WIP

Allow sorting on the /documents route

.gitignore

@@ -11,12 +11,18 @@
 /bench
 /_xtask_benchmark.ms
 /benchmarks
+.DS_Store
 
 # Snapshots
 ## ... large
 *.full.snap
-##  ... unreviewed
+## ... unreviewed
 *.snap.new
+## ... pending
+*.pending-snap
+
+# Tmp files
+.tmp*
 
 # Database snapshot
 crates/meilisearch/db.snapshot

Cargo.lock

@@ -1778,12 +1778,15 @@ version = "1.16.0"
 dependencies = [
  "anyhow",
  "big_s",
+ "bytemuck",
  "flate2",
  "http 1.3.1",
  "maplit",
  "meili-snap",
  "meilisearch-types",
+ "memmap2",
  "once_cell",
+ "rayon",
  "regex",
  "roaring",
  "serde",

crates/benchmarks/Cargo.toml

@@ -51,3 +51,8 @@ harness = false
 [[bench]]
 name = "indexing"
 harness = false
+
+[[bench]]
+name = "sort"
+harness = false
+

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/Cargo.toml

@@ -12,18 +12,26 @@ license.workspace = true
 
 [dependencies]
 anyhow = "1.0.98"
+bytemuck = { version = "1.23.1", features = ["extern_crate_alloc"] }
 flate2 = "1.1.2"
 http = "1.3.1"
 meilisearch-types = { path = "../meilisearch-types" }
+memmap2 = "0.9.5"
 once_cell = "1.21.3"
 regex = "1.11.1"
+rayon = "1.10.0"
 roaring = { version = "0.10.12", features = ["serde"] }
 serde = { version = "1.0.219", features = ["derive"] }
 serde_json = { version = "1.0.140", features = ["preserve_order"] }
 tar = "0.4.44"
 tempfile = "3.20.0"
 thiserror = "2.0.12"
-time = { version = "0.3.41", features = ["serde-well-known", "formatting", "parsing", "macros"] }
+time = { version = "0.3.41", features = [
+    "serde-well-known",
+    "formatting",
+    "parsing",
+    "macros",
+] }
 tracing = "0.1.41"
 uuid = { version = "1.17.0", features = ["serde", "v4"] }
 

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

@@ -50,6 +50,8 @@ pub type RankingRuleView = meilisearch_types::settings::RankingRuleView;
 
 pub type FilterableAttributesRule = meilisearch_types::milli::FilterableAttributesRule;
 
+pub mod vector;
+
 pub struct V6Reader {
     dump: TempDir,
     instance_uid: Option<Uuid>,

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

@@ -0,0 +1,154 @@
+//! Read vectors from a `vectors` directory for each index.
+//!
+//! The `vectors` directory is architected in the following way:
+//! - `commands/` directory containing binary files that indicate which vectors should go into which embedder and fragment for which document
+//! - `data/` directory containing the vector data.
+//! - `status/` directory containing embedding metadata (`EmbeddingStatus`)
+
+use std::fs::File;
+use std::io::{BufReader, ErrorKind, Read};
+use std::path::PathBuf;
+
+use meilisearch_types::heed::byteorder::{BigEndian, ReadBytesExt};
+use meilisearch_types::heed::RoTxn;
+use meilisearch_types::milli::vector::RuntimeEmbedders;
+use meilisearch_types::milli::DocumentId;
+use meilisearch_types::Index;
+use memmap2::Mmap;
+
+use crate::Result;
+
+pub struct VectorReader {
+    dir: PathBuf,
+    file_count: usize,
+}
+
+impl VectorReader {
+    pub fn new(dir: PathBuf) -> Result<Self> {
+        let commands = dir.join("commands");
+        let file_count = commands.read_dir()?.count();
+        Ok(Self { dir, file_count })
+    }
+
+    pub fn visit<V: Visitor>(
+        &self,
+        mut v: V,
+        index: usize,
+    ) -> Result<std::result::Result<(), V::Error>> {
+        let filename = format!("{:04}.bin", index);
+        let commands = self.dir.join("commands").join(&filename);
+        let data = self.dir.join("data").join(&filename);
+        let mut commands = BufReader::new(File::open(commands)?);
+        let data = File::open(data)?;
+        let data = unsafe { Mmap::map(&data)? };
+        let mut buf = Vec::new();
+        let mut dimensions = None;
+        while let Some(command) = read_next_command(&mut buf, &mut commands)? {
+            let res = match command {
+                Command::ChangeCurrentEmbedder { name } => v
+                    .on_current_embedder_change(name)
+                    .map(|new_dimensions| dimensions = Some(new_dimensions)),
+                Command::ChangeCurrentStore { name } => v.on_current_store_change(name),
+                Command::ChangeDocid { external_docid } => {
+                    v.on_current_docid_change(external_docid)
+                }
+                Command::SetVector { offset } => {
+                    let dimensions = dimensions.unwrap();
+                    let vec = &data[(offset as usize)
+                        ..(offset as usize + (dimensions * std::mem::size_of::<f32>()))];
+
+                    v.on_set_vector(bytemuck::cast_slice(vec))
+                }
+            };
+            if let Err(err) = res {
+                return Ok(Err(err));
+            }
+        }
+        Ok(Ok(()))
+    }
+}
+
+fn read_next_command(buf: &mut Vec<u8>, mut commands: impl Read) -> Result<Option<Command>> {
+    let kind = match commands.read_u8() {
+        Ok(kind) => kind,
+        Err(err) if err.kind() == ErrorKind::UnexpectedEof => return Ok(None),
+        Err(err) => return Err(err.into()),
+    };
+    let s = if Command::has_len(kind) {
+        let len = commands.read_u32::<BigEndian>()?;
+        buf.resize(len as usize, 0);
+        if len != 0 {
+            commands.read_exact(buf)?;
+            std::str::from_utf8(buf).unwrap()
+        } else {
+            ""
+        }
+    } else {
+        ""
+    };
+    let offset = if Command::has_offset(kind) { commands.read_u64::<BigEndian>()? } else { 0 };
+    Ok(Some(Command::from_raw(kind, s, offset)))
+}
+
+#[repr(u8)]
+pub enum Command<'pl> {
+    /// Tell the importer that the next embeddings are to be added in the context of the specified embedder.
+    ///
+    /// Replaces the embedder specified by the previous such command.
+    ///
+    /// Embedder is specified by its name.
+    ChangeCurrentEmbedder { name: &'pl str },
+    /// Tell the importer that the next embeddings are to be added in the context of the specified store.
+    ///
+    /// Replaces the store specified by the previous such command.
+    ///
+    /// The store is specified by an optional fragment name
+    ChangeCurrentStore { name: Option<&'pl str> },
+    /// Tell the importer that the next embeddings are to be added in the context of the specified document.
+    ///
+    /// Replaces the store specified by the previous such command.
+    ///
+    /// The document is specified by the external docid of the document.
+    ChangeDocid { external_docid: &'pl str },
+    /// Tell the importer where to find the next vector in the current data file.
+    SetVector { offset: u64 },
+}
+
+impl Command<'_> {
+    const CHANGE_CURRENT_EMBEDDER: Self = Self::ChangeCurrentEmbedder { name: "" };
+    const CHANGE_CURRENT_STORE: Self = Self::ChangeCurrentStore { name: Some("") };
+    const CHANGE_DOCID: Self = Self::ChangeDocid { external_docid: "" };
+    const SET_VECTOR: Self = Self::SetVector { offset: 0 };
+
+    fn has_len(kind: u8) -> bool {
+        kind == Self::CHANGE_CURRENT_EMBEDDER.discriminant()
+            || kind == Self::CHANGE_CURRENT_STORE.discriminant()
+            || kind == Self::CHANGE_DOCID.discriminant()
+    }
+
+    fn has_offset(kind: u8) -> bool {
+        kind == Self::SET_VECTOR.discriminant()
+    }
+
+    /// See <https://doc.rust-lang.org/std/mem/fn.discriminant.html#accessing-the-numeric-value-of-the-discriminant>
+    fn discriminant(&self) -> u8 {
+        // SAFETY: Because `Self` is marked `repr(u8)`, its layout is a `repr(C)` `union`
+        // between `repr(C)` structs, each of which has the `u8` discriminant as its first
+        // field, so we can read the discriminant without offsetting the pointer.
+        unsafe { *<*const _>::from(self).cast::<u8>() }
+    }
+
+    fn from_raw(kind: u8, s: &str, offset: u64) -> Command {
+        if kind == Self::CHANGE_CURRENT_EMBEDDER.discriminant() {
+            Command::ChangeCurrentEmbedder { name: s }
+        } else if kind == Self::CHANGE_CURRENT_STORE.discriminant() {
+            Command::ChangeCurrentStore { name: (!s.is_empty()).then_some(s) }
+        } else if kind == Self::CHANGE_DOCID.discriminant() {
+            Command::ChangeDocid { external_docid: s }
+        } else if kind == Self::SET_VECTOR.discriminant() {
+            Command::SetVector { offset }
+        } else {
+            panic!("unknown command")
+        }
+    }
+}

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

@@ -62,13 +62,14 @@ 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 +91,8 @@ 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 +104,8 @@ 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 +123,6 @@ 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 +167,10 @@ 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()
@@ -265,9 +265,8 @@ 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 +275,7 @@ 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 +283,8 @@ 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 +297,9 @@ impl IndexScheduler {
                         Some(uid.to_string()),
                     )
                 })?;
+            for result in results {
+                result?;
+            }
 
             step.store(total_documents, atomic::Ordering::Relaxed);
         }

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]

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 ;
@@ -415,6 +416,7 @@ 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
 }
@@ -476,7 +478,8 @@ 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
                     }
@@ -492,7 +495,8 @@ 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)]
@@ -164,6 +165,7 @@ pub struct ChatCompletionPrompts {
     pub system: String,
     pub search_description: String,
     pub search_q_param: String,
+    pub search_filter_param: String,
     pub search_index_uid_param: String,
 }
 
@@ -173,6 +175,7 @@ impl Default for ChatCompletionPrompts {
             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();
@@ -218,6 +233,9 @@ pub enum Action {
     #[serde(rename = "*")]
     #[deserr(rename = "*")]
     All = 0,
+    #[serde(rename = "*.get")]
+    #[deserr(rename = "*.get")]
+    AllGet,
     #[serde(rename = "search")]
     #[deserr(rename = "search")]
     Search,
@@ -399,6 +417,52 @@ impl Action {
         }
     }
 
+    /// 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 => 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,
+        }
+    }
+
     pub const fn repr(&self) -> u8 {
         *self as u8
     }
@@ -408,6 +472,7 @@ 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();

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/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/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;
@@ -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,
@@ -280,14 +300,23 @@ 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();
@@ -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()),
                     };
 
@@ -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/export_analytics.rs

@@ -1,3 +1,5 @@
+use url::Url;
+
 use crate::analytics::Aggregate;
 use crate::routes::export::Export;
 
@@ -5,6 +7,7 @@ use crate::routes::export::Export;
 pub struct ExportAnalytics {
     total_received: usize,
     has_api_key: bool,
+    sum_exports_meilisearch_cloud: usize,
     sum_index_patterns: usize,
     sum_patterns_with_filter: usize,
     sum_patterns_with_override_settings: usize,
@@ -13,8 +16,14 @@ pub struct ExportAnalytics {
 
 impl ExportAnalytics {
     pub fn from_export(export: &Export) -> Self {
-        let Export { url: _, api_key, payload_size, indexes } = export;
+        let Export { url, api_key, payload_size, indexes } = export;
 
+        let url = Url::parse(url).ok();
+        let is_meilisearch_cloud = url.as_ref().and_then(Url::host_str).is_some_and(|host| {
+            host.ends_with("meilisearch.dev")
+                || host.ends_with("meilisearch.com")
+                || host.ends_with("meilisearch.io")
+        });
         let has_api_key = api_key.is_some();
         let index_patterns_count = indexes.as_ref().map_or(0, |indexes| indexes.len());
         let patterns_with_filter_count = indexes.as_ref().map_or(0, |indexes| {
@@ -33,6 +42,7 @@ impl ExportAnalytics {
         Self {
             total_received: 1,
             has_api_key,
+            sum_exports_meilisearch_cloud: is_meilisearch_cloud as usize,
             sum_index_patterns: index_patterns_count,
             sum_patterns_with_filter: patterns_with_filter_count,
             sum_patterns_with_override_settings: patterns_with_override_settings_count,
@@ -49,6 +59,7 @@ impl Aggregate for ExportAnalytics {
     fn aggregate(mut self: Box<Self>, other: Box<Self>) -> Box<Self> {
         self.total_received += other.total_received;
         self.has_api_key |= other.has_api_key;
+        self.sum_exports_meilisearch_cloud += other.sum_exports_meilisearch_cloud;
         self.sum_index_patterns += other.sum_index_patterns;
         self.sum_patterns_with_filter += other.sum_patterns_with_filter;
         self.sum_patterns_with_override_settings += other.sum_patterns_with_override_settings;
@@ -63,6 +74,12 @@ impl Aggregate for ExportAnalytics {
             Some(self.payload_sizes.iter().sum::<u64>() / self.payload_sizes.len() as u64)
         };
 
+        let avg_exports_meilisearch_cloud = if self.total_received == 0 {
+            None
+        } else {
+            Some(self.sum_exports_meilisearch_cloud as f64 / self.total_received as f64)
+        };
+
         let avg_index_patterns = if self.total_received == 0 {
             None
         } else {
@@ -84,6 +101,7 @@ impl Aggregate for ExportAnalytics {
         serde_json::json!({
             "total_received": self.total_received,
             "has_api_key": self.has_api_key,
+            "avg_exports_meilisearch_cloud": avg_exports_meilisearch_cloud,
             "avg_index_patterns": avg_index_patterns,
             "avg_patterns_with_filter": avg_patterns_with_filter,
             "avg_patterns_with_override_settings": avg_patterns_with_override_settings,

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 +18,10 @@ 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::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 +44,7 @@ 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 +138,8 @@ pub struct DocumentsFetchAggregator<Method: AggregateMethod> {
     per_document_id: bool,
     // if a filter was used
     per_filter: bool,
+    // if documents were sorted
+    sort: bool,
 
     #[serde(rename = "vector.retrieve_vectors")]
     retrieve_vectors: bool,
@@ -151,39 +156,6 @@ 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 +165,7 @@ 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,
+            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 +249,7 @@ pub async fn get_document(
             retrieve_vectors: param_retrieve_vectors.0,
             per_document_id: true,
             per_filter: false,
+            sort: false,
             max_limit: 0,
             max_offset: 0,
             max_document_ids: 0,
@@ -406,6 +380,8 @@ 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 +406,9 @@ 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 +474,7 @@ pub async fn documents_by_query_post(
     analytics.publish(
         DocumentsFetchAggregator::<DocumentsPOST> {
             per_filter: body.filter.is_some(),
+            sort: body.sort.is_some(),
             retrieve_vectors: body.retrieve_vectors,
             max_limit: body.limit,
             max_offset: body.offset,
@@ -571,7 +551,7 @@ 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 +562,20 @@ 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(),
+            sort: query.sort.is_some(),
             retrieve_vectors: query.retrieve_vectors,
             max_limit: query.limit,
             max_offset: query.offset,
@@ -615,7 +595,7 @@ 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 +613,18 @@ 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 +635,7 @@ fn documents_by_query(
         fields,
         retrieve_vectors,
         index_scheduler.features(),
+        sort_criteria,
     )?;
 
     let ret = PaginationView::new(offset, limit, total as usize, documents);
@@ -1494,6 +1487,7 @@ 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 +1520,32 @@ 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/search/federated/perform.rs

@@ -745,10 +745,9 @@ 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)

crates/meilisearch/src/search/mod.rs

@@ -1051,6 +1051,7 @@ pub fn prepare_search<'t>(
         .unwrap_or(DEFAULT_PAGINATION_MAX_TOTAL_HITS);
 
     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 +1092,7 @@ 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())
             }
         };
 

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 `*`, `*.get`, `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`",
       "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 `*`, `*.get`, `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`",
       "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

@@ -562,5 +562,7 @@ 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/server.rs

@@ -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());
     }

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().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/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/get_settings.rs

@@ -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/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

@@ -4,7 +4,7 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
 {
   "results": [
     {
-      "uid": 24,
+      "uid": 30,
       "progress": null,
       "details": {
         "upgradeFrom": "v1.12.0",
@@ -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

@@ -4,7 +4,7 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
 {
   "results": [
     {
-      "uid": 24,
+      "uid": 30,
       "progress": null,
       "details": {
         "upgradeFrom": "v1.12.0",
@@ -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

@@ -4,7 +4,7 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
 {
   "results": [
     {
-      "uid": 24,
+      "uid": 30,
       "progress": null,
       "details": {
         "upgradeFrom": "v1.12.0",
@@ -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

@@ -4,8 +4,8 @@ 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",
@@ -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

@@ -4,8 +4,8 @@ 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",
@@ -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

@@ -4,8 +4,8 @@ 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",
@@ -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/the_whole_batch_queue_once_everything_has_been_processed.snap

@@ -4,7 +4,7 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
 {
   "results": [
     {
-      "uid": 24,
+      "uid": 30,
       "progress": null,
       "details": {
         "upgradeFrom": "v1.12.0",
@@ -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,
@@ -642,8 +791,8 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
       "batchStrategy": "unspecified"
     }
   ],
-  "total": 25,
+  "total": 31,
   "limit": 1000,
-  "from": 24,
+  "from": 30,
   "next": null
 }

crates/meilisearch/tests/upgrade/v1_12/snapshots/v1_12_0.rs/check_the_index_scheduler/the_whole_task_queue_once_everything_has_been_processed.snap

@@ -4,8 +4,8 @@ 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",
@@ -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,
@@ -497,8 +609,8 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
       "finishedAt": "2025-01-16T16:45:16.131303739Z"
     }
   ],
-  "total": 26,
+  "total": 32,
   "limit": 1000,
-  "from": 25,
+  "from": 31,
   "next": null
 }

crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs

@@ -114,13 +114,13 @@ async fn check_the_index_scheduler(server: &Server) {
 
     // All the indexes are still present
     let (indexes, _) = server.list_indexes(None, None).await;
-    snapshot!(indexes, @r#"
+    snapshot!(indexes, @r###"
     {
       "results": [
         {
           "uid": "kefir",
           "createdAt": "2025-01-16T16:45:16.020663157Z",
-          "updatedAt": "2025-01-23T11:36:22.634859166Z",
+          "updatedAt": "2025-07-07T13:43:08.835381Z",
           "primaryKey": "id"
         }
       ],
@@ -128,7 +128,7 @@ async fn check_the_index_scheduler(server: &Server) {
       "limit": 20,
       "total": 1
     }
-    "#);
+    "###);
     // And their metadata are still right
     let (stats, _) = server.stats().await;
     assert_json_snapshot!(stats, {
@@ -141,21 +141,21 @@ async fn check_the_index_scheduler(server: &Server) {
     {
       "databaseSize": "[bytes]",
       "usedDatabaseSize": "[bytes]",
-      "lastUpdate": "2025-01-23T11:36:22.634859166Z",
+      "lastUpdate": "2025-07-07T13:43:08.835381Z",
       "indexes": {
         "kefir": {
-          "numberOfDocuments": 1,
+          "numberOfDocuments": 2,
           "rawDocumentDbSize": "[bytes]",
           "avgDocumentSize": "[bytes]",
           "isIndexing": false,
-          "numberOfEmbeddings": 0,
-          "numberOfEmbeddedDocuments": 0,
+          "numberOfEmbeddings": 2,
+          "numberOfEmbeddedDocuments": 2,
           "fieldDistribution": {
-            "age": 1,
-            "description": 1,
-            "id": 1,
-            "name": 1,
-            "surname": 1
+            "age": 2,
+            "description": 2,
+            "id": 2,
+            "name": 2,
+            "surname": 2
           }
         }
       }
@@ -227,21 +227,21 @@ async fn check_the_index_scheduler(server: &Server) {
     {
       "databaseSize": "[bytes]",
       "usedDatabaseSize": "[bytes]",
-      "lastUpdate": "2025-01-23T11:36:22.634859166Z",
+      "lastUpdate": "2025-07-07T13:43:08.835381Z",
       "indexes": {
         "kefir": {
-          "numberOfDocuments": 1,
+          "numberOfDocuments": 2,
           "rawDocumentDbSize": "[bytes]",
           "avgDocumentSize": "[bytes]",
           "isIndexing": false,
-          "numberOfEmbeddings": 0,
-          "numberOfEmbeddedDocuments": 0,
+          "numberOfEmbeddings": 2,
+          "numberOfEmbeddedDocuments": 2,
           "fieldDistribution": {
-            "age": 1,
-            "description": 1,
-            "id": 1,
-            "name": 1,
-            "surname": 1
+            "age": 2,
+            "description": 2,
+            "id": 2,
+            "name": 2,
+            "surname": 2
           }
         }
       }
@@ -254,18 +254,18 @@ async fn check_the_index_scheduler(server: &Server) {
         ".avgDocumentSize" => "[bytes]",
     }), @r###"
     {
-      "numberOfDocuments": 1,
+      "numberOfDocuments": 2,
       "rawDocumentDbSize": "[bytes]",
       "avgDocumentSize": "[bytes]",
       "isIndexing": false,
-      "numberOfEmbeddings": 0,
-      "numberOfEmbeddedDocuments": 0,
+      "numberOfEmbeddings": 2,
+      "numberOfEmbeddedDocuments": 2,
       "fieldDistribution": {
-        "age": 1,
-        "description": 1,
-        "id": 1,
-        "name": 1,
-        "surname": 1
+        "age": 2,
+        "description": 2,
+        "id": 2,
+        "name": 2,
+        "surname": 2
       }
     }
     "###);
@@ -295,4 +295,8 @@ async fn check_the_index_features(server: &Server) {
     let (results, _status) =
         kefir.search_post(json!({ "sort": ["age:asc"], "filter": "surname = kefirounet" })).await;
     snapshot!(results, name: "search_with_sort_and_filter");
+
+    // ensuring we can get the vectors and their `regenerate` is still good.
+    let (results, _status) = kefir.search_post(json!({"retrieveVectors": true})).await;
+    snapshot!(json_string!(results["hits"], {"[]._vectors.doggo_embedder.embeddings" => "[vector]"}), name: "search_with_retrieve_vectors");
 }

crates/meilisearch/tests/vector/settings.rs

@@ -101,14 +101,7 @@ async fn reset_embedder_documents() {
     server.wait_task(response.uid()).await;
 
     // Make sure the documents are still present
-    let (documents, _code) = index
-        .get_all_documents(GetAllDocumentsOptions {
-            limit: None,
-            offset: None,
-            retrieve_vectors: false,
-            fields: None,
-        })
-        .await;
+    let (documents, _code) = index.get_all_documents(GetAllDocumentsOptions::default()).await;
     snapshot!(json_string!(documents), @r###"
     {
       "results": [

crates/milli/src/asc_desc.rs

@@ -168,6 +168,16 @@ pub enum SortError {
     ReservedNameForFilter { name: String },
 }
 
+impl SortError {
+    pub fn into_search_error(self) -> Error {
+        Error::UserError(UserError::SortError { error: self, search: true })
+    }
+
+    pub fn into_document_error(self) -> Error {
+        Error::UserError(UserError::SortError { error: self, search: false })
+    }
+}
+
 impl From<AscDescError> for SortError {
     fn from(error: AscDescError) -> Self {
         match error {
@@ -190,12 +200,6 @@ impl From<AscDescError> for SortError {
     }
 }
 
-impl From<SortError> for Error {
-    fn from(error: SortError) -> Self {
-        Self::UserError(UserError::SortError(error))
-    }
-}
-
 #[cfg(test)]
 mod tests {
     use big_s::S;

crates/milli/src/documents/geo_sort.rs

@@ -0,0 +1,294 @@
+use crate::{
+    distance_between_two_points,
+    heed_codec::facet::{FieldDocIdFacetCodec, OrderedF64Codec},
+    lat_lng_to_xyz,
+    search::new::{facet_string_values, facet_values_prefix_key},
+    GeoPoint, Index,
+};
+use heed::{
+    types::{Bytes, Unit},
+    RoPrefix, RoTxn,
+};
+use roaring::RoaringBitmap;
+use rstar::RTree;
+use std::collections::VecDeque;
+
+#[derive(Debug, Clone, Copy)]
+pub struct GeoSortParameter {
+    // Define the strategy used by the geo sort
+    pub strategy: GeoSortStrategy,
+    // Limit the number of docs in a single bucket to avoid unexpectedly large overhead
+    pub max_bucket_size: u64,
+    // Considering the errors of GPS and geographical calculations, distances less than distance_error_margin will be treated as equal
+    pub distance_error_margin: f64,
+}
+
+impl Default for GeoSortParameter {
+    fn default() -> Self {
+        Self {
+            strategy: GeoSortStrategy::default(),
+            max_bucket_size: 1000,
+            distance_error_margin: 1.0,
+        }
+    }
+}
+/// Define the strategy used by the geo sort.
+/// The parameter represents the cache size, and, in the case of the Dynamic strategy,
+/// the point where we move from using the iterative strategy to the rtree.
+#[derive(Debug, Clone, Copy)]
+pub enum GeoSortStrategy {
+    AlwaysIterative(usize),
+    AlwaysRtree(usize),
+    Dynamic(usize),
+}
+
+impl Default for GeoSortStrategy {
+    fn default() -> Self {
+        GeoSortStrategy::Dynamic(1000)
+    }
+}
+
+impl GeoSortStrategy {
+    pub fn use_rtree(&self, candidates: usize) -> bool {
+        match self {
+            GeoSortStrategy::AlwaysIterative(_) => false,
+            GeoSortStrategy::AlwaysRtree(_) => true,
+            GeoSortStrategy::Dynamic(i) => candidates >= *i,
+        }
+    }
+
+    pub fn cache_size(&self) -> usize {
+        match self {
+            GeoSortStrategy::AlwaysIterative(i)
+            | GeoSortStrategy::AlwaysRtree(i)
+            | GeoSortStrategy::Dynamic(i) => *i,
+        }
+    }
+}
+
+#[allow(clippy::too_many_arguments)]
+pub fn fill_cache(
+    index: &Index,
+    txn: &RoTxn<heed::AnyTls>,
+    strategy: GeoSortStrategy,
+    ascending: bool,
+    target_point: [f64; 2],
+    field_ids: &Option<[u16; 2]>,
+    rtree: &mut Option<RTree<GeoPoint>>,
+    geo_candidates: &RoaringBitmap,
+    cached_sorted_docids: &mut VecDeque<(u32, [f64; 2])>,
+) -> crate::Result<()> {
+    debug_assert!(cached_sorted_docids.is_empty());
+
+    // lazily initialize the rtree if needed by the strategy, and cache it in `self.rtree`
+    let rtree = if strategy.use_rtree(geo_candidates.len() as usize) {
+        if let Some(rtree) = rtree.as_ref() {
+            // get rtree from cache
+            Some(rtree)
+        } else {
+            let rtree2 = index.geo_rtree(txn)?.expect("geo candidates but no rtree");
+            // insert rtree in cache and returns it.
+            // Can't use `get_or_insert_with` because getting the rtree from the DB is a fallible operation.
+            Some(&*rtree.insert(rtree2))
+        }
+    } else {
+        None
+    };
+
+    let cache_size = strategy.cache_size();
+    if let Some(rtree) = rtree {
+        if ascending {
+            let point = lat_lng_to_xyz(&target_point);
+            for point in rtree.nearest_neighbor_iter(&point) {
+                if geo_candidates.contains(point.data.0) {
+                    cached_sorted_docids.push_back(point.data);
+                    if cached_sorted_docids.len() >= cache_size {
+                        break;
+                    }
+                }
+            }
+        } else {
+            // in the case of the desc geo sort we look for the closest point to the opposite of the queried point
+            // and we insert the points in reverse order they get reversed when emptying the cache later on
+            let point = lat_lng_to_xyz(&opposite_of(target_point));
+            for point in rtree.nearest_neighbor_iter(&point) {
+                if geo_candidates.contains(point.data.0) {
+                    cached_sorted_docids.push_front(point.data);
+                    if cached_sorted_docids.len() >= cache_size {
+                        break;
+                    }
+                }
+            }
+        }
+    } else {
+        // the iterative version
+        let [lat, lng] = field_ids.expect("fill_buffer can't be called without the lat&lng");
+
+        let mut documents = geo_candidates
+            .iter()
+            .map(|id| -> crate::Result<_> { Ok((id, geo_value(id, lat, lng, index, txn)?)) })
+            .collect::<crate::Result<Vec<(u32, [f64; 2])>>>()?;
+        // computing the distance between two points is expensive thus we cache the result
+        documents
+            .sort_by_cached_key(|(_, p)| distance_between_two_points(&target_point, p) as usize);
+        cached_sorted_docids.extend(documents);
+    };
+
+    Ok(())
+}
+
+#[allow(clippy::too_many_arguments)]
+pub fn next_bucket(
+    index: &Index,
+    txn: &RoTxn<heed::AnyTls>,
+    universe: &RoaringBitmap,
+    ascending: bool,
+    target_point: [f64; 2],
+    field_ids: &Option<[u16; 2]>,
+    rtree: &mut Option<RTree<GeoPoint>>,
+    cached_sorted_docids: &mut VecDeque<(u32, [f64; 2])>,
+    geo_candidates: &RoaringBitmap,
+    parameter: GeoSortParameter,
+) -> crate::Result<Option<(RoaringBitmap, Option<[f64; 2]>)>> {
+    let mut geo_candidates = geo_candidates & universe;
+
+    if geo_candidates.is_empty() {
+        return Ok(Some((universe.clone(), None)));
+    }
+
+    let next = |cache: &mut VecDeque<_>| {
+        if ascending {
+            cache.pop_front()
+        } else {
+            cache.pop_back()
+        }
+    };
+    let put_back = |cache: &mut VecDeque<_>, x: _| {
+        if ascending {
+            cache.push_front(x)
+        } else {
+            cache.push_back(x)
+        }
+    };
+
+    let mut current_bucket = RoaringBitmap::new();
+    // current_distance stores the first point and distance in current bucket
+    let mut current_distance: Option<([f64; 2], f64)> = None;
+    loop {
+        // The loop will only exit when we have found all points with equal distance or have exhausted the candidates.
+        if let Some((id, point)) = next(cached_sorted_docids) {
+            if geo_candidates.contains(id) {
+                let distance = distance_between_two_points(&target_point, &point);
+                if let Some((point0, bucket_distance)) = current_distance.as_ref() {
+                    if (bucket_distance - distance).abs() > parameter.distance_error_margin {
+                        // different distance, point belongs to next bucket
+                        put_back(cached_sorted_docids, (id, point));
+                        return Ok(Some((current_bucket, Some(point0.to_owned()))));
+                    } else {
+                        // same distance, point belongs to current bucket
+                        current_bucket.insert(id);
+                        // remove from candidates to prevent it from being added to the cache again
+                        geo_candidates.remove(id);
+                        // current bucket size reaches limit, force return
+                        if current_bucket.len() == parameter.max_bucket_size {
+                            return Ok(Some((current_bucket, Some(point0.to_owned()))));
+                        }
+                    }
+                } else {
+                    // first doc in current bucket
+                    current_distance = Some((point, distance));
+                    current_bucket.insert(id);
+                    geo_candidates.remove(id);
+                    // current bucket size reaches limit, force return
+                    if current_bucket.len() == parameter.max_bucket_size {
+                        return Ok(Some((current_bucket, Some(point.to_owned()))));
+                    }
+                }
+            }
+        } else {
+            // cache exhausted, we need to refill it
+            fill_cache(
+                index,
+                txn,
+                parameter.strategy,
+                ascending,
+                target_point,
+                field_ids,
+                rtree,
+                &geo_candidates,
+                cached_sorted_docids,
+            )?;
+
+            if cached_sorted_docids.is_empty() {
+                // candidates exhausted, exit
+                if let Some((point0, _)) = current_distance.as_ref() {
+                    return Ok(Some((current_bucket, Some(point0.to_owned()))));
+                } else {
+                    return Ok(Some((universe.clone(), None)));
+                }
+            }
+        }
+    }
+}
+
+/// Return an iterator over each number value in the given field of the given document.
+fn facet_number_values<'a>(
+    docid: u32,
+    field_id: u16,
+    index: &Index,
+    txn: &'a RoTxn<'a>,
+) -> crate::Result<RoPrefix<'a, FieldDocIdFacetCodec<OrderedF64Codec>, Unit>> {
+    let key = facet_values_prefix_key(field_id, docid);
+
+    let iter = index
+        .field_id_docid_facet_f64s
+        .remap_key_type::<Bytes>()
+        .prefix_iter(txn, &key)?
+        .remap_key_type();
+
+    Ok(iter)
+}
+
+/// Extracts the lat and long values from a single document.
+///
+/// If it is not able to find it in the facet number index it will extract it
+/// from the facet string index and parse it as f64 (as the geo extraction behaves).
+pub(crate) fn geo_value(
+    docid: u32,
+    field_lat: u16,
+    field_lng: u16,
+    index: &Index,
+    rtxn: &RoTxn<'_>,
+) -> crate::Result<[f64; 2]> {
+    let extract_geo = |geo_field: u16| -> crate::Result<f64> {
+        match facet_number_values(docid, geo_field, index, rtxn)?.next() {
+            Some(Ok(((_, _, geo), ()))) => Ok(geo),
+            Some(Err(e)) => Err(e.into()),
+            None => match facet_string_values(docid, geo_field, index, rtxn)?.next() {
+                Some(Ok((_, geo))) => {
+                    Ok(geo.parse::<f64>().expect("cannot parse geo field as f64"))
+                }
+                Some(Err(e)) => Err(e.into()),
+                None => panic!("A geo faceted document doesn't contain any lat or lng"),
+            },
+        }
+    };
+
+    let lat = extract_geo(field_lat)?;
+    let lng = extract_geo(field_lng)?;
+
+    Ok([lat, lng])
+}
+
+/// Compute the antipodal coordinate of `coord`
+pub(crate) fn opposite_of(mut coord: [f64; 2]) -> [f64; 2] {
+    coord[0] *= -1.;
+    // in the case of x,0 we want to return x,180
+    if coord[1] > 0. {
+        coord[1] -= 180.;
+    } else {
+        coord[1] += 180.;
+    }
+
+    coord
+}

crates/milli/src/documents/mod.rs

@@ -1,8 +1,10 @@
 mod builder;
 mod enriched;
+pub mod geo_sort;
 mod primary_key;
 mod reader;
 mod serde_impl;
+pub mod sort;
 
 use std::fmt::Debug;
 use std::io;
@@ -19,6 +21,7 @@ pub use primary_key::{
 pub use reader::{DocumentsBatchCursor, DocumentsBatchCursorError, DocumentsBatchReader};
 use serde::{Deserialize, Serialize};
 
+pub use self::geo_sort::{GeoSortParameter, GeoSortStrategy};
 use crate::error::{FieldIdMapMissingEntry, InternalError};
 use crate::{FieldId, Object, Result};
 

crates/milli/src/documents/sort.rs

@@ -0,0 +1,444 @@
+use std::collections::{BTreeSet, VecDeque};
+
+use crate::{
+    constants::RESERVED_GEO_FIELD_NAME,
+    documents::{geo_sort::next_bucket, GeoSortParameter},
+    heed_codec::{
+        facet::{FacetGroupKeyCodec, FacetGroupValueCodec},
+        BytesRefCodec,
+    },
+    is_faceted,
+    search::facet::{ascending_facet_sort, descending_facet_sort},
+    AscDesc, DocumentId, Member, UserError,
+};
+use heed::Database;
+use roaring::RoaringBitmap;
+
+#[derive(Debug, Clone, Copy)]
+enum AscDescId {
+    Facet { field_id: u16, ascending: bool },
+    Geo { field_ids: [u16; 2], target_point: [f64; 2], ascending: bool },
+}
+
+/// A [`SortedDocumentsIterator`] allows efficient access to a continuous range of sorted documents.
+/// This is ideal in the context of paginated queries in which only a small number of documents are needed at a time.
+/// Search operations will only be performed upon access.
+pub enum SortedDocumentsIterator<'ctx> {
+    Leaf {
+        /// The exact number of documents remaining
+        size: usize,
+        values: Box<dyn Iterator<Item = DocumentId> + 'ctx>,
+    },
+    Branch {
+        /// The current child, got from the children iterator
+        current_child: Option<Box<SortedDocumentsIterator<'ctx>>>,
+        /// The exact number of documents remaining, excluding documents in the current child
+        next_children_size: usize,
+        /// Iterators to become the current child once it is exhausted
+        next_children:
+            Box<dyn Iterator<Item = crate::Result<SortedDocumentsIteratorBuilder<'ctx>>> + 'ctx>,
+    },
+}
+
+impl SortedDocumentsIterator<'_> {
+    /// Takes care of updating the current child if it is `None`, and also updates the size
+    fn update_current<'ctx>(
+        current_child: &mut Option<Box<SortedDocumentsIterator<'ctx>>>,
+        next_children_size: &mut usize,
+        next_children: &mut Box<
+            dyn Iterator<Item = crate::Result<SortedDocumentsIteratorBuilder<'ctx>>> + 'ctx,
+        >,
+    ) -> crate::Result<()> {
+        if current_child.is_none() {
+            *current_child = match next_children.next() {
+                Some(Ok(builder)) => {
+                    let next_child = Box::new(builder.build()?);
+                    *next_children_size -= next_child.size_hint().0;
+                    Some(next_child)
+                }
+                Some(Err(e)) => return Err(e),
+                None => return Ok(()),
+            };
+        }
+        Ok(())
+    }
+}
+
+impl Iterator for SortedDocumentsIterator<'_> {
+    type Item = crate::Result<DocumentId>;
+
+    /// Implementing the `nth` method allows for efficient access to the nth document in the sorted order.
+    /// It's used by `skip` internally.
+    /// The default implementation of `nth` would iterate over all children, which is inefficient for large datasets.
+    /// This implementation will jump over whole chunks of children until it gets close.
+    fn nth(&mut self, n: usize) -> Option<Self::Item> {
+        if n == 0 {
+            return self.next();
+        }
+
+        // If it's at the leaf level, just forward the call to the values iterator
+        let (current_child, next_children, next_children_size) = match self {
+            SortedDocumentsIterator::Leaf { values, size } => {
+                *size = size.saturating_sub(n);
+                return values.nth(n).map(Ok);
+            }
+            SortedDocumentsIterator::Branch {
+                current_child,
+                next_children,
+                next_children_size,
+            } => (current_child, next_children, next_children_size),
+        };
+
+        // Otherwise don't directly iterate over children, skip them if we know we will go further
+        let mut to_skip = n - 1;
+        while to_skip > 0 {
+            if let Err(e) = SortedDocumentsIterator::update_current(
+                current_child,
+                next_children_size,
+                next_children,
+            ) {
+                return Some(Err(e));
+            }
+            let Some(inner) = current_child else {
+                return None; // No more inner iterators, everything has been consumed.
+            };
+
+            if to_skip >= inner.size_hint().0 {
+                // The current child isn't large enough to contain the nth element.
+                // Skip it and continue with the next one.
+                to_skip -= inner.size_hint().0;
+                *current_child = None;
+                continue;
+            } else {
+                // The current iterator is large enough, so we can forward the call to it.
+                return inner.nth(to_skip + 1);
+            }
+        }
+
+        self.next()
+    }
+
+    /// Iterators need to keep track of their size so that they can be skipped efficiently by the `nth` method.
+    fn size_hint(&self) -> (usize, Option<usize>) {
+        let size = match self {
+            SortedDocumentsIterator::Leaf { size, .. } => *size,
+            SortedDocumentsIterator::Branch {
+                next_children_size,
+                current_child: Some(current_child),
+                ..
+            } => current_child.size_hint().0 + next_children_size,
+            SortedDocumentsIterator::Branch { next_children_size, current_child: None, .. } => {
+                *next_children_size
+            }
+        };
+
+        (size, Some(size))
+    }
+
+    fn next(&mut self) -> Option<Self::Item> {
+        match self {
+            SortedDocumentsIterator::Leaf { values, size } => {
+                let result = values.next().map(Ok);
+                if result.is_some() {
+                    *size -= 1;
+                }
+                result
+            }
+            SortedDocumentsIterator::Branch {
+                current_child,
+                next_children_size,
+                next_children,
+            } => {
+                let mut result = None;
+                while result.is_none() {
+                    // Ensure we have selected an iterator to work with
+                    if let Err(e) = SortedDocumentsIterator::update_current(
+                        current_child,
+                        next_children_size,
+                        next_children,
+                    ) {
+                        return Some(Err(e));
+                    }
+                    let Some(inner) = current_child else {
+                        return None;
+                    };
+
+                    result = inner.next();
+
+                    // If the current iterator is exhausted, we need to try the next one
+                    if result.is_none() {
+                        *current_child = None;
+                    }
+                }
+                result
+            }
+        }
+    }
+}
+
+/// Builder for a [`SortedDocumentsIterator`].
+/// Most builders won't ever be built, because pagination will skip them.
+pub struct SortedDocumentsIteratorBuilder<'ctx> {
+    index: &'ctx crate::Index,
+    rtxn: &'ctx heed::RoTxn<'ctx>,
+    number_db: Database<FacetGroupKeyCodec<BytesRefCodec>, FacetGroupValueCodec>,
+    string_db: Database<FacetGroupKeyCodec<BytesRefCodec>, FacetGroupValueCodec>,
+    fields: &'ctx [AscDescId],
+    candidates: RoaringBitmap,
+    geo_candidates: &'ctx RoaringBitmap,
+}
+
+impl<'ctx> SortedDocumentsIteratorBuilder<'ctx> {
+    /// Performs the sort and builds a [`SortedDocumentsIterator`].
+    fn build(self) -> crate::Result<SortedDocumentsIterator<'ctx>> {
+        let size = self.candidates.len() as usize;
+
+        match self.fields {
+            [] => Ok(SortedDocumentsIterator::Leaf {
+                size,
+                values: Box::new(self.candidates.into_iter()),
+            }),
+            [AscDescId::Facet { field_id, ascending }, next_fields @ ..] => {
+                SortedDocumentsIteratorBuilder::build_facet(
+                    self.index,
+                    self.rtxn,
+                    self.number_db,
+                    self.string_db,
+                    next_fields,
+                    self.candidates,
+                    self.geo_candidates,
+                    *field_id,
+                    *ascending,
+                )
+            }
+            [AscDescId::Geo { field_ids, target_point, ascending }, next_fields @ ..] => {
+                SortedDocumentsIteratorBuilder::build_geo(
+                    self.index,
+                    self.rtxn,
+                    self.number_db,
+                    self.string_db,
+                    next_fields,
+                    self.candidates,
+                    self.geo_candidates,
+                    *field_ids,
+                    *target_point,
+                    *ascending,
+                )
+            }
+        }
+    }
+
+    /// Builds a [`SortedDocumentsIterator`] based on the results of a facet sort.
+    #[allow(clippy::too_many_arguments)]
+    fn build_facet(
+        index: &'ctx crate::Index,
+        rtxn: &'ctx heed::RoTxn<'ctx>,
+        number_db: Database<FacetGroupKeyCodec<BytesRefCodec>, FacetGroupValueCodec>,
+        string_db: Database<FacetGroupKeyCodec<BytesRefCodec>, FacetGroupValueCodec>,
+        next_fields: &'ctx [AscDescId],
+        candidates: RoaringBitmap,
+        geo_candidates: &'ctx RoaringBitmap,
+        field_id: u16,
+        ascending: bool,
+    ) -> crate::Result<SortedDocumentsIterator<'ctx>> {
+        let size = candidates.len() as usize;
+
+        // Perform the sort on the first field
+        let (number_iter, string_iter) = if ascending {
+            let number_iter = ascending_facet_sort(rtxn, number_db, field_id, candidates.clone())?;
+            let string_iter = ascending_facet_sort(rtxn, string_db, field_id, candidates)?;
+
+            (itertools::Either::Left(number_iter), itertools::Either::Left(string_iter))
+        } else {
+            let number_iter = descending_facet_sort(rtxn, number_db, field_id, candidates.clone())?;
+            let string_iter = descending_facet_sort(rtxn, string_db, field_id, candidates)?;
+
+            (itertools::Either::Right(number_iter), itertools::Either::Right(string_iter))
+        };
+
+        // Create builders for the next level of the tree
+        let number_iter = number_iter.map(|r| r.map(|(d, _)| d));
+        let string_iter = string_iter.map(|r| r.map(|(d, _)| d));
+        let next_children = number_iter.chain(string_iter).map(move |r| {
+            Ok(SortedDocumentsIteratorBuilder {
+                index,
+                rtxn,
+                number_db,
+                string_db,
+                fields: next_fields,
+                candidates: r?,
+                geo_candidates,
+            })
+        });
+
+        Ok(SortedDocumentsIterator::Branch {
+            current_child: None,
+            next_children_size: size,
+            next_children: Box::new(next_children),
+        })
+    }
+
+    /// Builds a [`SortedDocumentsIterator`] based on the (lazy) results of a geo sort.
+    #[allow(clippy::too_many_arguments)]
+    fn build_geo(
+        index: &'ctx crate::Index,
+        rtxn: &'ctx heed::RoTxn<'ctx>,
+        number_db: Database<FacetGroupKeyCodec<BytesRefCodec>, FacetGroupValueCodec>,
+        string_db: Database<FacetGroupKeyCodec<BytesRefCodec>, FacetGroupValueCodec>,
+        next_fields: &'ctx [AscDescId],
+        candidates: RoaringBitmap,
+        geo_candidates: &'ctx RoaringBitmap,
+        field_ids: [u16; 2],
+        target_point: [f64; 2],
+        ascending: bool,
+    ) -> crate::Result<SortedDocumentsIterator<'ctx>> {
+        let mut cache = VecDeque::new();
+        let mut rtree = None;
+        let size = candidates.len() as usize;
+        let not_geo_candidates = candidates.clone() - geo_candidates;
+        let mut geo_remaining = size - not_geo_candidates.len() as usize;
+        let mut not_geo_candidates = Some(not_geo_candidates);
+
+        let next_children = std::iter::from_fn(move || {
+            // Find the next bucket of geo-sorted documents.
+            // next_bucket loops and will go back to the beginning so we use a variable to track how many are left.
+            if geo_remaining > 0 {
+                if let Ok(Some((docids, _point))) = next_bucket(
+                    index,
+                    rtxn,
+                    &candidates,
+                    ascending,
+                    target_point,
+                    &Some(field_ids),
+                    &mut rtree,
+                    &mut cache,
+                    geo_candidates,
+                    GeoSortParameter::default(),
+                ) {
+                    geo_remaining -= docids.len() as usize;
+                    return Some(Ok(SortedDocumentsIteratorBuilder {
+                        index,
+                        rtxn,
+                        number_db,
+                        string_db,
+                        fields: next_fields,
+                        candidates: docids,
+                        geo_candidates,
+                    }));
+                }
+            }
+
+            // Once all geo candidates have been processed, we can return the others
+            if let Some(not_geo_candidates) = not_geo_candidates.take() {
+                if !not_geo_candidates.is_empty() {
+                    return Some(Ok(SortedDocumentsIteratorBuilder {
+                        index,
+                        rtxn,
+                        number_db,
+                        string_db,
+                        fields: next_fields,
+                        candidates: not_geo_candidates,
+                        geo_candidates,
+                    }));
+                }
+            }
+
+            None
+        });
+
+        Ok(SortedDocumentsIterator::Branch {
+            current_child: None,
+            next_children_size: size,
+            next_children: Box::new(next_children),
+        })
+    }
+}
+
+/// A structure owning the data needed during the lifetime of a [`SortedDocumentsIterator`].
+pub struct SortedDocuments<'ctx> {
+    index: &'ctx crate::Index,
+    rtxn: &'ctx heed::RoTxn<'ctx>,
+    fields: Vec<AscDescId>,
+    number_db: Database<FacetGroupKeyCodec<BytesRefCodec>, FacetGroupValueCodec>,
+    string_db: Database<FacetGroupKeyCodec<BytesRefCodec>, FacetGroupValueCodec>,
+    candidates: &'ctx RoaringBitmap,
+    geo_candidates: RoaringBitmap,
+}
+
+impl<'ctx> SortedDocuments<'ctx> {
+    pub fn iter(&'ctx self) -> crate::Result<SortedDocumentsIterator<'ctx>> {
+        let builder = SortedDocumentsIteratorBuilder {
+            index: self.index,
+            rtxn: self.rtxn,
+            number_db: self.number_db,
+            string_db: self.string_db,
+            fields: &self.fields,
+            candidates: self.candidates.clone(),
+            geo_candidates: &self.geo_candidates,
+        };
+        builder.build()
+    }
+}
+
+pub fn recursive_sort<'ctx>(
+    index: &'ctx crate::Index,
+    rtxn: &'ctx heed::RoTxn<'ctx>,
+    sort: Vec<AscDesc>,
+    candidates: &'ctx RoaringBitmap,
+) -> crate::Result<SortedDocuments<'ctx>> {
+    let sortable_fields: BTreeSet<_> = index.sortable_fields(rtxn)?.into_iter().collect();
+    let fields_ids_map = index.fields_ids_map(rtxn)?;
+
+    // Retrieve the field ids that are used for sorting
+    let mut fields = Vec::new();
+    let mut need_geo_candidates = false;
+    for asc_desc in sort {
+        let (field, geofield) = match asc_desc {
+            AscDesc::Asc(Member::Field(field)) => (Some((field, true)), None),
+            AscDesc::Desc(Member::Field(field)) => (Some((field, false)), None),
+            AscDesc::Asc(Member::Geo(target_point)) => (None, Some((target_point, true))),
+            AscDesc::Desc(Member::Geo(target_point)) => (None, Some((target_point, false))),
+        };
+        if let Some((field, ascending)) = field {
+            if is_faceted(&field, &sortable_fields) {
+                if let Some(field_id) = fields_ids_map.id(&field) {
+                    fields.push(AscDescId::Facet { field_id, ascending });
+                    continue;
+                }
+            }
+            return Err(UserError::InvalidDocumentSortableAttribute {
+                field: field.to_string(),
+                sortable_fields: sortable_fields.clone(),
+            }
+            .into());
+        }
+        if let Some((target_point, ascending)) = geofield {
+            if sortable_fields.contains(RESERVED_GEO_FIELD_NAME) {
+                if let (Some(lat), Some(lng)) =
+                    (fields_ids_map.id("_geo.lat"), fields_ids_map.id("_geo.lng"))
+                {
+                    need_geo_candidates = true;
+                    fields.push(AscDescId::Geo { field_ids: [lat, lng], target_point, ascending });
+                    continue;
+                }
+            }
+            return Err(UserError::InvalidDocumentSortableAttribute {
+                field: RESERVED_GEO_FIELD_NAME.to_string(),
+                sortable_fields: sortable_fields.clone(),
+            }
+            .into());
+        }
+    }
+
+    let geo_candidates = if need_geo_candidates {
+        index.geo_faceted_documents_ids(rtxn)?
+    } else {
+        RoaringBitmap::new()
+    };
+
+    let number_db = index.facet_id_f64_docids.remap_key_type::<FacetGroupKeyCodec<BytesRefCodec>>();
+    let string_db =
+        index.facet_id_string_docids.remap_key_type::<FacetGroupKeyCodec<BytesRefCodec>>();
+
+    Ok(SortedDocuments { index, rtxn, fields, number_db, string_db, candidates, geo_candidates })
+}

crates/milli/src/error.rs

@@ -191,7 +191,21 @@ and can not be more than 511 bytes.", .document_id.to_string()
                 ),
         }
     )]
-    InvalidSortableAttribute { field: String, valid_fields: BTreeSet<String>, hidden_fields: bool },
+    InvalidSearchSortableAttribute {
+        field: String,
+        valid_fields: BTreeSet<String>,
+        hidden_fields: bool,
+    },
+    #[error("Attribute `{}` is not sortable. {}",
+        .field,
+        match .sortable_fields.is_empty() {
+            true => "This index does not have configured sortable attributes.".to_string(),
+            false => format!("Available sortable attributes are: `{}`.",
+                    sortable_fields.iter().map(AsRef::as_ref).collect::<Vec<&str>>().join(", ")
+                ),
+        }
+    )]
+    InvalidDocumentSortableAttribute { field: String, sortable_fields: BTreeSet<String> },
     #[error("Attribute `{}` is not filterable and thus, cannot be used as distinct attribute. {}",
         .field,
         match (.valid_patterns.is_empty(), .matching_rule_index) {
@@ -272,8 +286,8 @@ and can not be more than 511 bytes.", .document_id.to_string()
     PrimaryKeyCannotBeChanged(String),
     #[error(transparent)]
     SerdeJson(serde_json::Error),
-    #[error(transparent)]
-    SortError(#[from] SortError),
+    #[error("{error}")]
+    SortError { error: SortError, search: bool },
     #[error("An unknown internal document id have been used: `{document_id}`.")]
     UnknownInternalDocumentId { document_id: DocumentId },
     #[error("`minWordSizeForTypos` setting is invalid. `oneTypo` and `twoTypos` fields should be between `0` and `255`, and `twoTypos` should be greater or equals to `oneTypo` but found `oneTypo: {0}` and twoTypos: {1}`.")]
@@ -616,7 +630,7 @@ fn conditionally_lookup_for_error_message() {
     ];
 
     for (list, suffix) in messages {
-        let err = UserError::InvalidSortableAttribute {
+        let err = UserError::InvalidSearchSortableAttribute {
             field: "name".to_string(),
             valid_fields: list,
             hidden_fields: false,

crates/milli/src/lib.rs

@@ -43,12 +43,13 @@ use std::fmt;
 use std::hash::BuildHasherDefault;
 
 use charabia::normalizer::{CharNormalizer, CompatibilityDecompositionNormalizer};
+pub use documents::GeoSortStrategy;
 pub use filter_parser::{Condition, FilterCondition, Span, Token};
 use fxhash::{FxHasher32, FxHasher64};
 pub use grenad::CompressionType;
 pub use search::new::{
-    execute_search, filtered_universe, DefaultSearchLogger, GeoSortStrategy, SearchContext,
-    SearchLogger, VisualSearchLogger,
+    execute_search, filtered_universe, DefaultSearchLogger, SearchContext, SearchLogger,
+    VisualSearchLogger,
 };
 use serde_json::Value;
 pub use thread_pool_no_abort::{PanicCatched, ThreadPoolNoAbort, ThreadPoolNoAbortBuilder};

crates/milli/src/search/hybrid.rs

@@ -210,6 +210,7 @@ impl Search<'_> {
             scoring_strategy: ScoringStrategy::Detailed,
             words_limit: self.words_limit,
             exhaustive_number_hits: self.exhaustive_number_hits,
+            max_total_hits: self.max_total_hits,
             rtxn: self.rtxn,
             index: self.index,
             semantic: self.semantic.clone(),

crates/milli/src/search/mod.rs

@@ -9,6 +9,7 @@ use roaring::bitmap::RoaringBitmap;
 pub use self::facet::{FacetDistribution, Filter, OrderBy, DEFAULT_VALUES_PER_FACET};
 pub use self::new::matches::{FormatOptions, MatchBounds, MatcherBuilder, MatchingWords};
 use self::new::{execute_vector_search, PartialSearchResult, VectorStoreStats};
+use crate::documents::GeoSortParameter;
 use crate::filterable_attributes_rules::{filtered_matching_patterns, matching_features};
 use crate::index::MatchingStrategy;
 use crate::score_details::{ScoreDetails, ScoringStrategy};
@@ -47,11 +48,12 @@ pub struct Search<'a> {
     sort_criteria: Option<Vec<AscDesc>>,
     distinct: Option<String>,
     searchable_attributes: Option<&'a [String]>,
-    geo_param: new::GeoSortParameter,
+    geo_param: GeoSortParameter,
     terms_matching_strategy: TermsMatchingStrategy,
     scoring_strategy: ScoringStrategy,
     words_limit: usize,
     exhaustive_number_hits: bool,
+    max_total_hits: Option<usize>,
     rtxn: &'a heed::RoTxn<'a>,
     index: &'a Index,
     semantic: Option<SemanticSearch>,
@@ -70,10 +72,11 @@ impl<'a> Search<'a> {
             sort_criteria: None,
             distinct: None,
             searchable_attributes: None,
-            geo_param: new::GeoSortParameter::default(),
+            geo_param: GeoSortParameter::default(),
             terms_matching_strategy: TermsMatchingStrategy::default(),
             scoring_strategy: Default::default(),
             exhaustive_number_hits: false,
+            max_total_hits: None,
             words_limit: 10,
             rtxn,
             index,
@@ -147,7 +150,7 @@ impl<'a> Search<'a> {
     }
 
     #[cfg(test)]
-    pub fn geo_sort_strategy(&mut self, strategy: new::GeoSortStrategy) -> &mut Search<'a> {
+    pub fn geo_sort_strategy(&mut self, strategy: crate::GeoSortStrategy) -> &mut Search<'a> {
         self.geo_param.strategy = strategy;
         self
     }
@@ -165,6 +168,11 @@ impl<'a> Search<'a> {
         self
     }
 
+    pub fn max_total_hits(&mut self, max_total_hits: Option<usize>) -> &mut Search<'a> {
+        self.max_total_hits = max_total_hits;
+        self
+    }
+
     pub fn time_budget(&mut self, time_budget: TimeBudget) -> &mut Search<'a> {
         self.time_budget = time_budget;
         self
@@ -243,6 +251,8 @@ impl<'a> Search<'a> {
                 &mut ctx,
                 vector,
                 self.scoring_strategy,
+                self.exhaustive_number_hits,
+                self.max_total_hits,
                 universe,
                 &self.sort_criteria,
                 &self.distinct,
@@ -261,6 +271,7 @@ impl<'a> Search<'a> {
                 self.terms_matching_strategy,
                 self.scoring_strategy,
                 self.exhaustive_number_hits,
+                self.max_total_hits,
                 universe,
                 &self.sort_criteria,
                 &self.distinct,
@@ -314,6 +325,7 @@ impl fmt::Debug for Search<'_> {
             scoring_strategy,
             words_limit,
             exhaustive_number_hits,
+            max_total_hits,
             rtxn: _,
             index: _,
             semantic,
@@ -333,6 +345,7 @@ impl fmt::Debug for Search<'_> {
             .field("terms_matching_strategy", terms_matching_strategy)
             .field("scoring_strategy", scoring_strategy)
             .field("exhaustive_number_hits", exhaustive_number_hits)
+            .field("max_total_hits", max_total_hits)
             .field("words_limit", words_limit)
             .field(
                 "semantic.embedder_name",

crates/milli/src/search/new/bucket_sort.rs

@@ -32,6 +32,8 @@ pub fn bucket_sort<'ctx, Q: RankingRuleQueryTrait>(
     logger: &mut dyn SearchLogger<Q>,
     time_budget: TimeBudget,
     ranking_score_threshold: Option<f64>,
+    exhaustive_number_hits: bool,
+    max_total_hits: Option<usize>,
 ) -> Result<BucketSortOutput> {
     logger.initial_query(query);
     logger.ranking_rules(&ranking_rules);
@@ -159,7 +161,13 @@ pub fn bucket_sort<'ctx, Q: RankingRuleQueryTrait>(
         };
     }
 
-    while valid_docids.len() < length {
+    let max_len_to_evaluate =
+        match (max_total_hits, exhaustive_number_hits && ranking_score_threshold.is_some()) {
+            (Some(max_total_hits), true) => max_total_hits,
+            _ => length,
+        };
+
+    while valid_docids.len() < max_len_to_evaluate {
         if time_budget.exceeded() {
             loop {
                 let bucket = std::mem::take(&mut ranking_rule_universes[cur_ranking_rule_index]);

crates/milli/src/search/new/distinct.rs

@@ -82,7 +82,7 @@ fn facet_value_docids(
 }
 
 /// Return an iterator over each number value in the given field of the given document.
-fn facet_number_values<'a>(
+pub(crate) fn facet_number_values<'a>(
     docid: u32,
     field_id: u16,
     index: &Index,
@@ -118,7 +118,7 @@ pub fn facet_string_values<'a>(
 }
 
 #[allow(clippy::drop_non_drop)]
-fn facet_values_prefix_key(distinct: u16, id: u32) -> [u8; FID_SIZE + DOCID_SIZE] {
+pub(crate) fn facet_values_prefix_key(distinct: u16, id: u32) -> [u8; FID_SIZE + DOCID_SIZE] {
     concat_arrays::concat_arrays!(distinct.to_be_bytes(), id.to_be_bytes())
 }
 

crates/milli/src/search/new/geo_sort.rs

@@ -1,96 +1,18 @@
 use std::collections::VecDeque;
 
-use heed::types::{Bytes, Unit};
-use heed::{RoPrefix, RoTxn};
 use roaring::RoaringBitmap;
 use rstar::RTree;
 
-use super::facet_string_values;
 use super::ranking_rules::{RankingRule, RankingRuleOutput, RankingRuleQueryTrait};
-use crate::heed_codec::facet::{FieldDocIdFacetCodec, OrderedF64Codec};
+use crate::documents::geo_sort::{fill_cache, next_bucket};
+use crate::documents::{GeoSortParameter, GeoSortStrategy};
 use crate::score_details::{self, ScoreDetails};
-use crate::{
-    distance_between_two_points, lat_lng_to_xyz, GeoPoint, Index, Result, SearchContext,
-    SearchLogger,
-};
-
-const FID_SIZE: usize = 2;
-const DOCID_SIZE: usize = 4;
-
-#[allow(clippy::drop_non_drop)]
-fn facet_values_prefix_key(distinct: u16, id: u32) -> [u8; FID_SIZE + DOCID_SIZE] {
-    concat_arrays::concat_arrays!(distinct.to_be_bytes(), id.to_be_bytes())
-}
-
-/// Return an iterator over each number value in the given field of the given document.
-fn facet_number_values<'a>(
-    docid: u32,
-    field_id: u16,
-    index: &Index,
-    txn: &'a RoTxn<'a>,
-) -> Result<RoPrefix<'a, FieldDocIdFacetCodec<OrderedF64Codec>, Unit>> {
-    let key = facet_values_prefix_key(field_id, docid);
-
-    let iter = index
-        .field_id_docid_facet_f64s
-        .remap_key_type::<Bytes>()
-        .prefix_iter(txn, &key)?
-        .remap_key_type();
-
-    Ok(iter)
-}
-
-#[derive(Debug, Clone, Copy)]
-pub struct Parameter {
-    // Define the strategy used by the geo sort
-    pub strategy: Strategy,
-    // Limit the number of docs in a single bucket to avoid unexpectedly large overhead
-    pub max_bucket_size: u64,
-    // Considering the errors of GPS and geographical calculations, distances less than distance_error_margin will be treated as equal
-    pub distance_error_margin: f64,
-}
-
-impl Default for Parameter {
-    fn default() -> Self {
-        Self { strategy: Strategy::default(), max_bucket_size: 1000, distance_error_margin: 1.0 }
-    }
-}
-/// Define the strategy used by the geo sort.
-/// The parameter represents the cache size, and, in the case of the Dynamic strategy,
-/// the point where we move from using the iterative strategy to the rtree.
-#[derive(Debug, Clone, Copy)]
-pub enum Strategy {
-    AlwaysIterative(usize),
-    AlwaysRtree(usize),
-    Dynamic(usize),
-}
-
-impl Default for Strategy {
-    fn default() -> Self {
-        Strategy::Dynamic(1000)
-    }
-}
-
-impl Strategy {
-    pub fn use_rtree(&self, candidates: usize) -> bool {
-        match self {
-            Strategy::AlwaysIterative(_) => false,
-            Strategy::AlwaysRtree(_) => true,
-            Strategy::Dynamic(i) => candidates >= *i,
-        }
-    }
-
-    pub fn cache_size(&self) -> usize {
-        match self {
-            Strategy::AlwaysIterative(i) | Strategy::AlwaysRtree(i) | Strategy::Dynamic(i) => *i,
-        }
-    }
-}
+use crate::{GeoPoint, Result, SearchContext, SearchLogger};
 
 pub struct GeoSort<Q: RankingRuleQueryTrait> {
     query: Option<Q>,
 
-    strategy: Strategy,
+    strategy: GeoSortStrategy,
     ascending: bool,
     point: [f64; 2],
     field_ids: Option<[u16; 2]>,
@@ -107,12 +29,12 @@ pub struct GeoSort<Q: RankingRuleQueryTrait> {
 
 impl<Q: RankingRuleQueryTrait> GeoSort<Q> {
     pub fn new(
-        parameter: Parameter,
+        parameter: GeoSortParameter,
         geo_faceted_docids: RoaringBitmap,
         point: [f64; 2],
         ascending: bool,
     ) -> Result<Self> {
-        let Parameter { strategy, max_bucket_size, distance_error_margin } = parameter;
+        let GeoSortParameter { strategy, max_bucket_size, distance_error_margin } = parameter;
         Ok(Self {
             query: None,
             strategy,
@@ -134,98 +56,22 @@ impl<Q: RankingRuleQueryTrait> GeoSort<Q> {
         ctx: &mut SearchContext<'_>,
         geo_candidates: &RoaringBitmap,
     ) -> Result<()> {
-        debug_assert!(self.field_ids.is_some(), "fill_buffer can't be called without the lat&lng");
-        debug_assert!(self.cached_sorted_docids.is_empty());
-
-        // lazily initialize the rtree if needed by the strategy, and cache it in `self.rtree`
-        let rtree = if self.strategy.use_rtree(geo_candidates.len() as usize) {
-            if let Some(rtree) = self.rtree.as_ref() {
-                // get rtree from cache
-                Some(rtree)
-            } else {
-                let rtree = ctx.index.geo_rtree(ctx.txn)?.expect("geo candidates but no rtree");
-                // insert rtree in cache and returns it.
-                // Can't use `get_or_insert_with` because getting the rtree from the DB is a fallible operation.
-                Some(&*self.rtree.insert(rtree))
-            }
-        } else {
-            None
-        };
-
-        let cache_size = self.strategy.cache_size();
-        if let Some(rtree) = rtree {
-            if self.ascending {
-                let point = lat_lng_to_xyz(&self.point);
-                for point in rtree.nearest_neighbor_iter(&point) {
-                    if geo_candidates.contains(point.data.0) {
-                        self.cached_sorted_docids.push_back(point.data);
-                        if self.cached_sorted_docids.len() >= cache_size {
-                            break;
-                        }
-                    }
-                }
-            } else {
-                // in the case of the desc geo sort we look for the closest point to the opposite of the queried point
-                // and we insert the points in reverse order they get reversed when emptying the cache later on
-                let point = lat_lng_to_xyz(&opposite_of(self.point));
-                for point in rtree.nearest_neighbor_iter(&point) {
-                    if geo_candidates.contains(point.data.0) {
-                        self.cached_sorted_docids.push_front(point.data);
-                        if self.cached_sorted_docids.len() >= cache_size {
-                            break;
-                        }
-                    }
-                }
-            }
-        } else {
-            // the iterative version
-            let [lat, lng] = self.field_ids.unwrap();
-
-            let mut documents = geo_candidates
-                .iter()
-                .map(|id| -> Result<_> { Ok((id, geo_value(id, lat, lng, ctx.index, ctx.txn)?)) })
-                .collect::<Result<Vec<(u32, [f64; 2])>>>()?;
-            // computing the distance between two points is expensive thus we cache the result
-            documents
-                .sort_by_cached_key(|(_, p)| distance_between_two_points(&self.point, p) as usize);
-            self.cached_sorted_docids.extend(documents);
-        };
+        fill_cache(
+            ctx.index,
+            ctx.txn,
+            self.strategy,
+            self.ascending,
+            self.point,
+            &self.field_ids,
+            &mut self.rtree,
+            geo_candidates,
+            &mut self.cached_sorted_docids,
+        )?;
 
         Ok(())
     }
 }
 
-/// Extracts the lat and long values from a single document.
-///
-/// If it is not able to find it in the facet number index it will extract it
-/// from the facet string index and parse it as f64 (as the geo extraction behaves).
-fn geo_value(
-    docid: u32,
-    field_lat: u16,
-    field_lng: u16,
-    index: &Index,
-    rtxn: &RoTxn<'_>,
-) -> Result<[f64; 2]> {
-    let extract_geo = |geo_field: u16| -> Result<f64> {
-        match facet_number_values(docid, geo_field, index, rtxn)?.next() {
-            Some(Ok(((_, _, geo), ()))) => Ok(geo),
-            Some(Err(e)) => Err(e.into()),
-            None => match facet_string_values(docid, geo_field, index, rtxn)?.next() {
-                Some(Ok((_, geo))) => {
-                    Ok(geo.parse::<f64>().expect("cannot parse geo field as f64"))
-                }
-                Some(Err(e)) => Err(e.into()),
-                None => panic!("A geo faceted document doesn't contain any lat or lng"),
-            },
-        }
-    };
-
-    let lat = extract_geo(field_lat)?;
-    let lng = extract_geo(field_lng)?;
-
-    Ok([lat, lng])
-}
-
 impl<'ctx, Q: RankingRuleQueryTrait> RankingRule<'ctx, Q> for GeoSort<Q> {
     fn id(&self) -> String {
         "geo_sort".to_owned()
@@ -267,124 +113,33 @@ impl<'ctx, Q: RankingRuleQueryTrait> RankingRule<'ctx, Q> for GeoSort<Q> {
     ) -> Result<Option<RankingRuleOutput<Q>>> {
         let query = self.query.as_ref().unwrap().clone();
 
-        let mut geo_candidates = &self.geo_candidates & universe;
-
-        if geo_candidates.is_empty() {
-            return Ok(Some(RankingRuleOutput {
+        next_bucket(
+            ctx.index,
+            ctx.txn,
+            universe,
+            self.ascending,
+            self.point,
+            &self.field_ids,
+            &mut self.rtree,
+            &mut self.cached_sorted_docids,
+            &self.geo_candidates,
+            GeoSortParameter {
+                strategy: self.strategy,
+                max_bucket_size: self.max_bucket_size,
+                distance_error_margin: self.distance_error_margin,
+            },
+        )
+        .map(|o| {
+            o.map(|(candidates, point)| RankingRuleOutput {
                 query,
-                candidates: universe.clone(),
+                candidates,
                 score: ScoreDetails::GeoSort(score_details::GeoSort {
                     target_point: self.point,
                     ascending: self.ascending,
-                    value: None,
+                    value: point,
                 }),
-            }));
-        }
-
-        let ascending = self.ascending;
-        let next = |cache: &mut VecDeque<_>| {
-            if ascending {
-                cache.pop_front()
-            } else {
-                cache.pop_back()
-            }
-        };
-        let put_back = |cache: &mut VecDeque<_>, x: _| {
-            if ascending {
-                cache.push_front(x)
-            } else {
-                cache.push_back(x)
-            }
-        };
-
-        let mut current_bucket = RoaringBitmap::new();
-        // current_distance stores the first point and distance in current bucket
-        let mut current_distance: Option<([f64; 2], f64)> = None;
-        loop {
-            // The loop will only exit when we have found all points with equal distance or have exhausted the candidates.
-            if let Some((id, point)) = next(&mut self.cached_sorted_docids) {
-                if geo_candidates.contains(id) {
-                    let distance = distance_between_two_points(&self.point, &point);
-                    if let Some((point0, bucket_distance)) = current_distance.as_ref() {
-                        if (bucket_distance - distance).abs() > self.distance_error_margin {
-                            // different distance, point belongs to next bucket
-                            put_back(&mut self.cached_sorted_docids, (id, point));
-                            return Ok(Some(RankingRuleOutput {
-                                query,
-                                candidates: current_bucket,
-                                score: ScoreDetails::GeoSort(score_details::GeoSort {
-                                    target_point: self.point,
-                                    ascending: self.ascending,
-                                    value: Some(point0.to_owned()),
-                                }),
-                            }));
-                        } else {
-                            // same distance, point belongs to current bucket
-                            current_bucket.insert(id);
-                            // remove from cadidates to prevent it from being added to the cache again
-                            geo_candidates.remove(id);
-                            // current bucket size reaches limit, force return
-                            if current_bucket.len() == self.max_bucket_size {
-                                return Ok(Some(RankingRuleOutput {
-                                    query,
-                                    candidates: current_bucket,
-                                    score: ScoreDetails::GeoSort(score_details::GeoSort {
-                                        target_point: self.point,
-                                        ascending: self.ascending,
-                                        value: Some(point0.to_owned()),
-                                    }),
-                                }));
-                            }
-                        }
-                    } else {
-                        // first doc in current bucket
-                        current_distance = Some((point, distance));
-                        current_bucket.insert(id);
-                        geo_candidates.remove(id);
-                        // current bucket size reaches limit, force return
-                        if current_bucket.len() == self.max_bucket_size {
-                            return Ok(Some(RankingRuleOutput {
-                                query,
-                                candidates: current_bucket,
-                                score: ScoreDetails::GeoSort(score_details::GeoSort {
-                                    target_point: self.point,
-                                    ascending: self.ascending,
-                                    value: Some(point.to_owned()),
-                                }),
-                            }));
-                        }
-                    }
-                }
-            } else {
-                // cache exhausted, we need to refill it
-                self.fill_buffer(ctx, &geo_candidates)?;
-
-                if self.cached_sorted_docids.is_empty() {
-                    // candidates exhausted, exit
-                    if let Some((point0, _)) = current_distance.as_ref() {
-                        return Ok(Some(RankingRuleOutput {
-                            query,
-                            candidates: current_bucket,
-                            score: ScoreDetails::GeoSort(score_details::GeoSort {
-                                target_point: self.point,
-                                ascending: self.ascending,
-                                value: Some(point0.to_owned()),
-                            }),
-                        }));
-                    } else {
-                        return Ok(Some(RankingRuleOutput {
-                            query,
-                            candidates: universe.clone(),
-                            score: ScoreDetails::GeoSort(score_details::GeoSort {
-                                target_point: self.point,
-                                ascending: self.ascending,
-                                value: None,
-                            }),
-                        }));
-                    }
-                }
-            }
-        }
+            })
+        })
     }
 
     #[tracing::instrument(level = "trace", skip_all, target = "search::geo_sort")]
@@ -394,16 +149,3 @@ impl<'ctx, Q: RankingRuleQueryTrait> RankingRule<'ctx, Q> for GeoSort<Q> {
         self.cached_sorted_docids.clear();
     }
 }
-
-/// Compute the antipodal coordinate of `coord`
-fn opposite_of(mut coord: [f64; 2]) -> [f64; 2] {
-    coord[0] *= -1.;
-    // in the case of x,0 we want to return x,180
-    if coord[1] > 0. {
-        coord[1] -= 180.;
-    } else {
-        coord[1] += 180.;
-    }
-
-    coord
-}

crates/milli/src/search/new/matches/mod.rs

@@ -510,6 +510,7 @@ mod tests {
                 crate::TermsMatchingStrategy::default(),
                 crate::score_details::ScoringStrategy::Skip,
                 false,
+                None,
                 universe,
                 &None,
                 &None,

crates/milli/src/search/new/mod.rs

@@ -1,7 +1,7 @@
 mod bucket_sort;
 mod db_cache;
 mod distinct;
-mod geo_sort;
+pub(crate) mod geo_sort;
 mod graph_based_ranking_rule;
 mod interner;
 mod limits;
@@ -46,14 +46,14 @@ use resolve_query_graph::{compute_query_graph_docids, PhraseDocIdsCache};
 use roaring::RoaringBitmap;
 use sort::Sort;
 
-use self::distinct::facet_string_values;
+pub(crate) use self::distinct::{facet_string_values, facet_values_prefix_key};
 use self::geo_sort::GeoSort;
-pub use self::geo_sort::{Parameter as GeoSortParameter, Strategy as GeoSortStrategy};
 use self::graph_based_ranking_rule::Words;
 use self::interner::Interned;
 use self::vector_sort::VectorSort;
 use crate::attribute_patterns::{match_pattern, PatternMatch};
 use crate::constants::RESERVED_GEO_FIELD_NAME;
+use crate::documents::GeoSortParameter;
 use crate::index::PrefixSearch;
 use crate::localized_attributes_rules::LocalizedFieldIds;
 use crate::score_details::{ScoreDetails, ScoringStrategy};
@@ -319,7 +319,7 @@ fn resolve_negative_phrases(
 fn get_ranking_rules_for_placeholder_search<'ctx>(
     ctx: &SearchContext<'ctx>,
     sort_criteria: &Option<Vec<AscDesc>>,
-    geo_param: geo_sort::Parameter,
+    geo_param: GeoSortParameter,
 ) -> Result<Vec<BoxRankingRule<'ctx, PlaceholderQuery>>> {
     let mut sort = false;
     let mut sorted_fields = HashSet::new();
@@ -371,7 +371,7 @@ fn get_ranking_rules_for_placeholder_search<'ctx>(
 fn get_ranking_rules_for_vector<'ctx>(
     ctx: &SearchContext<'ctx>,
     sort_criteria: &Option<Vec<AscDesc>>,
-    geo_param: geo_sort::Parameter,
+    geo_param: GeoSortParameter,
     limit_plus_offset: usize,
     target: &[f32],
     embedder_name: &str,
@@ -448,7 +448,7 @@ fn get_ranking_rules_for_vector<'ctx>(
 fn get_ranking_rules_for_query_graph_search<'ctx>(
     ctx: &SearchContext<'ctx>,
     sort_criteria: &Option<Vec<AscDesc>>,
-    geo_param: geo_sort::Parameter,
+    geo_param: GeoSortParameter,
     terms_matching_strategy: TermsMatchingStrategy,
 ) -> Result<Vec<BoxRankingRule<'ctx, QueryGraph>>> {
     // query graph search
@@ -559,7 +559,7 @@ fn resolve_sort_criteria<'ctx, Query: RankingRuleQueryTrait>(
     ranking_rules: &mut Vec<BoxRankingRule<'ctx, Query>>,
     sorted_fields: &mut HashSet<String>,
     geo_sorted: &mut bool,
-    geo_param: geo_sort::Parameter,
+    geo_param: GeoSortParameter,
 ) -> Result<()> {
     let sort_criteria = sort_criteria.clone().unwrap_or_default();
     ranking_rules.reserve(sort_criteria.len());
@@ -626,10 +626,12 @@ pub fn execute_vector_search(
     ctx: &mut SearchContext<'_>,
     vector: &[f32],
     scoring_strategy: ScoringStrategy,
+    exhaustive_number_hits: bool,
+    max_total_hits: Option<usize>,
     universe: RoaringBitmap,
     sort_criteria: &Option<Vec<AscDesc>>,
     distinct: &Option<String>,
-    geo_param: geo_sort::Parameter,
+    geo_param: GeoSortParameter,
     from: usize,
     length: usize,
     embedder_name: &str,
@@ -669,6 +671,8 @@ pub fn execute_vector_search(
         placeholder_search_logger,
         time_budget,
         ranking_score_threshold,
+        exhaustive_number_hits,
+        max_total_hits,
     )?;
 
     Ok(PartialSearchResult {
@@ -689,10 +693,11 @@ pub fn execute_search(
     terms_matching_strategy: TermsMatchingStrategy,
     scoring_strategy: ScoringStrategy,
     exhaustive_number_hits: bool,
+    max_total_hits: Option<usize>,
     mut universe: RoaringBitmap,
     sort_criteria: &Option<Vec<AscDesc>>,
     distinct: &Option<String>,
-    geo_param: geo_sort::Parameter,
+    geo_param: GeoSortParameter,
     from: usize,
     length: usize,
     words_limit: Option<usize>,
@@ -825,6 +830,8 @@ pub fn execute_search(
             query_graph_logger,
             time_budget,
             ranking_score_threshold,
+            exhaustive_number_hits,
+            max_total_hits,
         )?
     } else {
         let ranking_rules =
@@ -841,6 +848,8 @@ pub fn execute_search(
             placeholder_search_logger,
             time_budget,
             ranking_score_threshold,
+            exhaustive_number_hits,
+            max_total_hits,
         )?
     };
 
@@ -872,7 +881,7 @@ pub fn execute_search(
     })
 }
 
-fn check_sort_criteria(
+pub(crate) fn check_sort_criteria(
     ctx: &SearchContext<'_>,
     sort_criteria: Option<&Vec<AscDesc>>,
 ) -> Result<()> {
@@ -902,7 +911,7 @@ fn check_sort_criteria(
                 let (valid_fields, hidden_fields) =
                     ctx.index.remove_hidden_fields(ctx.txn, sortable_fields)?;
 
-                return Err(UserError::InvalidSortableAttribute {
+                return Err(UserError::InvalidSearchSortableAttribute {
                     field: field.to_string(),
                     valid_fields,
                     hidden_fields,
@@ -913,7 +922,7 @@ fn check_sort_criteria(
                 let (valid_fields, hidden_fields) =
                     ctx.index.remove_hidden_fields(ctx.txn, sortable_fields)?;
 
-                return Err(UserError::InvalidSortableAttribute {
+                return Err(UserError::InvalidSearchSortableAttribute {
                     field: RESERVED_GEO_FIELD_NAME.to_string(),
                     valid_fields,
                     hidden_fields,

crates/milli/src/update/new/channel.rs

@@ -575,6 +575,63 @@ impl<'b> ExtractorBbqueueSender<'b> {
         Ok(())
     }
 
+    fn set_vectors_flat(
+        &self,
+        docid: u32,
+        embedder_id: u8,
+        dimensions: usize,
+        flat_embeddings: &[f32],
+    ) -> crate::Result<()> {
+        let max_grant = self.max_grant;
+        let refcell = self.producers.get().unwrap();
+        let mut producer = refcell.0.borrow_mut_or_yield();
+
+        let arroy_set_vector = ArroySetVectors { docid, embedder_id, _padding: [0; 3] };
+        let payload_header = EntryHeader::ArroySetVectors(arroy_set_vector);
+        // we are taking the number of floats in the flat embeddings so we mustn't use the dimensions here
+        let total_length = EntryHeader::total_set_vectors_size(flat_embeddings.len(), 1);
+        if total_length > max_grant {
+            let mut value_file = tempfile::tempfile().map(BufWriter::new)?;
+
+            let mut embedding_bytes = bytemuck::cast_slice(flat_embeddings);
+            io::copy(&mut embedding_bytes, &mut value_file)?;
+
+            let value_file = value_file.into_inner().map_err(|ie| ie.into_error())?;
+            let embeddings = unsafe { Mmap::map(&value_file)? };
+
+            let large_vectors = LargeVectors { docid, embedder_id, embeddings };
+            self.sender.send(ReceiverAction::LargeVectors(large_vectors)).unwrap();
+
+            return Ok(());
+        }
+
+        // Spin loop to have a frame the size we requested.
+        reserve_and_write_grant(
+            &mut producer,
+            total_length,
+            &self.sender,
+            &self.sent_messages_attempts,
+            &self.blocking_sent_messages_attempts,
+            |grant| {
+                let header_size = payload_header.header_size();
+                let (header_bytes, remaining) = grant.split_at_mut(header_size);
+                payload_header.serialize_into(header_bytes);
+
+                if dimensions != 0 {
+                    let output_iter =
+                        remaining.chunks_exact_mut(dimensions * mem::size_of::<f32>());
+                    for (embedding, output) in flat_embeddings.chunks(dimensions).zip(output_iter) {
+                        output.copy_from_slice(bytemuck::cast_slice(embedding));
+                    }
+                }
+
+                Ok(())
+            },
+        )?;
+
+        Ok(())
+    }
+
     fn set_vectors(
         &self,
         docid: u32,
@@ -640,7 +697,7 @@ impl<'b> ExtractorBbqueueSender<'b> {
         docid: u32,
         embedder_id: u8,
         extractor_id: u8,
-        embedding: Option<Embedding>,
+        embedding: Option<&[f32]>,
     ) -> crate::Result<()> {
         let max_grant = self.max_grant;
         let refcell = self.producers.get().unwrap();
@@ -648,7 +705,7 @@ impl<'b> ExtractorBbqueueSender<'b> {
 
         // If there are no vectors we specify the dimensions
         // to zero to allocate no extra space at all
-        let dimensions = embedding.as_ref().map_or(0, |emb| emb.len());
+        let dimensions = embedding.map_or(0, |emb| emb.len());
 
         let arroy_set_vector =
             ArroySetVector { docid, embedder_id, extractor_id, _padding: [0; 2] };
@@ -1081,12 +1138,22 @@ impl EmbeddingSender<'_, '_> {
         self.0.set_vectors(docid, embedder_id, &embeddings[..])
     }
 
+    pub fn set_vectors_flat(
+        &self,
+        docid: DocumentId,
+        embedder_id: u8,
+        dimensions: usize,
+        flat_embeddings: &[f32],
+    ) -> crate::Result<()> {
+        self.0.set_vectors_flat(docid, embedder_id, dimensions, flat_embeddings)
+    }
+
     pub fn set_vector(
         &self,
         docid: DocumentId,
         embedder_id: u8,
         extractor_id: u8,
-        embedding: Option<Embedding>,
+        embedding: Option<&[f32]>,
     ) -> crate::Result<()> {
         self.0.set_vector_for_extractor(docid, embedder_id, extractor_id, embedding)
     }

crates/milli/src/update/new/extract/vectors/mod.rs

@@ -469,7 +469,7 @@ impl<'doc> OnEmbed<'doc> for OnEmbeddingDocumentUpdates<'doc, '_> {
                 response.metadata.docid,
                 self.embedder_id,
                 response.metadata.extractor_id,
-                response.embedding,
+                response.embedding.as_deref(),
             )
             .unwrap();
     }

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

@@ -21,8 +21,10 @@ use super::thread_local::ThreadLocal;
 use crate::documents::PrimaryKey;
 use crate::fields_ids_map::metadata::{FieldIdMapWithMetadata, MetadataBuilder};
 use crate::progress::{EmbedderStats, Progress};
+use crate::update::new::indexer::vector::Visitable;
 use crate::update::settings::SettingsDelta;
 use crate::update::GrenadParameters;
+use crate::vector::db::EmbeddingStatus;
 use crate::vector::settings::{EmbedderAction, RemoveFragments, WriteBackToDocuments};
 use crate::vector::{ArroyWrapper, Embedder, RuntimeEmbedders};
 use crate::{FieldsIdsMap, GlobalFieldsIdsMap, Index, InternalError, Result, ThreadPoolNoAbort};
@@ -37,6 +39,7 @@ mod partial_dump;
 mod post_processing;
 pub mod settings_changes;
 mod update_by_function;
+mod vector;
 mod write;
 
 static LOG_MEMORY_METRICS_ONCE: Once = Once::new();
@@ -336,6 +339,115 @@ where
     Ok(congestion)
 }
 
+#[allow(clippy::too_many_arguments)]
+pub fn import_vectors<'indexer, DC, MSP, V>(
+    visitables: &[V],
+    statuses: HashMap<String, EmbeddingStatus>,
+    wtxn: &mut RwTxn,
+    index: &Index,
+    pool: &ThreadPoolNoAbort,
+    grenad_parameters: GrenadParameters,
+    embedders: RuntimeEmbedders,
+    must_stop_processing: &'indexer MSP,
+    progress: &'indexer Progress,
+) -> Result<ChannelCongestion>
+where
+    MSP: Fn() -> bool + Sync,
+    V: Visitable + Sync,
+{
+    let mut bbbuffers = Vec::new();
+    let finished_extraction = AtomicBool::new(false);
+
+    let arroy_memory = grenad_parameters.max_memory;
+
+    let (_, total_bbbuffer_capacity) =
+        indexer_memory_settings(pool.current_num_threads(), grenad_parameters);
+
+    let (extractor_sender, writer_receiver) = pool
+        .install(|| extractor_writer_bbqueue(&mut bbbuffers, total_bbbuffer_capacity, 1000))
+        .unwrap();
+
+    let index_embeddings = index.embedding_configs().embedding_configs(wtxn)?;
+
+    let congestion = thread::scope(|s| -> Result<ChannelCongestion> {
+        let indexer_span = tracing::Span::current();
+        let embedders = &embedders;
+        let finished_extraction = &finished_extraction;
+
+        let extractor_handle =
+            Builder::new().name(S("indexer-extractors")).spawn_scoped(s, move || {
+                pool.install(move || {
+                    vector::import_vectors(
+                        visitables,
+                        statuses,
+                        must_stop_processing,
+                        progress,
+                        indexer_span,
+                        extractor_sender,
+                        finished_extraction,
+                        index,
+                        embedders,
+                    )
+                })
+                .unwrap()
+            })?;
+
+        let vector_arroy = index.vector_arroy;
+        let arroy_writers: Result<HashMap<_, _>> = embedders
+            .inner_as_ref()
+            .iter()
+            .map(|(embedder_name, runtime)| {
+                let embedder_index = index
+                    .embedding_configs()
+                    .embedder_id(wtxn, embedder_name)?
+                    .ok_or(InternalError::DatabaseMissingEntry {
+                        db_name: "embedder_category_id",
+                        key: None,
+                    })?;
+
+                let dimensions = runtime.embedder.dimensions();
+                let writer = ArroyWrapper::new(vector_arroy, embedder_index, runtime.is_quantized);
+
+                Ok((
+                    embedder_index,
+                    (embedder_name.as_str(), &*runtime.embedder, writer, dimensions),
+                ))
+            })
+            .collect();
+
+        let mut arroy_writers = arroy_writers?;
+
+        let congestion =
+            write_to_db(writer_receiver, finished_extraction, index, wtxn, &arroy_writers)?;
+
+        progress.update_progress(IndexingStep::WaitingForExtractors);
+
+        let () = extractor_handle.join().unwrap()?;
+
+        progress.update_progress(IndexingStep::WritingEmbeddingsToDatabase);
+
+        pool.install(|| {
+            build_vectors(
+                index,
+                wtxn,
+                progress,
+                index_embeddings,
+                arroy_memory,
+                &mut arroy_writers,
+                None,
+                &must_stop_processing,
+            )
+        })
+        .unwrap()?;
+
+        progress.update_progress(IndexingStep::Finalizing);
+
+        Ok(congestion) as Result<_>
+    })?;
+
+    Ok(congestion)
+}
+
 fn arroy_writers_from_embedder_actions<'indexer>(
     index: &Index,
     embedder_actions: &'indexer BTreeMap<String, EmbedderAction>,

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

@@ -0,0 +1,213 @@
+use std::sync::atomic::AtomicBool;
+use std::sync::Arc;
+
+use hashbrown::HashMap;
+use heed::{RoTxn, WithoutTls};
+use rayon::iter::IntoParallelIterator as _;
+use tracing::Span;
+
+use crate::progress::Progress;
+use crate::update::new::channel::{EmbeddingSender, ExtractorBbqueueSender};
+use crate::update::new::parallel_iterator_ext::ParallelIteratorExt as _;
+use crate::update::new::steps::IndexingStep;
+use crate::vector::db::EmbeddingStatus;
+use crate::vector::RuntimeEmbedders;
+use crate::{DocumentId, Index, InternalError, Result};
+
+// 1. a parallel iterator of visitables
+// implement the latter on dump::VectorReader
+// add skip vectors to regular indexing ops
+// call import vectors
+// write vector files
+
+pub trait Visitor {
+    type Error: 'static + std::fmt::Debug;
+
+    fn on_current_embedder_change(&mut self, name: &str)
+        -> std::result::Result<usize, Self::Error>;
+    fn on_current_store_change(
+        &mut self,
+        name: Option<&str>,
+    ) -> std::result::Result<(), Self::Error>;
+    fn on_current_docid_change(
+        &mut self,
+        external_docid: &str,
+    ) -> std::result::Result<(), Self::Error>;
+    fn on_set_vector(&mut self, v: &[f32]) -> std::result::Result<(), Self::Error>;
+    fn on_set_vectors_flat(&mut self, v: &[f32]) -> std::result::Result<(), Self::Error>;
+}
+
+pub trait Visitable {
+    type Error: std::fmt::Debug;
+    fn visit<V: Visitor>(
+        &self,
+        v: &mut V,
+    ) -> std::result::Result<std::result::Result<(), V::Error>, Self::Error>;
+}
+
+struct ImportVectorVisitor<'a, 'b, MSP> {
+    embedder: Option<EmbedderData>,
+    store_id: Option<u8>,
+    docid: Option<DocumentId>,
+    sender: EmbeddingSender<'a, 'b>,
+    rtxn: RoTxn<'a, WithoutTls>,
+    index: &'a Index,
+    runtimes: &'a RuntimeEmbedders,
+    must_stop_processing: MSP,
+}
+
+impl<'a, 'b, MSP> ImportVectorVisitor<'a, 'b, MSP>
+where
+    MSP: Fn() -> bool + Sync,
+{
+    pub fn new(
+        sender: EmbeddingSender<'a, 'b>,
+        index: &'a Index,
+        rtxn: RoTxn<'a, WithoutTls>,
+        runtimes: &'a RuntimeEmbedders,
+        must_stop_processing: MSP,
+    ) -> Self {
+        Self {
+            embedder: None,
+            store_id: None,
+            docid: None,
+            sender,
+            rtxn,
+            index,
+            runtimes,
+            must_stop_processing,
+        }
+    }
+}
+
+struct EmbedderData {
+    id: u8,
+    dimensions: usize,
+    name: String,
+}
+
+impl<MSP> Visitor for ImportVectorVisitor<'_, '_, MSP>
+where
+    MSP: Fn() -> bool + Sync,
+{
+    type Error = crate::Error;
+
+    fn on_current_embedder_change(
+        &mut self,
+        name: &str,
+    ) -> std::result::Result<usize, Self::Error> {
+        if (self.must_stop_processing)() {
+            return Err(InternalError::AbortedIndexation.into());
+        }
+        let embedder_id = self.index.embedding_configs().embedder_id(&self.rtxn, name)?.unwrap();
+        let embedder_name = name.to_string();
+        let runtime_embedder = self.runtimes.get(name).unwrap();
+        let dimensions = runtime_embedder.embedder.dimensions();
+        self.embedder = Some(EmbedderData { id: embedder_id, dimensions, name: embedder_name });
+        self.store_id = None;
+        self.docid = None;
+        Ok(dimensions)
+    }
+
+    fn on_current_store_change(
+        &mut self,
+        name: Option<&str>,
+    ) -> std::result::Result<(), Self::Error> {
+        if (self.must_stop_processing)() {
+            return Err(InternalError::AbortedIndexation.into());
+        }
+        self.store_id = if let Some(fragment_name) = name {
+            let embedder_name = self.embedder.as_ref().map(|e| &e.name).unwrap();
+            let fragments = self.runtimes.get(embedder_name).unwrap().fragments();
+            Some(
+                fragments[fragments
+                    .binary_search_by(|fragment| fragment.name.as_str().cmp(fragment_name))
+                    .unwrap()]
+                .id,
+            )
+        } else {
+            None
+        };
+        Ok(())
+    }
+
+    fn on_current_docid_change(
+        &mut self,
+        external_docid: &str,
+    ) -> std::result::Result<(), Self::Error> {
+        if (self.must_stop_processing)() {
+            return Err(InternalError::AbortedIndexation.into());
+        }
+        let docid = self.index.external_documents_ids().get(&self.rtxn, external_docid)?.unwrap();
+        self.docid = Some(docid);
+        Ok(())
+    }
+
+    fn on_set_vector(&mut self, v: &[f32]) -> std::result::Result<(), Self::Error> {
+        if (self.must_stop_processing)() {
+            return Err(InternalError::AbortedIndexation.into());
+        }
+        self.sender.set_vector(
+            self.docid.unwrap(),
+            self.embedder.as_ref().unwrap().id,
+            self.store_id.unwrap(),
+            Some(v),
+        )
+    }
+
+    fn on_set_vectors_flat(&mut self, v: &[f32]) -> std::result::Result<(), Self::Error> {
+        if (self.must_stop_processing)() {
+            return Err(InternalError::AbortedIndexation.into());
+        }
+        let embedder = self.embedder.as_ref().unwrap();
+        self.sender.set_vectors_flat(self.docid.unwrap(), embedder.id, embedder.dimensions, v)
+    }
+}
+
+#[allow(clippy::too_many_arguments)]
+pub(super) fn import_vectors<MSP, V: Visitable + Sync>(
+    visitables: &[V],
+    statuses: HashMap<String, EmbeddingStatus>,
+    must_stop_processing: MSP,
+    progress: &Progress,
+    indexer_span: Span,
+    extractor_sender: ExtractorBbqueueSender,
+    finished_extraction: &AtomicBool,
+    index: &Index,
+    runtimes: &RuntimeEmbedders,
+) -> Result<()>
+where
+    MSP: Fn() -> bool + Sync,
+{
+    let span = tracing::trace_span!(target: "indexing::vectors", parent: &indexer_span, "import");
+    let _entered = span.enter();
+    let rtxn = index.read_txn()?;
+    let embedders = index.embedding_configs();
+    let embedding_sender = extractor_sender.embeddings();
+
+    for (name, status) in statuses {
+        let Some(mut info) = embedders.embedder_info(&rtxn, &name)? else { continue };
+        info.embedding_status = status;
+        embedding_sender.embedding_status(&name, info)?;
+    }
+
+    visitables.into_par_iter().try_arc_for_each_try_init(
+        || {
+            let rtxn = index.read_txn()?;
+            let v = ImportVectorVisitor::new(
+                extractor_sender.embeddings(),
+                index,
+                rtxn,
+                runtimes,
+                &must_stop_processing,
+            );
+            Ok(v)
+        },
+        |context, visitable| visitable.visit(context).unwrap().map_err(Arc::new),
+    )?;
+
+    progress.update_progress(IndexingStep::WaitingForDatabaseWrites);
+    finished_extraction.store(true, std::sync::atomic::Ordering::Relaxed);
+
+    Result::Ok(())
+}

crates/milli/src/update/settings.rs

@@ -554,10 +554,10 @@ impl<'a, 't, 'i> Settings<'a, 't, 'i> {
         match self.searchable_fields {
             Setting::Set(ref fields) => {
                 // Check to see if the searchable fields changed before doing anything else
-                let old_fields = self.index.searchable_fields(self.wtxn)?;
+                let old_fields = self.index.user_defined_searchable_fields(self.wtxn)?;
                 let did_change = {
                     let new_fields = fields.iter().map(String::as_str).collect::<Vec<_>>();
-                    new_fields != old_fields
+                    old_fields.is_none_or(|old| new_fields != old)
                 };
                 if !did_change {
                     return Ok(false);

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

@@ -2,6 +2,7 @@ mod v1_12;
 mod v1_13;
 mod v1_14;
 mod v1_15;
+mod v1_16;
 use heed::RwTxn;
 use v1_12::{V1_12_3_To_V1_13_0, V1_12_To_V1_12_3};
 use v1_13::{V1_13_0_To_V1_13_1, V1_13_1_To_Latest_V1_13};
@@ -10,6 +11,7 @@ use v1_15::Latest_V1_14_To_Latest_V1_15;
 
 use crate::constants::{VERSION_MAJOR, VERSION_MINOR, VERSION_PATCH};
 use crate::progress::{Progress, VariableNameStep};
+use crate::update::upgrade::v1_16::Latest_V1_15_To_V1_16_0;
 use crate::{Index, InternalError, Result};
 
 trait UpgradeIndex {
@@ -24,6 +26,59 @@ trait UpgradeIndex {
     fn target_version(&self) -> (u32, u32, u32);
 }
 
+const UPGRADE_FUNCTIONS: &[&dyn UpgradeIndex] = &[
+    &V1_12_To_V1_12_3 {},
+    &V1_12_3_To_V1_13_0 {},
+    &V1_13_0_To_V1_13_1 {},
+    &V1_13_1_To_Latest_V1_13 {},
+    &Latest_V1_13_To_Latest_V1_14 {},
+    &Latest_V1_14_To_Latest_V1_15 {},
+    &Latest_V1_15_To_V1_16_0 {},
+    // This is the last upgrade function, it will be called when the index is up to date.
+    // any other upgrade function should be added before this one.
+    &ToCurrentNoOp {},
+];
+
+/// Causes a compile-time error if the argument is not in range of `0..UPGRADE_FUNCTIONS.len()`
+macro_rules! function_index {
+    ($start:expr) => {{
+        const _CHECK_INDEX: () = {
+            if $start >= $crate::update::upgrade::UPGRADE_FUNCTIONS.len() {
+                panic!("upgrade functions out of range")
+            }
+        };
+
+        $start
+    }};
+}
+
+const fn start(from: (u32, u32, u32)) -> Option<usize> {
+    let start = match from {
+        (1, 12, 0..=2) => function_index!(0),
+        (1, 12, 3..) => function_index!(1),
+        (1, 13, 0) => function_index!(2),
+        (1, 13, _) => function_index!(4),
+        (1, 14, _) => function_index!(5),
+        // We must handle the current version in the match because in case of a failure some index may have been upgraded but not other.
+        (1, 15, _) => function_index!(6),
+        (1, 16, _) => function_index!(7),
+        // We deliberately don't add a placeholder with (VERSION_MAJOR, VERSION_MINOR, VERSION_PATCH) here to force manually
+        // considering dumpless upgrade.
+        (_major, _minor, _patch) => return None,
+    };
+
+    Some(start)
+}
+
+/// Causes a compile-time error if the latest package cannot be upgraded.
+///
+/// This serves as a reminder to consider the proper dumpless upgrade implementation when changing the package version.
+const _CHECK_PACKAGE_CAN_UPGRADE: () = {
+    if start((VERSION_MAJOR, VERSION_MINOR, VERSION_PATCH)).is_none() {
+        panic!("cannot upgrade from latest package version")
+    }
+};
+
 /// Return true if the cached stats of the index must be regenerated
 pub fn upgrade<MSP>(
     wtxn: &mut RwTxn,
@@ -36,33 +91,12 @@ where
     MSP: Fn() -> bool + Sync,
 {
     let from = index.get_version(wtxn)?.unwrap_or(db_version);
-    let upgrade_functions: &[&dyn UpgradeIndex] = &[
-        &V1_12_To_V1_12_3 {},
-        &V1_12_3_To_V1_13_0 {},
-        &V1_13_0_To_V1_13_1 {},
-        &V1_13_1_To_Latest_V1_13 {},
-        &Latest_V1_13_To_Latest_V1_14 {},
-        &Latest_V1_14_To_Latest_V1_15 {},
-        // This is the last upgrade function, it will be called when the index is up to date.
-        // any other upgrade function should be added before this one.
-        &ToCurrentNoOp {},
-    ];
 
-    let start = match from {
-        (1, 12, 0..=2) => 0,
-        (1, 12, 3..) => 1,
-        (1, 13, 0) => 2,
-        (1, 13, _) => 4,
-        (1, 14, _) => 5,
-        // We must handle the current version in the match because in case of a failure some index may have been upgraded but not other.
-        (1, 15, _) => 6,
-        (major, minor, patch) => {
-            return Err(InternalError::CannotUpgradeToVersion(major, minor, patch).into())
-        }
-    };
+    let start =
+        start(from).ok_or_else(|| InternalError::CannotUpgradeToVersion(from.0, from.1, from.2))?;
 
     enum UpgradeVersion {}
-    let upgrade_path = &upgrade_functions[start..];
+    let upgrade_path = &UPGRADE_FUNCTIONS[start..];
 
     let mut current_version = from;
     let mut regenerate_stats = false;

crates/milli/src/update/upgrade/v1_15.rs

@@ -1,4 +1,6 @@
 use heed::RwTxn;
+use roaring::RoaringBitmap;
+use serde::Deserialize;
 
 use super::UpgradeIndex;
 use crate::progress::Progress;
@@ -26,3 +28,14 @@ impl UpgradeIndex for Latest_V1_14_To_Latest_V1_15 {
         (1, 15, 0)
     }
 }
+
+/// Parts of v1.15 `IndexingEmbeddingConfig` that are relevant for upgrade to v1.16
+///
+/// # Warning
+///
+/// This object should not be rewritten to the DB, only read to get the name and `user_provided` roaring.
+#[derive(Debug, Deserialize)]
+pub struct IndexEmbeddingConfig {
+    pub name: String,
+    pub user_provided: RoaringBitmap,
+}

crates/milli/src/update/upgrade/v1_16.rs

@@ -0,0 +1,48 @@
+use heed::types::{SerdeJson, Str};
+use heed::RwTxn;
+
+use super::UpgradeIndex;
+use crate::progress::Progress;
+use crate::vector::db::{EmbedderInfo, EmbeddingStatus};
+use crate::{Index, InternalError, Result};
+
+#[allow(non_camel_case_types)]
+pub(super) struct Latest_V1_15_To_V1_16_0();
+
+impl UpgradeIndex for Latest_V1_15_To_V1_16_0 {
+    fn upgrade(
+        &self,
+        wtxn: &mut RwTxn,
+        index: &Index,
+        _original: (u32, u32, u32),
+        _progress: Progress,
+    ) -> Result<bool> {
+        let v1_15_indexing_configs = index
+            .main
+            .remap_types::<Str, SerdeJson<Vec<super::v1_15::IndexEmbeddingConfig>>>()
+            .get(wtxn, crate::index::main_key::EMBEDDING_CONFIGS)?
+            .unwrap_or_default();
+
+        let embedders = index.embedding_configs();
+        for config in v1_15_indexing_configs {
+            let embedder_id = embedders.embedder_id(wtxn, &config.name)?.ok_or(
+                InternalError::DatabaseMissingEntry {
+                    db_name: crate::index::db_name::VECTOR_EMBEDDER_CATEGORY_ID,
+                    key: None,
+                },
+            )?;
+            let info = EmbedderInfo {
+                embedder_id,
+                // v1.15 used not to make a difference between `user_provided` and `! regenerate`.
+                embedding_status: EmbeddingStatus::from_user_provided(config.user_provided),
+            };
+            embedders.put_embedder_info(wtxn, &config.name, &info)?;
+        }
+
+        Ok(false)
+    }
+
+    fn target_version(&self) -> (u32, u32, u32) {
+        (1, 16, 0)
+    }
+}

crates/milli/src/vector/db.rs

@@ -117,6 +117,13 @@ impl EmbeddingStatus {
         Default::default()
     }
 
+    /// Create a new `EmbeddingStatus` that assumes that any `user_provided` docid is also skipping regenerate.
+    ///
+    /// Used for migration from v1.15 and earlier DBs.
+    pub(crate) fn from_user_provided(user_provided: RoaringBitmap) -> Self {
+        Self { user_provided, skip_regenerate_different_from_user_provided: Default::default() }
+    }
+
     /// Whether the document contains user-provided vectors for that embedder.
     pub fn is_user_provided(&self, docid: DocumentId) -> bool {
         self.user_provided.contains(docid)