                  1.0,
+                  3.0
+                ]
+              ],
+              "regenerate": false
+            }
+          },
+          "_rankingScore": 0.9472135901451112
+        }
+      ],
+      "query": "Captain",
+      "queryVector": [
+        1.0,
+        1.0
+      ],
+      "processingTimeMs": "[duration]",
+      "limit": 20,
+      "offset": 0,
+      "estimatedTotalHits": 3,
+      "semanticHitCount": 2
+    }
+    "#);
     snapshot!(response["semanticHitCount"], @"2");
 
     let (response, code) = index
@@ -166,7 +295,73 @@ async fn simple_search() {
         )
         .await;
     snapshot!(code, @"200 OK");
-    snapshot!(response["hits"], @r###"[{"title":"Captain Marvel","desc":"a Shazam ersatz","id":"3","_vectors":{"default":{"embeddings":[[2.0,3.0]],"regenerate":false}},"_rankingScore":0.990290343761444},{"title":"Captain Planet","desc":"He's not part of the Marvel Cinematic Universe","id":"2","_vectors":{"default":{"embeddings":[[1.0,2.0]],"regenerate":false}},"_rankingScore":0.974341630935669},{"title":"Shazam!","desc":"a Captain Marvel ersatz","id":"1","_vectors":{"default":{"embeddings":[[1.0,3.0]],"regenerate":false}},"_rankingScore":0.9472135901451112}]"###);
+    snapshot!(response, @r#"
+    {
+      "hits": [
+        {
+          "title": "Captain Marvel",
+          "desc": "a Shazam ersatz",
+          "id": "3",
+          "_vectors": {
+            "default": {
+              "embeddings": [
+                [
+                  2.0,
+                  3.0
+                ]
+              ],
+              "regenerate": false
+            }
+          },
+          "_rankingScore": 0.990290343761444
+        },
+        {
+          "title": "Captain Planet",
+          "desc": "He's not part of the Marvel Cinematic Universe",
+          "id": "2",
+          "_vectors": {
+            "default": {
+              "embeddings": [
+                [
+                  1.0,
+                  2.0
+                ]
+              ],
+              "regenerate": false
+            }
+          },
+          "_rankingScore": 0.974341630935669
+        },
+        {
+          "title": "Shazam!",
+          "desc": "a Captain Marvel ersatz",
+          "id": "1",
+          "_vectors": {
+            "default": {
+              "embeddings": [
+                [
+                  1.0,
+                  3.0
+                ]
+              ],
+              "regenerate": false
+            }
+          },
+          "_rankingScore": 0.9472135901451112
+        }
+      ],
+      "query": "Captain",
+      "queryVector": [
+        1.0,
+        1.0
+      ],
+      "processingTimeMs": "[duration]",
+      "limit": 20,
+      "offset": 0,
+      "estimatedTotalHits": 3,
+      "semanticHitCount": 3
+    }
+    "#);
     snapshot!(response["semanticHitCount"], @"3");
 }
 

crates/meilisearch/tests/search/multi/mod.rs

@@ -3703,7 +3703,7 @@ async fn federation_vector_two_indexes() {
         ]}))
         .await;
     snapshot!(code, @"200 OK");
-    snapshot!(json_string!(response, { ".processingTimeMs" => "[duration]", ".**._rankingScore" => "[score]" }), @r###"
+    snapshot!(json_string!(response, { ".processingTimeMs" => "[duration]", ".**._rankingScore" => "[score]" }), @r#"
     {
       "hits": [
         {
@@ -3911,9 +3911,20 @@ async fn federation_vector_two_indexes() {
       "limit": 20,
       "offset": 0,
       "estimatedTotalHits": 8,
+      "queryVectors": {
+        "0": [
+          1.0,
+          0.0,
+          0.5
+        ],
+        "1": [
+          0.8,
+          0.6
+        ]
+      },
       "semanticHitCount": 6
     }
-    "###);
+    "#);
 
     // hybrid search, distinct embedder
     let (response, code) = server
@@ -3923,7 +3934,7 @@ async fn federation_vector_two_indexes() {
         ]}))
         .await;
     snapshot!(code, @"200 OK");
-    snapshot!(json_string!(response, { ".processingTimeMs" => "[duration]", ".**._rankingScore" => "[score]" }), @r###"
+    snapshot!(json_string!(response, { ".processingTimeMs" => "[duration]", ".**._rankingScore" => "[score]" }), @r#"
     {
       "hits": [
         {
@@ -4139,9 +4150,20 @@ async fn federation_vector_two_indexes() {
       "limit": 20,
       "offset": 0,
       "estimatedTotalHits": 8,
+      "queryVectors": {
+        "0": [
+          1.0,
+          0.0,
+          0.5
+        ],
+        "1": [
+          -1.0,
+          0.6
+        ]
+      },
       "semanticHitCount": 8
     }
-    "###);
+    "#);
 }
 
 #[actix_rt::test]

crates/meilisearch/tests/search/multi/proxy.rs

@@ -2,8 +2,9 @@ use std::sync::Arc;
 
 use actix_http::StatusCode;
 use meili_snap::{json_string, snapshot};
-use wiremock::matchers::AnyMatcher;
-use wiremock::{Mock, MockServer, ResponseTemplate};
+use wiremock::matchers::method;
+use wiremock::matchers::{path, AnyMatcher};
+use wiremock::{Mock, MockServer, Request, ResponseTemplate};
 
 use crate::common::{Server, Value, SCORE_DOCUMENTS};
 use crate::json;
@@ -415,6 +416,503 @@ async fn remote_sharding() {
     "###);
 }
 
+#[actix_rt::test]
+async fn remote_sharding_retrieve_vectors() {
+    let ms0 = Server::new().await;
+    let ms1 = Server::new().await;
+    let ms2 = Server::new().await;
+    let index0 = ms0.index("test");
+    let index1 = ms1.index("test");
+    let index2 = ms2.index("test");
+
+    // enable feature
+
+    let (response, code) = ms0.set_features(json!({"network": true})).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response["network"]), @"true");
+    let (response, code) = ms1.set_features(json!({"network": true})).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response["network"]), @"true");
+    let (response, code) = ms2.set_features(json!({"network": true})).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response["network"]), @"true");
+
+    // set self
+
+    let (response, code) = ms0.set_network(json!({"self": "ms0"})).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response), @r###"
+    {
+      "self": "ms0",
+      "remotes": {}
+    }
+    "###);
+    let (response, code) = ms1.set_network(json!({"self": "ms1"})).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response), @r###"
+    {
+      "self": "ms1",
+      "remotes": {}
+    }
+    "###);
+    let (response, code) = ms2.set_network(json!({"self": "ms2"})).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response), @r###"
+    {
+      "self": "ms2",
+      "remotes": {}
+    }
+    "###);
+
+    // setup embedders
+
+    let mock_server = MockServer::start().await;
+    Mock::given(method("POST"))
+        .and(path("/"))
+        .respond_with(move |req: &Request| {
+            println!("Received request: {:?}", req);
+            let text = req.body_json::<String>().unwrap().to_lowercase();
+            let patterns = [
+                ("batman", [1.0, 0.0, 0.0]),
+                ("dark", [0.0, 0.1, 0.0]),
+                ("knight", [0.1, 0.1, 0.0]),
+                ("returns", [0.0, 0.0, 0.2]),
+                ("part", [0.05, 0.1, 0.0]),
+                ("1", [0.3, 0.05, 0.0]),
+                ("2", [0.2, 0.05, 0.0]),
+            ];
+            let mut embedding = vec![0.; 3];
+            for (pattern, vector) in patterns {
+                if text.contains(pattern) {
+                    for (i, v) in vector.iter().enumerate() {
+                        embedding[i] += v;
+                    }
+                }
+            }
+            ResponseTemplate::new(200).set_body_json(json!({ "data": embedding }))
+        })
+        .mount(&mock_server)
+        .await;
+    let url = mock_server.uri();
+
+    for (server, index) in [(&ms0, &index0), (&ms1, &index1), (&ms2, &index2)] {
+        let (response, code) = index
+            .update_settings(json!({
+                "embedders": {
+                    "rest": {
+                        "source": "rest",
+                        "url": url,
+                        "dimensions": 3,
+                        "request": "{{text}}",
+                        "response": { "data": "{{embedding}}" },
+                        "documentTemplate": "{{doc.name}}",
+                    },
+                },
+            }))
+            .await;
+        snapshot!(code, @"202 Accepted");
+        server.wait_task(response.uid()).await.succeeded();
+    }
+
+    // wrap servers
+    let ms0 = Arc::new(ms0);
+    let ms1 = Arc::new(ms1);
+    let ms2 = Arc::new(ms2);
+
+    let rms0 = LocalMeili::new(ms0.clone()).await;
+    let rms1 = LocalMeili::new(ms1.clone()).await;
+    let rms2 = LocalMeili::new(ms2.clone()).await;
+
+    // set network
+    let network = json!({"remotes": {
+        "ms0": {
+            "url": rms0.url()
+        },
+        "ms1": {
+            "url": rms1.url()
+        },
+        "ms2": {
+            "url": rms2.url()
+        }
+    }});
+
+    let (_response, status_code) = ms0.set_network(network.clone()).await;
+    snapshot!(status_code, @"200 OK");
+    let (_response, status_code) = ms1.set_network(network.clone()).await;
+    snapshot!(status_code, @"200 OK");
+    let (_response, status_code) = ms2.set_network(network.clone()).await;
+    snapshot!(status_code, @"200 OK");
+
+    // multi vector search: one query per remote
+
+    let request = json!({
+        "federation": {},
+        "queries": [
+            {
+                "q": "batman",
+                "indexUid": "test",
+                "hybrid": {
+                    "semanticRatio": 1.0,
+                    "embedder": "rest"
+                },
+                "retrieveVectors": true,
+                "federationOptions": {
+                    "remote": "ms0"
+                }
+            },
+            {
+                "q": "dark knight",
+                "indexUid": "test",
+                "hybrid": {
+                    "semanticRatio": 1.0,
+                    "embedder": "rest"
+                },
+                "retrieveVectors": true,
+                "federationOptions": {
+                    "remote": "ms1"
+                }
+            },
+            {
+                "q": "returns",
+                "indexUid": "test",
+                "hybrid": {
+                    "semanticRatio": 1.0,
+                    "embedder": "rest"
+                },
+                "retrieveVectors": true,
+                "federationOptions": {
+                    "remote": "ms2"
+                }
+            },
+        ]
+    });
+
+    let (response, _status_code) = ms0.multi_search(request.clone()).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response, { ".processingTimeMs" => "[time]" }), @r#"
+    {
+      "hits": [],
+      "processingTimeMs": "[time]",
+      "limit": 20,
+      "offset": 0,
+      "estimatedTotalHits": 0,
+      "queryVectors": {
+        "0": [
+          1.0,
+          0.0,
+          0.0
+        ],
+        "1": [
+          0.1,
+          0.2,
+          0.0
+        ],
+        "2": [
+          0.0,
+          0.0,
+          0.2
+        ]
+      },
+      "semanticHitCount": 0,
+      "remoteErrors": {}
+    }
+    "#);
+
+    // multi vector search: two local queries, one remote
+
+    let request = json!({
+        "federation": {},
+        "queries": [
+            {
+                "q": "batman",
+                "indexUid": "test",
+                "hybrid": {
+                    "semanticRatio": 1.0,
+                    "embedder": "rest"
+                },
+                "retrieveVectors": true,
+                "federationOptions": {
+                    "remote": "ms0"
+                }
+            },
+            {
+                "q": "dark knight",
+                "indexUid": "test",
+                "hybrid": {
+                    "semanticRatio": 1.0,
+                    "embedder": "rest"
+                },
+                "retrieveVectors": true,
+                "federationOptions": {
+                    "remote": "ms0"
+                }
+            },
+            {
+                "q": "returns",
+                "indexUid": "test",
+                "hybrid": {
+                    "semanticRatio": 1.0,
+                    "embedder": "rest"
+                },
+                "retrieveVectors": true,
+                "federationOptions": {
+                    "remote": "ms2"
+                }
+            },
+        ]
+    });
+
+    let (response, _status_code) = ms0.multi_search(request.clone()).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response, { ".processingTimeMs" => "[time]" }), @r#"
+    {
+      "hits": [],
+      "processingTimeMs": "[time]",
+      "limit": 20,
+      "offset": 0,
+      "estimatedTotalHits": 0,
+      "queryVectors": {
+        "0": [
+          1.0,
+          0.0,
+          0.0
+        ],
+        "1": [
+          0.1,
+          0.2,
+          0.0
+        ],
+        "2": [
+          0.0,
+          0.0,
+          0.2
+        ]
+      },
+      "semanticHitCount": 0,
+      "remoteErrors": {}
+    }
+    "#);
+
+    // multi vector search: two queries on the same remote
+
+    let request = json!({
+        "federation": {},
+        "queries": [
+            {
+                "q": "batman",
+                "indexUid": "test",
+                "hybrid": {
+                    "semanticRatio": 1.0,
+                    "embedder": "rest"
+                },
+                "retrieveVectors": true,
+                "federationOptions": {
+                    "remote": "ms0"
+                }
+            },
+            {
+                "q": "dark knight",
+                "indexUid": "test",
+                "hybrid": {
+                    "semanticRatio": 1.0,
+                    "embedder": "rest"
+                },
+                "retrieveVectors": true,
+                "federationOptions": {
+                    "remote": "ms1"
+                }
+            },
+            {
+                "q": "returns",
+                "indexUid": "test",
+                "hybrid": {
+                    "semanticRatio": 1.0,
+                    "embedder": "rest"
+                },
+                "retrieveVectors": true,
+                "federationOptions": {
+                    "remote": "ms1"
+                }
+            },
+        ]
+    });
+
+    let (response, _status_code) = ms0.multi_search(request.clone()).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response, { ".processingTimeMs" => "[time]" }), @r#"
+    {
+      "hits": [],
+      "processingTimeMs": "[time]",
+      "limit": 20,
+      "offset": 0,
+      "estimatedTotalHits": 0,
+      "queryVectors": {
+        "0": [
+          1.0,
+          0.0,
+          0.0
+        ],
+        "1": [
+          0.1,
+          0.2,
+          0.0
+        ],
+        "2": [
+          0.0,
+          0.0,
+          0.2
+        ]
+      },
+      "semanticHitCount": 0,
+      "remoteErrors": {}
+    }
+    "#);
+
+    // multi search: two vector, one keyword
+
+    let request = json!({
+        "federation": {},
+        "queries": [
+            {
+                "q": "batman",
+                "indexUid": "test",
+                "hybrid": {
+                    "semanticRatio": 1.0,
+                    "embedder": "rest"
+                },
+                "retrieveVectors": true,
+                "federationOptions": {
+                    "remote": "ms0"
+                }
+            },
+            {
+                "q": "dark knight",
+                "indexUid": "test",
+                "hybrid": {
+                    "semanticRatio": 0.0,
+                    "embedder": "rest"
+                },
+                "retrieveVectors": true,
+                "federationOptions": {
+                    "remote": "ms1"
+                }
+            },
+            {
+                "q": "returns",
+                "indexUid": "test",
+                "hybrid": {
+                    "semanticRatio": 1.0,
+                    "embedder": "rest"
+                },
+                "retrieveVectors": true,
+                "federationOptions": {
+                    "remote": "ms1"
+                }
+            },
+        ]
+    });
+
+    let (response, _status_code) = ms0.multi_search(request.clone()).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response, { ".processingTimeMs" => "[time]" }), @r#"
+    {
+      "hits": [],
+      "processingTimeMs": "[time]",
+      "limit": 20,
+      "offset": 0,
+      "estimatedTotalHits": 0,
+      "queryVectors": {
+        "0": [
+          1.0,
+          0.0,
+          0.0
+        ],
+        "2": [
+          0.0,
+          0.0,
+          0.2
+        ]
+      },
+      "semanticHitCount": 0,
+      "remoteErrors": {}
+    }
+    "#);
+
+    // multi vector search: no local queries, all remote
+
+    let request = json!({
+        "federation": {},
+        "queries": [
+            {
+                "q": "batman",
+                "indexUid": "test",
+                "hybrid": {
+                    "semanticRatio": 1.0,
+                    "embedder": "rest"
+                },
+                "retrieveVectors": true,
+                "federationOptions": {
+                    "remote": "ms1"
+                }
+            },
+            {
+                "q": "dark knight",
+                "indexUid": "test",
+                "hybrid": {
+                    "semanticRatio": 1.0,
+                    "embedder": "rest"
+                },
+                "retrieveVectors": true,
+                "federationOptions": {
+                    "remote": "ms1"
+                }
+            },
+            {
+                "q": "returns",
+                "indexUid": "test",
+                "hybrid": {
+                    "semanticRatio": 1.0,
+                    "embedder": "rest"
+                },
+                "retrieveVectors": true,
+                "federationOptions": {
+                    "remote": "ms1"
+                }
+            },
+        ]
+    });
+
+    let (response, _status_code) = ms0.multi_search(request.clone()).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response, { ".processingTimeMs" => "[time]" }), @r#"
+    {
+      "hits": [],
+      "processingTimeMs": "[time]",
+      "limit": 20,
+      "offset": 0,
+      "estimatedTotalHits": 0,
+      "queryVectors": {
+        "0": [
+          1.0,
+          0.0,
+          0.0
+        ],
+        "1": [
+          0.1,
+          0.2,
+          0.0
+        ],
+        "2": [
+          0.0,
+          0.0,
+          0.2
+        ]
+      },
+      "remoteErrors": {}
+    }
+    "#);
+}
+
 #[actix_rt::test]
 async fn error_unregistered_remote() {
     let ms0 = Server::new().await;
@@ -2500,7 +2998,7 @@ pub struct LocalMeiliParams {
 
 /// A server that exploits [`MockServer`] to provide an URL for testing network and the network.
 pub struct LocalMeili {
-    mock_server: MockServer,
+    mock_server: &'static MockServer,
 }
 
 impl LocalMeili {
@@ -2509,7 +3007,7 @@ impl LocalMeili {
     }
 
     pub async fn with_params(server: Arc<Server>, params: LocalMeiliParams) -> Self {
-        let mock_server = MockServer::start().await;
+        let mock_server = Box::leak(Box::new(MockServer::start().await));
 
         // tokio won't let us execute asynchronous code from a sync function inside of an async test,
         // so instead we spawn another thread that will call the service on a brand new tokio runtime
@@ -2573,7 +3071,7 @@ impl LocalMeili {
                     response.set_body_json(value)
                 }
             })
-            .mount(&mock_server)
+            .mount(mock_server)
             .await;
         Self { mock_server }
     }

crates/meilisearch/tests/search/pagination.rs

@@ -1,6 +1,7 @@
 use super::shared_index_with_documents;
 use crate::common::Server;
 use crate::json;
+use meili_snap::{json_string, snapshot};
 
 #[actix_rt::test]
 async fn default_search_should_return_estimated_total_hit() {
@@ -133,3 +134,61 @@ async fn ensure_placeholder_search_hit_count_valid() {
             .await;
     }
 }
+
+#[actix_rt::test]
+async fn test_issue_5274() {
+    let server = Server::new_shared();
+    let index = server.unique_index();
+
+    let documents = json!([
+        {
+            "id": 1,
+            "title": "Document 1",
+            "content": "This is the first."
+        },
+        {
+            "id": 2,
+            "title": "Document 2",
+            "content": "This is the second doc."
+        }
+    ]);
+    let (task, _code) = index.add_documents(documents, None).await;
+    server.wait_task(task.uid()).await.succeeded();
+
+    // Find out the lowest ranking score among the documents
+    let (rep, _status) = index
+        .search_post(json!({"q": "doc", "page": 1, "hitsPerPage": 2, "showRankingScore": true}))
+        .await;
+    let hits = rep["hits"].as_array().expect("Missing hits array");
+    let second_hit = hits.get(1).expect("Missing second hit");
+    let ranking_score = second_hit
+        .get("_rankingScore")
+        .expect("Missing _rankingScore field")
+        .as_f64()
+        .expect("Expected _rankingScore to be a f64");
+
+    // Search with a ranking score threshold just above and expect to be a single hit
+    let (rep, _status) = index
+        .search_post(json!({"q": "doc", "page": 1, "hitsPerPage": 1, "rankingScoreThreshold": ranking_score + 0.0001}))
+        .await;
+
+    snapshot!(json_string!(rep, {
+        ".processingTimeMs" => "[ignored]",
+    }), @r#"
+    {
+      "hits": [
+        {
+          "id": 2,
+          "title": "Document 2",
+          "content": "This is the second doc."
+        }
+      ],
+      "query": "doc",
+      "processingTimeMs": "[ignored]",
+      "hitsPerPage": 1,
+      "page": 1,
+      "totalPages": 1,
+      "totalHits": 1
+    }
+    "#);
+}

crates/meilisearch/tests/settings/chat.rs

@@ -0,0 +1,66 @@
+use crate::common::Server;
+use crate::json;
+use meili_snap::{json_string, snapshot};
+
+#[actix_rt::test]
+async fn set_reset_chat_issue_5772() {
+    let server = Server::new().await;
+    let index = server.unique_index();
+
+    let (_, code) = server
+        .set_features(json!({
+            "chatCompletions": true,
+        }))
+        .await;
+    snapshot!(code, @r#"200 OK"#);
+
+    let (task1, _code) = index.update_settings_chat(json!({
+        "description": "test!",
+        "documentTemplate": "{% for field in fields %}{% if field.is_searchable and field.value != nil %}{{ field.name }}: {{ field.value }}\n{% endif %}{% endfor %}",
+        "documentTemplateMaxBytes": 400,
+        "searchParameters": {
+            "limit": 15,
+            "sort": [],
+            "attributesToSearchOn": []
+        }
+    })).await;
+    server.wait_task(task1.uid()).await.succeeded();
+
+    let (response, _) = index.settings().await;
+    snapshot!(json_string!(response["chat"]), @r#"
+    {
+      "description": "test!",
+      "documentTemplate": "{% for field in fields %}{% if field.is_searchable and field.value != nil %}{{ field.name }}: {{ field.value }}\n{% endif %}{% endfor %}",
+      "documentTemplateMaxBytes": 400,
+      "searchParameters": {
+        "limit": 15,
+        "sort": [],
+        "attributesToSearchOn": []
+      }
+    }
+    "#);
+
+    let (task2, _status_code) = index.update_settings_chat(json!({
+        "description": "test!",
+        "documentTemplate": "{% for field in fields %}{% if field.is_searchable and field.value != nil %}{{ field.name }}: {{ field.value }}\n{% endif %}{% endfor %}",
+        "documentTemplateMaxBytes": 400,
+        "searchParameters": {
+            "limit": 16
+        }
+    })).await;
+    server.wait_task(task2.uid()).await.succeeded();
+
+    let (response, _) = index.settings().await;
+    snapshot!(json_string!(response["chat"]), @r#"
+    {
+      "description": "test!",
+      "documentTemplate": "{% for field in fields %}{% if field.is_searchable and field.value != nil %}{{ field.name }}: {{ field.value }}\n{% endif %}{% endfor %}",
+      "documentTemplateMaxBytes": 400,
+      "searchParameters": {
+        "limit": 16,
+        "sort": [],
+        "attributesToSearchOn": []
+      }
+    }
+    "#);
+}

crates/meilisearch/tests/settings/get_settings.rs

@@ -186,7 +186,7 @@ test_setting_routes!(
     },
     {
         setting: chat,
-        update_verb: put,
+        update_verb: patch,
         default_value: {
             "description": "",
             "documentTemplate": "{% for field in fields %}{% if field.is_searchable and field.value != nil %}{{ field.name }}: {{ field.value }}\n{% endif %}{% endfor %}",
@@ -692,3 +692,68 @@ async fn granular_filterable_attributes() {
     ]
     "###);
 }
+
+#[actix_rt::test]
+async fn test_searchable_attributes_order() {
+    let server = Server::new_shared();
+    let index = server.unique_index();
+
+    // 1) Create an index with settings "searchableAttributes": ["title", "overview"]
+    let (response, code) = index.create(None).await;
+    assert_eq!(code, 202, "{response}");
+    server.wait_task(response.uid()).await.succeeded();
+
+    let (task, code) = index
+        .update_settings(json!({
+            "searchableAttributes": ["title", "overview"]
+        }))
+        .await;
+    assert_eq!(code, 202, "{task}");
+    server.wait_task(task.uid()).await.succeeded();
+
+    // 2) Add documents in the index
+    let documents = json!([
+        {
+            "id": 1,
+            "title": "The Matrix",
+            "overview": "A computer hacker learns from mysterious rebels about the true nature of his reality."
+        },
+        {
+            "id": 2,
+            "title": "Inception",
+            "overview": "A thief who steals corporate secrets through dream-sharing technology."
+        }
+    ]);
+
+    let (response, code) = index.add_documents(documents, None).await;
+    assert_eq!(code, 202, "{response}");
+    server.wait_task(response.uid()).await.succeeded();
+
+    // 3) Modify the settings "searchableAttributes": ["overview", "title"] (overview is put first)
+    let (task, code) = index
+        .update_settings(json!({
+            "searchableAttributes": ["overview", "title"]
+        }))
+        .await;
+    assert_eq!(code, 202, "{task}");
+    server.wait_task(task.uid()).await.succeeded();
+
+    // 4) Check if it has been applied
+    let (response, code) = index.settings().await;
+    assert_eq!(code, 200, "{response}");
+    assert_eq!(response["searchableAttributes"], json!(["overview", "title"]));
+
+    // 5) Re-modify the settings "searchableAttributes": ["title", "overview"] (title is put first)
+    let (task, code) = index
+        .update_settings(json!({
+            "searchableAttributes": ["title", "overview"]
+        }))
+        .await;
+    assert_eq!(code, 202, "{task}");
+    server.wait_task(task.uid()).await.succeeded();
+
+    // 6) Check if it has been applied
+    let (response, code) = index.settings().await;
+    assert_eq!(code, 200, "{response}");
+    assert_eq!(response["searchableAttributes"], json!(["title", "overview"]));
+}

crates/meilisearch/tests/settings/mod.rs

@@ -1,3 +1,4 @@
+mod chat;
 mod distinct;
 mod errors;
 mod get_settings;

crates/meilisearch/tests/snapshot/mod.rs

@@ -122,11 +122,7 @@ async fn perform_on_demand_snapshot() {
     let server = Server::new_with_options(options).await.unwrap();
 
     let index = server.index("catto");
-    index
-        .update_settings(json! ({
-        "searchableAttributes": [],
-        }))
-        .await;
+    index.update_settings(json! ({ "searchableAttributes": [] })).await;
 
     index.load_test_set(&server).await;
 
@@ -203,3 +199,70 @@ async fn perform_on_demand_snapshot() {
         server.index("doggo").settings(),
     );
 }
+
+#[actix_rt::test]
+#[cfg_attr(target_os = "windows", ignore)]
+async fn snapshotception_issue_4653() {
+    let temp = tempfile::tempdir().unwrap();
+    let snapshot_dir = tempfile::tempdir().unwrap();
+    let options =
+        Opt { snapshot_dir: snapshot_dir.path().to_owned(), ..default_settings(temp.path()) };
+
+    let server = Server::new_with_options(options).await.unwrap();
+
+    let (task, code) = server.create_snapshot().await;
+    snapshot!(code, @"202 Accepted");
+    snapshot!(json_string!(task, { ".enqueuedAt" => "[date]" }), @r###"
+    {
+      "taskUid": 0,
+      "indexUid": null,
+      "status": "enqueued",
+      "type": "snapshotCreation",
+      "enqueuedAt": "[date]"
+    }
+    "###);
+    server.wait_task(task.uid()).await.succeeded();
+
+    let temp = tempfile::tempdir().unwrap();
+    let snapshot_path = snapshot_dir.path().to_owned().join("db.snapshot");
+
+    let options = Opt { import_snapshot: Some(snapshot_path), ..default_settings(temp.path()) };
+    let snapshot_server = Server::new_with_options(options).await.unwrap();
+
+    // The snapshot should have been taken without the snapshot creation task
+    let (tasks, code) = snapshot_server.tasks().await;
+    snapshot!(code, @"200 OK");
+    snapshot!(tasks, @r#"
+    {
+      "results": [],
+      "total": 0,
+      "limit": 20,
+      "from": null,
+      "next": null
+    }
+    "#);
+
+    // Ensure the task is not present in the snapshot
+    let (task, code) = snapshot_server.get_task(0).await;
+    snapshot!(code, @"404 Not Found");
+    snapshot!(task, @r#"
+    {
+      "message": "Task `0` not found.",
+      "code": "task_not_found",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#task_not_found"
+    }
+    "#);
+
+    // Ensure the batch is also not present
+    let (batch, code) = snapshot_server.get_batch(0).await;
+    snapshot!(code, @"404 Not Found");
+    snapshot!(batch, @r#"
+    {
+      "message": "Batch `0` not found.",
+      "code": "batch_not_found",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#batch_not_found"
+    }
+    "#);
+}

crates/meilisearch/tests/tasks/webhook.rs

@@ -2,16 +2,18 @@
 //! post requests. The webhook handle starts a server and forwards all the
 //! received requests into a channel for you to handle.
 
+use std::path::PathBuf;
 use std::sync::Arc;
 
 use actix_http::body::MessageBody;
 use actix_web::dev::{ServiceFactory, ServiceResponse};
 use actix_web::web::{Bytes, Data};
 use actix_web::{post, App, HttpRequest, HttpResponse, HttpServer};
-use meili_snap::snapshot;
+use meili_snap::{json_string, snapshot};
 use meilisearch::Opt;
 use tokio::sync::mpsc;
 use url::Url;
+use uuid::Uuid;
 
 use crate::common::{self, default_settings, Server};
 use crate::json;
@@ -68,21 +70,55 @@ async fn create_webhook_server() -> WebhookHandle {
 }
 
 #[actix_web::test]
-async fn test_basic_webhook() {
-    let WebhookHandle { server_handle, url, mut receiver } = create_webhook_server().await;
-
+async fn cli_only() {
     let db_path = tempfile::tempdir().unwrap();
     let server = Server::new_with_options(Opt {
-        task_webhook_url: Some(Url::parse(&url).unwrap()),
+        task_webhook_url: Some(Url::parse("https://example-cli.com/").unwrap()),
+        task_webhook_authorization_header: Some(String::from("Bearer a-secret-token")),
         ..default_settings(db_path.path())
     })
     .await
     .unwrap();
 
-    let index = server.index("tamo");
+    let (webhooks, code) = server.get_webhooks().await;
+    snapshot!(code, @"200 OK");
+    snapshot!(webhooks, @r#"
+    {
+      "results": [
+        {
+          "uuid": "00000000-0000-0000-0000-000000000000",
+          "isEditable": false,
+          "url": "https://example-cli.com/",
+          "headers": {
+            "Authorization": "Bearer a-secret-token"
+          }
+        }
+      ]
+    }
+    "#);
+}
+
+#[actix_web::test]
+async fn single_receives_data() {
+    let WebhookHandle { server_handle, url, mut receiver } = create_webhook_server().await;
+
+    let server = Server::new().await;
+
+    let (value, code) = server.create_webhook(json!({ "url": url })).await;
+    snapshot!(code, @"201 Created");
+    snapshot!(json_string!(value, { ".uuid" => "[uuid]", ".url" => "[ignored]" }), @r#"
+    {
+      "uuid": "[uuid]",
+      "isEditable": true,
+      "url": "[ignored]",
+      "headers": {}
+    }
+    "#);
+
     // May be flaky: we're relying on the fact that while the first document addition is processed, the other
     // operations will be received and will be batched together. If it doesn't happen it's not a problem
     // the rest of the test won't assume anything about the number of tasks per batch.
+    let index = server.index("tamo");
     for i in 0..5 {
         let (_, _status) = index.add_documents(json!({ "id": i, "doggo": "bone" }), None).await;
     }
@@ -127,3 +163,496 @@ async fn test_basic_webhook() {
 
     server_handle.abort();
 }
+
+#[actix_web::test]
+async fn multiple_receive_data() {
+    let WebhookHandle { server_handle: handle1, url: url1, receiver: mut receiver1 } =
+        create_webhook_server().await;
+    let WebhookHandle { server_handle: handle2, url: url2, receiver: mut receiver2 } =
+        create_webhook_server().await;
+    let WebhookHandle { server_handle: handle3, url: url3, receiver: mut receiver3 } =
+        create_webhook_server().await;
+
+    let db_path = tempfile::tempdir().unwrap();
+    let server = Server::new_with_options(Opt {
+        task_webhook_url: Some(Url::parse(&url3).unwrap()),
+        ..default_settings(db_path.path())
+    })
+    .await
+    .unwrap();
+
+    for url in [url1, url2] {
+        let (value, code) = server.create_webhook(json!({ "url": url })).await;
+        snapshot!(code, @"201 Created");
+        snapshot!(json_string!(value, { ".uuid" => "[uuid]", ".url" => "[ignored]" }), @r#"
+        {
+          "uuid": "[uuid]",
+          "isEditable": true,
+          "url": "[ignored]",
+          "headers": {}
+        }
+        "#);
+    }
+    let index = server.index("tamo");
+    let (_, status) = index.add_documents(json!({ "id": 1, "doggo": "bone" }), None).await;
+    snapshot!(status, @"202 Accepted");
+
+    let mut count1 = 0;
+    let mut count2 = 0;
+    let mut count3 = 0;
+    while count1 == 0 || count2 == 0 || count3 == 0 {
+        tokio::select! {
+            msg = receiver1.recv() => { if msg.is_some() { count1 += 1; } },
+            msg = receiver2.recv() => { if msg.is_some() { count2 += 1; } },
+            msg = receiver3.recv() => { if msg.is_some() { count3 += 1; } },
+        }
+    }
+
+    assert_eq!(count1, 1);
+    assert_eq!(count2, 1);
+    assert_eq!(count3, 1);
+
+    handle1.abort();
+    handle2.abort();
+    handle3.abort();
+}
+
+#[actix_web::test]
+async fn cli_with_dumps() {
+    let db_path = tempfile::tempdir().unwrap();
+    let server = Server::new_with_options(Opt {
+        task_webhook_url: Some(Url::parse("http://defined-in-test-cli.com").unwrap()),
+        task_webhook_authorization_header: Some(String::from(
+            "Bearer a-secret-token-defined-in-test-cli",
+        )),
+        import_dump: Some(PathBuf::from("../dump/tests/assets/v6-with-webhooks.dump")),
+        ..default_settings(db_path.path())
+    })
+    .await
+    .unwrap();
+
+    let (webhooks, code) = server.get_webhooks().await;
+    snapshot!(code, @"200 OK");
+    snapshot!(webhooks, @r#"
+    {
+      "results": [
+        {
+          "uuid": "00000000-0000-0000-0000-000000000000",
+          "isEditable": false,
+          "url": "http://defined-in-test-cli.com/",
+          "headers": {
+            "Authorization": "Bearer a-secret-token-defined-in-test-cli"
+          }
+        },
+        {
+          "uuid": "627ea538-733d-4545-8d2d-03526eb381ce",
+          "isEditable": true,
+          "url": "https://example.com/authorization-less",
+          "headers": {}
+        },
+        {
+          "uuid": "771b0a28-ef28-4082-b984-536f82958c65",
+          "isEditable": true,
+          "url": "https://example.com/hook",
+          "headers": {
+            "authorization": "TOKEN"
+          }
+        },
+        {
+          "uuid": "f3583083-f8a7-4cbf-a5e7-fb3f1e28a7e9",
+          "isEditable": true,
+          "url": "https://third.com",
+          "headers": {}
+        }
+      ]
+    }
+    "#);
+}
+
+#[actix_web::test]
+async fn reserved_names() {
+    let db_path = tempfile::tempdir().unwrap();
+    let server = Server::new_with_options(Opt {
+        task_webhook_url: Some(Url::parse("https://example-cli.com/").unwrap()),
+        task_webhook_authorization_header: Some(String::from("Bearer a-secret-token")),
+        ..default_settings(db_path.path())
+    })
+    .await
+    .unwrap();
+
+    let (value, code) = server
+        .patch_webhook(Uuid::nil().to_string(), json!({ "url": "http://localhost:8080" }))
+        .await;
+    snapshot!(value, @r#"
+    {
+      "message": "Webhook `[uuid]` is immutable. The webhook defined from the command line cannot be modified using the API.",
+      "code": "immutable_webhook",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#immutable_webhook"
+    }
+    "#);
+    snapshot!(code, @"400 Bad Request");
+
+    let (value, code) = server.delete_webhook(Uuid::nil().to_string()).await;
+    snapshot!(value, @r#"
+    {
+      "message": "Webhook `[uuid]` is immutable. The webhook defined from the command line cannot be modified using the API.",
+      "code": "immutable_webhook",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#immutable_webhook"
+    }
+    "#);
+    snapshot!(code, @"400 Bad Request");
+}
+
+#[actix_web::test]
+async fn over_limits() {
+    let server = Server::new().await;
+
+    // Too many webhooks
+    let mut uuids = Vec::new();
+    for _ in 0..20 {
+        let (value, code) = server.create_webhook(json!({ "url": "http://localhost:8080" } )).await;
+        snapshot!(code, @"201 Created");
+        uuids.push(value.get("uuid").unwrap().as_str().unwrap().to_string());
+    }
+    let (value, code) = server.create_webhook(json!({ "url": "http://localhost:8080" })).await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(value, @r#"
+    {
+      "message": "Defining too many webhooks would crush the server. Please limit the number of webhooks to 20. You may use a third-party proxy server to dispatch events to more than 20 endpoints.",
+      "code": "invalid_webhooks",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#invalid_webhooks"
+    }
+    "#);
+
+    // Reset webhooks
+    for uuid in uuids {
+        let (_value, code) = server.delete_webhook(&uuid).await;
+        snapshot!(code, @"204 No Content");
+    }
+
+    // Test too many headers
+    let (value, code) = server.create_webhook(json!({ "url": "http://localhost:8080" })).await;
+    snapshot!(code, @"201 Created");
+    let uuid = value.get("uuid").unwrap().as_str().unwrap();
+    for i in 0..200 {
+        let header_name = format!("header_{i}");
+        let (_value, code) =
+            server.patch_webhook(uuid, json!({ "headers": { header_name: "" } })).await;
+        snapshot!(code, @"200 OK");
+    }
+    let (value, code) =
+        server.patch_webhook(uuid, json!({ "headers": { "header_200": "" } })).await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(value, @r#"
+    {
+      "message": "Too many headers for the webhook `[uuid]`. Please limit the number of headers to 200. Hint: To remove an already defined header set its value to `null`",
+      "code": "invalid_webhook_headers",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#invalid_webhook_headers"
+    }
+    "#);
+}
+
+#[actix_web::test]
+async fn post_get_delete() {
+    let server = Server::new().await;
+
+    let (value, code) = server
+        .create_webhook(json!({
+            "url": "https://example.com/hook",
+            "headers": { "authorization": "TOKEN" }
+        }))
+        .await;
+    snapshot!(code, @"201 Created");
+    snapshot!(json_string!(value, { ".uuid" => "[uuid]" }), @r#"
+    {
+      "uuid": "[uuid]",
+      "isEditable": true,
+      "url": "https://example.com/hook",
+      "headers": {
+        "authorization": "TOKEN"
+      }
+    }
+    "#);
+
+    let uuid = value.get("uuid").unwrap().as_str().unwrap();
+    let (value, code) = server.get_webhook(uuid).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(value, { ".uuid" => "[uuid]" }), @r#"
+    {
+      "uuid": "[uuid]",
+      "isEditable": true,
+      "url": "https://example.com/hook",
+      "headers": {
+        "authorization": "TOKEN"
+      }
+    }
+    "#);
+
+    let (_value, code) = server.delete_webhook(uuid).await;
+    snapshot!(code, @"204 No Content");
+
+    let (_value, code) = server.get_webhook(uuid).await;
+    snapshot!(code, @"404 Not Found");
+}
+
+#[actix_web::test]
+async fn create_and_patch() {
+    let server = Server::new().await;
+
+    let (value, code) =
+        server.create_webhook(json!({ "headers": { "authorization": "TOKEN" } })).await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(value, @r#"
+    {
+      "message": "The URL for the webhook `[uuid]` is missing.",
+      "code": "invalid_webhook_url",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#invalid_webhook_url"
+    }
+    "#);
+
+    let (value, code) = server.create_webhook(json!({ "url": "https://example.com/hook" })).await;
+    snapshot!(code, @"201 Created");
+    snapshot!(json_string!(value, { ".uuid" => "[uuid]" }), @r#"
+    {
+      "uuid": "[uuid]",
+      "isEditable": true,
+      "url": "https://example.com/hook",
+      "headers": {}
+    }
+    "#);
+
+    let uuid = value.get("uuid").unwrap().as_str().unwrap();
+    let (value, code) =
+        server.patch_webhook(&uuid, json!({ "headers": { "authorization": "TOKEN" } })).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(value, { ".uuid" => "[uuid]" }), @r#"
+    {
+      "uuid": "[uuid]",
+      "isEditable": true,
+      "url": "https://example.com/hook",
+      "headers": {
+        "authorization": "TOKEN"
+      }
+    }
+    "#);
+
+    let (value, code) =
+        server.patch_webhook(&uuid, json!({ "headers": { "authorization2": "TOKEN" } })).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(value, { ".uuid" => "[uuid]" }), @r#"
+    {
+      "uuid": "[uuid]",
+      "isEditable": true,
+      "url": "https://example.com/hook",
+      "headers": {
+        "authorization": "TOKEN",
+        "authorization2": "TOKEN"
+      }
+    }
+    "#);
+
+    let (value, code) =
+        server.patch_webhook(&uuid, json!({ "headers": { "authorization": null } })).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(value, { ".uuid" => "[uuid]" }), @r#"
+    {
+      "uuid": "[uuid]",
+      "isEditable": true,
+      "url": "https://example.com/hook",
+      "headers": {
+        "authorization2": "TOKEN"
+      }
+    }
+    "#);
+
+    let (value, code) = server.patch_webhook(&uuid, json!({ "url": null })).await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(json_string!(value, { ".uuid" => "[uuid]" }), @r#"
+    {
+      "message": "The URL for the webhook `[uuid]` is missing.",
+      "code": "invalid_webhook_url",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#invalid_webhook_url"
+    }
+    "#);
+}
+
+#[actix_web::test]
+async fn invalid_url_and_headers() {
+    let server = Server::new().await;
+
+    // Test invalid URL format
+    let (value, code) = server.create_webhook(json!({ "url": "not-a-valid-url" })).await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(value, @r#"
+    {
+      "message": "Invalid URL `not-a-valid-url`: relative URL without a base",
+      "code": "invalid_webhook_url",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#invalid_webhook_url"
+    }
+    "#);
+
+    // Test invalid header name (containing spaces)
+    let (value, code) = server
+        .create_webhook(json!({
+            "url": "https://example.com/hook",
+            "headers": { "invalid header name": "value" }
+        }))
+        .await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(value, @r#"
+    {
+      "message": "Invalid header name `invalid header name`: invalid HTTP header name",
+      "code": "invalid_webhook_headers",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#invalid_webhook_headers"
+    }
+    "#);
+
+    // Test invalid header value (containing control characters)
+    let (value, code) = server
+        .create_webhook(json!({
+            "url": "https://example.com/hook",
+            "headers": { "authorization": "token\nwith\nnewlines" }
+        }))
+        .await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(value, @r#"
+    {
+      "message": "Invalid header value `authorization`: failed to parse header value",
+      "code": "invalid_webhook_headers",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#invalid_webhook_headers"
+    }
+    "#);
+}
+
+#[actix_web::test]
+async fn invalid_uuid() {
+    let server = Server::new().await;
+
+    // Test get webhook with invalid UUID
+    let (value, code) = server.get_webhook("invalid-uuid").await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(value, @r#"
+    {
+      "message": "Invalid UUID: invalid character: expected an optional prefix of `urn:uuid:` followed by [0-9a-fA-F-], found `i` at 1",
+      "code": "invalid_webhook_uuid",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#invalid_webhook_uuid"
+    }
+    "#);
+
+    // Test update webhook with invalid UUID
+    let (value, code) =
+        server.patch_webhook("invalid-uuid", json!({ "url": "https://example.com/hook" })).await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(value, @r#"
+    {
+      "message": "Invalid UUID: invalid character: expected an optional prefix of `urn:uuid:` followed by [0-9a-fA-F-], found `i` at 1",
+      "code": "invalid_webhook_uuid",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#invalid_webhook_uuid"
+    }
+    "#);
+
+    // Test delete webhook with invalid UUID
+    let (value, code) = server.delete_webhook("invalid-uuid").await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(value, @r#"
+    {
+      "message": "Invalid UUID: invalid character: expected an optional prefix of `urn:uuid:` followed by [0-9a-fA-F-], found `i` at 1",
+      "code": "invalid_webhook_uuid",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#invalid_webhook_uuid"
+    }
+    "#);
+}
+
+#[actix_web::test]
+async fn forbidden_fields() {
+    let server = Server::new().await;
+
+    // Test creating webhook with uuid field
+    let custom_uuid = Uuid::new_v4();
+    let (value, code) = server
+        .create_webhook(json!({
+            "url": "https://example.com/hook",
+            "uuid": custom_uuid.to_string(),
+            "headers": { "authorization": "TOKEN" }
+        }))
+        .await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(value, @r#"
+    {
+      "message": "Immutable field `uuid`: expected one of `url`, `headers`",
+      "code": "immutable_webhook_uuid",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#immutable_webhook_uuid"
+    }
+    "#);
+
+    // Test creating webhook with isEditable field
+    let (value, code) = server
+        .create_webhook(json!({
+            "url": "https://example.com/hook2",
+            "isEditable": false,
+            "headers": { "authorization": "TOKEN" }
+        }))
+        .await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(value, @r#"
+    {
+      "message": "Immutable field `isEditable`: expected one of `url`, `headers`",
+      "code": "immutable_webhook_is_editable",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#immutable_webhook_is_editable"
+    }
+    "#);
+
+    // Test patching webhook with uuid field
+    let (value, code) = server
+        .patch_webhook(
+            "uuid-whatever",
+            json!({
+                "uuid": Uuid::new_v4(),
+                "headers": { "new-header": "value" }
+            }),
+        )
+        .await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(value, @r#"
+    {
+      "message": "Immutable field `uuid`: expected one of `url`, `headers`",
+      "code": "immutable_webhook_uuid",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#immutable_webhook_uuid"
+    }
+    "#);
+
+    // Test patching webhook with isEditable field
+    let (value, code) = server
+        .patch_webhook(
+            "uuid-whatever",
+            json!({
+                "isEditable": false,
+                "headers": { "another-header": "value" }
+            }),
+        )
+        .await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(json_string!(value, { ".uuid" => "[uuid]" }), @r#"
+    {
+      "message": "Immutable field `isEditable`: expected one of `url`, `headers`",
+      "code": "immutable_webhook_is_editable",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#immutable_webhook_is_editable"
+    }
+    "#);
+}

crates/meilisearch/tests/upgrade/mod.rs

@@ -43,7 +43,7 @@ async fn version_too_old() {
     std::fs::write(db_path.join("VERSION"), "1.11.9999").unwrap();
     let options = Opt { experimental_dumpless_upgrade: true, ..default_settings };
     let err = Server::new_with_options(options).await.map(|_| ()).unwrap_err();
-    snapshot!(err, @"Database version 1.11.9999 is too old for the experimental dumpless upgrade feature. Please generate a dump using the v1.11.9999 and import it in the v1.16.0");
+    snapshot!(err, @"Database version 1.11.9999 is too old for the experimental dumpless upgrade feature. Please generate a dump using the v1.11.9999 and import it in the v1.17.1");
 }
 
 #[actix_rt::test]
@@ -58,7 +58,7 @@ async fn version_requires_downgrade() {
     std::fs::write(db_path.join("VERSION"), format!("{major}.{minor}.{patch}")).unwrap();
     let options = Opt { experimental_dumpless_upgrade: true, ..default_settings };
     let err = Server::new_with_options(options).await.map(|_| ()).unwrap_err();
-    snapshot!(err, @"Database version 1.16.1 is higher than the Meilisearch version 1.16.0. Downgrade is not supported");
+    snapshot!(err, @"Database version 1.17.2 is higher than the Meilisearch version 1.17.1. Downgrade is not supported");
 }
 
 #[actix_rt::test]

crates/meilisearch/tests/upgrade/v1_12/snapshots/v1_12_0.rs/check_the_index_features/kefir_settings.snap

@@ -61,7 +61,16 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
   "pagination": {
     "maxTotalHits": 15
   },
-  "embedders": {},
+  "embedders": {
+    "doggo_embedder": {
+      "source": "huggingFace",
+      "model": "sentence-transformers/all-MiniLM-L6-v2",
+      "revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
+      "pooling": "forceMean",
+      "documentTemplate": "{{doc.description}}",
+      "documentTemplateMaxBytes": 400
+    }
+  },
   "searchCutoffMs": 8000,
   "localizedAttributes": [
     {

crates/meilisearch/tests/upgrade/v1_12/snapshots/v1_12_0.rs/check_the_index_features/search_with_retrieve_vectors.snap

@@ -0,0 +1,40 @@
+---
+source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
+---
+[
+  {
+    "id": 1,
+    "name": "kefir",
+    "surname": [
+      "kef",
+      "kefkef",
+      "kefirounet",
+      "boubou"
+    ],
+    "age": 1.4,
+    "description": "kefir est un petit chien blanc très mignon",
+    "_vectors": {
+      "doggo_embedder": {
+        "embeddings": "[vector]",
+        "regenerate": true
+      }
+    }
+  },
+  {
+    "id": 2,
+    "name": "intel",
+    "surname": [
+      "untel",
+      "tétel",
+      "iouiou"
+    ],
+    "age": 11.5,
+    "description": "intel est un grand beagle très mignon",
+    "_vectors": {
+      "doggo_embedder": {
+        "embeddings": "[vector]",
+        "regenerate": false
+      }
+    }
+  }
+]

crates/meilisearch/tests/upgrade/v1_12/snapshots/v1_12_0.rs/check_the_index_scheduler/batches_filter_afterEnqueuedAt_equal_2025-01-16T16_47_41.snap

@@ -4,11 +4,11 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
 {
   "results": [
     {
-      "uid": 24,
+      "uid": 30,
       "progress": null,
       "details": {
         "upgradeFrom": "v1.12.0",
-        "upgradeTo": "v1.16.0"
+        "upgradeTo": "v1.17.1"
       },
       "stats": {
         "totalNbTasks": 1,
@@ -26,6 +26,155 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
       "finishedAt": "[date]",
       "batchStrategy": "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type."
     },
+    {
+      "uid": 29,
+      "progress": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 1
+      },
+      "stats": {
+        "totalNbTasks": 1,
+        "status": {
+          "succeeded": 1
+        },
+        "types": {
+          "documentAdditionOrUpdate": 1
+        },
+        "indexUids": {
+          "kefir": 1
+        }
+      },
+      "duration": "PT0.067201S",
+      "startedAt": "2025-07-07T13:43:08.772854Z",
+      "finishedAt": "2025-07-07T13:43:08.840055Z",
+      "batchStrategy": "unspecified"
+    },
+    {
+      "uid": 28,
+      "progress": null,
+      "details": {
+        "deletedDocuments": 1
+      },
+      "stats": {
+        "totalNbTasks": 1,
+        "status": {
+          "succeeded": 1
+        },
+        "types": {
+          "indexDeletion": 1
+        },
+        "indexUids": {
+          "mieli": 1
+        }
+      },
+      "duration": "PT0.012727S",
+      "startedAt": "2025-07-07T13:42:50.745461Z",
+      "finishedAt": "2025-07-07T13:42:50.758188Z",
+      "batchStrategy": "unspecified"
+    },
+    {
+      "uid": 27,
+      "progress": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 0
+      },
+      "stats": {
+        "totalNbTasks": 1,
+        "status": {
+          "failed": 1
+        },
+        "types": {
+          "documentAdditionOrUpdate": 1
+        },
+        "indexUids": {
+          "kefir": 1
+        }
+      },
+      "duration": "PT0.059920S",
+      "startedAt": "2025-07-07T13:42:15.625413Z",
+      "finishedAt": "2025-07-07T13:42:15.685333Z",
+      "batchStrategy": "unspecified"
+    },
+    {
+      "uid": 26,
+      "progress": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 1
+      },
+      "stats": {
+        "totalNbTasks": 1,
+        "status": {
+          "succeeded": 1
+        },
+        "types": {
+          "documentAdditionOrUpdate": 1
+        },
+        "indexUids": {
+          "mieli": 1
+        }
+      },
+      "duration": "PT0.088879S",
+      "startedAt": "2025-07-07T13:40:01.461741Z",
+      "finishedAt": "2025-07-07T13:40:01.55062Z",
+      "batchStrategy": "unspecified"
+    },
+    {
+      "uid": 25,
+      "progress": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 1
+      },
+      "stats": {
+        "totalNbTasks": 1,
+        "status": {
+          "succeeded": 1
+        },
+        "types": {
+          "documentAdditionOrUpdate": 1
+        },
+        "indexUids": {
+          "kefir": 1
+        }
+      },
+      "duration": "PT0.312911S",
+      "startedAt": "2025-07-07T13:32:46.139785Z",
+      "finishedAt": "2025-07-07T13:32:46.452696Z",
+      "batchStrategy": "unspecified"
+    },
+    {
+      "uid": 24,
+      "progress": null,
+      "details": {
+        "embedders": {
+          "doggo_embedder": {
+            "source": "huggingFace",
+            "model": "sentence-transformers/all-MiniLM-L6-v2",
+            "revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
+            "documentTemplate": "{{doc.description}}"
+          }
+        }
+      },
+      "stats": {
+        "totalNbTasks": 1,
+        "status": {
+          "succeeded": 1
+        },
+        "types": {
+          "settingsUpdate": 1
+        },
+        "indexUids": {
+          "kefir": 1
+        }
+      },
+      "duration": "PT0.247378S",
+      "startedAt": "2025-07-07T13:28:27.391344Z",
+      "finishedAt": "2025-07-07T13:28:27.638722Z",
+      "batchStrategy": "unspecified"
+    },
     {
       "uid": 23,
       "progress": null,
@@ -348,179 +497,10 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
       "startedAt": "2025-01-16T17:01:14.112756687Z",
       "finishedAt": "2025-01-16T17:01:14.120064527Z",
       "batchStrategy": "unspecified"
-    },
-    {
-      "uid": 10,
-      "progress": null,
-      "details": {
-        "faceting": {
-          "maxValuesPerFacet": 99
-        },
-        "pagination": {
-          "maxTotalHits": 15
-        }
-      },
-      "stats": {
-        "totalNbTasks": 1,
-        "status": {
-          "succeeded": 1
-        },
-        "types": {
-          "settingsUpdate": 1
-        },
-        "indexUids": {
-          "kefir": 1
-        }
-      },
-      "duration": "PT0.007391353S",
-      "startedAt": "2025-01-16T17:00:29.201180268Z",
-      "finishedAt": "2025-01-16T17:00:29.208571621Z",
-      "batchStrategy": "unspecified"
-    },
-    {
-      "uid": 9,
-      "progress": null,
-      "details": {
-        "faceting": {
-          "maxValuesPerFacet": 100
-        },
-        "pagination": {
-          "maxTotalHits": 1000
-        }
-      },
-      "stats": {
-        "totalNbTasks": 1,
-        "status": {
-          "succeeded": 1
-        },
-        "types": {
-          "settingsUpdate": 1
-        },
-        "indexUids": {
-          "kefir": 1
-        }
-      },
-      "duration": "PT0.007445825S",
-      "startedAt": "2025-01-16T17:00:15.77629445Z",
-      "finishedAt": "2025-01-16T17:00:15.783740275Z",
-      "batchStrategy": "unspecified"
-    },
-    {
-      "uid": 8,
-      "progress": null,
-      "details": {
-        "typoTolerance": {
-          "minWordSizeForTypos": {
-            "oneTypo": 4
-          },
-          "disableOnWords": [
-            "kefir"
-          ],
-          "disableOnAttributes": [
-            "surname"
-          ]
-        }
-      },
-      "stats": {
-        "totalNbTasks": 1,
-        "status": {
-          "succeeded": 1
-        },
-        "types": {
-          "settingsUpdate": 1
-        },
-        "indexUids": {
-          "kefir": 1
-        }
-      },
-      "duration": "PT0.012020083S",
-      "startedAt": "2025-01-16T16:59:42.744086671Z",
-      "finishedAt": "2025-01-16T16:59:42.756106754Z",
-      "batchStrategy": "unspecified"
-    },
-    {
-      "uid": 7,
-      "progress": null,
-      "details": {
-        "typoTolerance": {
-          "minWordSizeForTypos": {
-            "oneTypo": 4
-          }
-        }
-      },
-      "stats": {
-        "totalNbTasks": 1,
-        "status": {
-          "succeeded": 1
-        },
-        "types": {
-          "settingsUpdate": 1
-        },
-        "indexUids": {
-          "kefir": 1
-        }
-      },
-      "duration": "PT0.007440092S",
-      "startedAt": "2025-01-16T16:58:41.2155771Z",
-      "finishedAt": "2025-01-16T16:58:41.223017192Z",
-      "batchStrategy": "unspecified"
-    },
-    {
-      "uid": 6,
-      "progress": null,
-      "details": {
-        "synonyms": {
-          "boubou": [
-            "kefir"
-          ]
-        }
-      },
-      "stats": {
-        "totalNbTasks": 1,
-        "status": {
-          "succeeded": 1
-        },
-        "types": {
-          "settingsUpdate": 1
-        },
-        "indexUids": {
-          "kefir": 1
-        }
-      },
-      "duration": "PT0.007565161S",
-      "startedAt": "2025-01-16T16:54:51.940332781Z",
-      "finishedAt": "2025-01-16T16:54:51.947897942Z",
-      "batchStrategy": "unspecified"
-    },
-    {
-      "uid": 5,
-      "progress": null,
-      "details": {
-        "stopWords": [
-          "le",
-          "un"
-        ]
-      },
-      "stats": {
-        "totalNbTasks": 1,
-        "status": {
-          "succeeded": 1
-        },
-        "types": {
-          "settingsUpdate": 1
-        },
-        "indexUids": {
-          "kefir": 1
-        }
-      },
-      "duration": "PT0.016307263S",
-      "startedAt": "2025-01-16T16:53:19.913351957Z",
-      "finishedAt": "2025-01-16T16:53:19.92965922Z",
-      "batchStrategy": "unspecified"
     }
   ],
-  "total": 23,
+  "total": 29,
   "limit": 20,
-  "from": 24,
-  "next": 4
+  "from": 30,
+  "next": 10
 }

crates/meilisearch/tests/upgrade/v1_12/snapshots/v1_12_0.rs/check_the_index_scheduler/batches_filter_afterFinishedAt_equal_2025-01-16T16_47_41.snap

@@ -4,11 +4,11 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
 {
   "results": [
     {
-      "uid": 24,
+      "uid": 30,
       "progress": null,
       "details": {
         "upgradeFrom": "v1.12.0",
-        "upgradeTo": "v1.16.0"
+        "upgradeTo": "v1.17.1"
       },
       "stats": {
         "totalNbTasks": 1,
@@ -26,6 +26,155 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
       "finishedAt": "[date]",
       "batchStrategy": "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type."
     },
+    {
+      "uid": 29,
+      "progress": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 1
+      },
+      "stats": {
+        "totalNbTasks": 1,
+        "status": {
+          "succeeded": 1
+        },
+        "types": {
+          "documentAdditionOrUpdate": 1
+        },
+        "indexUids": {
+          "kefir": 1
+        }
+      },
+      "duration": "PT0.067201S",
+      "startedAt": "2025-07-07T13:43:08.772854Z",
+      "finishedAt": "2025-07-07T13:43:08.840055Z",
+      "batchStrategy": "unspecified"
+    },
+    {
+      "uid": 28,
+      "progress": null,
+      "details": {
+        "deletedDocuments": 1
+      },
+      "stats": {
+        "totalNbTasks": 1,
+        "status": {
+          "succeeded": 1
+        },
+        "types": {
+          "indexDeletion": 1
+        },
+        "indexUids": {
+          "mieli": 1
+        }
+      },
+      "duration": "PT0.012727S",
+      "startedAt": "2025-07-07T13:42:50.745461Z",
+      "finishedAt": "2025-07-07T13:42:50.758188Z",
+      "batchStrategy": "unspecified"
+    },
+    {
+      "uid": 27,
+      "progress": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 0
+      },
+      "stats": {
+        "totalNbTasks": 1,
+        "status": {
+          "failed": 1
+        },
+        "types": {
+          "documentAdditionOrUpdate": 1
+        },
+        "indexUids": {
+          "kefir": 1
+        }
+      },
+      "duration": "PT0.059920S",
+      "startedAt": "2025-07-07T13:42:15.625413Z",
+      "finishedAt": "2025-07-07T13:42:15.685333Z",
+      "batchStrategy": "unspecified"
+    },
+    {
+      "uid": 26,
+      "progress": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 1
+      },
+      "stats": {
+        "totalNbTasks": 1,
+        "status": {
+          "succeeded": 1
+        },
+        "types": {
+          "documentAdditionOrUpdate": 1
+        },
+        "indexUids": {
+          "mieli": 1
+        }
+      },
+      "duration": "PT0.088879S",
+      "startedAt": "2025-07-07T13:40:01.461741Z",
+      "finishedAt": "2025-07-07T13:40:01.55062Z",
+      "batchStrategy": "unspecified"
+    },
+    {
+      "uid": 25,
+      "progress": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 1
+      },
+      "stats": {
+        "totalNbTasks": 1,
+        "status": {
+          "succeeded": 1
+        },
+        "types": {
+          "documentAdditionOrUpdate": 1
+        },
+        "indexUids": {
+          "kefir": 1
+        }
+      },
+      "duration": "PT0.312911S",
+      "startedAt": "2025-07-07T13:32:46.139785Z",
+      "finishedAt": "2025-07-07T13:32:46.452696Z",
+      "batchStrategy": "unspecified"
+    },
+    {
+      "uid": 24,
+      "progress": null,
+      "details": {
+        "embedders": {
+          "doggo_embedder": {
+            "source": "huggingFace",
+            "model": "sentence-transformers/all-MiniLM-L6-v2",
+            "revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
+            "documentTemplate": "{{doc.description}}"
+          }
+        }
+      },
+      "stats": {
+        "totalNbTasks": 1,
+        "status": {
+          "succeeded": 1
+        },
+        "types": {
+          "settingsUpdate": 1
+        },
+        "indexUids": {
+          "kefir": 1
+        }
+      },
+      "duration": "PT0.247378S",
+      "startedAt": "2025-07-07T13:28:27.391344Z",
+      "finishedAt": "2025-07-07T13:28:27.638722Z",
+      "batchStrategy": "unspecified"
+    },
     {
       "uid": 23,
       "progress": null,
@@ -348,179 +497,10 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
       "startedAt": "2025-01-16T17:01:14.112756687Z",
       "finishedAt": "2025-01-16T17:01:14.120064527Z",
       "batchStrategy": "unspecified"
-    },
-    {
-      "uid": 10,
-      "progress": null,
-      "details": {
-        "faceting": {
-          "maxValuesPerFacet": 99
-        },
-        "pagination": {
-          "maxTotalHits": 15
-        }
-      },
-      "stats": {
-        "totalNbTasks": 1,
-        "status": {
-          "succeeded": 1
-        },
-        "types": {
-          "settingsUpdate": 1
-        },
-        "indexUids": {
-          "kefir": 1
-        }
-      },
-      "duration": "PT0.007391353S",
-      "startedAt": "2025-01-16T17:00:29.201180268Z",
-      "finishedAt": "2025-01-16T17:00:29.208571621Z",
-      "batchStrategy": "unspecified"
-    },
-    {
-      "uid": 9,
-      "progress": null,
-      "details": {
-        "faceting": {
-          "maxValuesPerFacet": 100
-        },
-        "pagination": {
-          "maxTotalHits": 1000
-        }
-      },
-      "stats": {
-        "totalNbTasks": 1,
-        "status": {
-          "succeeded": 1
-        },
-        "types": {
-          "settingsUpdate": 1
-        },
-        "indexUids": {
-          "kefir": 1
-        }
-      },
-      "duration": "PT0.007445825S",
-      "startedAt": "2025-01-16T17:00:15.77629445Z",
-      "finishedAt": "2025-01-16T17:00:15.783740275Z",
-      "batchStrategy": "unspecified"
-    },
-    {
-      "uid": 8,
-      "progress": null,
-      "details": {
-        "typoTolerance": {
-          "minWordSizeForTypos": {
-            "oneTypo": 4
-          },
-          "disableOnWords": [
-            "kefir"
-          ],
-          "disableOnAttributes": [
-            "surname"
-          ]
-        }
-      },
-      "stats": {
-        "totalNbTasks": 1,
-        "status": {
-          "succeeded": 1
-        },
-        "types": {
-          "settingsUpdate": 1
-        },
-        "indexUids": {
-          "kefir": 1
-        }
-      },
-      "duration": "PT0.012020083S",
-      "startedAt": "2025-01-16T16:59:42.744086671Z",
-      "finishedAt": "2025-01-16T16:59:42.756106754Z",
-      "batchStrategy": "unspecified"
-    },
-    {
-      "uid": 7,
-      "progress": null,
-      "details": {
-        "typoTolerance": {
-          "minWordSizeForTypos": {
-            "oneTypo": 4
-          }
-        }
-      },
-      "stats": {
-        "totalNbTasks": 1,
-        "status": {
-          "succeeded": 1
-        },
-        "types": {
-          "settingsUpdate": 1
-        },
-        "indexUids": {
-          "kefir": 1
-        }
-      },
-      "duration": "PT0.007440092S",
-      "startedAt": "2025-01-16T16:58:41.2155771Z",
-      "finishedAt": "2025-01-16T16:58:41.223017192Z",
-      "batchStrategy": "unspecified"
-    },
-    {
-      "uid": 6,
-      "progress": null,
-      "details": {
-        "synonyms": {
-          "boubou": [
-            "kefir"
-          ]
-        }
-      },
-      "stats": {
-        "totalNbTasks": 1,
-        "status": {
-          "succeeded": 1
-        },
-        "types": {
-          "settingsUpdate": 1
-        },
-        "indexUids": {
-          "kefir": 1
-        }
-      },
-      "duration": "PT0.007565161S",
-      "startedAt": "2025-01-16T16:54:51.940332781Z",
-      "finishedAt": "2025-01-16T16:54:51.947897942Z",
-      "batchStrategy": "unspecified"
-    },
-    {
-      "uid": 5,
-      "progress": null,
-      "details": {
-        "stopWords": [
-          "le",
-          "un"
-        ]
-      },
-      "stats": {
-        "totalNbTasks": 1,
-        "status": {
-          "succeeded": 1
-        },
-        "types": {
-          "settingsUpdate": 1
-        },
-        "indexUids": {
-          "kefir": 1
-        }
-      },
-      "duration": "PT0.016307263S",
-      "startedAt": "2025-01-16T16:53:19.913351957Z",
-      "finishedAt": "2025-01-16T16:53:19.92965922Z",
-      "batchStrategy": "unspecified"
     }
   ],
-  "total": 23,
+  "total": 29,
   "limit": 20,
-  "from": 24,
-  "next": 4
+  "from": 30,
+  "next": 10
 }

crates/meilisearch/tests/upgrade/v1_12/snapshots/v1_12_0.rs/check_the_index_scheduler/batches_filter_afterStartedAt_equal_2025-01-16T16_47_41.snap

@@ -4,11 +4,11 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
 {
   "results": [
     {
-      "uid": 24,
+      "uid": 30,
       "progress": null,
       "details": {
         "upgradeFrom": "v1.12.0",
-        "upgradeTo": "v1.16.0"
+        "upgradeTo": "v1.17.1"
       },
       "stats": {
         "totalNbTasks": 1,
@@ -26,6 +26,155 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
       "finishedAt": "[date]",
       "batchStrategy": "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type."
     },
+    {
+      "uid": 29,
+      "progress": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 1
+      },
+      "stats": {
+        "totalNbTasks": 1,
+        "status": {
+          "succeeded": 1
+        },
+        "types": {
+          "documentAdditionOrUpdate": 1
+        },
+        "indexUids": {
+          "kefir": 1
+        }
+      },
+      "duration": "PT0.067201S",
+      "startedAt": "2025-07-07T13:43:08.772854Z",
+      "finishedAt": "2025-07-07T13:43:08.840055Z",
+      "batchStrategy": "unspecified"
+    },
+    {
+      "uid": 28,
+      "progress": null,
+      "details": {
+        "deletedDocuments": 1
+      },
+      "stats": {
+        "totalNbTasks": 1,
+        "status": {
+          "succeeded": 1
+        },
+        "types": {
+          "indexDeletion": 1
+        },
+        "indexUids": {
+          "mieli": 1
+        }
+      },
+      "duration": "PT0.012727S",
+      "startedAt": "2025-07-07T13:42:50.745461Z",
+      "finishedAt": "2025-07-07T13:42:50.758188Z",
+      "batchStrategy": "unspecified"
+    },
+    {
+      "uid": 27,
+      "progress": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 0
+      },
+      "stats": {
+        "totalNbTasks": 1,
+        "status": {
+          "failed": 1
+        },
+        "types": {
+          "documentAdditionOrUpdate": 1
+        },
+        "indexUids": {
+          "kefir": 1
+        }
+      },
+      "duration": "PT0.059920S",
+      "startedAt": "2025-07-07T13:42:15.625413Z",
+      "finishedAt": "2025-07-07T13:42:15.685333Z",
+      "batchStrategy": "unspecified"
+    },
+    {
+      "uid": 26,
+      "progress": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 1
+      },
+      "stats": {
+        "totalNbTasks": 1,
+        "status": {
+          "succeeded": 1
+        },
+        "types": {
+          "documentAdditionOrUpdate": 1
+        },
+        "indexUids": {
+          "mieli": 1
+        }
+      },
+      "duration": "PT0.088879S",
+      "startedAt": "2025-07-07T13:40:01.461741Z",
+      "finishedAt": "2025-07-07T13:40:01.55062Z",
+      "batchStrategy": "unspecified"
+    },
+    {
+      "uid": 25,
+      "progress": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 1
+      },
+      "stats": {
+        "totalNbTasks": 1,
+        "status": {
+          "succeeded": 1
+        },
+        "types": {
+          "documentAdditionOrUpdate": 1
+        },
+        "indexUids": {
+          "kefir": 1
+        }
+      },
+      "duration": "PT0.312911S",
+      "startedAt": "2025-07-07T13:32:46.139785Z",
+      "finishedAt": "2025-07-07T13:32:46.452696Z",
+      "batchStrategy": "unspecified"
+    },
+    {
+      "uid": 24,
+      "progress": null,
+      "details": {
+        "embedders": {
+          "doggo_embedder": {
+            "source": "huggingFace",
+            "model": "sentence-transformers/all-MiniLM-L6-v2",
+            "revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
+            "documentTemplate": "{{doc.description}}"
+          }
+        }
+      },
+      "stats": {
+        "totalNbTasks": 1,
+        "status": {
+          "succeeded": 1
+        },
+        "types": {
+          "settingsUpdate": 1
+        },
+        "indexUids": {
+          "kefir": 1
+        }
+      },
+      "duration": "PT0.247378S",
+      "startedAt": "2025-07-07T13:28:27.391344Z",
+      "finishedAt": "2025-07-07T13:28:27.638722Z",
+      "batchStrategy": "unspecified"
+    },
     {
       "uid": 23,
       "progress": null,
@@ -348,179 +497,10 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
       "startedAt": "2025-01-16T17:01:14.112756687Z",
       "finishedAt": "2025-01-16T17:01:14.120064527Z",
       "batchStrategy": "unspecified"
-    },
-    {
-      "uid": 10,
-      "progress": null,
-      "details": {
-        "faceting": {
-          "maxValuesPerFacet": 99
-        },
-        "pagination": {
-          "maxTotalHits": 15
-        }
-      },
-      "stats": {
-        "totalNbTasks": 1,
-        "status": {
-          "succeeded": 1
-        },
-        "types": {
-          "settingsUpdate": 1
-        },
-        "indexUids": {
-          "kefir": 1
-        }
-      },
-      "duration": "PT0.007391353S",
-      "startedAt": "2025-01-16T17:00:29.201180268Z",
-      "finishedAt": "2025-01-16T17:00:29.208571621Z",
-      "batchStrategy": "unspecified"
-    },
-    {
-      "uid": 9,
-      "progress": null,
-      "details": {
-        "faceting": {
-          "maxValuesPerFacet": 100
-        },
-        "pagination": {
-          "maxTotalHits": 1000
-        }
-      },
-      "stats": {
-        "totalNbTasks": 1,
-        "status": {
-          "succeeded": 1
-        },
-        "types": {
-          "settingsUpdate": 1
-        },
-        "indexUids": {
-          "kefir": 1
-        }
-      },
-      "duration": "PT0.007445825S",
-      "startedAt": "2025-01-16T17:00:15.77629445Z",
-      "finishedAt": "2025-01-16T17:00:15.783740275Z",
-      "batchStrategy": "unspecified"
-    },
-    {
-      "uid": 8,
-      "progress": null,
-      "details": {
-        "typoTolerance": {
-          "minWordSizeForTypos": {
-            "oneTypo": 4
-          },
-          "disableOnWords": [
-            "kefir"
-          ],
-          "disableOnAttributes": [
-            "surname"
-          ]
-        }
-      },
-      "stats": {
-        "totalNbTasks": 1,
-        "status": {
-          "succeeded": 1
-        },
-        "types": {
-          "settingsUpdate": 1
-        },
-        "indexUids": {
-          "kefir": 1
-        }
-      },
-      "duration": "PT0.012020083S",
-      "startedAt": "2025-01-16T16:59:42.744086671Z",
-      "finishedAt": "2025-01-16T16:59:42.756106754Z",
-      "batchStrategy": "unspecified"
-    },
-    {
-      "uid": 7,
-      "progress": null,
-      "details": {
-        "typoTolerance": {
-          "minWordSizeForTypos": {
-            "oneTypo": 4
-          }
-        }
-      },
-      "stats": {
-        "totalNbTasks": 1,
-        "status": {
-          "succeeded": 1
-        },
-        "types": {
-          "settingsUpdate": 1
-        },
-        "indexUids": {
-          "kefir": 1
-        }
-      },
-      "duration": "PT0.007440092S",
-      "startedAt": "2025-01-16T16:58:41.2155771Z",
-      "finishedAt": "2025-01-16T16:58:41.223017192Z",
-      "batchStrategy": "unspecified"
-    },
-    {
-      "uid": 6,
-      "progress": null,
-      "details": {
-        "synonyms": {
-          "boubou": [
-            "kefir"
-          ]
-        }
-      },
-      "stats": {
-        "totalNbTasks": 1,
-        "status": {
-          "succeeded": 1
-        },
-        "types": {
-          "settingsUpdate": 1
-        },
-        "indexUids": {
-          "kefir": 1
-        }
-      },
-      "duration": "PT0.007565161S",
-      "startedAt": "2025-01-16T16:54:51.940332781Z",
-      "finishedAt": "2025-01-16T16:54:51.947897942Z",
-      "batchStrategy": "unspecified"
-    },
-    {
-      "uid": 5,
-      "progress": null,
-      "details": {
-        "stopWords": [
-          "le",
-          "un"
-        ]
-      },
-      "stats": {
-        "totalNbTasks": 1,
-        "status": {
-          "succeeded": 1
-        },
-        "types": {
-          "settingsUpdate": 1
-        },
-        "indexUids": {
-          "kefir": 1
-        }
-      },
-      "duration": "PT0.016307263S",
-      "startedAt": "2025-01-16T16:53:19.913351957Z",
-      "finishedAt": "2025-01-16T16:53:19.92965922Z",
-      "batchStrategy": "unspecified"
     }
   ],
-  "total": 23,
+  "total": 29,
   "limit": 20,
-  "from": 24,
-  "next": 4
+  "from": 30,
+  "next": 10
 }

crates/meilisearch/tests/upgrade/v1_12/snapshots/v1_12_0.rs/check_the_index_scheduler/tasks_filter_afterEnqueuedAt_equal_2025-01-16T16_47_41.snap

@@ -4,15 +4,15 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
 {
   "results": [
     {
-      "uid": 25,
-      "batchUid": 24,
+      "uid": 31,
+      "batchUid": 30,
       "indexUid": null,
       "status": "succeeded",
       "type": "upgradeDatabase",
       "canceledBy": null,
       "details": {
         "upgradeFrom": "v1.12.0",
-        "upgradeTo": "v1.16.0"
+        "upgradeTo": "v1.17.1"
       },
       "error": null,
       "duration": "[duration]",
@@ -20,6 +20,118 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
       "startedAt": "[date]",
       "finishedAt": "[date]"
     },
+    {
+      "uid": 30,
+      "batchUid": 29,
+      "indexUid": "kefir",
+      "status": "succeeded",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 1
+      },
+      "error": null,
+      "duration": "PT0.067201S",
+      "enqueuedAt": "2025-07-07T13:43:08.772432Z",
+      "startedAt": "2025-07-07T13:43:08.772854Z",
+      "finishedAt": "2025-07-07T13:43:08.840055Z"
+    },
+    {
+      "uid": 29,
+      "batchUid": 28,
+      "indexUid": "mieli",
+      "status": "succeeded",
+      "type": "indexDeletion",
+      "canceledBy": null,
+      "details": {
+        "deletedDocuments": 1
+      },
+      "error": null,
+      "duration": "PT0.012727S",
+      "enqueuedAt": "2025-07-07T13:42:50.744793Z",
+      "startedAt": "2025-07-07T13:42:50.745461Z",
+      "finishedAt": "2025-07-07T13:42:50.758188Z"
+    },
+    {
+      "uid": 28,
+      "batchUid": 27,
+      "indexUid": "kefir",
+      "status": "failed",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 0
+      },
+      "error": {
+        "message": "Index `kefir`: Bad embedder configuration in the document with id: `2`. Could not parse `._vectors.doggo_embedder`: trailing characters at line 1 column 13",
+        "code": "invalid_vectors_type",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
+      },
+      "duration": "PT0.059920S",
+      "enqueuedAt": "2025-07-07T13:42:15.624598Z",
+      "startedAt": "2025-07-07T13:42:15.625413Z",
+      "finishedAt": "2025-07-07T13:42:15.685333Z"
+    },
+    {
+      "uid": 27,
+      "batchUid": 26,
+      "indexUid": "mieli",
+      "status": "succeeded",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 1
+      },
+      "error": null,
+      "duration": "PT0.088879S",
+      "enqueuedAt": "2025-07-07T13:40:01.46081Z",
+      "startedAt": "2025-07-07T13:40:01.461741Z",
+      "finishedAt": "2025-07-07T13:40:01.55062Z"
+    },
+    {
+      "uid": 26,
+      "batchUid": 25,
+      "indexUid": "kefir",
+      "status": "succeeded",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 1
+      },
+      "error": null,
+      "duration": "PT0.312911S",
+      "enqueuedAt": "2025-07-07T13:32:46.13871Z",
+      "startedAt": "2025-07-07T13:32:46.139785Z",
+      "finishedAt": "2025-07-07T13:32:46.452696Z"
+    },
+    {
+      "uid": 25,
+      "batchUid": 24,
+      "indexUid": "kefir",
+      "status": "succeeded",
+      "type": "settingsUpdate",
+      "canceledBy": null,
+      "details": {
+        "embedders": {
+          "doggo_embedder": {
+            "source": "huggingFace",
+            "model": "sentence-transformers/all-MiniLM-L6-v2",
+            "revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
+            "documentTemplate": "{{doc.description}}"
+          }
+        }
+      },
+      "error": null,
+      "duration": "PT0.247378S",
+      "enqueuedAt": "2025-07-07T13:28:27.390054Z",
+      "startedAt": "2025-07-07T13:28:27.391344Z",
+      "finishedAt": "2025-07-07T13:28:27.638722Z"
+    },
     {
       "uid": 24,
       "batchUid": 23,
@@ -264,134 +376,10 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
       "enqueuedAt": "2025-01-16T17:02:52.527382964Z",
       "startedAt": "2025-01-16T17:02:52.539749853Z",
       "finishedAt": "2025-01-16T17:02:52.547390016Z"
-    },
-    {
-      "uid": 11,
-      "batchUid": 11,
-      "indexUid": "kefir",
-      "status": "succeeded",
-      "type": "settingsUpdate",
-      "canceledBy": null,
-      "details": {
-        "searchCutoffMs": 8000
-      },
-      "error": null,
-      "duration": "PT0.007307840S",
-      "enqueuedAt": "2025-01-16T17:01:14.100316617Z",
-      "startedAt": "2025-01-16T17:01:14.112756687Z",
-      "finishedAt": "2025-01-16T17:01:14.120064527Z"
-    },
-    {
-      "uid": 10,
-      "batchUid": 10,
-      "indexUid": "kefir",
-      "status": "succeeded",
-      "type": "settingsUpdate",
-      "canceledBy": null,
-      "details": {
-        "faceting": {
-          "maxValuesPerFacet": 99
-        },
-        "pagination": {
-          "maxTotalHits": 15
-        }
-      },
-      "error": null,
-      "duration": "PT0.007391353S",
-      "enqueuedAt": "2025-01-16T17:00:29.188815062Z",
-      "startedAt": "2025-01-16T17:00:29.201180268Z",
-      "finishedAt": "2025-01-16T17:00:29.208571621Z"
-    },
-    {
-      "uid": 9,
-      "batchUid": 9,
-      "indexUid": "kefir",
-      "status": "succeeded",
-      "type": "settingsUpdate",
-      "canceledBy": null,
-      "details": {
-        "faceting": {
-          "maxValuesPerFacet": 100
-        },
-        "pagination": {
-          "maxTotalHits": 1000
-        }
-      },
-      "error": null,
-      "duration": "PT0.007445825S",
-      "enqueuedAt": "2025-01-16T17:00:15.759501709Z",
-      "startedAt": "2025-01-16T17:00:15.77629445Z",
-      "finishedAt": "2025-01-16T17:00:15.783740275Z"
-    },
-    {
-      "uid": 8,
-      "batchUid": 8,
-      "indexUid": "kefir",
-      "status": "succeeded",
-      "type": "settingsUpdate",
-      "canceledBy": null,
-      "details": {
-        "typoTolerance": {
-          "minWordSizeForTypos": {
-            "oneTypo": 4
-          },
-          "disableOnWords": [
-            "kefir"
-          ],
-          "disableOnAttributes": [
-            "surname"
-          ]
-        }
-      },
-      "error": null,
-      "duration": "PT0.012020083S",
-      "enqueuedAt": "2025-01-16T16:59:42.727292501Z",
-      "startedAt": "2025-01-16T16:59:42.744086671Z",
-      "finishedAt": "2025-01-16T16:59:42.756106754Z"
-    },
-    {
-      "uid": 7,
-      "batchUid": 7,
-      "indexUid": "kefir",
-      "status": "succeeded",
-      "type": "settingsUpdate",
-      "canceledBy": null,
-      "details": {
-        "typoTolerance": {
-          "minWordSizeForTypos": {
-            "oneTypo": 4
-          }
-        }
-      },
-      "error": null,
-      "duration": "PT0.007440092S",
-      "enqueuedAt": "2025-01-16T16:58:41.203145044Z",
-      "startedAt": "2025-01-16T16:58:41.2155771Z",
-      "finishedAt": "2025-01-16T16:58:41.223017192Z"
-    },
-    {
-      "uid": 6,
-      "batchUid": 6,
-      "indexUid": "kefir",
-      "status": "succeeded",
-      "type": "settingsUpdate",
-      "canceledBy": null,
-      "details": {
-        "synonyms": {
-          "boubou": [
-            "kefir"
-          ]
-        }
-      },
-      "error": null,
-      "duration": "PT0.007565161S",
-      "enqueuedAt": "2025-01-16T16:54:51.927866243Z",
-      "startedAt": "2025-01-16T16:54:51.940332781Z",
-      "finishedAt": "2025-01-16T16:54:51.947897942Z"
     }
   ],
-  "total": 24,
+  "total": 30,
   "limit": 20,
-  "from": 25,
-  "next": 5
+  "from": 31,
+  "next": 11
 }

crates/meilisearch/tests/upgrade/v1_12/snapshots/v1_12_0.rs/check_the_index_scheduler/tasks_filter_afterFinishedAt_equal_2025-01-16T16_47_41.snap

@@ -4,15 +4,15 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
 {
   "results": [
     {
-      "uid": 25,
-      "batchUid": 24,
+      "uid": 31,
+      "batchUid": 30,
       "indexUid": null,
       "status": "succeeded",
       "type": "upgradeDatabase",
       "canceledBy": null,
       "details": {
         "upgradeFrom": "v1.12.0",
-        "upgradeTo": "v1.16.0"
+        "upgradeTo": "v1.17.1"
       },
       "error": null,
       "duration": "[duration]",
@@ -20,6 +20,118 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
       "startedAt": "[date]",
       "finishedAt": "[date]"
     },
+    {
+      "uid": 30,
+      "batchUid": 29,
+      "indexUid": "kefir",
+      "status": "succeeded",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 1
+      },
+      "error": null,
+      "duration": "PT0.067201S",
+      "enqueuedAt": "2025-07-07T13:43:08.772432Z",
+      "startedAt": "2025-07-07T13:43:08.772854Z",
+      "finishedAt": "2025-07-07T13:43:08.840055Z"
+    },
+    {
+      "uid": 29,
+      "batchUid": 28,
+      "indexUid": "mieli",
+      "status": "succeeded",
+      "type": "indexDeletion",
+      "canceledBy": null,
+      "details": {
+        "deletedDocuments": 1
+      },
+      "error": null,
+      "duration": "PT0.012727S",
+      "enqueuedAt": "2025-07-07T13:42:50.744793Z",
+      "startedAt": "2025-07-07T13:42:50.745461Z",
+      "finishedAt": "2025-07-07T13:42:50.758188Z"
+    },
+    {
+      "uid": 28,
+      "batchUid": 27,
+      "indexUid": "kefir",
+      "status": "failed",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 0
+      },
+      "error": {
+        "message": "Index `kefir`: Bad embedder configuration in the document with id: `2`. Could not parse `._vectors.doggo_embedder`: trailing characters at line 1 column 13",
+        "code": "invalid_vectors_type",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
+      },
+      "duration": "PT0.059920S",
+      "enqueuedAt": "2025-07-07T13:42:15.624598Z",
+      "startedAt": "2025-07-07T13:42:15.625413Z",
+      "finishedAt": "2025-07-07T13:42:15.685333Z"
+    },
+    {
+      "uid": 27,
+      "batchUid": 26,
+      "indexUid": "mieli",
+      "status": "succeeded",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 1
+      },
+      "error": null,
+      "duration": "PT0.088879S",
+      "enqueuedAt": "2025-07-07T13:40:01.46081Z",
+      "startedAt": "2025-07-07T13:40:01.461741Z",
+      "finishedAt": "2025-07-07T13:40:01.55062Z"
+    },
+    {
+      "uid": 26,
+      "batchUid": 25,
+      "indexUid": "kefir",
+      "status": "succeeded",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 1
+      },
+      "error": null,
+      "duration": "PT0.312911S",
+      "enqueuedAt": "2025-07-07T13:32:46.13871Z",
+      "startedAt": "2025-07-07T13:32:46.139785Z",
+      "finishedAt": "2025-07-07T13:32:46.452696Z"
+    },
+    {
+      "uid": 25,
+      "batchUid": 24,
+      "indexUid": "kefir",
+      "status": "succeeded",
+      "type": "settingsUpdate",
+      "canceledBy": null,
+      "details": {
+        "embedders": {
+          "doggo_embedder": {
+            "source": "huggingFace",
+            "model": "sentence-transformers/all-MiniLM-L6-v2",
+            "revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
+            "documentTemplate": "{{doc.description}}"
+          }
+        }
+      },
+      "error": null,
+      "duration": "PT0.247378S",
+      "enqueuedAt": "2025-07-07T13:28:27.390054Z",
+      "startedAt": "2025-07-07T13:28:27.391344Z",
+      "finishedAt": "2025-07-07T13:28:27.638722Z"
+    },
     {
       "uid": 24,
       "batchUid": 23,
@@ -264,134 +376,10 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
       "enqueuedAt": "2025-01-16T17:02:52.527382964Z",
       "startedAt": "2025-01-16T17:02:52.539749853Z",
       "finishedAt": "2025-01-16T17:02:52.547390016Z"
-    },
-    {
-      "uid": 11,
-      "batchUid": 11,
-      "indexUid": "kefir",
-      "status": "succeeded",
-      "type": "settingsUpdate",
-      "canceledBy": null,
-      "details": {
-        "searchCutoffMs": 8000
-      },
-      "error": null,
-      "duration": "PT0.007307840S",
-      "enqueuedAt": "2025-01-16T17:01:14.100316617Z",
-      "startedAt": "2025-01-16T17:01:14.112756687Z",
-      "finishedAt": "2025-01-16T17:01:14.120064527Z"
-    },
-    {
-      "uid": 10,
-      "batchUid": 10,
-      "indexUid": "kefir",
-      "status": "succeeded",
-      "type": "settingsUpdate",
-      "canceledBy": null,
-      "details": {
-        "faceting": {
-          "maxValuesPerFacet": 99
-        },
-        "pagination": {
-          "maxTotalHits": 15
-        }
-      },
-      "error": null,
-      "duration": "PT0.007391353S",
-      "enqueuedAt": "2025-01-16T17:00:29.188815062Z",
-      "startedAt": "2025-01-16T17:00:29.201180268Z",
-      "finishedAt": "2025-01-16T17:00:29.208571621Z"
-    },
-    {
-      "uid": 9,
-      "batchUid": 9,
-      "indexUid": "kefir",
-      "status": "succeeded",
-      "type": "settingsUpdate",
-      "canceledBy": null,
-      "details": {
-        "faceting": {
-          "maxValuesPerFacet": 100
-        },
-        "pagination": {
-          "maxTotalHits": 1000
-        }
-      },
-      "error": null,
-      "duration": "PT0.007445825S",
-      "enqueuedAt": "2025-01-16T17:00:15.759501709Z",
-      "startedAt": "2025-01-16T17:00:15.77629445Z",
-      "finishedAt": "2025-01-16T17:00:15.783740275Z"
-    },
-    {
-      "uid": 8,
-      "batchUid": 8,
-      "indexUid": "kefir",
-      "status": "succeeded",
-      "type": "settingsUpdate",
-      "canceledBy": null,
-      "details": {
-        "typoTolerance": {
-          "minWordSizeForTypos": {
-            "oneTypo": 4
-          },
-          "disableOnWords": [
-            "kefir"
-          ],
-          "disableOnAttributes": [
-            "surname"
-          ]
-        }
-      },
-      "error": null,
-      "duration": "PT0.012020083S",
-      "enqueuedAt": "2025-01-16T16:59:42.727292501Z",
-      "startedAt": "2025-01-16T16:59:42.744086671Z",
-      "finishedAt": "2025-01-16T16:59:42.756106754Z"
-    },
-    {
-      "uid": 7,
-      "batchUid": 7,
-      "indexUid": "kefir",
-      "status": "succeeded",
-      "type": "settingsUpdate",
-      "canceledBy": null,
-      "details": {
-        "typoTolerance": {
-          "minWordSizeForTypos": {
-            "oneTypo": 4
-          }
-        }
-      },
-      "error": null,
-      "duration": "PT0.007440092S",
-      "enqueuedAt": "2025-01-16T16:58:41.203145044Z",
-      "startedAt": "2025-01-16T16:58:41.2155771Z",
-      "finishedAt": "2025-01-16T16:58:41.223017192Z"
-    },
-    {
-      "uid": 6,
-      "batchUid": 6,
-      "indexUid": "kefir",
-      "status": "succeeded",
-      "type": "settingsUpdate",
-      "canceledBy": null,
-      "details": {
-        "synonyms": {
-          "boubou": [
-            "kefir"
-          ]
-        }
-      },
-      "error": null,
-      "duration": "PT0.007565161S",
-      "enqueuedAt": "2025-01-16T16:54:51.927866243Z",
-      "startedAt": "2025-01-16T16:54:51.940332781Z",
-      "finishedAt": "2025-01-16T16:54:51.947897942Z"
     }
   ],
-  "total": 24,
+  "total": 30,
   "limit": 20,
-  "from": 25,
-  "next": 5
+  "from": 31,
+  "next": 11
 }

crates/meilisearch/tests/upgrade/v1_12/snapshots/v1_12_0.rs/check_the_index_scheduler/tasks_filter_afterStartedAt_equal_2025-01-16T16_47_41.snap

@@ -4,15 +4,15 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
 {
   "results": [
     {
-      "uid": 25,
-      "batchUid": 24,
+      "uid": 31,
+      "batchUid": 30,
       "indexUid": null,
       "status": "succeeded",
       "type": "upgradeDatabase",
       "canceledBy": null,
       "details": {
         "upgradeFrom": "v1.12.0",
-        "upgradeTo": "v1.16.0"
+        "upgradeTo": "v1.17.1"
       },
       "error": null,
       "duration": "[duration]",
@@ -20,6 +20,118 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
       "startedAt": "[date]",
       "finishedAt": "[date]"
     },
+    {
+      "uid": 30,
+      "batchUid": 29,
+      "indexUid": "kefir",
+      "status": "succeeded",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 1
+      },
+      "error": null,
+      "duration": "PT0.067201S",
+      "enqueuedAt": "2025-07-07T13:43:08.772432Z",
+      "startedAt": "2025-07-07T13:43:08.772854Z",
+      "finishedAt": "2025-07-07T13:43:08.840055Z"
+    },
+    {
+      "uid": 29,
+      "batchUid": 28,
+      "indexUid": "mieli",
+      "status": "succeeded",
+      "type": "indexDeletion",
+      "canceledBy": null,
+      "details": {
+        "deletedDocuments": 1
+      },
+      "error": null,
+      "duration": "PT0.012727S",
+      "enqueuedAt": "2025-07-07T13:42:50.744793Z",
+      "startedAt": "2025-07-07T13:42:50.745461Z",
+      "finishedAt": "2025-07-07T13:42:50.758188Z"
+    },
+    {
+      "uid": 28,
+      "batchUid": 27,
+      "indexUid": "kefir",
+      "status": "failed",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 0
+      },
+      "error": {
+        "message": "Index `kefir`: Bad embedder configuration in the document with id: `2`. Could not parse `._vectors.doggo_embedder`: trailing characters at line 1 column 13",
+        "code": "invalid_vectors_type",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
+      },
+      "duration": "PT0.059920S",
+      "enqueuedAt": "2025-07-07T13:42:15.624598Z",
+      "startedAt": "2025-07-07T13:42:15.625413Z",
+      "finishedAt": "2025-07-07T13:42:15.685333Z"
+    },
+    {
+      "uid": 27,
+      "batchUid": 26,
+      "indexUid": "mieli",
+      "status": "succeeded",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 1
+      },
+      "error": null,
+      "duration": "PT0.088879S",
+      "enqueuedAt": "2025-07-07T13:40:01.46081Z",
+      "startedAt": "2025-07-07T13:40:01.461741Z",
+      "finishedAt": "2025-07-07T13:40:01.55062Z"
+    },
+    {
+      "uid": 26,
+      "batchUid": 25,
+      "indexUid": "kefir",
+      "status": "succeeded",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 1
+      },
+      "error": null,
+      "duration": "PT0.312911S",
+      "enqueuedAt": "2025-07-07T13:32:46.13871Z",
+      "startedAt": "2025-07-07T13:32:46.139785Z",
+      "finishedAt": "2025-07-07T13:32:46.452696Z"
+    },
+    {
+      "uid": 25,
+      "batchUid": 24,
+      "indexUid": "kefir",
+      "status": "succeeded",
+      "type": "settingsUpdate",
+      "canceledBy": null,
+      "details": {
+        "embedders": {
+          "doggo_embedder": {
+            "source": "huggingFace",
+            "model": "sentence-transformers/all-MiniLM-L6-v2",
+            "revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
+            "documentTemplate": "{{doc.description}}"
+          }
+        }
+      },
+      "error": null,
+      "duration": "PT0.247378S",
+      "enqueuedAt": "2025-07-07T13:28:27.390054Z",
+      "startedAt": "2025-07-07T13:28:27.391344Z",
+      "finishedAt": "2025-07-07T13:28:27.638722Z"
+    },
     {
       "uid": 24,
       "batchUid": 23,
@@ -264,134 +376,10 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
       "enqueuedAt": "2025-01-16T17:02:52.527382964Z",
       "startedAt": "2025-01-16T17:02:52.539749853Z",
       "finishedAt": "2025-01-16T17:02:52.547390016Z"
-    },
-    {
-      "uid": 11,
-      "batchUid": 11,
-      "indexUid": "kefir",
-      "status": "succeeded",
-      "type": "settingsUpdate",
-      "canceledBy": null,
-      "details": {
-        "searchCutoffMs": 8000
-      },
-      "error": null,
-      "duration": "PT0.007307840S",
-      "enqueuedAt": "2025-01-16T17:01:14.100316617Z",
-      "startedAt": "2025-01-16T17:01:14.112756687Z",
-      "finishedAt": "2025-01-16T17:01:14.120064527Z"
-    },
-    {
-      "uid": 10,
-      "batchUid": 10,
-      "indexUid": "kefir",
-      "status": "succeeded",
-      "type": "settingsUpdate",
-      "canceledBy": null,
-      "details": {
-        "faceting": {
-          "maxValuesPerFacet": 99
-        },
-        "pagination": {
-          "maxTotalHits": 15
-        }
-      },
-      "error": null,
-      "duration": "PT0.007391353S",
-      "enqueuedAt": "2025-01-16T17:00:29.188815062Z",
-      "startedAt": "2025-01-16T17:00:29.201180268Z",
-      "finishedAt": "2025-01-16T17:00:29.208571621Z"
-    },
-    {
-      "uid": 9,
-      "batchUid": 9,
-      "indexUid": "kefir",
-      "status": "succeeded",
-      "type": "settingsUpdate",
-      "canceledBy": null,
-      "details": {
-        "faceting": {
-          "maxValuesPerFacet": 100
-        },
-        "pagination": {
-          "maxTotalHits": 1000
-        }
-      },
-      "error": null,
-      "duration": "PT0.007445825S",
-      "enqueuedAt": "2025-01-16T17:00:15.759501709Z",
-      "startedAt": "2025-01-16T17:00:15.77629445Z",
-      "finishedAt": "2025-01-16T17:00:15.783740275Z"
-    },
-    {
-      "uid": 8,
-      "batchUid": 8,
-      "indexUid": "kefir",
-      "status": "succeeded",
-      "type": "settingsUpdate",
-      "canceledBy": null,
-      "details": {
-        "typoTolerance": {
-          "minWordSizeForTypos": {
-            "oneTypo": 4
-          },
-          "disableOnWords": [
-            "kefir"
-          ],
-          "disableOnAttributes": [
-            "surname"
-          ]
-        }
-      },
-      "error": null,
-      "duration": "PT0.012020083S",
-      "enqueuedAt": "2025-01-16T16:59:42.727292501Z",
-      "startedAt": "2025-01-16T16:59:42.744086671Z",
-      "finishedAt": "2025-01-16T16:59:42.756106754Z"
-    },
-    {
-      "uid": 7,
-      "batchUid": 7,
-      "indexUid": "kefir",
-      "status": "succeeded",
-      "type": "settingsUpdate",
-      "canceledBy": null,
-      "details": {
-        "typoTolerance": {
-          "minWordSizeForTypos": {
-            "oneTypo": 4
-          }
-        }
-      },
-      "error": null,
-      "duration": "PT0.007440092S",
-      "enqueuedAt": "2025-01-16T16:58:41.203145044Z",
-      "startedAt": "2025-01-16T16:58:41.2155771Z",
-      "finishedAt": "2025-01-16T16:58:41.223017192Z"
-    },
-    {
-      "uid": 6,
-      "batchUid": 6,
-      "indexUid": "kefir",
-      "status": "succeeded",
-      "type": "settingsUpdate",
-      "canceledBy": null,
-      "details": {
-        "synonyms": {
-          "boubou": [
-            "kefir"
-          ]
-        }
-      },
-      "error": null,
-      "duration": "PT0.007565161S",
-      "enqueuedAt": "2025-01-16T16:54:51.927866243Z",
-      "startedAt": "2025-01-16T16:54:51.940332781Z",
-      "finishedAt": "2025-01-16T16:54:51.947897942Z"
     }
   ],
-  "total": 24,
+  "total": 30,
   "limit": 20,
-  "from": 25,
-  "next": 5
+  "from": 31,
+  "next": 11
 }