Merge #4332

4332: Update the dependencies r=irevoire a=Kerollmops

This PR upgrades the dependencies and fixes #4287.

 - ~We keep arroy at the current commit. We will release and use the latest version published when possible~
 - We also updated arroy to 0.2.0.
 - I rolled back the version of rustls has too many breaking changes.
 - I had to keep HTTP to 0.2.11 due to actix-cors.

Co-authored-by: Clément Renault <clement@meilisearch.com>

.github/workflows/test-suite.yml

@@ -66,6 +66,10 @@ jobs:
       - uses: actions/checkout@v3
       - name: Cache dependencies
         uses: Swatinem/rust-cache@v2.7.1
+      - uses: actions-rs/toolchain@v1
+        with:
+          toolchain: stable
+          override: true
       - name: Run cargo check without any default features
         uses: actions-rs/cargo@v1
         with:
@@ -164,7 +168,7 @@ jobs:
       - uses: actions-rs/toolchain@v1
         with:
           profile: minimal
-          toolchain: 1.71.1
+          toolchain: 1.75.0
           override: true
           components: clippy
       - name: Cache dependencies

Dockerfile

@@ -1,5 +1,5 @@
 # Compile
-FROM    rust:1.71.1-alpine3.18 AS compiler
+FROM    rust:1.75.0-alpine3.18 AS compiler
 
 RUN     apk add -q --update-cache --no-cache build-base openssl-dev
 

benchmarks/Cargo.toml

@@ -11,24 +11,24 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-anyhow = "1.0.70"
+anyhow = "1.0.79"
-csv = "1.2.1"
+csv = "1.3.0"
 milli = { path = "../milli" }
-mimalloc = { version = "0.1.37", default-features = false }
+mimalloc = { version = "0.1.39", default-features = false }
-serde_json = { version = "1.0.95", features = ["preserve_order"] }
+serde_json = { version = "1.0.111", features = ["preserve_order"] }
 
 [dev-dependencies]
 criterion = { version = "0.5.1", features = ["html_reports"] }
 rand = "0.8.5"
 rand_chacha = "0.3.1"
-roaring = "0.10.1"
+roaring = "0.10.2"
 
 [build-dependencies]
-anyhow = "1.0.70"
+anyhow = "1.0.79"
-bytes = "1.4.0"
+bytes = "1.5.0"
 convert_case = "0.6.0"
-flate2 = "1.0.25"
+flate2 = "1.0.28"
-reqwest = { version = "0.11.16", features = ["blocking", "rustls-tls"], default-features = false }
+reqwest = { version = "0.11.23", features = ["blocking", "rustls-tls"], default-features = false }
 
 [features]
 default = ["milli/all-tokenizations"]

dump/Cargo.toml

@@ -11,22 +11,22 @@ readme.workspace = true
 license.workspace = true
 
 [dependencies]
-anyhow = "1.0.70"
+anyhow = "1.0.79"
-flate2 = "1.0.25"
+flate2 = "1.0.28"
-http = "0.2.9"
+http = "0.2.11"
-log = "0.4.17"
+log = "0.4.20"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
-once_cell = "1.17.1"
+once_cell = "1.19.0"
-regex = "1.7.3"
+regex = "1.10.2"
-roaring = { version = "0.10.1", features = ["serde"] }
+roaring = { version = "0.10.2", features = ["serde"] }
-serde = { version = "1.0.160", features = ["derive"] }
+serde = { version = "1.0.195", features = ["derive"] }
-serde_json = { version = "1.0.95", features = ["preserve_order"] }
+serde_json = { version = "1.0.111", features = ["preserve_order"] }
-tar = "0.4.38"
+tar = "0.4.40"
-tempfile = "3.5.0"
+tempfile = "3.9.0"
-thiserror = "1.0.40"
+thiserror = "1.0.56"
-time = { version = "0.3.20", features = ["serde-well-known", "formatting", "parsing", "macros"] }
+time = { version = "0.3.31", features = ["serde-well-known", "formatting", "parsing", "macros"] }
-uuid = { version = "1.3.1", features = ["serde", "v4"] }
+uuid = { version = "1.6.1", features = ["serde", "v4"] }
 
 [dev-dependencies]
 big_s = "1.0.2"

dump/src/reader/v3/errors.rs

@@ -1,5 +1,6 @@
 use serde::{Deserialize, Serialize};
 
+#[allow(clippy::enum_variant_names)]
 #[derive(Serialize, Deserialize, Debug, Clone, Copy)]
 pub enum Code {
     // index related error

dump/src/reader/v4/errors.rs

@@ -95,6 +95,7 @@ impl fmt::Display for ErrorType {
     }
 }
 
+#[allow(clippy::enum_variant_names)]
 #[derive(Serialize, Deserialize, Debug, Clone, Copy)]
 pub enum Code {
     // index related error

dump/src/reader/v5/errors.rs

@@ -31,6 +31,7 @@ impl ResponseError {
     }
 }
 
+#[allow(clippy::enum_variant_names)]
 #[derive(Deserialize, Debug, Clone, Copy)]
 #[cfg_attr(test, derive(serde::Serialize))]
 pub enum Code {

file-store/Cargo.toml

@@ -11,9 +11,9 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-tempfile = "3.5.0"
+tempfile = "3.9.0"
-thiserror = "1.0.40"
+thiserror = "1.0.56"
-uuid = { version = "1.3.1", features = ["serde", "v4"] }
+uuid = { version = "1.6.1", features = ["serde", "v4"] }
 
 [dev-dependencies]
-faux = "0.1.9"
+faux = "0.1.10"

filter-parser/Cargo.toml

@@ -13,8 +13,8 @@ license.workspace = true
 
 [dependencies]
 nom = "7.1.3"
-nom_locate = "4.1.0"
+nom_locate = "4.2.0"
-unescaper = "0.1.2"
+unescaper = "0.1.3"
 
 [dev-dependencies]
-insta = "1.29.0"
+insta = "1.34.0"

fuzzers/Cargo.toml

@@ -11,10 +11,10 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-arbitrary = { version = "1.3.0", features = ["derive"] }
+arbitrary = { version = "1.3.2", features = ["derive"] }
-clap = { version = "4.3.0", features = ["derive"] }
+clap = { version = "4.4.17", features = ["derive"] }
-fastrand = "2.0.0"
+fastrand = "2.0.1"
 milli = { path = "../milli" }
-serde = { version = "1.0.160", features = ["derive"] }
+serde = { version = "1.0.195", features = ["derive"] }
-serde_json = { version = "1.0.95", features = ["preserve_order"] }
+serde_json = { version = "1.0.111", features = ["preserve_order"] }
-tempfile = "3.5.0"
+tempfile = "3.9.0"

index-scheduler/Cargo.toml

@@ -11,32 +11,32 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-anyhow = "1.0.70"
+anyhow = "1.0.79"
 bincode = "1.3.3"
-csv = "1.2.1"
+csv = "1.3.0"
 derive_builder = "0.12.0"
 dump = { path = "../dump" }
-enum-iterator = "1.4.0"
+enum-iterator = "1.5.0"
 file-store = { path = "../file-store" }
 flate2 = "1.0.28"
-log = "0.4.17"
+log = "0.4.20"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
 page_size = "0.5.0"
 puffin = { version = "0.16.0", features = ["serialization"] }
-roaring = { version = "0.10.1", features = ["serde"] }
+roaring = { version = "0.10.2", features = ["serde"] }
-serde = { version = "1.0.160", features = ["derive"] }
+serde = { version = "1.0.195", features = ["derive"] }
-serde_json = { version = "1.0.95", features = ["preserve_order"] }
+serde_json = { version = "1.0.111", features = ["preserve_order"] }
 synchronoise = "1.0.1"
-tempfile = "3.5.0"
+tempfile = "3.9.0"
-thiserror = "1.0.40"
+thiserror = "1.0.56"
-time = { version = "0.3.20", features = ["serde-well-known", "formatting", "parsing", "macros"] }
+time = { version = "0.3.31", features = ["serde-well-known", "formatting", "parsing", "macros"] }
 ureq = "2.9.1"
-uuid = { version = "1.3.1", features = ["serde", "v4"] }
+uuid = { version = "1.6.1", features = ["serde", "v4"] }
 
 [dev-dependencies]
 big_s = "1.0.2"
-crossbeam = "0.8.2"
+crossbeam = "0.8.4"
-insta = { version = "1.29.0", features = ["json", "redactions"] }
+insta = { version = "1.34.0", features = ["json", "redactions"] }
 meili-snap = { path = "../meili-snap" }
 nelson = { git = "https://github.com/meilisearch/nelson.git", rev = "675f13885548fb415ead8fbb447e9e6d9314000a"}

meili-snap/Cargo.toml

@@ -11,6 +11,6 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-insta = { version = "^1.29.0", features = ["json", "redactions"] }
+insta = { version = "^1.34.0", features = ["json", "redactions"] }
 md5 = "0.7.0"
-once_cell = "1.17"
+once_cell = "1.19"

meilisearch-auth/Cargo.toml

@@ -11,16 +11,16 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-base64 = "0.21.0"
+base64 = "0.21.7"
-enum-iterator = "1.4.0"
+enum-iterator = "1.5.0"
 hmac = "0.12.1"
 maplit = "1.0.2"
 meilisearch-types = { path = "../meilisearch-types" }
 rand = "0.8.5"
-roaring = { version = "0.10.1", features = ["serde"] }
+roaring = { version = "0.10.2", features = ["serde"] }
-serde = { version = "1.0.160", features = ["derive"] }
+serde = { version = "1.0.195", features = ["derive"] }
-serde_json = { version = "1.0.95", features = ["preserve_order"] }
+serde_json = { version = "1.0.111", features = ["preserve_order"] }
-sha2 = "0.10.6"
+sha2 = "0.10.8"
-thiserror = "1.0.40"
+thiserror = "1.0.56"
-time = { version = "0.3.20", features = ["serde-well-known", "formatting", "parsing", "macros"] }
+time = { version = "0.3.31", features = ["serde-well-known", "formatting", "parsing", "macros"] }
-uuid = { version = "1.3.1", features = ["serde", "v4"] }
+uuid = { version = "1.6.1", features = ["serde", "v4"] }

meilisearch-types/Cargo.toml

@@ -11,31 +11,31 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-actix-web = { version = "4.3.1", default-features = false }
+actix-web = { version = "4.4.1", default-features = false }
-anyhow = "1.0.70"
+anyhow = "1.0.79"
 convert_case = "0.6.0"
-csv = "1.2.1"
+csv = "1.3.0"
-deserr = { version = "0.6.0", features = ["actix-web"] }
+deserr = { version = "0.6.1", features = ["actix-web"] }
-either = { version = "1.8.1", features = ["serde"] }
+either = { version = "1.9.0", features = ["serde"] }
-enum-iterator = "1.4.0"
+enum-iterator = "1.5.0"
 file-store = { path = "../file-store" }
-flate2 = "1.0.25"
+flate2 = "1.0.28"
 fst = "0.4.7"
 memmap2 = "0.7.1"
 milli = { path = "../milli" }
-roaring = { version = "0.10.1", features = ["serde"] }
+roaring = { version = "0.10.2", features = ["serde"] }
-serde = { version = "1.0.160", features = ["derive"] }
+serde = { version = "1.0.195", features = ["derive"] }
 serde-cs = "0.2.4"
-serde_json = "1.0.95"
+serde_json = "1.0.111"
-tar = "0.4.38"
+tar = "0.4.40"
-tempfile = "3.5.0"
+tempfile = "3.9.0"
-thiserror = "1.0.40"
+thiserror = "1.0.56"
-time = { version = "0.3.20", features = ["serde-well-known", "formatting", "parsing", "macros"] }
+time = { version = "0.3.31", features = ["serde-well-known", "formatting", "parsing", "macros"] }
-tokio = "1.27"
+tokio = "1.35"
-uuid = { version = "1.3.1", features = ["serde", "v4"] }
+uuid = { version = "1.6.1", features = ["serde", "v4"] }
 
 [dev-dependencies]
-insta = "1.29.0"
+insta = "1.34.0"
 meili-snap = { path = "../meili-snap" }
 
 [features]

meilisearch/Cargo.toml

@@ -13,14 +13,14 @@ license.workspace = true
 default-run = "meilisearch"
 
 [dependencies]
-actix-cors = "0.6.4"
+actix-cors = "0.7.0"
-actix-http = { version = "3.3.1", default-features = false, features = [
+actix-http = { version = "3.5.1", default-features = false, features = [
     "compress-brotli",
     "compress-gzip",
     "rustls",
 ] }
 actix-utils = "3.0.1"
-actix-web = { version = "4.3.1", default-features = false, features = [
+actix-web = { version = "4.4.1", default-features = false, features = [
     "macros",
     "compress-brotli",
     "compress-gzip",
@@ -28,109 +28,109 @@ actix-web = { version = "4.3.1", default-features = false, features = [
     "rustls",
 ] }
 actix-web-static-files = { git = "https://github.com/kilork/actix-web-static-files.git", rev = "2d3b6160", optional = true }
-anyhow = { version = "1.0.70", features = ["backtrace"] }
+anyhow = { version = "1.0.79", features = ["backtrace"] }
 async-stream = "0.3.5"
-async-trait = "0.1.68"
+async-trait = "0.1.77"
-bstr = "1.4.0"
+bstr = "1.9.0"
 byte-unit = { version = "4.0.19", default-features = false, features = [
     "std",
     "serde",
 ] }
-bytes = "1.4.0"
+bytes = "1.5.0"
-clap = { version = "4.2.1", features = ["derive", "env"] }
+clap = { version = "4.4.17", features = ["derive", "env"] }
-crossbeam-channel = "0.5.8"
+crossbeam-channel = "0.5.11"
-deserr = { version = "0.6.0", features = ["actix-web"] }
+deserr = { version = "0.6.1", features = ["actix-web"] }
 dump = { path = "../dump" }
-either = "1.8.1"
+either = "1.9.0"
-env_logger = "0.10.0"
+env_logger = "0.10.1"
 file-store = { path = "../file-store" }
-flate2 = "1.0.25"
+flate2 = "1.0.28"
 fst = "0.4.7"
-futures = "0.3.28"
+futures = "0.3.30"
-futures-util = "0.3.28"
+futures-util = "0.3.30"
-http = "0.2.9"
+http = "0.2.11"
 index-scheduler = { path = "../index-scheduler" }
-indexmap = { version = "2.0.0", features = ["serde"] }
+indexmap = { version = "2.1.0", features = ["serde"] }
-is-terminal = "0.4.8"
+is-terminal = "0.4.10"
 itertools = "0.11.0"
 jsonwebtoken = "8.3.0"
 lazy_static = "1.4.0"
-log = "0.4.17"
+log = "0.4.20"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
-mimalloc = { version = "0.1.37", default-features = false }
+mimalloc = { version = "0.1.39", default-features = false }
 mime = "0.3.17"
-num_cpus = "1.15.0"
+num_cpus = "1.16.0"
-obkv = "0.2.0"
+obkv = "0.2.1"
-once_cell = "1.17.1"
+once_cell = "1.19.0"
-ordered-float = "3.7.0"
+ordered-float = "4.2.0"
 parking_lot = "0.12.1"
 permissive-json-pointer = { path = "../permissive-json-pointer" }
-pin-project-lite = "0.2.9"
+pin-project-lite = "0.2.13"
 platform-dirs = "0.3.0"
 prometheus = { version = "0.13.3", features = ["process"] }
 puffin = { version = "0.16.0", features = ["serialization"] }
 rand = "0.8.5"
-rayon = "1.7.0"
+rayon = "1.8.0"
-regex = "1.7.3"
+regex = "1.10.2"
-reqwest = { version = "0.11.16", features = [
+reqwest = { version = "0.11.23", features = [
     "rustls-tls",
     "json",
 ], default-features = false }
 rustls = "0.20.8"
 rustls-pemfile = "1.0.2"
-segment = { version = "0.2.2", optional = true }
+segment = { version = "0.2.3", optional = true }
-serde = { version = "1.0.160", features = ["derive"] }
+serde = { version = "1.0.195", features = ["derive"] }
-serde_json = { version = "1.0.95", features = ["preserve_order"] }
+serde_json = { version = "1.0.111", features = ["preserve_order"] }
-sha2 = "0.10.6"
+sha2 = "0.10.8"
-siphasher = "0.3.10"
+siphasher = "1.0.0"
-slice-group-by = "0.3.0"
+slice-group-by = "0.3.1"
 static-files = { version = "0.2.3", optional = true }
-sysinfo = "0.29.7"
+sysinfo = "0.30.5"
-tar = "0.4.38"
+tar = "0.4.40"
-tempfile = "3.5.0"
+tempfile = "3.9.0"
-thiserror = "1.0.40"
+thiserror = "1.0.56"
-time = { version = "0.3.20", features = [
+time = { version = "0.3.31", features = [
     "serde-well-known",
     "formatting",
     "parsing",
     "macros",
 ] }
-tokio = { version = "1.27.0", features = ["full"] }
+tokio = { version = "1.35.1", features = ["full"] }
-tokio-stream = "0.1.12"
+tokio-stream = "0.1.14"
-toml = "0.7.3"
+toml = "0.8.8"
-uuid = { version = "1.3.1", features = ["serde", "v4"] }
+uuid = { version = "1.6.1", features = ["serde", "v4"] }
-walkdir = "2.3.3"
+walkdir = "2.4.0"
 yaup = "0.2.1"
 serde_urlencoded = "0.7.1"
-termcolor = "1.2.0"
+termcolor = "1.4.1"
 url = { version = "2.5.0", features = ["serde"] }
 
 [dev-dependencies]
-actix-rt = "2.8.0"
+actix-rt = "2.9.0"
 assert-json-diff = "2.0.2"
-brotli = "3.3.4"
+brotli = "3.4.0"
-insta = "1.29.0"
+insta = "1.34.0"
-manifest-dir-macros = "0.1.16"
+manifest-dir-macros = "0.1.18"
 maplit = "1.0.2"
 meili-snap = { path = "../meili-snap" }
-temp-env = "0.3.3"
+temp-env = "0.3.6"
-urlencoding = "2.1.2"
+urlencoding = "2.1.3"
 yaup = "0.2.1"
 
 [build-dependencies]
-anyhow = { version = "1.0.70", optional = true }
+anyhow = { version = "1.0.79", optional = true }
-cargo_toml = { version = "0.15.2", optional = true }
+cargo_toml = { version = "0.18.0", optional = true }
 hex = { version = "0.4.3", optional = true }
-reqwest = { version = "0.11.16", features = [
+reqwest = { version = "0.11.23", features = [
     "blocking",
     "rustls-tls",
 ], default-features = false, optional = true }
 sha-1 = { version = "0.10.1", optional = true }
 static-files = { version = "0.2.3", optional = true }
-tempfile = { version = "3.5.0", optional = true }
+tempfile = { version = "3.9.0", optional = true }
 vergen = { version = "7.5.1", default-features = false, features = ["git"] }
-zip = { version = "0.6.4", optional = true }
+zip = { version = "0.6.6", optional = true }
 
 [features]
 default = ["analytics", "meilisearch-types/all-tokenizations", "mini-dashboard"]

meilisearch/src/analytics/segment_analytics.rs

@@ -18,7 +18,7 @@ use segment::message::{Identify, Track, User};
 use segment::{AutoBatcher, Batcher, HttpClient};
 use serde::Serialize;
 use serde_json::{json, Value};
-use sysinfo::{DiskExt, System, SystemExt};
+use sysinfo::{Disks, System};
 use time::OffsetDateTime;
 use tokio::select;
 use tokio::sync::mpsc::{self, Receiver, Sender};
@@ -386,16 +386,17 @@ impl Segment {
     fn compute_traits(opt: &Opt, stats: Stats) -> Value {
         static FIRST_START_TIMESTAMP: Lazy<Instant> = Lazy::new(Instant::now);
         static SYSTEM: Lazy<Value> = Lazy::new(|| {
+            let disks = Disks::new_with_refreshed_list();
             let mut sys = System::new_all();
             sys.refresh_all();
-            let kernel_version =
+            let kernel_version = System::kernel_version()
-                sys.kernel_version().and_then(|k| k.split_once('-').map(|(k, _)| k.to_string()));
+                .and_then(|k| k.split_once('-').map(|(k, _)| k.to_string()));
             json!({
-                    "distribution": sys.name(),
+                    "distribution": System::name(),
                     "kernel_version": kernel_version,
                     "cores": sys.cpus().len(),
                     "ram_size": sys.total_memory(),
-                    "disk_size": sys.disks().iter().map(|disk| disk.total_space()).max(),
+                    "disk_size": disks.iter().map(|disk| disk.total_space()).max(),
                     "server_provider": std::env::var("MEILI_SERVER_PROVIDER").ok(),
             })
         });

meilisearch/src/option.rs

@@ -20,7 +20,7 @@ use rustls::server::{
 use rustls::RootCertStore;
 use rustls_pemfile::{certs, pkcs8_private_keys, rsa_private_keys};
 use serde::{Deserialize, Serialize};
-use sysinfo::{RefreshKind, System, SystemExt};
+use sysinfo::{MemoryRefreshKind, RefreshKind, System};
 use url::Url;
 
 const POSSIBLE_ENV: [&str; 2] = ["development", "production"];
@@ -633,8 +633,8 @@ impl MaxMemory {
 
 /// Returns the total amount of bytes available or `None` if this system isn't supported.
 fn total_memory_bytes() -> Option<u64> {
-    if System::IS_SUPPORTED {
+    if sysinfo::IS_SUPPORTED_SYSTEM {
-        let memory_kind = RefreshKind::new().with_memory();
+        let memory_kind = RefreshKind::new().with_memory(MemoryRefreshKind::new().with_ram());
         let mut system = System::new_with_specifics(memory_kind);
         system.refresh_memory();
         Some(system.total_memory())

meilitool/Cargo.toml

@@ -9,11 +9,11 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-anyhow = "1.0.75"
+anyhow = "1.0.79"
-clap = { version = "4.2.1", features = ["derive"] }
+clap = { version = "4.4.17", features = ["derive"] }
 dump = { path = "../dump" }
 file-store = { path = "../file-store" }
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
-time = { version = "0.3.30", features = ["formatting"] }
+time = { version = "0.3.31", features = ["formatting"] }
-uuid = { version = "1.5.0", features = ["v4"], default-features = false }
+uuid = { version = "1.6.1", features = ["v4"], default-features = false }

milli/Cargo.toml

@@ -14,14 +14,14 @@ license.workspace = true
 [dependencies]
 bimap = { version = "0.6.3", features = ["serde"] }
 bincode = "1.3.3"
-bstr = "1.4.0"
+bstr = "1.9.0"
-bytemuck = { version = "1.13.1", features = ["extern_crate_alloc"] }
+bytemuck = { version = "1.14.0", features = ["extern_crate_alloc"] }
-byteorder = "1.4.3"
+byteorder = "1.5.0"
 charabia = { version = "0.8.5", default-features = false }
 concat-arrays = "0.1.2"
-crossbeam-channel = "0.5.8"
+crossbeam-channel = "0.5.11"
-deserr = "0.6.0"
+deserr = "0.6.1"
-either = { version = "1.8.1", features = ["serde"] }
+either = { version = "1.9.0", features = ["serde"] }
 flatten-serde-json = { path = "../flatten-serde-json" }
 fst = "0.4.7"
 fxhash = "0.2.1"
@@ -35,32 +35,32 @@ heed = { version = "0.20.0-alpha.9", default-features = false, features = [
     "serde-bincode",
     "read-txn-no-tls",
 ] }
-indexmap = { version = "2.0.0", features = ["serde"] }
+indexmap = { version = "2.1.0", features = ["serde"] }
 json-depth-checker = { path = "../json-depth-checker" }
 levenshtein_automata = { version = "0.2.1", features = ["fst_automaton"] }
 memmap2 = "0.7.1"
-obkv = "0.2.0"
+obkv = "0.2.1"
-once_cell = "1.17.1"
+once_cell = "1.19.0"
-ordered-float = "3.6.0"
+ordered-float = "4.2.0"
 rand_pcg = { version = "0.3.1", features = ["serde1"] }
-rayon = "1.7.0"
+rayon = "1.8.0"
-roaring = "0.10.1"
+roaring = "0.10.2"
 rstar = { version = "0.11.0", features = ["serde"] }
-serde = { version = "1.0.160", features = ["derive"] }
+serde = { version = "1.0.195", features = ["derive"] }
-serde_json = { version = "1.0.95", features = ["preserve_order"] }
+serde_json = { version = "1.0.111", features = ["preserve_order"] }
-slice-group-by = "0.3.0"
+slice-group-by = "0.3.1"
 smallstr = { version = "0.3.0", features = ["serde"] }
-smallvec = "1.10.0"
+smallvec = "1.12.0"
 smartstring = "1.0.1"
-tempfile = "3.5.0"
+tempfile = "3.9.0"
-thiserror = "1.0.40"
+thiserror = "1.0.56"
-time = { version = "0.3.20", features = [
+time = { version = "0.3.31", features = [
     "serde-well-known",
     "formatting",
     "parsing",
     "macros",
 ] }
-uuid = { version = "1.3.1", features = ["v4"] }
+uuid = { version = "1.6.1", features = ["v4"] }
 
 filter-parser = { path = "../filter-parser" }
 
@@ -71,9 +71,9 @@ itertools = "0.11.0"
 puffin = "0.16.0"
 
 # logging
-log = "0.4.17"
+log = "0.4.20"
 logging_timer = "1.1.0"
-csv = "1.2.1"
+csv = "1.3.0"
 candle-core = { git = "https://github.com/huggingface/candle.git", version = "0.3.1" }
 candle-transformers = { git = "https://github.com/huggingface/candle.git", version = "0.3.1" }
 candle-nn = { git = "https://github.com/huggingface/candle.git", version = "0.3.1" }
@@ -81,21 +81,21 @@ tokenizers = { git = "https://github.com/huggingface/tokenizers.git", tag = "v0.
 hf-hub = { git = "https://github.com/dureuill/hf-hub.git", branch = "rust_tls", default_features = false, features = [
     "online",
 ] }
-tokio = { version = "1.34.0", features = ["rt"] }
+tokio = { version = "1.35.1", features = ["rt"] }
-futures = "0.3.29"
+futures = "0.3.30"
-reqwest = { version = "0.11.16", features = [
+reqwest = { version = "0.11.23", features = [
     "rustls-tls",
     "json",
 ], default-features = false }
-tiktoken-rs = "0.5.7"
+tiktoken-rs = "0.5.8"
 liquid = "0.26.4"
-arroy = { git = "https://github.com/meilisearch/arroy.git", version = "0.1.0" }
+arroy = "0.2.0"
 rand = "0.8.5"
 
 [dev-dependencies]
-mimalloc = { version = "0.1.37", default-features = false }
+mimalloc = { version = "0.1.39", default-features = false }
 big_s = "1.0.2"
-insta = "1.29.0"
+insta = "1.34.0"
 maplit = "1.0.2"
 md5 = "0.7.0"
 meili-snap = { path = "../meili-snap" }

milli/src/error.rs

@@ -172,7 +172,7 @@ only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and undersco
     TooManyDocumentIds { primary_key: String, document: Object },
     #[error("The primary key inference failed as the engine did not find any field ending with `id` in its name. Please specify the primary key manually using the `primaryKey` query parameter.")]
     NoPrimaryKeyCandidateFound,
-    #[error("The primary key inference failed as the engine found {} fields ending with `id` in their names: '{}' and '{}'. Please specify the primary key manually using the `primaryKey` query parameter.", .candidates.len(), .candidates.get(0).unwrap(), .candidates.get(1).unwrap())]
+    #[error("The primary key inference failed as the engine found {} fields ending with `id` in their names: '{}' and '{}'. Please specify the primary key manually using the `primaryKey` query parameter.", .candidates.len(), .candidates.first().unwrap(), .candidates.get(1).unwrap())]
     MultiplePrimaryKeyCandidatesFound { candidates: Vec<String> },
     #[error("There is no more space left on the device. Consider increasing the size of the disk/partition.")]
     NoSpaceLeftOnDevice,
@@ -251,6 +251,7 @@ impl From<arroy::Error> for Error {
             arroy::Error::DatabaseFull
             | arroy::Error::InvalidItemAppend
             | arroy::Error::UnmatchingDistance { .. }
+            | arroy::Error::MissingNode
             | arroy::Error::MissingMetadata => {
                 Error::InternalError(InternalError::ArroyError(value))
             }

milli/src/search/facet/facet_sort_ascending.rs

@@ -181,7 +181,7 @@ mod tests {
             get_simple_string_index_with_multiple_field_ids(),
             get_random_looking_string_index_with_multiple_field_ids(),
         ];
-        for (_i, index) in indexes.iter().enumerate() {
+        for index in indexes {
             let txn = index.env.read_txn().unwrap();
             let candidates = RoaringBitmap::new();
             let mut results = String::new();
@@ -212,7 +212,7 @@ mod tests {
             get_simple_string_index_with_multiple_field_ids(),
             get_random_looking_string_index_with_multiple_field_ids(),
         ];
-        for (_i, index) in indexes.iter().enumerate() {
+        for index in indexes {
             let txn = index.env.read_txn().unwrap();
             let candidates = RoaringBitmap::new();
             let mut results = String::new();

milli/src/search/facet/facet_sort_descending.rs

@@ -195,7 +195,7 @@ mod tests {
             get_simple_string_index_with_multiple_field_ids(),
             get_random_looking_string_index_with_multiple_field_ids(),
         ];
-        for (_i, index) in indexes.iter().enumerate() {
+        for index in indexes {
             let txn = index.env.read_txn().unwrap();
             let candidates = RoaringBitmap::new();
             let mut results = String::new();
@@ -226,7 +226,7 @@ mod tests {
             get_simple_string_index_with_multiple_field_ids(),
             get_random_looking_string_index_with_multiple_field_ids(),
         ];
-        for (_i, index) in indexes.iter().enumerate() {
+        for index in indexes {
             let txn = index.env.read_txn().unwrap();
             let candidates = RoaringBitmap::new();
             let mut results = String::new();

milli/src/search/facet/mod.rs

@@ -142,7 +142,7 @@ pub(crate) mod tests {
         let mut txn = index.env.write_txn().unwrap();
         let mut rng = rand::rngs::SmallRng::from_seed([0; 32]);
 
-        for (_i, key) in std::iter::from_fn(|| Some(rng.gen_range(0..256))).take(128).enumerate() {
+        for key in std::iter::from_fn(|| Some(rng.gen_range(0..256))).take(128) {
             let mut bitmap = RoaringBitmap::new();
             bitmap.insert(key);
             bitmap.insert(key + 100);
@@ -172,7 +172,7 @@ pub(crate) mod tests {
         let keys =
             std::iter::from_fn(|| Some(rng.gen_range(0..256))).take(128).collect::<Vec<u32>>();
         for fid in 0..2 {
-            for (_i, &key) in keys.iter().enumerate() {
+            for &key in &keys {
                 let mut bitmap = RoaringBitmap::new();
                 bitmap.insert(key);
                 bitmap.insert(key + 100);
@@ -207,7 +207,7 @@ pub(crate) mod tests {
         let keys =
             std::iter::from_fn(|| Some(rng.gen_range(0..256))).take(128).collect::<Vec<u32>>();
         for fid in 0..2 {
-            for (_i, &key) in keys.iter().enumerate() {
+            for &key in &keys {
                 let mut bitmap = RoaringBitmap::new();
                 bitmap.insert(key);
                 bitmap.insert(key + 100);

milli/src/update/facet/incremental.rs

@@ -751,7 +751,7 @@ mod tests {
         let mut rng = rand::rngs::SmallRng::from_seed([0; 32]);
         keys.shuffle(&mut rng);
 
-        for (_i, key) in keys.into_iter().enumerate() {
+        for key in keys {
             let mut bitmap = RoaringBitmap::new();
             bitmap.insert(key);
             index.insert(&mut txn, 0, &(key as f64), &bitmap);
@@ -770,7 +770,7 @@ mod tests {
         let mut rng = rand::rngs::SmallRng::from_seed([0; 32]);
         keys.shuffle(&mut rng);
 
-        for (_i, key) in keys.into_iter().enumerate() {
+        for key in keys {
             let mut bitmap = RoaringBitmap::new();
             bitmap.insert(key);
             bitmap.insert(rng.gen_range(256..512));

milli/src/update/index_documents/extract/extract_vector_points.rs

@@ -135,7 +135,7 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
                 let del_vectors = extract_vectors(old, document_id, embedder_name)?;
                 let add_vectors = extract_vectors(new, document_id, embedder_name)?;
 
-                if add_vectors.len() > u8::MAX.into() {
+                if add_vectors.len() > usize::from(u8::MAX) {
                     return Err(crate::Error::UserError(crate::UserError::TooManyVectors(
                         document_id().to_string(),
                         add_vectors.len(),
@@ -164,7 +164,7 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
             (None, Some(new)) => {
                 // was possibly autogenerated, remove all vectors for that document
                 let add_vectors = extract_vectors(new, document_id, embedder_name)?;
-                if add_vectors.len() > u8::MAX.into() {
+                if add_vectors.len() > usize::from(u8::MAX) {
                     return Err(crate::Error::UserError(crate::UserError::TooManyVectors(
                         document_id().to_string(),
                         add_vectors.len(),

milli/src/update/index_documents/extract/extract_word_pair_proximity_docids.rs

@@ -77,7 +77,7 @@ pub fn extract_word_pair_proximity_docids<R: io::Read + io::Seek>(
                 if let Some(deletion) = KvReaderDelAdd::new(value).get(DelAdd::Deletion) {
                     for (position, word) in KvReaderU16::new(deletion).iter() {
                         // drain the proximity window until the head word is considered close to the word we are inserting.
-                        while del_word_positions.get(0).map_or(false, |(_w, p)| {
+                        while del_word_positions.front().map_or(false, |(_w, p)| {
                             index_proximity(*p as u32, position as u32) >= MAX_DISTANCE
                         }) {
                             word_positions_into_word_pair_proximity(
@@ -106,7 +106,7 @@ pub fn extract_word_pair_proximity_docids<R: io::Read + io::Seek>(
                 if let Some(addition) = KvReaderDelAdd::new(value).get(DelAdd::Addition) {
                     for (position, word) in KvReaderU16::new(addition).iter() {
                         // drain the proximity window until the head word is considered close to the word we are inserting.
-                        while add_word_positions.get(0).map_or(false, |(_w, p)| {
+                        while add_word_positions.front().map_or(false, |(_w, p)| {
                             index_proximity(*p as u32, position as u32) >= MAX_DISTANCE
                         }) {
                             word_positions_into_word_pair_proximity(

milli/src/update/index_documents/mod.rs

@@ -522,12 +522,8 @@ where
             pool.install(|| {
                 let writer_index = (embedder_index as u16) << 8;
                 for k in 0..=u8::MAX {
-                    let writer = arroy::Writer::prepare(
+                    let writer =
-                        wtxn,
+                        arroy::Writer::new(vector_arroy, writer_index | (k as u16), dimension)?;
-                        vector_arroy,
-                        writer_index | (k as u16),
-                        dimension,
-                    )?;
                     if writer.is_empty(wtxn)? {
                         break;
                     }

milli/src/update/index_documents/typed_chunk.rs

@@ -372,8 +372,7 @@ pub(crate) fn write_typed_chunk_into_index(
             // FIXME: allow customizing distance
             let writers: std::result::Result<Vec<_>, _> = (0..=u8::MAX)
                 .map(|k| {
-                    arroy::Writer::prepare(
+                    arroy::Writer::new(
-                        wtxn,
                         index.vector_arroy,
                         writer_index | (k as u16),
                         expected_dimension,
@@ -407,7 +406,7 @@ pub(crate) fn write_typed_chunk_into_index(
                             // code error if we somehow got the wrong dimension
                             .unwrap();
 
-                    if embeddings.embedding_count() > u8::MAX.into() {
+                    if embeddings.embedding_count() > usize::from(u8::MAX) {
                         let external_docid = if let Ok(Some(Ok(index))) = index
                             .external_id_of(wtxn, std::iter::once(docid))
                             .map(|it| it.into_iter().next())