Remove the unused distance

This reverts commit 7a4b6c065482f988b01298642f4c18775503f92f.

.github/scripts/check-release.sh

@@ -1,41 +1,24 @@
-#!/usr/bin/env bash
-set -eu -o pipefail
+#!/bin/bash
 
-check_tag() {
-    local expected=$1
-    local actual=$2
-    local filename=$3
-
-    if [[ $actual != $expected ]]; then
-        echo >&2 "Error: the current tag does not match the version in $filename: found $actual, expected $expected"
-        return 1
-    fi
+# check_tag $current_tag $file_tag $file_name
+function check_tag {
+  if [[ "$1" != "$2" ]]; then
+      echo "Error: the current tag does not match the version in Cargo.toml: found $2 - expected $1"
+      ret=1
+  fi
 }
 
-read_version() {
-    grep '^version = ' | cut -d \" -f 2
-}
-
-if [[ -z "${GITHUB_REF:-}" ]]; then
-    echo >&2 "Error: GITHUB_REF is not set"
-    exit 1
-fi
-
-if [[ ! "$GITHUB_REF" =~ ^refs/tags/v[0-9]+\.[0-9]+\.[0-9]+(-[a-z0-9]+)?$ ]]; then
-    echo >&2 "Error: GITHUB_REF is not a valid tag: $GITHUB_REF"
-    exit 1
-fi
-
-current_tag=${GITHUB_REF#refs/tags/v}
 ret=0
+current_tag=${GITHUB_REF#'refs/tags/v'}
 
-toml_tag="$(cat Cargo.toml | read_version)"
-check_tag "$current_tag" "$toml_tag" Cargo.toml || ret=1
+file_tag="$(grep '^version = ' Cargo.toml | cut -d '=' -f 2 | tr -d '"' | tr -d ' ')"
+check_tag $current_tag $file_tag
 
-lock_tag=$(grep -A 1 '^name = "meilisearch-auth"' Cargo.lock | read_version)
-check_tag "$current_tag" "$lock_tag" Cargo.lock || ret=1
+lock_file='Cargo.lock'
+lock_tag=$(grep -A 1 'name = "meilisearch-auth"' $lock_file | grep version | cut -d '=' -f 2 | tr -d '"' | tr -d ' ')
+check_tag $current_tag $lock_tag $lock_file
 
-if (( ret == 0 )); then
-    echo 'OK'
+if [[ "$ret" -eq 0 ]] ; then
+  echo 'OK'
 fi
 exit $ret

.github/workflows/fuzzer-indexing.yml

@@ -1,24 +0,0 @@
-name: Run the indexing fuzzer
-
-on:
-  push:
-    branches:
-      - main
-
-jobs:
-  fuzz:
-    name: Setup the action
-    runs-on: ubuntu-latest
-    timeout-minutes: 4320 # 72h
-    steps:
-      - uses: actions/checkout@v3
-      - uses: actions-rs/toolchain@v1
-        with:
-          profile: minimal
-          toolchain: stable
-          override: true
-
-      # Run benchmarks
-      - name: Run the fuzzer
-        run: |
-          cargo run --release --bin fuzz-indexing

.github/workflows/sdks-tests.yml

@@ -25,7 +25,7 @@ jobs:
       - name: Define the Docker image we need to use
         id: define-image
         run: |
-          event=${{ github.event_name }}
+          event=${{ github.event.action }}
           echo "docker-image=nightly" >> $GITHUB_OUTPUT
           if [[ $event == 'workflow_dispatch' ]]; then
             echo "docker-image=${{ github.event.inputs.docker_image }}" >> $GITHUB_OUTPUT
@@ -37,7 +37,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
+        image: getmeili/meilisearch:${{ github.event.inputs.docker_image }}
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -72,7 +72,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
+        image: getmeili/meilisearch:${{ github.event.inputs.docker_image }}
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -99,7 +99,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
+        image: getmeili/meilisearch:${{ github.event.inputs.docker_image }}
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -130,7 +130,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
+        image: getmeili/meilisearch:${{ github.event.inputs.docker_image }}
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -155,7 +155,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
+        image: getmeili/meilisearch:${{ github.event.inputs.docker_image }}
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -185,7 +185,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
+        image: getmeili/meilisearch:${{ github.event.inputs.docker_image }}
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
@@ -210,7 +210,7 @@ jobs:
     runs-on: ubuntu-latest
     services:
       meilisearch:
-        image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
+        image: getmeili/meilisearch:${{ github.event.inputs.docker_image }}
         env:
           MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
           MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}

Cargo.toml

@@ -13,12 +13,11 @@ members = [
     "filter-parser",
     "flatten-serde-json",
     "json-depth-checker",
-    "benchmarks",
-    "fuzzers",
+    "benchmarks"
 ]
 
 [workspace.package]
-version = "1.3.0"
+version = "1.2.0"
 authors = ["Quentin de Quelen <quentin@dequelen.me>", "Clément Renault <clement@meilisearch.com>"]
 description = "Meilisearch HTTP server"
 homepage = "https://meilisearch.com"

README.md

@@ -6,7 +6,6 @@
 <h4 align="center">
   <a href="https://www.meilisearch.com">Website</a> |
   <a href="https://roadmap.meilisearch.com/tabs/1-under-consideration">Roadmap</a> |
-  <a href="https://www.meilisearch.com/pricing?utm_campaign=oss&utm_source=engine&utm_medium=meilisearch">Meilisearch Cloud</a> |
   <a href="https://blog.meilisearch.com">Blog</a> |
   <a href="https://www.meilisearch.com/docs">Documentation</a> |
   <a href="https://www.meilisearch.com/docs/faq">FAQ</a> |
@@ -38,10 +37,10 @@ Meilisearch helps you shape a delightful search experience in a snap, offering f
 
 - **Search-as-you-type:** find search results in less than 50 milliseconds
 - **[Typo tolerance](https://www.meilisearch.com/docs/learn/getting_started/customizing_relevancy#typo-tolerance):** get relevant matches even when queries contain typos and misspellings
-- **[Filtering](https://www.meilisearch.com/docs/learn/fine_tuning_results/filtering) and [faceted search](https://www.meilisearch.com/docs/learn/fine_tuning_results/faceted_search):** enhance your user's search experience with custom filters and build a faceted search interface in a few lines of code
-- **[Sorting](https://www.meilisearch.com/docs/learn/fine_tuning_results/sorting):** sort results based on price, date, or pretty much anything else your users need
+- **[Filtering](https://www.meilisearch.com/docs/learn/advanced/filtering) and [faceted search](https://www.meilisearch.com/docs/learn/advanced/faceted_search):** enhance your user's search experience with custom filters and build a faceted search interface in a few lines of code
+- **[Sorting](https://www.meilisearch.com/docs/learn/advanced/sorting):** sort results based on price, date, or pretty much anything else your users need
 - **[Synonym support](https://www.meilisearch.com/docs/learn/getting_started/customizing_relevancy#synonyms):** configure synonyms to include more relevant content in your search results
-- **[Geosearch](https://www.meilisearch.com/docs/learn/fine_tuning_results/geosearch):** filter and sort documents based on geographic data
+- **[Geosearch](https://www.meilisearch.com/docs/learn/advanced/geosearch):** filter and sort documents based on geographic data
 - **[Extensive language support](https://www.meilisearch.com/docs/learn/what_is_meilisearch/language):** search datasets in any language, with optimized support for Chinese, Japanese, Hebrew, and languages using the Latin alphabet
 - **[Security management](https://www.meilisearch.com/docs/learn/security/master_api_keys):** control which users can access what data with API keys that allow fine-grained permissions handling
 - **[Multi-Tenancy](https://www.meilisearch.com/docs/learn/security/tenant_tokens):** personalize search results for any number of application tenants
@@ -59,9 +58,9 @@ For basic instructions on how to set up Meilisearch, add documents to an index,
 
 You may also want to check out [Meilisearch 101](https://www.meilisearch.com/docs/learn/getting_started/filtering_and_sorting) for an introduction to some of Meilisearch's most popular features.
 
-## ⚡ Supercharge your Meilisearch experience
+## ☁️ Meilisearch cloud
 
-Say goodbye to server deployment and manual updates with [Meilisearch Cloud](https://www.meilisearch.com/pricing?utm_campaign=oss&utm_source=engine&utm_medium=meilisearch). No credit card required.
+Let us manage your infrastructure so you can focus on integrating a great search experience. Try [Meilisearch Cloud](https://meilisearch.com/pricing) today.
 
 ## 🧰 SDKs & integration tools
 
@@ -75,7 +74,7 @@ Take a look at the complete [Meilisearch integration list](https://www.meilisear
 
 Experienced users will want to keep our [API Reference](https://www.meilisearch.com/docs/reference/api/overview) close at hand.
 
-We also offer a wide range of dedicated guides to all Meilisearch features, such as [filtering](https://www.meilisearch.com/docs/learn/fine_tuning_results/filtering), [sorting](https://www.meilisearch.com/docs/learn/fine_tuning_results/sorting), [geosearch](https://www.meilisearch.com/docs/learn/fine_tuning_results/geosearch), [API keys](https://www.meilisearch.com/docs/learn/security/master_api_keys), and [tenant tokens](https://www.meilisearch.com/docs/learn/security/tenant_tokens).
+We also offer a wide range of dedicated guides to all Meilisearch features, such as [filtering](https://www.meilisearch.com/docs/learn/advanced/filtering), [sorting](https://www.meilisearch.com/docs/learn/advanced/sorting), [geosearch](https://www.meilisearch.com/docs/learn/advanced/geosearch), [API keys](https://www.meilisearch.com/docs/learn/security/master_api_keys), and [tenant tokens](https://www.meilisearch.com/docs/learn/security/tenant_tokens).
 
 Finally, for more in-depth information, refer to our articles explaining fundamental Meilisearch concepts such as [documents](https://www.meilisearch.com/docs/learn/core_concepts/documents) and [indexes](https://www.meilisearch.com/docs/learn/core_concepts/indexes).
 

assets/grafana-dashboard.json

@@ -98,7 +98,7 @@
         "showThresholdMarkers": true,
         "text": {}
       },
-      "pluginVersion": "10.0.1",
+      "pluginVersion": "9.5.2",
       "targets": [
         {
           "datasource": {
@@ -158,7 +158,7 @@
         "showThresholdMarkers": true,
         "text": {}
       },
-      "pluginVersion": "10.0.1",
+      "pluginVersion": "9.5.2",
       "targets": [
         {
           "datasource": {
@@ -176,7 +176,8 @@
     },
     {
       "datasource": {
-        "type": "prometheus"
+        "type": "prometheus",
+        "uid": "c4085c47-f6d3-45dd-b761-6809055bb749"
       },
       "fieldConfig": {
         "defaults": {
@@ -220,7 +221,7 @@
         "showThresholdMarkers": true,
         "text": {}
       },
-      "pluginVersion": "10.0.1",
+      "pluginVersion": "9.5.2",
       "targets": [
         {
           "datasource": {
@@ -240,7 +241,8 @@
     },
     {
       "datasource": {
-        "type": "prometheus"
+        "type": "prometheus",
+        "uid": "c4085c47-f6d3-45dd-b761-6809055bb749"
       },
       "fieldConfig": {
         "defaults": {
@@ -280,7 +282,7 @@
         "showThresholdMarkers": true,
         "text": {}
       },
-      "pluginVersion": "10.0.1",
+      "pluginVersion": "9.5.2",
       "targets": [
         {
           "datasource": {
@@ -300,7 +302,8 @@
     },
     {
       "datasource": {
-        "type": "prometheus"
+        "type": "prometheus",
+        "uid": "c4085c47-f6d3-45dd-b761-6809055bb749"
       },
       "fieldConfig": {
         "defaults": {
@@ -340,7 +343,7 @@
         "showThresholdMarkers": true,
         "text": {}
       },
-      "pluginVersion": "10.0.1",
+      "pluginVersion": "9.5.2",
       "targets": [
         {
           "datasource": {
@@ -360,7 +363,8 @@
     },
     {
       "datasource": {
-        "type": "prometheus"
+        "type": "prometheus",
+        "uid": "c4085c47-f6d3-45dd-b761-6809055bb749"
       },
       "description": "",
       "fieldConfig": {
@@ -407,7 +411,8 @@
             "mode": "absolute",
             "steps": [
               {
-                "color": "green"
+                "color": "green",
+                "value": null
               },
               {
                 "color": "red",
@@ -455,7 +460,8 @@
         },
         {
           "datasource": {
-            "type": "prometheus"
+            "type": "prometheus",
+            "uid": "c4085c47-f6d3-45dd-b761-6809055bb749"
           },
           "editorMode": "builder",
           "expr": "meilisearch_used_db_size_bytes{job=\"meilisearch\", instance=\"$instance\"}",
@@ -553,7 +559,7 @@
           },
           "editorMode": "builder",
           "exemplar": true,
-          "expr": "rate(meilisearch_http_response_time_seconds_sum{instance=\"$instance\", job=\"meilisearch\"}[5m]) / rate(meilisearch_http_response_time_seconds_count[5m])",
+          "expr": "rate(http_response_time_seconds_sum{instance=\"$instance\", job=\"meilisearch\"}[5m]) / rate(http_response_time_seconds_count[5m])",
           "interval": "",
           "legendFormat": "{{method}} {{path}}",
           "range": true,
@@ -565,7 +571,8 @@
     },
     {
       "datasource": {
-        "type": "prometheus"
+        "type": "prometheus",
+        "uid": "c4085c47-f6d3-45dd-b761-6809055bb749"
       },
       "fieldConfig": {
         "defaults": {
@@ -608,7 +615,8 @@
             "mode": "absolute",
             "steps": [
               {
-                "color": "green"
+                "color": "green",
+                "value": null
               },
               {
                 "color": "red",
@@ -735,7 +743,7 @@
           "unit": "s"
         }
       },
-      "pluginVersion": "10.0.1",
+      "pluginVersion": "9.5.2",
       "reverseYBuckets": false,
       "targets": [
         {
@@ -744,7 +752,7 @@
           },
           "editorMode": "builder",
           "exemplar": true,
-          "expr": "sum by(le) (increase(meilisearch_http_response_time_seconds_bucket{path=\"/indexes/$Index/search\", instance=\"$instance\", job=\"meilisearch\"}[30s]))",
+          "expr": "sum by(le) (increase(http_response_time_seconds_bucket{path=\"/indexes/$Index/search\", instance=\"$instance\", job=\"meilisearch\"}[30s]))",
           "format": "heatmap",
           "interval": "",
           "legendFormat": "{{le}}",
@@ -1298,7 +1306,8 @@
           "value": "localhost:7700"
         },
         "datasource": {
-          "type": "prometheus"
+          "type": "prometheus",
+          "uid": "bb3298a4-9acf-4da1-b86a-813f29f50888"
         },
         "definition": "label_values(instance)",
         "hide": 0,
@@ -1320,11 +1329,12 @@
       {
         "current": {
           "selected": false,
-          "text": "index-word-count-10-count",
-          "value": "index-word-count-10-count"
+          "text": "mieli",
+          "value": "mieli"
         },
         "datasource": {
-          "type": "prometheus"
+          "type": "prometheus",
+          "uid": "bb3298a4-9acf-4da1-b86a-813f29f50888"
         },
         "definition": "label_values(index)",
         "hide": 0,
@@ -1361,6 +1371,6 @@
   "timezone": "",
   "title": "Meilisearch",
   "uid": "7wcZ94dnz",
-  "version": 5,
+  "version": 6,
   "weekStart": ""
-}
+}

dump/src/lib.rs

@@ -208,13 +208,12 @@ pub(crate) mod test {
     use std::str::FromStr;
 
     use big_s::S;
-    use maplit::{btreemap, btreeset};
-    use meilisearch_types::facet_values_sort::FacetValuesSort;
+    use maplit::btreeset;
     use meilisearch_types::index_uid_pattern::IndexUidPattern;
     use meilisearch_types::keys::{Action, Key};
-    use meilisearch_types::milli;
     use meilisearch_types::milli::update::Setting;
-    use meilisearch_types::settings::{Checked, FacetingSettings, Settings};
+    use meilisearch_types::milli::{self};
+    use meilisearch_types::settings::{Checked, Settings};
     use meilisearch_types::tasks::{Details, Status};
     use serde_json::{json, Map, Value};
     use time::macros::datetime;
@@ -264,12 +263,7 @@ pub(crate) mod test {
             synonyms: Setting::NotSet,
             distinct_attribute: Setting::NotSet,
             typo_tolerance: Setting::NotSet,
-            faceting: Setting::Set(FacetingSettings {
-                max_values_per_facet: Setting::Set(111),
-                sort_facet_values_by: Setting::Set(
-                    btreemap! { S("age") => FacetValuesSort::Count },
-                ),
-            }),
+            faceting: Setting::NotSet,
             pagination: Setting::NotSet,
             _kind: std::marker::PhantomData,
         };
@@ -418,8 +412,6 @@ pub(crate) mod test {
         }
         keys.flush().unwrap();
 
-        // ========== TODO: create features here
-
         // create the dump
         let mut file = tempfile::tempfile().unwrap();
         dump.persist_to(&mut file).unwrap();

dump/src/reader/compat/v5_to_v6.rs

@@ -191,10 +191,6 @@ impl CompatV5ToV6 {
             })
         })))
     }
-
-    pub fn features(&self) -> Result<Option<v6::RuntimeTogglableFeatures>> {
-        Ok(None)
-    }
 }
 
 pub enum CompatIndexV5ToV6 {
@@ -362,7 +358,6 @@ impl<T> From<v5::Settings<T>> for v6::Settings<v6::Unchecked> {
             faceting: match settings.faceting {
                 v5::Setting::Set(faceting) => v6::Setting::Set(v6::FacetingSettings {
                     max_values_per_facet: faceting.max_values_per_facet.into(),
-                    sort_facet_values_by: v6::Setting::NotSet,
                 }),
                 v5::Setting::Reset => v6::Setting::Reset,
                 v5::Setting::NotSet => v6::Setting::NotSet,

dump/src/reader/mod.rs

@@ -107,13 +107,6 @@ impl DumpReader {
             DumpReader::Compat(compat) => compat.keys(),
         }
     }
-
-    pub fn features(&self) -> Result<Option<v6::RuntimeTogglableFeatures>> {
-        match self {
-            DumpReader::Current(current) => Ok(current.features()),
-            DumpReader::Compat(compat) => compat.features(),
-        }
-    }
 }
 
 impl From<V6Reader> for DumpReader {
@@ -196,8 +189,6 @@ pub(crate) mod test {
 
     use super::*;
 
-    // TODO: add `features` to tests
-
     #[test]
     fn import_dump_v5() {
         let dump = File::open("tests/assets/v5.dump").unwrap();

dump/src/reader/v6/mod.rs

@@ -2,7 +2,6 @@ use std::fs::{self, File};
 use std::io::{BufRead, BufReader, ErrorKind};
 use std::path::Path;
 
-use log::debug;
 pub use meilisearch_types::milli;
 use tempfile::TempDir;
 use time::OffsetDateTime;
@@ -19,7 +18,6 @@ pub type Unchecked = meilisearch_types::settings::Unchecked;
 
 pub type Task = crate::TaskDump;
 pub type Key = meilisearch_types::keys::Key;
-pub type RuntimeTogglableFeatures = meilisearch_types::features::RuntimeTogglableFeatures;
 
 // ===== Other types to clarify the code of the compat module
 // everything related to the tasks
@@ -49,7 +47,6 @@ pub struct V6Reader {
     metadata: Metadata,
     tasks: BufReader<File>,
     keys: BufReader<File>,
-    features: Option<RuntimeTogglableFeatures>,
 }
 
 impl V6Reader {
@@ -61,29 +58,11 @@ impl V6Reader {
             Err(e) => return Err(e.into()),
         };
 
-        let feature_file = match fs::read(dump.path().join("experimental-features.json")) {
-            Ok(feature_file) => Some(feature_file),
-            Err(error) => match error.kind() {
-                // Allows the file to be missing, this will only result in all experimental features disabled.
-                ErrorKind::NotFound => {
-                    debug!("`experimental-features.json` not found in dump");
-                    None
-                }
-                _ => return Err(error.into()),
-            },
-        };
-        let features = if let Some(feature_file) = feature_file {
-            Some(serde_json::from_reader(&*feature_file)?)
-        } else {
-            None
-        };
-
         Ok(V6Reader {
             metadata: serde_json::from_reader(&*meta_file)?,
             instance_uid,
             tasks: BufReader::new(File::open(dump.path().join("tasks").join("queue.jsonl"))?),
             keys: BufReader::new(File::open(dump.path().join("keys.jsonl"))?),
-            features,
             dump,
         })
     }
@@ -150,10 +129,6 @@ impl V6Reader {
             (&mut self.keys).lines().map(|line| -> Result<_> { Ok(serde_json::from_str(&line?)?) }),
         )
     }
-
-    pub fn features(&self) -> Option<RuntimeTogglableFeatures> {
-        self.features
-    }
 }
 
 pub struct UpdateFile {

dump/src/writer.rs

@@ -4,7 +4,6 @@ use std::path::PathBuf;
 
 use flate2::write::GzEncoder;
 use flate2::Compression;
-use meilisearch_types::features::RuntimeTogglableFeatures;
 use meilisearch_types::keys::Key;
 use meilisearch_types::settings::{Checked, Settings};
 use serde_json::{Map, Value};
@@ -54,13 +53,6 @@ impl DumpWriter {
         TaskWriter::new(self.dir.path().join("tasks"))
     }
 
-    pub fn create_experimental_features(&self, features: RuntimeTogglableFeatures) -> Result<()> {
-        Ok(std::fs::write(
-            self.dir.path().join("experimental-features.json"),
-            serde_json::to_string(&features)?,
-        )?)
-    }
-
     pub fn persist_to(self, mut writer: impl Write) -> Result<()> {
         let gz_encoder = GzEncoder::new(&mut writer, Compression::default());
         let mut tar_encoder = tar::Builder::new(gz_encoder);

fuzzers/Cargo.toml

@@ -1,20 +0,0 @@
-[package]
-name = "fuzzers"
-publish = false
-
-version.workspace = true
-authors.workspace = true
-description.workspace = true
-homepage.workspace = true
-readme.workspace = true
-edition.workspace = true
-license.workspace = true
-
-[dependencies]
-arbitrary = { version = "1.3.0", features = ["derive"] }
-clap = { version = "4.3.0", features = ["derive"] }
-fastrand = "1.9.0"
-milli = { path = "../milli" }
-serde = { version = "1.0.160", features = ["derive"] }
-serde_json = { version = "1.0.95", features = ["preserve_order"] }
-tempfile = "3.5.0"

fuzzers/README.md

@@ -1,3 +0,0 @@
-# Fuzzers
-
-The purpose of this crate is to contains all the handmade "fuzzer" we may need.

fuzzers/src/bin/fuzz-indexing.rs

@@ -1,152 +0,0 @@
-use std::num::NonZeroUsize;
-use std::path::PathBuf;
-use std::sync::atomic::{AtomicBool, AtomicUsize, Ordering};
-use std::time::Duration;
-
-use arbitrary::{Arbitrary, Unstructured};
-use clap::Parser;
-use fuzzers::Operation;
-use milli::heed::EnvOpenOptions;
-use milli::update::{IndexDocuments, IndexDocumentsConfig, IndexerConfig};
-use milli::Index;
-use tempfile::TempDir;
-
-#[derive(Debug, Arbitrary)]
-struct Batch([Operation; 5]);
-
-#[derive(Debug, Clone, Parser)]
-struct Opt {
-    /// The number of fuzzer to run in parallel.
-    #[clap(long)]
-    par: Option<NonZeroUsize>,
-    // We need to put a lot of newlines in the following documentation or else everything gets collapsed on one line
-    /// The path in which the databases will be created.
-    /// Using a ramdisk is recommended.
-    ///
-    /// Linux:
-    ///
-    /// sudo mount -t tmpfs -o size=2g tmpfs ramdisk # to create it
-    ///
-    /// sudo umount ramdisk # to remove it
-    ///
-    /// MacOS:
-    ///
-    /// diskutil erasevolume HFS+ 'RAM Disk' `hdiutil attach -nobrowse -nomount ram://4194304 # create it
-    ///
-    /// hdiutil detach /dev/:the_disk
-    #[clap(long)]
-    path: Option<PathBuf>,
-}
-
-fn main() {
-    let opt = Opt::parse();
-    let progression: &'static AtomicUsize = Box::leak(Box::new(AtomicUsize::new(0)));
-    let stop: &'static AtomicBool = Box::leak(Box::new(AtomicBool::new(false)));
-
-    let par = opt.par.unwrap_or_else(|| std::thread::available_parallelism().unwrap()).get();
-    let mut handles = Vec::with_capacity(par);
-
-    for _ in 0..par {
-        let opt = opt.clone();
-
-        let handle = std::thread::spawn(move || {
-            let mut options = EnvOpenOptions::new();
-            options.map_size(1024 * 1024 * 1024 * 1024);
-            let tempdir = match opt.path {
-                Some(path) => TempDir::new_in(path).unwrap(),
-                None => TempDir::new().unwrap(),
-            };
-            let index = Index::new(options, tempdir.path()).unwrap();
-            let indexer_config = IndexerConfig::default();
-            let index_documents_config = IndexDocumentsConfig::default();
-
-            std::thread::scope(|s| {
-                loop {
-                    if stop.load(Ordering::Relaxed) {
-                        return;
-                    }
-                    let v: Vec<u8> =
-                        std::iter::repeat_with(|| fastrand::u8(..)).take(1000).collect();
-
-                    let mut data = Unstructured::new(&v);
-                    let batches = <[Batch; 5]>::arbitrary(&mut data).unwrap();
-                    // will be used to display the error once a thread crashes
-                    let dbg_input = format!("{:#?}", batches);
-
-                    let handle = s.spawn(|| {
-                        let mut wtxn = index.write_txn().unwrap();
-
-                        for batch in batches {
-                            let mut builder = IndexDocuments::new(
-                                &mut wtxn,
-                                &index,
-                                &indexer_config,
-                                index_documents_config.clone(),
-                                |_| (),
-                                || false,
-                            )
-                            .unwrap();
-
-                            for op in batch.0 {
-                                match op {
-                                    Operation::AddDoc(doc) => {
-                                        let documents =
-                                            milli::documents::objects_from_json_value(doc.to_d());
-                                        let documents =
-                                            milli::documents::documents_batch_reader_from_objects(
-                                                documents,
-                                            );
-                                        let (b, _added) = builder.add_documents(documents).unwrap();
-                                        builder = b;
-                                    }
-                                    Operation::DeleteDoc(id) => {
-                                        let (b, _removed) =
-                                            builder.remove_documents(vec![id.to_s()]).unwrap();
-                                        builder = b;
-                                    }
-                                }
-                            }
-                            builder.execute().unwrap();
-
-                            // after executing a batch we check if the database is corrupted
-                            let res = index.search(&wtxn).execute().unwrap();
-                            index.documents(&wtxn, res.documents_ids).unwrap();
-                            progression.fetch_add(1, Ordering::Relaxed);
-                        }
-                        wtxn.abort().unwrap();
-                    });
-                    if let err @ Err(_) = handle.join() {
-                        stop.store(true, Ordering::Relaxed);
-                        err.expect(&dbg_input);
-                    }
-                }
-            });
-        });
-        handles.push(handle);
-    }
-
-    std::thread::spawn(|| {
-        let mut last_value = 0;
-        let start = std::time::Instant::now();
-        loop {
-            let total = progression.load(Ordering::Relaxed);
-            let elapsed = start.elapsed().as_secs();
-            if elapsed > 3600 {
-                // after 1 hour, stop the fuzzer, success
-                std::process::exit(0);
-            }
-            println!(
-                "Has been running for {:?} seconds. Tested {} new values for a total of {}.",
-                elapsed,
-                total - last_value,
-                total
-            );
-            last_value = total;
-            std::thread::sleep(Duration::from_secs(1));
-        }
-    });
-
-    for handle in handles {
-        handle.join().unwrap();
-    }
-}

fuzzers/src/lib.rs

@@ -1,46 +0,0 @@
-use arbitrary::Arbitrary;
-use serde_json::{json, Value};
-
-#[derive(Debug, Arbitrary)]
-pub enum Document {
-    One,
-    Two,
-    Three,
-    Four,
-    Five,
-    Six,
-}
-
-impl Document {
-    pub fn to_d(&self) -> Value {
-        match self {
-            Document::One => json!({ "id": 0, "doggo": "bernese" }),
-            Document::Two => json!({ "id": 0, "doggo": "golden" }),
-            Document::Three => json!({ "id": 0, "catto": "jorts" }),
-            Document::Four => json!({ "id": 1, "doggo": "bernese" }),
-            Document::Five => json!({ "id": 1, "doggo": "golden" }),
-            Document::Six => json!({ "id": 1, "catto": "jorts" }),
-        }
-    }
-}
-
-#[derive(Debug, Arbitrary)]
-pub enum DocId {
-    Zero,
-    One,
-}
-
-impl DocId {
-    pub fn to_s(&self) -> String {
-        match self {
-            DocId::Zero => "0".to_string(),
-            DocId::One => "1".to_string(),
-        }
-    }
-}
-
-#[derive(Debug, Arbitrary)]
-pub enum Operation {
-    AddDoc(Document),
-    DeleteDoc(DocId),
-}

index-scheduler/src/autobatcher.rs

@@ -160,7 +160,7 @@ impl BatchKind {
 impl BatchKind {
     /// Returns a `ControlFlow::Break` if you must stop right now.
     /// The boolean tell you if an index has been created by the batched task.
-    /// To ease the writing of the code. `true` can be returned when you don't need to create an index
+    /// To ease the writting of the code. `true` can be returned when you don't need to create an index
     /// but false can't be returned if you needs to create an index.
     // TODO use an AutoBatchKind as input
     pub fn new(
@@ -214,7 +214,7 @@ impl BatchKind {
 
     /// Returns a `ControlFlow::Break` if you must stop right now.
     /// The boolean tell you if an index has been created by the batched task.
-    /// To ease the writing of the code. `true` can be returned when you don't need to create an index
+    /// To ease the writting of the code. `true` can be returned when you don't need to create an index
     /// but false can't be returned if you needs to create an index.
     #[rustfmt::skip]
     fn accumulate(self, id: TaskId, kind: AutobatchKind, index_already_exists: bool, primary_key: Option<&str>) -> ControlFlow<BatchKind, BatchKind> {
@@ -321,18 +321,9 @@ impl BatchKind {
                 })
             }
             (
-                BatchKind::DocumentOperation { method, allow_index_creation, primary_key, mut operation_ids },
+                this @ BatchKind::DocumentOperation { .. },
                 K::DocumentDeletion,
-            ) => {
-                operation_ids.push(id);
-
-                Continue(BatchKind::DocumentOperation {
-                    method,
-                    allow_index_creation,
-                    primary_key,
-                    operation_ids,
-                })
-            }
+            ) => Break(this),
             // but we can't autobatch documents if it's not the same kind
             // this match branch MUST be AFTER the previous one
             (
@@ -355,35 +346,7 @@ impl BatchKind {
                 deletion_ids.push(id);
                 Continue(BatchKind::DocumentClear { ids: deletion_ids })
             }
-            // we can autobatch the deletion and import if the index already exists
-            (
-                BatchKind::DocumentDeletion { mut deletion_ids },
-                K::DocumentImport { method, allow_index_creation, primary_key }
-            ) if index_already_exists => {
-                deletion_ids.push(id);
-
-                Continue(BatchKind::DocumentOperation {
-                    method,
-                    allow_index_creation,
-                    primary_key,
-                    operation_ids: deletion_ids,
-                })
-            }
-            // we can autobatch the deletion and import if both can't create an index
-            (
-                BatchKind::DocumentDeletion { mut deletion_ids },
-                K::DocumentImport { method, allow_index_creation, primary_key }
-            ) if !allow_index_creation => {
-                deletion_ids.push(id);
-
-                Continue(BatchKind::DocumentOperation {
-                    method,
-                    allow_index_creation,
-                    primary_key,
-                    operation_ids: deletion_ids,
-                })
-            }
-            // we can't autobatch a deletion and an import if the index does not exists but would be created by an addition
+            // we can't autobatch a deletion and an import
             (
                 this @ BatchKind::DocumentDeletion { .. },
                 K::DocumentImport { .. }
@@ -685,36 +648,36 @@ mod tests {
         debug_snapshot!(autobatch_from(false,None,  [settings(false)]), @"Some((Settings { allow_index_creation: false, settings_ids: [0] }, false))");
         debug_snapshot!(autobatch_from(false,None,  [settings(false), settings(false), settings(false)]), @"Some((Settings { allow_index_creation: false, settings_ids: [0, 1, 2] }, false))");
 
-        // We can autobatch document addition with document deletion
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, true))"###);
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, true))"###);
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
-        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
-        debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
-        debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
-        debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, true))"###);
-        debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, true))"###);
-        debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
-        debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
-        // And the other way around
-        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, true, Some("catto"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
-        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, true, Some("catto"))]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
-        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
-        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
-        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
-        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
-        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
+        // We can't autobatch document addition with document deletion
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###);
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###);
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###);
+        debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###);
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###);
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###);
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###);
+        debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###);
+        // we also can't do the only way around
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
+        debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0] }, false))");
     }
 
     #[test]

index-scheduler/src/batch.rs

@@ -839,10 +839,6 @@ impl IndexScheduler {
                     Ok(())
                 })?;
 
-                // 4. Dump experimental feature settings
-                let features = self.features()?.runtime_features();
-                dump.create_experimental_features(features)?;
-
                 let dump_uid = started_at.format(format_description!(
                     "[year repr:full][month repr:numerical][day padding:zero]-[hour padding:zero][minute padding:zero][second padding:zero][subsecond digits:3]"
                 )).unwrap();
@@ -1002,7 +998,7 @@ impl IndexScheduler {
                 }()
                 .unwrap_or_default();
 
-                // The write transaction is directly owned and committed inside.
+                // The write transaction is directly owned and commited inside.
                 match self.index_mapper.delete_index(wtxn, &index_uid) {
                     Ok(()) => (),
                     Err(Error::IndexNotFound(_)) if index_has_been_created => (),

index-scheduler/src/error.rs

@@ -123,8 +123,6 @@ pub enum Error {
     IoError(#[from] std::io::Error),
     #[error(transparent)]
     Persist(#[from] tempfile::PersistError),
-    #[error(transparent)]
-    FeatureNotEnabled(#[from] FeatureNotEnabledError),
 
     #[error(transparent)]
     Anyhow(#[from] anyhow::Error),
@@ -144,16 +142,6 @@ pub enum Error {
     PlannedFailure,
 }
 
-#[derive(Debug, thiserror::Error)]
-#[error(
-    "{disabled_action} requires enabling the `{feature}` experimental feature. See {issue_link}"
-)]
-pub struct FeatureNotEnabledError {
-    pub disabled_action: &'static str,
-    pub feature: &'static str,
-    pub issue_link: &'static str,
-}
-
 impl Error {
     pub fn is_recoverable(&self) -> bool {
         match self {
@@ -182,7 +170,6 @@ impl Error {
             | Error::FileStore(_)
             | Error::IoError(_)
             | Error::Persist(_)
-            | Error::FeatureNotEnabled(_)
             | Error::Anyhow(_) => true,
             Error::CreateBatch(_)
             | Error::CorruptedTaskQueue
@@ -227,7 +214,6 @@ impl ErrorCode for Error {
             Error::FileStore(e) => e.error_code(),
             Error::IoError(e) => e.error_code(),
             Error::Persist(e) => e.error_code(),
-            Error::FeatureNotEnabled(_) => Code::FeatureNotEnabled,
 
             // Irrecoverable errors
             Error::Anyhow(_) => Code::Internal,

index-scheduler/src/features.rs

@@ -1,98 +0,0 @@
-use meilisearch_types::features::{InstanceTogglableFeatures, RuntimeTogglableFeatures};
-use meilisearch_types::heed::types::{SerdeJson, Str};
-use meilisearch_types::heed::{Database, Env, RoTxn, RwTxn};
-
-use crate::error::FeatureNotEnabledError;
-use crate::Result;
-
-const EXPERIMENTAL_FEATURES: &str = "experimental-features";
-
-#[derive(Clone)]
-pub(crate) struct FeatureData {
-    runtime: Database<Str, SerdeJson<RuntimeTogglableFeatures>>,
-    instance: InstanceTogglableFeatures,
-}
-
-#[derive(Debug, Clone, Copy)]
-pub struct RoFeatures {
-    runtime: RuntimeTogglableFeatures,
-    instance: InstanceTogglableFeatures,
-}
-
-impl RoFeatures {
-    fn new(txn: RoTxn<'_>, data: &FeatureData) -> Result<Self> {
-        let runtime = data.runtime_features(txn)?;
-        Ok(Self { runtime, instance: data.instance })
-    }
-
-    pub fn runtime_features(&self) -> RuntimeTogglableFeatures {
-        self.runtime
-    }
-
-    pub fn check_score_details(&self) -> Result<()> {
-        if self.runtime.score_details {
-            Ok(())
-        } else {
-            Err(FeatureNotEnabledError {
-                disabled_action: "Computing score details",
-                feature: "score details",
-                issue_link: "https://github.com/meilisearch/product/discussions/674",
-            }
-            .into())
-        }
-    }
-
-    pub fn check_metrics(&self) -> Result<()> {
-        if self.instance.metrics {
-            Ok(())
-        } else {
-            Err(FeatureNotEnabledError {
-                disabled_action: "Getting metrics",
-                feature: "metrics",
-                issue_link: "https://github.com/meilisearch/meilisearch/discussions/3518",
-            }
-            .into())
-        }
-    }
-
-    pub fn check_vector(&self) -> Result<()> {
-        if self.runtime.vector_store {
-            Ok(())
-        } else {
-            Err(FeatureNotEnabledError {
-                disabled_action: "Passing `vector` as a query parameter",
-                feature: "vector store",
-                issue_link: "https://github.com/meilisearch/product/discussions/677",
-            }
-            .into())
-        }
-    }
-}
-
-impl FeatureData {
-    pub fn new(env: &Env, instance_features: InstanceTogglableFeatures) -> Result<Self> {
-        let mut wtxn = env.write_txn()?;
-        let runtime_features = env.create_database(&mut wtxn, Some(EXPERIMENTAL_FEATURES))?;
-        wtxn.commit()?;
-
-        Ok(Self { runtime: runtime_features, instance: instance_features })
-    }
-
-    pub fn put_runtime_features(
-        &self,
-        mut wtxn: RwTxn,
-        features: RuntimeTogglableFeatures,
-    ) -> Result<()> {
-        self.runtime.put(&mut wtxn, EXPERIMENTAL_FEATURES, &features)?;
-        wtxn.commit()?;
-        Ok(())
-    }
-
-    fn runtime_features(&self, txn: RoTxn) -> Result<RuntimeTogglableFeatures> {
-        Ok(self.runtime.get(&txn, EXPERIMENTAL_FEATURES)?.unwrap_or_default())
-    }
-
-    pub fn features(&self, txn: RoTxn) -> Result<RoFeatures> {
-        RoFeatures::new(txn, self)
-    }
-}

index-scheduler/src/index_mapper/index_map.rs

@@ -223,9 +223,7 @@ impl IndexMap {
         enable_mdb_writemap: bool,
         map_size_growth: usize,
     ) {
-        let Some(index) = self.available.remove(uuid) else {
-            return;
-        };
+        let Some(index) = self.available.remove(uuid) else { return; };
         self.close(*uuid, index, enable_mdb_writemap, map_size_growth);
     }
 

index-scheduler/src/insta_snapshot.rs

@@ -28,7 +28,6 @@ pub fn snapshot_index_scheduler(scheduler: &IndexScheduler) -> String {
         started_at,
         finished_at,
         index_mapper,
-        features: _,
         max_number_of_tasks: _,
         wake_up: _,
         dumps_path: _,

index-scheduler/src/lib.rs

@@ -21,7 +21,6 @@ content of the scheduler or enqueue new tasks.
 mod autobatcher;
 mod batch;
 pub mod error;
-mod features;
 mod index_mapper;
 #[cfg(test)]
 mod insta_snapshot;
@@ -42,10 +41,8 @@ use std::time::Duration;
 
 use dump::{KindDump, TaskDump, UpdateFile};
 pub use error::Error;
-pub use features::RoFeatures;
 use file_store::FileStore;
 use meilisearch_types::error::ResponseError;
-use meilisearch_types::features::{InstanceTogglableFeatures, RuntimeTogglableFeatures};
 use meilisearch_types::heed::types::{OwnedType, SerdeBincode, SerdeJson, Str};
 use meilisearch_types::heed::{self, Database, Env, RoTxn, RwTxn};
 use meilisearch_types::milli::documents::DocumentsBatchBuilder;
@@ -250,8 +247,6 @@ pub struct IndexSchedulerOptions {
     /// The maximum number of tasks stored in the task queue before starting
     /// to auto schedule task deletions.
     pub max_number_of_tasks: usize,
-    /// The experimental features enabled for this instance.
-    pub instance_features: InstanceTogglableFeatures,
 }
 
 /// Structure which holds meilisearch's indexes and schedules the tasks
@@ -295,9 +290,6 @@ pub struct IndexScheduler {
     /// In charge of creating, opening, storing and returning indexes.
     pub(crate) index_mapper: IndexMapper,
 
-    /// In charge of fetching and setting the status of experimental features.
-    features: features::FeatureData,
-
     /// Get a signal when a batch needs to be processed.
     pub(crate) wake_up: Arc<SignalEvent>,
 
@@ -368,7 +360,6 @@ impl IndexScheduler {
             planned_failures: self.planned_failures.clone(),
             #[cfg(test)]
             run_loop_iteration: self.run_loop_iteration.clone(),
-            features: self.features.clone(),
         }
     }
 }
@@ -407,12 +398,9 @@ impl IndexScheduler {
         };
 
         let env = heed::EnvOpenOptions::new()
-            .max_dbs(11)
+            .max_dbs(10)
             .map_size(budget.task_db_size)
             .open(options.tasks_path)?;
-
-        let features = features::FeatureData::new(&env, options.instance_features)?;
-
         let file_store = FileStore::new(&options.update_file_path)?;
 
         let mut wtxn = env.write_txn()?;
@@ -464,7 +452,6 @@ impl IndexScheduler {
             planned_failures,
             #[cfg(test)]
             run_loop_iteration: Arc::new(RwLock::new(0)),
-            features,
         };
 
         this.run();
@@ -1227,17 +1214,6 @@ impl IndexScheduler {
         Ok(IndexStats { is_indexing, inner_stats: index_stats })
     }
 
-    pub fn features(&self) -> Result<RoFeatures> {
-        let rtxn = self.read_txn()?;
-        self.features.features(rtxn)
-    }
-
-    pub fn put_runtime_features(&self, features: RuntimeTogglableFeatures) -> Result<()> {
-        let wtxn = self.env.write_txn().map_err(Error::HeedTransaction)?;
-        self.features.put_runtime_features(wtxn, features)?;
-        Ok(())
-    }
-
     pub(crate) fn delete_persisted_task_data(&self, task: &Task) -> Result<()> {
         match task.content_uuid() {
             Some(content_file) => self.delete_update_file(content_file),
@@ -1558,7 +1534,6 @@ mod tests {
                 indexer_config,
                 autobatching_enabled: true,
                 max_number_of_tasks: 1_000_000,
-                instance_features: Default::default(),
             };
             configuration(&mut options);
 
@@ -1810,7 +1785,7 @@ mod tests {
             assert_eq!(task.kind.as_kind(), k);
         }
 
-        snapshot!(snapshot_index_scheduler(&index_scheduler), name: "everything_is_successfully_registered");
+        snapshot!(snapshot_index_scheduler(&index_scheduler), name: "everything_is_succesfully_registered");
     }
 
     #[test]
@@ -2100,105 +2075,6 @@ mod tests {
         snapshot!(snapshot_index_scheduler(&index_scheduler), name: "both_task_succeeded");
     }
 
-    #[test]
-    fn document_addition_and_document_deletion() {
-        let (index_scheduler, mut handle) = IndexScheduler::test(true, vec![]);
-
-        let content = r#"[
-            { "id": 1, "doggo": "jean bob" },
-            { "id": 2, "catto": "jorts" },
-            { "id": 3, "doggo": "bork" }
-        ]"#;
-
-        let (uuid, mut file) = index_scheduler.create_update_file_with_uuid(0).unwrap();
-        let documents_count = read_json(content.as_bytes(), file.as_file_mut()).unwrap();
-        file.persist().unwrap();
-        index_scheduler
-            .register(KindWithContent::DocumentAdditionOrUpdate {
-                index_uid: S("doggos"),
-                primary_key: Some(S("id")),
-                method: ReplaceDocuments,
-                content_file: uuid,
-                documents_count,
-                allow_index_creation: true,
-            })
-            .unwrap();
-        snapshot!(snapshot_index_scheduler(&index_scheduler), name: "registered_the_first_task");
-        index_scheduler
-            .register(KindWithContent::DocumentDeletion {
-                index_uid: S("doggos"),
-                documents_ids: vec![S("1"), S("2")],
-            })
-            .unwrap();
-        snapshot!(snapshot_index_scheduler(&index_scheduler), name: "registered_the_second_task");
-
-        handle.advance_one_successful_batch(); // The addition AND deletion should've been batched together
-        snapshot!(snapshot_index_scheduler(&index_scheduler), name: "after_processing_the_batch");
-
-        let index = index_scheduler.index("doggos").unwrap();
-        let rtxn = index.read_txn().unwrap();
-        let field_ids_map = index.fields_ids_map(&rtxn).unwrap();
-        let field_ids = field_ids_map.ids().collect::<Vec<_>>();
-        let documents = index
-            .all_documents(&rtxn)
-            .unwrap()
-            .map(|ret| obkv_to_json(&field_ids, &field_ids_map, ret.unwrap().1).unwrap())
-            .collect::<Vec<_>>();
-        snapshot!(serde_json::to_string_pretty(&documents).unwrap(), name: "documents");
-    }
-
-    #[test]
-    fn document_deletion_and_document_addition() {
-        let (index_scheduler, mut handle) = IndexScheduler::test(true, vec![]);
-        index_scheduler
-            .register(KindWithContent::DocumentDeletion {
-                index_uid: S("doggos"),
-                documents_ids: vec![S("1"), S("2")],
-            })
-            .unwrap();
-        snapshot!(snapshot_index_scheduler(&index_scheduler), name: "registered_the_first_task");
-
-        let content = r#"[
-            { "id": 1, "doggo": "jean bob" },
-            { "id": 2, "catto": "jorts" },
-            { "id": 3, "doggo": "bork" }
-        ]"#;
-
-        let (uuid, mut file) = index_scheduler.create_update_file_with_uuid(0).unwrap();
-        let documents_count = read_json(content.as_bytes(), file.as_file_mut()).unwrap();
-        file.persist().unwrap();
-        index_scheduler
-            .register(KindWithContent::DocumentAdditionOrUpdate {
-                index_uid: S("doggos"),
-                primary_key: Some(S("id")),
-                method: ReplaceDocuments,
-                content_file: uuid,
-                documents_count,
-                allow_index_creation: true,
-            })
-            .unwrap();
-        snapshot!(snapshot_index_scheduler(&index_scheduler), name: "registered_the_second_task");
-
-        // The deletion should have failed because it can't create an index
-        handle.advance_one_failed_batch();
-        snapshot!(snapshot_index_scheduler(&index_scheduler), name: "after_failing_the_deletion");
-
-        // The addition should works
-        handle.advance_one_successful_batch();
-        snapshot!(snapshot_index_scheduler(&index_scheduler), name: "after_last_successful_addition");
-
-        let index = index_scheduler.index("doggos").unwrap();
-        let rtxn = index.read_txn().unwrap();
-        let field_ids_map = index.fields_ids_map(&rtxn).unwrap();
-        let field_ids = field_ids_map.ids().collect::<Vec<_>>();
-        let documents = index
-            .all_documents(&rtxn)
-            .unwrap()
-            .map(|ret| obkv_to_json(&field_ids, &field_ids_map, ret.unwrap().1).unwrap())
-            .collect::<Vec<_>>();
-        snapshot!(serde_json::to_string_pretty(&documents).unwrap(), name: "documents");
-    }
-
     #[test]
     fn do_not_batch_task_of_different_indexes() {
         let (index_scheduler, mut handle) = IndexScheduler::test(true, vec![]);

index-scheduler/src/snapshots/lib.rs/document_addition_and_document_deletion/after_processing_the_batch.snap

@@ -1,43 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-### Autobatching Enabled = true
-### Processing Tasks:
-[]
-----------------------------------------------------------------------
-### All Tasks:
-0 {uid: 0, status: succeeded, details: { received_documents: 3, indexed_documents: Some(3) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
-1 {uid: 1, status: succeeded, details: { received_document_ids: 2, deleted_documents: Some(2) }, kind: DocumentDeletion { index_uid: "doggos", documents_ids: ["1", "2"] }}
-----------------------------------------------------------------------
-### Status:
-enqueued []
-succeeded [0,1,]
-----------------------------------------------------------------------
-### Kind:
-"documentAdditionOrUpdate" [0,]
-"documentDeletion" [1,]
-----------------------------------------------------------------------
-### Index Tasks:
-doggos [0,1,]
-----------------------------------------------------------------------
-### Index Mapper:
-doggos: { number_of_documents: 1, field_distribution: {"doggo": 1, "id": 1} }
-
-----------------------------------------------------------------------
-### Canceled By:
-
-----------------------------------------------------------------------
-### Enqueued At:
-[timestamp] [0,]
-[timestamp] [1,]
-----------------------------------------------------------------------
-### Started At:
-[timestamp] [0,1,]
-----------------------------------------------------------------------
-### Finished At:
-[timestamp] [0,1,]
-----------------------------------------------------------------------
-### File Store:
-
-----------------------------------------------------------------------
-

index-scheduler/src/snapshots/lib.rs/document_addition_and_document_deletion/documents.snap

@@ -1,9 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-[
-  {
-    "id": 3,
-    "doggo": "bork"
-  }
-]

index-scheduler/src/snapshots/lib.rs/document_addition_and_document_deletion/registered_the_first_task.snap

@@ -1,37 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-### Autobatching Enabled = true
-### Processing Tasks:
-[]
-----------------------------------------------------------------------
-### All Tasks:
-0 {uid: 0, status: enqueued, details: { received_documents: 3, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
-----------------------------------------------------------------------
-### Status:
-enqueued [0,]
-----------------------------------------------------------------------
-### Kind:
-"documentAdditionOrUpdate" [0,]
-----------------------------------------------------------------------
-### Index Tasks:
-doggos [0,]
-----------------------------------------------------------------------
-### Index Mapper:
-
-----------------------------------------------------------------------
-### Canceled By:
-
-----------------------------------------------------------------------
-### Enqueued At:
-[timestamp] [0,]
-----------------------------------------------------------------------
-### Started At:
-----------------------------------------------------------------------
-### Finished At:
-----------------------------------------------------------------------
-### File Store:
-00000000-0000-0000-0000-000000000000
-
-----------------------------------------------------------------------
-

index-scheduler/src/snapshots/lib.rs/document_addition_and_document_deletion/registered_the_second_task.snap

@@ -1,40 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-### Autobatching Enabled = true
-### Processing Tasks:
-[]
-----------------------------------------------------------------------
-### All Tasks:
-0 {uid: 0, status: enqueued, details: { received_documents: 3, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
-1 {uid: 1, status: enqueued, details: { received_document_ids: 2, deleted_documents: None }, kind: DocumentDeletion { index_uid: "doggos", documents_ids: ["1", "2"] }}
-----------------------------------------------------------------------
-### Status:
-enqueued [0,1,]
-----------------------------------------------------------------------
-### Kind:
-"documentAdditionOrUpdate" [0,]
-"documentDeletion" [1,]
-----------------------------------------------------------------------
-### Index Tasks:
-doggos [0,1,]
-----------------------------------------------------------------------
-### Index Mapper:
-
-----------------------------------------------------------------------
-### Canceled By:
-
-----------------------------------------------------------------------
-### Enqueued At:
-[timestamp] [0,]
-[timestamp] [1,]
-----------------------------------------------------------------------
-### Started At:
-----------------------------------------------------------------------
-### Finished At:
-----------------------------------------------------------------------
-### File Store:
-00000000-0000-0000-0000-000000000000
-
-----------------------------------------------------------------------
-

index-scheduler/src/snapshots/lib.rs/document_deletion_and_document_addition/after_failing_the_deletion.snap

@@ -1,43 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-### Autobatching Enabled = true
-### Processing Tasks:
-[]
-----------------------------------------------------------------------
-### All Tasks:
-0 {uid: 0, status: failed, error: ResponseError { code: 200, message: "Index `doggos` not found.", error_code: "index_not_found", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#index_not_found" }, details: { received_document_ids: 2, deleted_documents: Some(0) }, kind: DocumentDeletion { index_uid: "doggos", documents_ids: ["1", "2"] }}
-1 {uid: 1, status: enqueued, details: { received_documents: 3, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
-----------------------------------------------------------------------
-### Status:
-enqueued [1,]
-failed [0,]
-----------------------------------------------------------------------
-### Kind:
-"documentAdditionOrUpdate" [1,]
-"documentDeletion" [0,]
-----------------------------------------------------------------------
-### Index Tasks:
-doggos [0,1,]
-----------------------------------------------------------------------
-### Index Mapper:
-
-----------------------------------------------------------------------
-### Canceled By:
-
-----------------------------------------------------------------------
-### Enqueued At:
-[timestamp] [0,]
-[timestamp] [1,]
-----------------------------------------------------------------------
-### Started At:
-[timestamp] [0,]
-----------------------------------------------------------------------
-### Finished At:
-[timestamp] [0,]
-----------------------------------------------------------------------
-### File Store:
-00000000-0000-0000-0000-000000000000
-
-----------------------------------------------------------------------
-

index-scheduler/src/snapshots/lib.rs/document_deletion_and_document_addition/after_last_successful_addition.snap

@@ -1,46 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-### Autobatching Enabled = true
-### Processing Tasks:
-[]
-----------------------------------------------------------------------
-### All Tasks:
-0 {uid: 0, status: failed, error: ResponseError { code: 200, message: "Index `doggos` not found.", error_code: "index_not_found", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#index_not_found" }, details: { received_document_ids: 2, deleted_documents: Some(0) }, kind: DocumentDeletion { index_uid: "doggos", documents_ids: ["1", "2"] }}
-1 {uid: 1, status: succeeded, details: { received_documents: 3, indexed_documents: Some(3) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
-----------------------------------------------------------------------
-### Status:
-enqueued []
-succeeded [1,]
-failed [0,]
-----------------------------------------------------------------------
-### Kind:
-"documentAdditionOrUpdate" [1,]
-"documentDeletion" [0,]
-----------------------------------------------------------------------
-### Index Tasks:
-doggos [0,1,]
-----------------------------------------------------------------------
-### Index Mapper:
-doggos: { number_of_documents: 3, field_distribution: {"catto": 1, "doggo": 2, "id": 3} }
-
-----------------------------------------------------------------------
-### Canceled By:
-
-----------------------------------------------------------------------
-### Enqueued At:
-[timestamp] [0,]
-[timestamp] [1,]
-----------------------------------------------------------------------
-### Started At:
-[timestamp] [0,]
-[timestamp] [1,]
-----------------------------------------------------------------------
-### Finished At:
-[timestamp] [0,]
-[timestamp] [1,]
-----------------------------------------------------------------------
-### File Store:
-
-----------------------------------------------------------------------
-

index-scheduler/src/snapshots/lib.rs/document_deletion_and_document_addition/documents.snap

@@ -1,17 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-[
-  {
-    "id": 1,
-    "doggo": "jean bob"
-  },
-  {
-    "id": 2,
-    "catto": "jorts"
-  },
-  {
-    "id": 3,
-    "doggo": "bork"
-  }
-]

index-scheduler/src/snapshots/lib.rs/document_deletion_and_document_addition/registered_the_first_task.snap

@@ -1,36 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-### Autobatching Enabled = true
-### Processing Tasks:
-[]
-----------------------------------------------------------------------
-### All Tasks:
-0 {uid: 0, status: enqueued, details: { received_document_ids: 2, deleted_documents: None }, kind: DocumentDeletion { index_uid: "doggos", documents_ids: ["1", "2"] }}
-----------------------------------------------------------------------
-### Status:
-enqueued [0,]
-----------------------------------------------------------------------
-### Kind:
-"documentDeletion" [0,]
-----------------------------------------------------------------------
-### Index Tasks:
-doggos [0,]
-----------------------------------------------------------------------
-### Index Mapper:
-
-----------------------------------------------------------------------
-### Canceled By:
-
-----------------------------------------------------------------------
-### Enqueued At:
-[timestamp] [0,]
-----------------------------------------------------------------------
-### Started At:
-----------------------------------------------------------------------
-### Finished At:
-----------------------------------------------------------------------
-### File Store:
-
-----------------------------------------------------------------------
-

index-scheduler/src/snapshots/lib.rs/document_deletion_and_document_addition/registered_the_second_task.snap

@@ -1,40 +0,0 @@
----
-source: index-scheduler/src/lib.rs
----
-### Autobatching Enabled = true
-### Processing Tasks:
-[]
-----------------------------------------------------------------------
-### All Tasks:
-0 {uid: 0, status: enqueued, details: { received_document_ids: 2, deleted_documents: None }, kind: DocumentDeletion { index_uid: "doggos", documents_ids: ["1", "2"] }}
-1 {uid: 1, status: enqueued, details: { received_documents: 3, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
-----------------------------------------------------------------------
-### Status:
-enqueued [0,1,]
-----------------------------------------------------------------------
-### Kind:
-"documentAdditionOrUpdate" [1,]
-"documentDeletion" [0,]
-----------------------------------------------------------------------
-### Index Tasks:
-doggos [0,1,]
-----------------------------------------------------------------------
-### Index Mapper:
-
-----------------------------------------------------------------------
-### Canceled By:
-
-----------------------------------------------------------------------
-### Enqueued At:
-[timestamp] [0,]
-[timestamp] [1,]
-----------------------------------------------------------------------
-### Started At:
-----------------------------------------------------------------------
-### Finished At:
-----------------------------------------------------------------------
-### File Store:
-00000000-0000-0000-0000-000000000000
-
-----------------------------------------------------------------------
-

meilisearch-types/src/deserr/mod.rs

@@ -151,10 +151,6 @@ make_missing_field_convenience_builder!(MissingApiKeyExpiresAt, missing_api_key_
 make_missing_field_convenience_builder!(MissingApiKeyIndexes, missing_api_key_indexes);
 make_missing_field_convenience_builder!(MissingSwapIndexes, missing_swap_indexes);
 make_missing_field_convenience_builder!(MissingDocumentFilter, missing_document_filter);
-make_missing_field_convenience_builder!(
-    MissingFacetSearchFacetName,
-    missing_facet_search_facet_name
-);
 
 // Integrate a sub-error into a [`DeserrError`] by taking its error message but using
 // the default error code (C) from `Self`

meilisearch-types/src/error.rs

@@ -218,7 +218,6 @@ MissingDocumentFilter                 , InvalidRequest       , BAD_REQUEST ;
 InvalidDocumentFilter                 , InvalidRequest       , BAD_REQUEST ;
 InvalidDocumentGeoField               , InvalidRequest       , BAD_REQUEST ;
 InvalidVectorDimensions               , InvalidRequest       , BAD_REQUEST ;
-InvalidVectorsType                    , InvalidRequest       , BAD_REQUEST ;
 InvalidDocumentId                     , InvalidRequest       , BAD_REQUEST ;
 InvalidDocumentLimit                  , InvalidRequest       , BAD_REQUEST ;
 InvalidDocumentOffset                 , InvalidRequest       , BAD_REQUEST ;
@@ -226,14 +225,12 @@ InvalidIndexLimit                     , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexOffset                    , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexPrimaryKey                , InvalidRequest       , BAD_REQUEST ;
 InvalidIndexUid                       , InvalidRequest       , BAD_REQUEST ;
-InvalidSearchAttributesToSearchOn     , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchAttributesToCrop         , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchAttributesToHighlight    , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchAttributesToRetrieve     , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchCropLength               , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchCropMarker               , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchFacets                   , InvalidRequest       , BAD_REQUEST ;
-InvalidFacetSearchFacetName           , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchFilter                   , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchHighlightPostTag         , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchHighlightPreTag          , InvalidRequest       , BAD_REQUEST ;
@@ -243,12 +240,7 @@ InvalidSearchMatchingStrategy         , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchOffset                   , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchPage                     , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchQ                        , InvalidRequest       , BAD_REQUEST ;
-InvalidFacetSearchQuery               , InvalidRequest       , BAD_REQUEST ;
-InvalidFacetSearchName                , InvalidRequest       , BAD_REQUEST ;
-InvalidSearchVector                   , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchShowMatchesPosition      , InvalidRequest       , BAD_REQUEST ;
-InvalidSearchShowRankingScore         , InvalidRequest       , BAD_REQUEST ;
-InvalidSearchShowRankingScoreDetails  , InvalidRequest       , BAD_REQUEST ;
 InvalidSearchSort                     , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsDisplayedAttributes    , InvalidRequest       , BAD_REQUEST ;
 InvalidSettingsDistinctAttribute      , InvalidRequest       , BAD_REQUEST ;
@@ -278,7 +270,6 @@ InvalidTaskStatuses                   , InvalidRequest       , BAD_REQUEST ;
 InvalidTaskTypes                      , InvalidRequest       , BAD_REQUEST ;
 InvalidTaskUids                       , InvalidRequest       , BAD_REQUEST  ;
 IoError                               , System               , UNPROCESSABLE_ENTITY;
-FeatureNotEnabled                     , InvalidRequest       , BAD_REQUEST ;
 MalformedPayload                      , InvalidRequest       , BAD_REQUEST ;
 MaxFieldsLimitExceeded                , InvalidRequest       , BAD_REQUEST ;
 MissingApiKeyActions                  , InvalidRequest       , BAD_REQUEST ;
@@ -287,7 +278,6 @@ MissingApiKeyIndexes                  , InvalidRequest       , BAD_REQUEST ;
 MissingAuthorizationHeader            , Auth                 , UNAUTHORIZED ;
 MissingContentType                    , InvalidRequest       , UNSUPPORTED_MEDIA_TYPE ;
 MissingDocumentId                     , InvalidRequest       , BAD_REQUEST ;
-MissingFacetSearchFacetName           , InvalidRequest       , BAD_REQUEST ;
 MissingIndexUid                       , InvalidRequest       , BAD_REQUEST ;
 MissingMasterKey                      , Auth                 , UNAUTHORIZED ;
 MissingPayload                        , InvalidRequest       , BAD_REQUEST ;
@@ -341,16 +331,9 @@ impl ErrorCode for milli::Error {
                     UserError::SortRankingRuleMissing => Code::InvalidSearchSort,
                     UserError::InvalidFacetsDistribution { .. } => Code::InvalidSearchFacets,
                     UserError::InvalidSortableAttribute { .. } => Code::InvalidSearchSort,
-                    UserError::InvalidSearchableAttribute { .. } => {
-                        Code::InvalidSearchAttributesToSearchOn
-                    }
-                    UserError::InvalidFacetSearchFacetName { .. } => {
-                        Code::InvalidFacetSearchFacetName
-                    }
                     UserError::CriterionError(_) => Code::InvalidSettingsRankingRules,
                     UserError::InvalidGeoField { .. } => Code::InvalidDocumentGeoField,
                     UserError::InvalidVectorDimensions { .. } => Code::InvalidVectorDimensions,
-                    UserError::InvalidVectorsType { .. } => Code::InvalidVectorsType,
                     UserError::SortError(_) => Code::InvalidSearchSort,
                     UserError::InvalidMinTypoWordLenSetting(_, _) => {
                         Code::InvalidSettingsTypoTolerance

meilisearch-types/src/facet_values_sort.rs

@@ -1,33 +0,0 @@
-use deserr::Deserr;
-use milli::OrderBy;
-use serde::{Deserialize, Serialize};
-
-#[derive(Debug, Default, Copy, Clone, PartialEq, Eq, Serialize, Deserialize, Deserr)]
-#[serde(rename_all = "camelCase")]
-#[deserr(rename_all = camelCase)]
-pub enum FacetValuesSort {
-    /// Facet values are sorted in alphabetical order, ascending from A to Z.
-    #[default]
-    Alpha,
-    /// Facet values are sorted by decreasing count.
-    /// The count is the number of records containing this facet value in the results of the query.
-    Count,
-}
-
-impl From<FacetValuesSort> for OrderBy {
-    fn from(val: FacetValuesSort) -> Self {
-        match val {
-            FacetValuesSort::Alpha => OrderBy::Lexicographic,
-            FacetValuesSort::Count => OrderBy::Count,
-        }
-    }
-}
-
-impl From<OrderBy> for FacetValuesSort {
-    fn from(val: OrderBy) -> Self {
-        match val {
-            OrderBy::Lexicographic => FacetValuesSort::Alpha,
-            OrderBy::Count => FacetValuesSort::Count,
-        }
-    }
-}

meilisearch-types/src/features.rs

@@ -1,13 +0,0 @@
-use serde::{Deserialize, Serialize};
-
-#[derive(Serialize, Deserialize, Debug, Clone, Copy, Default)]
-#[serde(rename_all = "camelCase", default)]
-pub struct RuntimeTogglableFeatures {
-    pub score_details: bool,
-    pub vector_store: bool,
-}
-
-#[derive(Default, Debug, Clone, Copy)]
-pub struct InstanceTogglableFeatures {
-    pub metrics: bool,
-}

meilisearch-types/src/keys.rs

@@ -147,7 +147,9 @@ impl Key {
 fn parse_expiration_date(
     string: Option<String>,
 ) -> std::result::Result<Option<OffsetDateTime>, ParseOffsetDateTimeError> {
-    let Some(string) = string else { return Ok(None) };
+    let Some(string) = string else {
+        return Ok(None)
+    };
     let datetime = if let Ok(datetime) = OffsetDateTime::parse(&string, &Rfc3339) {
         datetime
     } else if let Ok(primitive_datetime) = PrimitiveDateTime::parse(
@@ -272,12 +274,6 @@ pub enum Action {
     #[serde(rename = "keys.delete")]
     #[deserr(rename = "keys.delete")]
     KeysDelete,
-    #[serde(rename = "experimental.get")]
-    #[deserr(rename = "experimental.get")]
-    ExperimentalFeaturesGet,
-    #[serde(rename = "experimental.update")]
-    #[deserr(rename = "experimental.update")]
-    ExperimentalFeaturesUpdate,
 }
 
 impl Action {
@@ -314,8 +310,6 @@ impl Action {
             KEYS_GET => Some(Self::KeysGet),
             KEYS_UPDATE => Some(Self::KeysUpdate),
             KEYS_DELETE => Some(Self::KeysDelete),
-            EXPERIMENTAL_FEATURES_GET => Some(Self::ExperimentalFeaturesGet),
-            EXPERIMENTAL_FEATURES_UPDATE => Some(Self::ExperimentalFeaturesUpdate),
             _otherwise => None,
         }
     }
@@ -358,6 +352,4 @@ pub mod actions {
     pub const KEYS_GET: u8 = KeysGet.repr();
     pub const KEYS_UPDATE: u8 = KeysUpdate.repr();
     pub const KEYS_DELETE: u8 = KeysDelete.repr();
-    pub const EXPERIMENTAL_FEATURES_GET: u8 = ExperimentalFeaturesGet.repr();
-    pub const EXPERIMENTAL_FEATURES_UPDATE: u8 = ExperimentalFeaturesUpdate.repr();
 }

meilisearch-types/src/lib.rs

@@ -2,8 +2,6 @@ pub mod compression;
 pub mod deserr;
 pub mod document_formats;
 pub mod error;
-pub mod facet_values_sort;
-pub mod features;
 pub mod index_uid;
 pub mod index_uid_pattern;
 pub mod keys;

meilisearch-types/src/settings.rs

@@ -14,9 +14,8 @@ use serde::{Deserialize, Serialize, Serializer};
 
 use crate::deserr::DeserrJsonError;
 use crate::error::deserr_codes::*;
-use crate::facet_values_sort::FacetValuesSort;
 
-/// The maximum number of results that the engine
+/// The maximimum number of results that the engine
 /// will be able to return in one search call.
 pub const DEFAULT_PAGINATION_MAX_TOTAL_HITS: usize = 1000;
 
@@ -103,9 +102,6 @@ pub struct FacetingSettings {
     #[serde(default, skip_serializing_if = "Setting::is_not_set")]
     #[deserr(default)]
     pub max_values_per_facet: Setting<usize>,
-    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
-    #[deserr(default)]
-    pub sort_facet_values_by: Setting<BTreeMap<String, FacetValuesSort>>,
 }
 
 #[derive(Debug, Clone, Default, Serialize, Deserialize, PartialEq, Eq, Deserr)]
@@ -402,25 +398,13 @@ pub fn apply_settings_to_builder(
         Setting::NotSet => (),
     }
 
-    match &settings.faceting {
-        Setting::Set(FacetingSettings { max_values_per_facet, sort_facet_values_by }) => {
-            match max_values_per_facet {
-                Setting::Set(val) => builder.set_max_values_per_facet(*val),
-                Setting::Reset => builder.reset_max_values_per_facet(),
-                Setting::NotSet => (),
-            }
-            match sort_facet_values_by {
-                Setting::Set(val) => builder.set_sort_facet_values_by(
-                    val.iter().map(|(name, order)| (name.clone(), (*order).into())).collect(),
-                ),
-                Setting::Reset => builder.reset_sort_facet_values_by(),
-                Setting::NotSet => (),
-            }
-        }
-        Setting::Reset => {
-            builder.reset_max_values_per_facet();
-            builder.reset_sort_facet_values_by();
-        }
+    match settings.faceting {
+        Setting::Set(ref value) => match value.max_values_per_facet {
+            Setting::Set(val) => builder.set_max_values_per_facet(val),
+            Setting::Reset => builder.reset_max_values_per_facet(),
+            Setting::NotSet => (),
+        },
+        Setting::Reset => builder.reset_max_values_per_facet(),
         Setting::NotSet => (),
     }
 
@@ -492,13 +476,6 @@ pub fn settings(
         max_values_per_facet: Setting::Set(
             index.max_values_per_facet(rtxn)?.unwrap_or(DEFAULT_VALUES_PER_FACET),
         ),
-        sort_facet_values_by: Setting::Set(
-            index
-                .sort_facet_values_by(rtxn)?
-                .into_iter()
-                .map(|(name, sort)| (name, sort.into()))
-                .collect(),
-        ),
     };
 
     let pagination = PaginationSettings {

meilisearch/Cargo.toml

@@ -14,27 +14,14 @@ default-run = "meilisearch"
 
 [dependencies]
 actix-cors = "0.6.4"
-actix-http = { version = "3.3.1", default-features = false, features = [
-    "compress-brotli",
-    "compress-gzip",
-    "rustls",
-] }
-actix-web = { version = "4.3.1", default-features = false, features = [
-    "macros",
-    "compress-brotli",
-    "compress-gzip",
-    "cookies",
-    "rustls",
-] }
+actix-http = { version = "3.3.1", default-features = false, features = ["compress-brotli", "compress-gzip", "rustls"] }
+actix-web = { version = "4.3.1", default-features = false, features = ["macros", "compress-brotli", "compress-gzip", "cookies", "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"] }
 async-stream = "0.3.5"
 async-trait = "0.1.68"
 bstr = "1.4.0"
-byte-unit = { version = "4.0.19", default-features = false, features = [
-    "std",
-    "serde",
-] }
+byte-unit = { version = "4.0.19", default-features = false, features = ["std", "serde"] }
 bytes = "1.4.0"
 clap = { version = "4.2.1", features = ["derive", "env"] }
 crossbeam-channel = "0.5.8"
@@ -61,7 +48,6 @@ mime = "0.3.17"
 num_cpus = "1.15.0"
 obkv = "0.2.0"
 once_cell = "1.17.1"
-ordered-float = "3.7.0"
 parking_lot = "0.12.1"
 permissive-json-pointer = { path = "../permissive-json-pointer" }
 pin-project-lite = "0.2.9"
@@ -70,10 +56,7 @@ prometheus = { version = "0.13.3", features = ["process"] }
 rand = "0.8.5"
 rayon = "1.7.0"
 regex = "1.7.3"
-reqwest = { version = "0.11.16", features = [
-    "rustls-tls",
-    "json",
-], default-features = false }
+reqwest = { version = "0.11.16", features = ["rustls-tls", "json"], default-features = false }
 rustls = "0.20.8"
 rustls-pemfile = "1.0.2"
 segment = { version = "0.2.2", optional = true }
@@ -87,12 +70,7 @@ sysinfo = "0.28.4"
 tar = "0.4.38"
 tempfile = "3.5.0"
 thiserror = "1.0.40"
-time = { version = "0.3.20", features = [
-    "serde-well-known",
-    "formatting",
-    "parsing",
-    "macros",
-] }
+time = { version = "0.3.20", features = ["serde-well-known", "formatting", "parsing", "macros"] }
 tokio = { version = "1.27.0", features = ["full"] }
 tokio-stream = "0.1.12"
 toml = "0.7.3"
@@ -111,7 +89,7 @@ brotli = "3.3.4"
 insta = "1.29.0"
 manifest-dir-macros = "0.1.16"
 maplit = "1.0.2"
-meili-snap = { path = "../meili-snap" }
+meili-snap = {path = "../meili-snap"}
 temp-env = "0.3.3"
 urlencoding = "2.1.2"
 yaup = "0.2.1"
@@ -120,10 +98,7 @@ yaup = "0.2.1"
 anyhow = { version = "1.0.70", optional = true }
 cargo_toml = { version = "0.15.2", optional = true }
 hex = { version = "0.4.3", optional = true }
-reqwest = { version = "0.11.16", features = [
-    "blocking",
-    "rustls-tls",
-], default-features = false, optional = true }
+reqwest = { version = "0.11.16", 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 }
@@ -133,17 +108,7 @@ zip = { version = "0.6.4", optional = true }
 [features]
 default = ["analytics", "meilisearch-types/all-tokenizations", "mini-dashboard"]
 analytics = ["segment"]
-mini-dashboard = [
-    "actix-web-static-files",
-    "static-files",
-    "anyhow",
-    "cargo_toml",
-    "hex",
-    "reqwest",
-    "sha-1",
-    "tempfile",
-    "zip",
-]
+mini-dashboard = ["actix-web-static-files", "static-files", "anyhow", "cargo_toml", "hex", "reqwest", "sha-1", "tempfile", "zip"]
 chinese = ["meilisearch-types/chinese"]
 hebrew = ["meilisearch-types/hebrew"]
 japanese = ["meilisearch-types/japanese"]

meilisearch/src/analytics/mock_analytics.rs

@@ -38,18 +38,6 @@ impl MultiSearchAggregator {
     pub fn succeed(&mut self) {}
 }
 
-#[derive(Default)]
-pub struct FacetSearchAggregator;
-
-#[allow(dead_code)]
-impl FacetSearchAggregator {
-    pub fn from_query(_: &dyn Any, _: &dyn Any) -> Self {
-        Self::default()
-    }
-
-    pub fn succeed(&mut self, _: &dyn Any) {}
-}
-
 impl MockAnalytics {
     #[allow(clippy::new_ret_no_self)]
     pub fn new(opt: &Opt) -> Arc<dyn Analytics> {
@@ -68,7 +56,6 @@ impl Analytics for MockAnalytics {
     fn get_search(&self, _aggregate: super::SearchAggregator) {}
     fn post_search(&self, _aggregate: super::SearchAggregator) {}
     fn post_multi_search(&self, _aggregate: super::MultiSearchAggregator) {}
-    fn post_facet_search(&self, _aggregate: super::FacetSearchAggregator) {}
     fn add_documents(
         &self,
         _documents_query: &UpdateDocumentsQuery,

meilisearch/src/analytics/mod.rs

@@ -25,8 +25,6 @@ pub type SegmentAnalytics = mock_analytics::MockAnalytics;
 pub type SearchAggregator = mock_analytics::SearchAggregator;
 #[cfg(any(debug_assertions, not(feature = "analytics")))]
 pub type MultiSearchAggregator = mock_analytics::MultiSearchAggregator;
-#[cfg(any(debug_assertions, not(feature = "analytics")))]
-pub type FacetSearchAggregator = mock_analytics::FacetSearchAggregator;
 
 // if we are in release mode and the feature analytics was enabled
 // we use the real analytics
@@ -36,8 +34,6 @@ pub type SegmentAnalytics = segment_analytics::SegmentAnalytics;
 pub type SearchAggregator = segment_analytics::SearchAggregator;
 #[cfg(all(not(debug_assertions), feature = "analytics"))]
 pub type MultiSearchAggregator = segment_analytics::MultiSearchAggregator;
-#[cfg(all(not(debug_assertions), feature = "analytics"))]
-pub type FacetSearchAggregator = segment_analytics::FacetSearchAggregator;
 
 /// The Meilisearch config dir:
 /// `~/.config/Meilisearch` on *NIX or *BSD.
@@ -92,9 +88,6 @@ pub trait Analytics: Sync + Send {
     /// This method should be called to aggregate a post array of searches
     fn post_multi_search(&self, aggregate: MultiSearchAggregator);
 
-    /// This method should be called to aggregate post facet values searches
-    fn post_facet_search(&self, aggregate: FacetSearchAggregator);
-
     // this method should be called to aggregate a add documents request
     fn add_documents(
         &self,

meilisearch/src/analytics/segment_analytics.rs

@@ -1,6 +1,5 @@
 use std::collections::{BinaryHeap, HashMap, HashSet};
 use std::fs;
-use std::mem::take;
 use std::path::{Path, PathBuf};
 use std::sync::Arc;
 use std::time::{Duration, Instant};
@@ -30,13 +29,11 @@ use super::{
 use crate::analytics::Analytics;
 use crate::option::{default_http_addr, IndexerOpts, MaxMemory, MaxThreads, ScheduleSnapshot};
 use crate::routes::indexes::documents::UpdateDocumentsQuery;
-use crate::routes::indexes::facet_search::FacetSearchQuery;
 use crate::routes::tasks::TasksFilterQuery;
 use crate::routes::{create_all_stats, Stats};
 use crate::search::{
-    FacetSearchResult, MatchingStrategy, SearchQuery, SearchQueryWithIndex, SearchResult,
-    DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
-    DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT,
+    SearchQuery, SearchQueryWithIndex, SearchResult, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER,
+    DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT,
 };
 use crate::Opt;
 
@@ -74,7 +71,6 @@ pub enum AnalyticsMsg {
     AggregateGetSearch(SearchAggregator),
     AggregatePostSearch(SearchAggregator),
     AggregatePostMultiSearch(MultiSearchAggregator),
-    AggregatePostFacetSearch(FacetSearchAggregator),
     AggregateAddDocuments(DocumentsAggregator),
     AggregateDeleteDocuments(DocumentsDeletionAggregator),
     AggregateUpdateDocuments(DocumentsAggregator),
@@ -143,7 +139,6 @@ impl SegmentAnalytics {
             batcher,
             post_search_aggregator: SearchAggregator::default(),
             post_multi_search_aggregator: MultiSearchAggregator::default(),
-            post_facet_search_aggregator: FacetSearchAggregator::default(),
             get_search_aggregator: SearchAggregator::default(),
             add_documents_aggregator: DocumentsAggregator::default(),
             delete_documents_aggregator: DocumentsDeletionAggregator::default(),
@@ -187,10 +182,6 @@ impl super::Analytics for SegmentAnalytics {
         let _ = self.sender.try_send(AnalyticsMsg::AggregatePostSearch(aggregate));
     }
 
-    fn post_facet_search(&self, aggregate: FacetSearchAggregator) {
-        let _ = self.sender.try_send(AnalyticsMsg::AggregatePostFacetSearch(aggregate));
-    }
-
     fn post_multi_search(&self, aggregate: MultiSearchAggregator) {
         let _ = self.sender.try_send(AnalyticsMsg::AggregatePostMultiSearch(aggregate));
     }
@@ -363,7 +354,6 @@ pub struct Segment {
     get_search_aggregator: SearchAggregator,
     post_search_aggregator: SearchAggregator,
     post_multi_search_aggregator: MultiSearchAggregator,
-    post_facet_search_aggregator: FacetSearchAggregator,
     add_documents_aggregator: DocumentsAggregator,
     delete_documents_aggregator: DocumentsDeletionAggregator,
     update_documents_aggregator: DocumentsAggregator,
@@ -428,7 +418,6 @@ impl Segment {
                         Some(AnalyticsMsg::AggregateGetSearch(agreg)) => self.get_search_aggregator.aggregate(agreg),
                         Some(AnalyticsMsg::AggregatePostSearch(agreg)) => self.post_search_aggregator.aggregate(agreg),
                         Some(AnalyticsMsg::AggregatePostMultiSearch(agreg)) => self.post_multi_search_aggregator.aggregate(agreg),
-                        Some(AnalyticsMsg::AggregatePostFacetSearch(agreg)) => self.post_facet_search_aggregator.aggregate(agreg),
                         Some(AnalyticsMsg::AggregateAddDocuments(agreg)) => self.add_documents_aggregator.aggregate(agreg),
                         Some(AnalyticsMsg::AggregateDeleteDocuments(agreg)) => self.delete_documents_aggregator.aggregate(agreg),
                         Some(AnalyticsMsg::AggregateUpdateDocuments(agreg)) => self.update_documents_aggregator.aggregate(agreg),
@@ -472,74 +461,55 @@ impl Segment {
                 })
                 .await;
         }
+        let get_search = std::mem::take(&mut self.get_search_aggregator)
+            .into_event(&self.user, "Documents Searched GET");
+        let post_search = std::mem::take(&mut self.post_search_aggregator)
+            .into_event(&self.user, "Documents Searched POST");
+        let post_multi_search = std::mem::take(&mut self.post_multi_search_aggregator)
+            .into_event(&self.user, "Documents Searched by Multi-Search POST");
+        let add_documents = std::mem::take(&mut self.add_documents_aggregator)
+            .into_event(&self.user, "Documents Added");
+        let delete_documents = std::mem::take(&mut self.delete_documents_aggregator)
+            .into_event(&self.user, "Documents Deleted");
+        let update_documents = std::mem::take(&mut self.update_documents_aggregator)
+            .into_event(&self.user, "Documents Updated");
+        let get_fetch_documents = std::mem::take(&mut self.get_fetch_documents_aggregator)
+            .into_event(&self.user, "Documents Fetched GET");
+        let post_fetch_documents = std::mem::take(&mut self.post_fetch_documents_aggregator)
+            .into_event(&self.user, "Documents Fetched POST");
+        let get_tasks =
+            std::mem::take(&mut self.get_tasks_aggregator).into_event(&self.user, "Tasks Seen");
+        let health =
+            std::mem::take(&mut self.health_aggregator).into_event(&self.user, "Health Seen");
 
-        let Segment {
-            inbox: _,
-            opt: _,
-            batcher: _,
-            user,
-            get_search_aggregator,
-            post_search_aggregator,
-            post_multi_search_aggregator,
-            post_facet_search_aggregator,
-            add_documents_aggregator,
-            delete_documents_aggregator,
-            update_documents_aggregator,
-            get_fetch_documents_aggregator,
-            post_fetch_documents_aggregator,
-            get_tasks_aggregator,
-            health_aggregator,
-        } = self;
-
-        if let Some(get_search) =
-            take(get_search_aggregator).into_event(&user, "Documents Searched GET")
-        {
+        if let Some(get_search) = get_search {
             let _ = self.batcher.push(get_search).await;
         }
-        if let Some(post_search) =
-            take(post_search_aggregator).into_event(&user, "Documents Searched POST")
-        {
+        if let Some(post_search) = post_search {
             let _ = self.batcher.push(post_search).await;
         }
-        if let Some(post_multi_search) = take(post_multi_search_aggregator)
-            .into_event(&user, "Documents Searched by Multi-Search POST")
-        {
+        if let Some(post_multi_search) = post_multi_search {
             let _ = self.batcher.push(post_multi_search).await;
         }
-        if let Some(post_facet_search) =
-            take(post_facet_search_aggregator).into_event(&user, "Facet Searched POST")
-        {
-            let _ = self.batcher.push(post_facet_search).await;
-        }
-        if let Some(add_documents) =
-            take(add_documents_aggregator).into_event(&user, "Documents Added")
-        {
+        if let Some(add_documents) = add_documents {
             let _ = self.batcher.push(add_documents).await;
         }
-        if let Some(delete_documents) =
-            take(delete_documents_aggregator).into_event(&user, "Documents Deleted")
-        {
+        if let Some(delete_documents) = delete_documents {
             let _ = self.batcher.push(delete_documents).await;
         }
-        if let Some(update_documents) =
-            take(update_documents_aggregator).into_event(&user, "Documents Updated")
-        {
+        if let Some(update_documents) = update_documents {
             let _ = self.batcher.push(update_documents).await;
         }
-        if let Some(get_fetch_documents) =
-            take(get_fetch_documents_aggregator).into_event(&user, "Documents Fetched GET")
-        {
+        if let Some(get_fetch_documents) = get_fetch_documents {
             let _ = self.batcher.push(get_fetch_documents).await;
         }
-        if let Some(post_fetch_documents) =
-            take(post_fetch_documents_aggregator).into_event(&user, "Documents Fetched POST")
-        {
+        if let Some(post_fetch_documents) = post_fetch_documents {
             let _ = self.batcher.push(post_fetch_documents).await;
         }
-        if let Some(get_tasks) = take(get_tasks_aggregator).into_event(&user, "Tasks Seen") {
+        if let Some(get_tasks) = get_tasks {
             let _ = self.batcher.push(get_tasks).await;
         }
-        if let Some(health) = take(health_aggregator).into_event(&user, "Health Seen") {
+        if let Some(health) = health {
             let _ = self.batcher.push(health).await;
         }
         let _ = self.batcher.flush().await;
@@ -578,10 +548,6 @@ pub struct SearchAggregator {
     // The maximum number of terms in a q request
     max_terms_number: usize,
 
-    // vector
-    // The maximum number of floats in a vector request
-    max_vector_size: usize,
-
     // every time a search is done, we increment the counter linked to the used settings
     matching_strategy: HashMap<String, usize>,
 
@@ -603,10 +569,6 @@ pub struct SearchAggregator {
     // facets
     facets_sum_of_terms: usize,
     facets_total_number_of_facets: usize,
-
-    // scoring
-    show_ranking_score: bool,
-    show_ranking_score_details: bool,
 }
 
 impl SearchAggregator {
@@ -651,10 +613,6 @@ impl SearchAggregator {
             ret.max_terms_number = q.split_whitespace().count();
         }
 
-        if let Some(ref vector) = query.vector {
-            ret.max_vector_size = vector.len();
-        }
-
         if query.is_finite_pagination() {
             let limit = query.hits_per_page.unwrap_or_else(DEFAULT_SEARCH_LIMIT);
             ret.max_limit = limit;
@@ -674,9 +632,6 @@ impl SearchAggregator {
         ret.crop_length = query.crop_length != DEFAULT_CROP_LENGTH();
         ret.show_matches_position = query.show_matches_position;
 
-        ret.show_ranking_score = query.show_ranking_score;
-        ret.show_ranking_score_details = query.show_ranking_score_details;
-
         ret
     }
 
@@ -751,10 +706,6 @@ impl SearchAggregator {
             let matching_strategy = self.matching_strategy.entry(key).or_insert(0);
             *matching_strategy = matching_strategy.saturating_add(value);
         }
-
-        // scoring
-        self.show_ranking_score |= other.show_ranking_score;
-        self.show_ranking_score_details |= other.show_ranking_score_details;
     }
 
     pub fn into_event(self, user: &User, event_name: &str) -> Option<Track> {
@@ -809,11 +760,7 @@ impl SearchAggregator {
                 },
                 "matching_strategy": {
                     "most_used_strategy": self.matching_strategy.iter().max_by_key(|(_, v)| *v).map(|(k, _)| json!(k)).unwrap_or_else(|| json!(null)),
-                },
-                "scoring": {
-                    "show_ranking_score": self.show_ranking_score,
-                    "show_ranking_score_details": self.show_ranking_score_details,
-                },
+                }
             });
 
             Some(Track {
@@ -939,120 +886,6 @@ impl MultiSearchAggregator {
     }
 }
 
-#[derive(Default)]
-pub struct FacetSearchAggregator {
-    timestamp: Option<OffsetDateTime>,
-
-    // context
-    user_agents: HashSet<String>,
-
-    // requests
-    total_received: usize,
-    total_succeeded: usize,
-    time_spent: BinaryHeap<usize>,
-
-    // The set of all facetNames that were used
-    facet_names: HashSet<String>,
-
-    // As there been any other parameter than the facetName or facetQuery ones?
-    additional_search_parameters_provided: bool,
-}
-
-impl FacetSearchAggregator {
-    pub fn from_query(query: &FacetSearchQuery, request: &HttpRequest) -> Self {
-        let FacetSearchQuery {
-            facet_query: _,
-            facet_name,
-            vector,
-            q,
-            filter,
-            matching_strategy,
-            attributes_to_search_on,
-        } = query;
-
-        let mut ret = Self::default();
-        ret.timestamp = Some(OffsetDateTime::now_utc());
-
-        ret.total_received = 1;
-        ret.user_agents = extract_user_agents(request).into_iter().collect();
-        ret.facet_names = Some(facet_name.clone()).into_iter().collect();
-
-        ret.additional_search_parameters_provided = q.is_some()
-            || vector.is_some()
-            || filter.is_some()
-            || *matching_strategy != MatchingStrategy::default()
-            || attributes_to_search_on.is_some();
-
-        ret
-    }
-
-    pub fn succeed(&mut self, result: &FacetSearchResult) {
-        self.total_succeeded = self.total_succeeded.saturating_add(1);
-        self.time_spent.push(result.processing_time_ms as usize);
-    }
-
-    /// Aggregate one [SearchAggregator] into another.
-    pub fn aggregate(&mut self, mut other: Self) {
-        if self.timestamp.is_none() {
-            self.timestamp = other.timestamp;
-        }
-
-        // context
-        for user_agent in other.user_agents.into_iter() {
-            self.user_agents.insert(user_agent);
-        }
-
-        // request
-        self.total_received = self.total_received.saturating_add(other.total_received);
-        self.total_succeeded = self.total_succeeded.saturating_add(other.total_succeeded);
-        self.time_spent.append(&mut other.time_spent);
-
-        // facet_names
-        for facet_name in other.facet_names.into_iter() {
-            self.facet_names.insert(facet_name);
-        }
-
-        // additional_search_parameters_provided
-        self.additional_search_parameters_provided = self.additional_search_parameters_provided
-            | other.additional_search_parameters_provided;
-    }
-
-    pub fn into_event(self, user: &User, event_name: &str) -> Option<Track> {
-        if self.total_received == 0 {
-            None
-        } else {
-            // the index of the 99th percentage of value
-            let percentile_99th = 0.99 * (self.total_succeeded as f64 - 1.) + 1.;
-            // we get all the values in a sorted manner
-            let time_spent = self.time_spent.into_sorted_vec();
-            // We are only interested by the slowest value of the 99th fastest results
-            let time_spent = time_spent.get(percentile_99th as usize);
-
-            let properties = json!({
-                "user-agent": self.user_agents,
-                "requests": {
-                    "99th_response_time":  time_spent.map(|t| format!("{:.2}", t)),
-                    "total_succeeded": self.total_succeeded,
-                    "total_failed": self.total_received.saturating_sub(self.total_succeeded), // just to be sure we never panics
-                    "total_received": self.total_received,
-                },
-                "facets": {
-                    "total_distinct_facet_count": self.facet_names.len(),
-                    "additional_search_parameters_provided": self.additional_search_parameters_provided,
-                },
-            });
-
-            Some(Track {
-                timestamp: self.timestamp,
-                user: user.clone(),
-                event: event_name.to_string(),
-                properties,
-                ..Default::default()
-            })
-        }
-    }
-}
-
 #[derive(Default)]
 pub struct DocumentsAggregator {
     timestamp: Option<OffsetDateTime>,

meilisearch/src/extractors/payload.rs

@@ -71,40 +71,3 @@ impl Stream for Payload {
         }
     }
 }
-
-#[cfg(test)]
-mod tests {
-    use actix_http::encoding::Decoder as Decompress;
-    use actix_http::BoxedPayloadStream;
-    use bytes::Bytes;
-    use futures_util::StreamExt;
-    use meili_snap::snapshot;
-
-    use super::*;
-
-    #[actix_rt::test]
-    async fn payload_to_large() {
-        let stream = futures::stream::iter(vec![
-            Ok(Bytes::from("1")),
-            Ok(Bytes::from("2")),
-            Ok(Bytes::from("3")),
-            Ok(Bytes::from("4")),
-        ]);
-        let boxed_stream: BoxedPayloadStream = Box::pin(stream);
-        let actix_payload = dev::Payload::from(boxed_stream);
-
-        let payload = Payload {
-            limit: 3,
-            remaining: 3,
-            payload: Decompress::new(actix_payload, actix_http::ContentEncoding::Identity),
-        };
-
-        let mut enumerated_payload_stream = payload.enumerate();
-
-        while let Some((idx, chunk)) = enumerated_payload_stream.next().await {
-            if idx == 3 {
-                snapshot!(chunk.unwrap_err(), @"The provided payload reached the size limit. The maximum accepted payload size is 3 B.");
-            }
-        }
-    }
-}

meilisearch/src/lib.rs

@@ -111,7 +111,7 @@ pub fn create_app(
                 analytics.clone(),
             )
         })
-        .configure(routes::configure)
+        .configure(|cfg| routes::configure(cfg, opt.experimental_enable_metrics))
         .configure(|s| dashboard(s, enable_dashboard));
 
     let app = app.wrap(actix_web::middleware::Condition::new(
@@ -221,7 +221,6 @@ fn open_or_create_database_unchecked(
     // we don't want to create anything in the data.ms yet, thus we
     // wrap our two builders in a closure that'll be executed later.
     let auth_controller = AuthController::new(&opt.db_path, &opt.master_key);
-    let instance_features = opt.to_instance_features();
     let index_scheduler_builder = || -> anyhow::Result<_> {
         Ok(IndexScheduler::new(IndexSchedulerOptions {
             version_file_path: opt.db_path.join(VERSION_FILE_NAME),
@@ -239,7 +238,6 @@ fn open_or_create_database_unchecked(
             max_number_of_tasks: 1_000_000,
             index_growth_amount: byte_unit::Byte::from_str("10GiB").unwrap().get_bytes() as usize,
             index_count: DEFAULT_INDEX_COUNT,
-            instance_features,
         })?)
     };
 
@@ -309,16 +307,12 @@ fn import_dump(
         keys.push(key);
     }
 
-    // 3. Import the runtime features.
-    let features = dump_reader.features()?.unwrap_or_default();
-    index_scheduler.put_runtime_features(features)?;
-
     let indexer_config = index_scheduler.indexer_config();
 
     // /!\ The tasks must be imported AFTER importing the indexes or else the scheduler might
     // try to process tasks while we're trying to import the indexes.
 
-    // 4. Import the indexes.
+    // 3. Import the indexes.
     for index_reader in dump_reader.indexes()? {
         let mut index_reader = index_reader?;
         let metadata = index_reader.metadata();
@@ -330,19 +324,19 @@ fn import_dump(
         let mut wtxn = index.write_txn()?;
 
         let mut builder = milli::update::Settings::new(&mut wtxn, &index, indexer_config);
-        // 4.1 Import the primary key if there is one.
+        // 3.1 Import the primary key if there is one.
         if let Some(ref primary_key) = metadata.primary_key {
             builder.set_primary_key(primary_key.to_string());
         }
 
-        // 4.2 Import the settings.
+        // 3.2 Import the settings.
         log::info!("Importing the settings.");
         let settings = index_reader.settings()?;
         apply_settings_to_builder(&settings, &mut builder);
         builder.execute(|indexing_step| log::debug!("update: {:?}", indexing_step), || false)?;
 
-        // 4.3 Import the documents.
-        // 4.3.1 We need to recreate the grenad+obkv format accepted by the index.
+        // 3.3 Import the documents.
+        // 3.3.1 We need to recreate the grenad+obkv format accepted by the index.
         log::info!("Importing the documents.");
         let file = tempfile::tempfile()?;
         let mut builder = DocumentsBatchBuilder::new(BufWriter::new(file));
@@ -353,7 +347,7 @@ fn import_dump(
         // This flush the content of the batch builder.
         let file = builder.into_inner()?.into_inner()?;
 
-        // 4.3.2 We feed it to the milli index.
+        // 3.3.2 We feed it to the milli index.
         let reader = BufReader::new(file);
         let reader = DocumentsBatchReader::from_reader(reader)?;
 
@@ -378,7 +372,7 @@ fn import_dump(
 
     let mut index_scheduler_dump = index_scheduler.register_dumped_task()?;
 
-    // 5. Import the tasks.
+    // 4. Import the tasks.
     for ret in dump_reader.tasks()? {
         let (task, file) = ret?;
         index_scheduler_dump.register_dumped_task(task, file)?;

meilisearch/src/main.rs

@@ -186,10 +186,9 @@ Anonymous telemetry:\t\"Enabled\""
     }
 
     eprintln!();
-    eprintln!("Check out Meilisearch Cloud!\thttps://cloud.meilisearch.com/login?utm_campaign=oss&utm_source=engine&utm_medium=cli");
-    eprintln!("Documentation:\t\t\thttps://www.meilisearch.com/docs");
-    eprintln!("Source code:\t\t\thttps://github.com/meilisearch/meilisearch");
-    eprintln!("Discord:\t\t\thttps://discord.meilisearch.com");
+    eprintln!("Documentation:\t\thttps://www.meilisearch.com/docs");
+    eprintln!("Source code:\t\thttps://github.com/meilisearch/meilisearch");
+    eprintln!("Discord:\t\thttps://discord.meilisearch.com");
     eprintln!();
 }
 

meilisearch/src/metrics.rs

@@ -16,7 +16,7 @@ fn create_buckets() -> [f64; 29] {
 }
 
 lazy_static! {
-    pub static ref MEILISEARCH_HTTP_RESPONSE_TIME_CUSTOM_BUCKETS: [f64; 29] = create_buckets();
+    pub static ref HTTP_RESPONSE_TIME_CUSTOM_BUCKETS: [f64; 29] = create_buckets();
     pub static ref MEILISEARCH_HTTP_REQUESTS_TOTAL: IntCounterVec = register_int_counter_vec!(
         opts!("meilisearch_http_requests_total", "Meilisearch HTTP requests total"),
         &["method", "path"]
@@ -39,10 +39,10 @@ lazy_static! {
     )
     .expect("Can't create a metric");
     pub static ref MEILISEARCH_HTTP_RESPONSE_TIME_SECONDS: HistogramVec = register_histogram_vec!(
-        "meilisearch_http_response_time_seconds",
-        "Meilisearch HTTP response times",
+        "http_response_time_seconds",
+        "HTTP response times",
         &["method", "path"],
-        MEILISEARCH_HTTP_RESPONSE_TIME_CUSTOM_BUCKETS.to_vec()
+        HTTP_RESPONSE_TIME_CUSTOM_BUCKETS.to_vec()
     )
     .expect("Can't create a metric");
     pub static ref MEILISEARCH_NB_TASKS: IntGaugeVec = register_int_gauge_vec!(

meilisearch/src/option.rs

@@ -12,7 +12,6 @@ use std::{env, fmt, fs};
 
 use byte_unit::{Byte, ByteError};
 use clap::Parser;
-use meilisearch_types::features::InstanceTogglableFeatures;
 use meilisearch_types::milli::update::IndexerConfig;
 use rustls::server::{
     AllowAnyAnonymousOrAuthenticatedClient, AllowAnyAuthenticatedClient, ServerSessionMemoryCache,
@@ -487,10 +486,6 @@ impl Opt {
             Ok(None)
         }
     }
-
-    pub(crate) fn to_instance_features(&self) -> InstanceTogglableFeatures {
-        InstanceTogglableFeatures { metrics: self.experimental_enable_metrics }
-    }
 }
 
 #[derive(Debug, Default, Clone, Parser, Deserialize)]

meilisearch/src/routes/features.rs

@@ -1,70 +0,0 @@
-use actix_web::web::{self, Data};
-use actix_web::{HttpRequest, HttpResponse};
-use deserr::actix_web::AwebJson;
-use deserr::Deserr;
-use index_scheduler::IndexScheduler;
-use log::debug;
-use meilisearch_types::deserr::DeserrJsonError;
-use meilisearch_types::error::ResponseError;
-use meilisearch_types::keys::actions;
-use serde_json::json;
-
-use crate::analytics::Analytics;
-use crate::extractors::authentication::policies::ActionPolicy;
-use crate::extractors::authentication::GuardedData;
-use crate::extractors::sequential_extractor::SeqHandler;
-
-pub fn configure(cfg: &mut web::ServiceConfig) {
-    cfg.service(
-        web::resource("")
-            .route(web::get().to(SeqHandler(get_features)))
-            .route(web::patch().to(SeqHandler(patch_features))),
-    );
-}
-
-async fn get_features(
-    index_scheduler: GuardedData<
-        ActionPolicy<{ actions::EXPERIMENTAL_FEATURES_GET }>,
-        Data<IndexScheduler>,
-    >,
-    req: HttpRequest,
-    analytics: Data<dyn Analytics>,
-) -> Result<HttpResponse, ResponseError> {
-    let features = index_scheduler.features()?;
-
-    analytics.publish("Experimental features Seen".to_string(), json!(null), Some(&req));
-    debug!("returns: {:?}", features.runtime_features());
-    Ok(HttpResponse::Ok().json(features.runtime_features()))
-}
-
-#[derive(Debug, Deserr)]
-#[deserr(error = DeserrJsonError, rename_all = camelCase, deny_unknown_fields)]
-pub struct RuntimeTogglableFeatures {
-    #[deserr(default)]
-    pub score_details: Option<bool>,
-    #[deserr(default)]
-    pub vector_store: Option<bool>,
-}
-
-async fn patch_features(
-    index_scheduler: GuardedData<
-        ActionPolicy<{ actions::EXPERIMENTAL_FEATURES_UPDATE }>,
-        Data<IndexScheduler>,
-    >,
-    new_features: AwebJson<RuntimeTogglableFeatures, DeserrJsonError>,
-    req: HttpRequest,
-    analytics: Data<dyn Analytics>,
-) -> Result<HttpResponse, ResponseError> {
-    let features = index_scheduler.features()?;
-
-    let old_features = features.runtime_features();
-
-    let new_features = meilisearch_types::features::RuntimeTogglableFeatures {
-        score_details: new_features.0.score_details.unwrap_or(old_features.score_details),
-        vector_store: new_features.0.vector_store.unwrap_or(old_features.vector_store),
-    };
-
-    analytics.publish("Experimental features Updated".to_string(), json!(new_features), Some(&req));
-    index_scheduler.put_runtime_features(new_features)?;
-    Ok(HttpResponse::Ok().json(new_features))
-}

meilisearch/src/routes/indexes/facet_search.rs

@@ -1,124 +0,0 @@
-use actix_web::web::Data;
-use actix_web::{web, HttpRequest, HttpResponse};
-use deserr::actix_web::AwebJson;
-use index_scheduler::IndexScheduler;
-use log::debug;
-use meilisearch_types::deserr::DeserrJsonError;
-use meilisearch_types::error::deserr_codes::*;
-use meilisearch_types::error::ResponseError;
-use meilisearch_types::index_uid::IndexUid;
-use serde_json::Value;
-
-use crate::analytics::{Analytics, FacetSearchAggregator};
-use crate::extractors::authentication::policies::*;
-use crate::extractors::authentication::GuardedData;
-use crate::search::{
-    add_search_rules, perform_facet_search, MatchingStrategy, SearchQuery, DEFAULT_CROP_LENGTH,
-    DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG,
-    DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET,
-};
-
-pub fn configure(cfg: &mut web::ServiceConfig) {
-    cfg.service(web::resource("").route(web::post().to(search)));
-}
-
-/// # Important
-///
-/// Intentionally don't use `deny_unknown_fields` to ignore search parameters sent by user
-#[derive(Debug, Clone, Default, PartialEq, deserr::Deserr)]
-#[deserr(error = DeserrJsonError, rename_all = camelCase)]
-pub struct FacetSearchQuery {
-    #[deserr(default, error = DeserrJsonError<InvalidFacetSearchQuery>)]
-    pub facet_query: Option<String>,
-    #[deserr(error = DeserrJsonError<InvalidFacetSearchFacetName>, missing_field_error = DeserrJsonError::missing_facet_search_facet_name)]
-    pub facet_name: String,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchQ>)]
-    pub q: Option<String>,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchVector>)]
-    pub vector: Option<Vec<f32>>,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchFilter>)]
-    pub filter: Option<Value>,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchMatchingStrategy>, default)]
-    pub matching_strategy: MatchingStrategy,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchAttributesToSearchOn>, default)]
-    pub attributes_to_search_on: Option<Vec<String>>,
-}
-
-pub async fn search(
-    index_scheduler: GuardedData<ActionPolicy<{ actions::SEARCH }>, Data<IndexScheduler>>,
-    index_uid: web::Path<String>,
-    params: AwebJson<FacetSearchQuery, DeserrJsonError>,
-    req: HttpRequest,
-    analytics: web::Data<dyn Analytics>,
-) -> Result<HttpResponse, ResponseError> {
-    let index_uid = IndexUid::try_from(index_uid.into_inner())?;
-
-    let query = params.into_inner();
-    debug!("facet search called with params: {:?}", query);
-
-    let mut aggregate = FacetSearchAggregator::from_query(&query, &req);
-
-    let facet_query = query.facet_query.clone();
-    let facet_name = query.facet_name.clone();
-    let mut search_query = SearchQuery::from(query);
-
-    // Tenant token search_rules.
-    if let Some(search_rules) = index_scheduler.filters().get_index_search_rules(&index_uid) {
-        add_search_rules(&mut search_query, search_rules);
-    }
-
-    let index = index_scheduler.index(&index_uid)?;
-    let features = index_scheduler.features()?;
-    let search_result = tokio::task::spawn_blocking(move || {
-        perform_facet_search(&index, search_query, facet_query, facet_name, features)
-    })
-    .await?;
-
-    if let Ok(ref search_result) = search_result {
-        aggregate.succeed(search_result);
-    }
-    analytics.post_facet_search(aggregate);
-
-    let search_result = search_result?;
-
-    debug!("returns: {:?}", search_result);
-    Ok(HttpResponse::Ok().json(search_result))
-}
-
-impl From<FacetSearchQuery> for SearchQuery {
-    fn from(value: FacetSearchQuery) -> Self {
-        let FacetSearchQuery {
-            facet_query: _,
-            facet_name: _,
-            q,
-            vector,
-            filter,
-            matching_strategy,
-            attributes_to_search_on,
-        } = value;
-
-        SearchQuery {
-            q,
-            offset: DEFAULT_SEARCH_OFFSET(),
-            limit: DEFAULT_SEARCH_LIMIT(),
-            page: None,
-            hits_per_page: None,
-            attributes_to_retrieve: None,
-            attributes_to_crop: None,
-            crop_length: DEFAULT_CROP_LENGTH(),
-            attributes_to_highlight: None,
-            show_matches_position: false,
-            show_ranking_score: false,
-            show_ranking_score_details: false,
-            filter,
-            sort: None,
-            facets: None,
-            highlight_pre_tag: DEFAULT_HIGHLIGHT_PRE_TAG(),
-            highlight_post_tag: DEFAULT_HIGHLIGHT_POST_TAG(),
-            crop_marker: DEFAULT_CROP_MARKER(),
-            matching_strategy,
-            vector,
-            attributes_to_search_on,
-        }
-    }
-}

meilisearch/src/routes/indexes/mod.rs

@@ -24,7 +24,6 @@ use crate::extractors::authentication::{AuthenticationError, GuardedData};
 use crate::extractors::sequential_extractor::SeqHandler;
 
 pub mod documents;
-pub mod facet_search;
 pub mod search;
 pub mod settings;
 
@@ -45,7 +44,6 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
             .service(web::resource("/stats").route(web::get().to(SeqHandler(get_index_stats))))
             .service(web::scope("/documents").configure(documents::configure))
             .service(web::scope("/search").configure(search::configure))
-            .service(web::scope("/facet-search").configure(facet_search::configure))
             .service(web::scope("/settings").configure(settings::configure)),
     );
 }

meilisearch/src/routes/indexes/search.rs

@@ -34,7 +34,7 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
 pub struct SearchQueryGet {
     #[deserr(default, error = DeserrQueryParamError<InvalidSearchQ>)]
     q: Option<String>,
-    #[deserr(default, error = DeserrQueryParamError<InvalidSearchVector>)]
+    #[deserr(default, error = DeserrQueryParamError<InvalidSearchQ>)]
     vector: Option<Vec<f32>>,
     #[deserr(default = Param(DEFAULT_SEARCH_OFFSET()), error = DeserrQueryParamError<InvalidSearchOffset>)]
     offset: Param<usize>,
@@ -58,10 +58,6 @@ pub struct SearchQueryGet {
     sort: Option<String>,
     #[deserr(default, error = DeserrQueryParamError<InvalidSearchShowMatchesPosition>)]
     show_matches_position: Param<bool>,
-    #[deserr(default, error = DeserrQueryParamError<InvalidSearchShowRankingScore>)]
-    show_ranking_score: Param<bool>,
-    #[deserr(default, error = DeserrQueryParamError<InvalidSearchShowRankingScoreDetails>)]
-    show_ranking_score_details: Param<bool>,
     #[deserr(default, error = DeserrQueryParamError<InvalidSearchFacets>)]
     facets: Option<CS<String>>,
     #[deserr( default = DEFAULT_HIGHLIGHT_PRE_TAG(), error = DeserrQueryParamError<InvalidSearchHighlightPreTag>)]
@@ -72,8 +68,6 @@ pub struct SearchQueryGet {
     crop_marker: String,
     #[deserr(default, error = DeserrQueryParamError<InvalidSearchMatchingStrategy>)]
     matching_strategy: MatchingStrategy,
-    #[deserr(default, error = DeserrQueryParamError<InvalidSearchAttributesToSearchOn>)]
-    pub attributes_to_search_on: Option<CS<String>>,
 }
 
 impl From<SearchQueryGet> for SearchQuery {
@@ -100,14 +94,11 @@ impl From<SearchQueryGet> for SearchQuery {
             filter,
             sort: other.sort.map(|attr| fix_sort_query_parameters(&attr)),
             show_matches_position: other.show_matches_position.0,
-            show_ranking_score: other.show_ranking_score.0,
-            show_ranking_score_details: other.show_ranking_score_details.0,
             facets: other.facets.map(|o| o.into_iter().collect()),
             highlight_pre_tag: other.highlight_pre_tag,
             highlight_post_tag: other.highlight_post_tag,
             crop_marker: other.crop_marker,
             matching_strategy: other.matching_strategy,
-            attributes_to_search_on: other.attributes_to_search_on.map(|o| o.into_iter().collect()),
         }
     }
 }
@@ -157,9 +148,7 @@ pub async fn search_with_url_query(
     let mut aggregate = SearchAggregator::from_query(&query, &req);
 
     let index = index_scheduler.index(&index_uid)?;
-    let features = index_scheduler.features()?;
-    let search_result =
-        tokio::task::spawn_blocking(move || perform_search(&index, query, features)).await?;
+    let search_result = tokio::task::spawn_blocking(move || perform_search(&index, query)).await?;
     if let Ok(ref search_result) = search_result {
         aggregate.succeed(search_result);
     }
@@ -191,10 +180,7 @@ pub async fn search_with_post(
     let mut aggregate = SearchAggregator::from_query(&query, &req);
 
     let index = index_scheduler.index(&index_uid)?;
-
-    let features = index_scheduler.features()?;
-    let search_result =
-        tokio::task::spawn_blocking(move || perform_search(&index, query, features)).await?;
+    let search_result = tokio::task::spawn_blocking(move || perform_search(&index, query)).await?;
     if let Ok(ref search_result) = search_result {
         aggregate.succeed(search_result);
     }

meilisearch/src/routes/indexes/settings.rs

@@ -401,17 +401,12 @@ make_setting_route!(
     analytics,
     |setting: &Option<meilisearch_types::settings::FacetingSettings>, req: &HttpRequest| {
         use serde_json::json;
-        use meilisearch_types::facet_values_sort::FacetValuesSort;
 
         analytics.publish(
             "Faceting Updated".to_string(),
             json!({
                 "faceting": {
                     "max_values_per_facet": setting.as_ref().and_then(|s| s.max_values_per_facet.set()),
-                    "sort_facet_values_by_star_count": setting.as_ref().and_then(|s| {
-                        s.sort_facet_values_by.as_ref().set().map(|s| s.iter().any(|(k, v)| k == "*" && v == &FacetValuesSort::Count))
-                    }),
-                    "sort_facet_values_by_total": setting.as_ref().and_then(|s| s.sort_facet_values_by.as_ref().set().map(|s| s.len())),
                 },
             }),
             Some(req),
@@ -550,10 +545,6 @@ pub async fn update_all(
                     .as_ref()
                     .set()
                     .and_then(|s| s.max_values_per_facet.as_ref().set()),
-                "sort_facet_values_by": new_settings.faceting
-                    .as_ref()
-                    .set()
-                    .and_then(|s| s.sort_facet_values_by.as_ref().set()),
             },
             "pagination": {
                 "max_total_hits": new_settings.pagination

meilisearch/src/routes/metrics.rs

@@ -19,7 +19,6 @@ pub async fn get_metrics(
     index_scheduler: GuardedData<ActionPolicy<{ actions::METRICS_GET }>, Data<IndexScheduler>>,
     auth_controller: Data<AuthController>,
 ) -> Result<HttpResponse, ResponseError> {
-    index_scheduler.features()?.check_metrics()?;
     let auth_filters = index_scheduler.filters();
     if !auth_filters.all_indexes_authorized() {
         let mut error = ResponseError::from(AuthenticationError::InvalidToken);

meilisearch/src/routes/mod.rs

@@ -20,14 +20,13 @@ const PAGINATION_DEFAULT_LIMIT: usize = 20;
 
 mod api_key;
 mod dump;
-pub mod features;
 pub mod indexes;
 mod metrics;
 mod multi_search;
 mod swap_indexes;
 pub mod tasks;
 
-pub fn configure(cfg: &mut web::ServiceConfig) {
+pub fn configure(cfg: &mut web::ServiceConfig, enable_metrics: bool) {
     cfg.service(web::scope("/tasks").configure(tasks::configure))
         .service(web::resource("/health").route(web::get().to(get_health)))
         .service(web::scope("/keys").configure(api_key::configure))
@@ -36,9 +35,11 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
         .service(web::resource("/version").route(web::get().to(get_version)))
         .service(web::scope("/indexes").configure(indexes::configure))
         .service(web::scope("/multi-search").configure(multi_search::configure))
-        .service(web::scope("/swap-indexes").configure(swap_indexes::configure))
-        .service(web::scope("/metrics").configure(metrics::configure))
-        .service(web::scope("/experimental-features").configure(features::configure));
+        .service(web::scope("/swap-indexes").configure(swap_indexes::configure));
+
+    if enable_metrics {
+        cfg.service(web::scope("/metrics").configure(metrics::configure));
+    }
 }
 
 #[derive(Debug, Serialize)]

meilisearch/src/routes/multi_search.rs

@@ -41,7 +41,6 @@ pub async fn multi_search_with_post(
     let queries = params.into_inner().queries;
 
     let mut multi_aggregate = MultiSearchAggregator::from_queries(&queries, &req);
-    let features = index_scheduler.features()?;
 
     // Explicitly expect a `(ResponseError, usize)` for the error type rather than `ResponseError` only,
     // so that `?` doesn't work if it doesn't use `with_index`, ensuring that it is not forgotten in case of code
@@ -75,9 +74,8 @@ pub async fn multi_search_with_post(
                         err
                     })
                     .with_index(query_index)?;
-
                 let search_result =
-                    tokio::task::spawn_blocking(move || perform_search(&index, query, features))
+                    tokio::task::spawn_blocking(move || perform_search(&index, query))
                         .await
                         .with_index(query_index)?;
 

meilisearch/src/search.rs

@@ -5,26 +5,17 @@ use std::time::Instant;
 
 use deserr::Deserr;
 use either::Either;
-use index_scheduler::RoFeatures;
-use indexmap::IndexMap;
-use log::warn;
 use meilisearch_auth::IndexSearchRules;
 use meilisearch_types::deserr::DeserrJsonError;
 use meilisearch_types::error::deserr_codes::*;
-use meilisearch_types::heed::RoTxn;
 use meilisearch_types::index_uid::IndexUid;
-use meilisearch_types::milli::score_details::{ScoreDetails, ScoringStrategy};
-use meilisearch_types::milli::{
-    dot_product_similarity, FacetValueHit, InternalError, OrderBy, SearchForFacetValues,
-};
 use meilisearch_types::settings::DEFAULT_PAGINATION_MAX_TOTAL_HITS;
 use meilisearch_types::{milli, Document};
 use milli::tokenizer::TokenizerBuilder;
 use milli::{
     AscDesc, FieldId, FieldsIdsMap, Filter, FormatOptions, Index, MatchBounds, MatcherBuilder,
-    SortError, TermsMatchingStrategy, VectorOrArrayOfVectors, DEFAULT_VALUES_PER_FACET,
+    SortError, TermsMatchingStrategy, DEFAULT_VALUES_PER_FACET,
 };
-use ordered_float::OrderedFloat;
 use regex::Regex;
 use serde::Serialize;
 use serde_json::{json, Value};
@@ -45,7 +36,7 @@ pub const DEFAULT_HIGHLIGHT_POST_TAG: fn() -> String = || "</em>".to_string();
 pub struct SearchQuery {
     #[deserr(default, error = DeserrJsonError<InvalidSearchQ>)]
     pub q: Option<String>,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchVector>)]
+    #[deserr(default, error = DeserrJsonError<InvalidSearchQ>)]
     pub vector: Option<Vec<f32>>,
     #[deserr(default = DEFAULT_SEARCH_OFFSET(), error = DeserrJsonError<InvalidSearchOffset>)]
     pub offset: usize,
@@ -65,10 +56,6 @@ pub struct SearchQuery {
     pub attributes_to_highlight: Option<HashSet<String>>,
     #[deserr(default, error = DeserrJsonError<InvalidSearchShowMatchesPosition>, default)]
     pub show_matches_position: bool,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchShowRankingScore>, default)]
-    pub show_ranking_score: bool,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchShowRankingScoreDetails>, default)]
-    pub show_ranking_score_details: bool,
     #[deserr(default, error = DeserrJsonError<InvalidSearchFilter>)]
     pub filter: Option<Value>,
     #[deserr(default, error = DeserrJsonError<InvalidSearchSort>)]
@@ -83,8 +70,6 @@ pub struct SearchQuery {
     pub crop_marker: String,
     #[deserr(default, error = DeserrJsonError<InvalidSearchMatchingStrategy>, default)]
     pub matching_strategy: MatchingStrategy,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchAttributesToSearchOn>, default)]
-    pub attributes_to_search_on: Option<Vec<String>>,
 }
 
 impl SearchQuery {
@@ -122,10 +107,6 @@ pub struct SearchQueryWithIndex {
     pub crop_length: usize,
     #[deserr(default, error = DeserrJsonError<InvalidSearchAttributesToHighlight>)]
     pub attributes_to_highlight: Option<HashSet<String>>,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchShowRankingScore>, default)]
-    pub show_ranking_score: bool,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchShowRankingScoreDetails>, default)]
-    pub show_ranking_score_details: bool,
     #[deserr(default, error = DeserrJsonError<InvalidSearchShowMatchesPosition>, default)]
     pub show_matches_position: bool,
     #[deserr(default, error = DeserrJsonError<InvalidSearchFilter>)]
@@ -142,8 +123,6 @@ pub struct SearchQueryWithIndex {
     pub crop_marker: String,
     #[deserr(default, error = DeserrJsonError<InvalidSearchMatchingStrategy>, default)]
     pub matching_strategy: MatchingStrategy,
-    #[deserr(default, error = DeserrJsonError<InvalidSearchAttributesToSearchOn>, default)]
-    pub attributes_to_search_on: Option<Vec<String>>,
 }
 
 impl SearchQueryWithIndex {
@@ -160,8 +139,6 @@ impl SearchQueryWithIndex {
             attributes_to_crop,
             crop_length,
             attributes_to_highlight,
-            show_ranking_score,
-            show_ranking_score_details,
             show_matches_position,
             filter,
             sort,
@@ -170,7 +147,6 @@ impl SearchQueryWithIndex {
             highlight_post_tag,
             crop_marker,
             matching_strategy,
-            attributes_to_search_on,
         } = self;
         (
             index_uid,
@@ -185,8 +161,6 @@ impl SearchQueryWithIndex {
                 attributes_to_crop,
                 crop_length,
                 attributes_to_highlight,
-                show_ranking_score,
-                show_ranking_score_details,
                 show_matches_position,
                 filter,
                 sort,
@@ -195,7 +169,6 @@ impl SearchQueryWithIndex {
                 highlight_post_tag,
                 crop_marker,
                 matching_strategy,
-                attributes_to_search_on,
                 // do not use ..Default::default() here,
                 // rather add any missing field from `SearchQuery` to `SearchQueryWithIndex`
             },
@@ -203,7 +176,7 @@ impl SearchQueryWithIndex {
     }
 }
 
-#[derive(Debug, Copy, Clone, PartialEq, Eq, Deserr)]
+#[derive(Debug, Clone, PartialEq, Eq, Deserr)]
 #[deserr(rename_all = camelCase)]
 pub enum MatchingStrategy {
     /// Remove query words from last to first
@@ -227,27 +200,7 @@ impl From<MatchingStrategy> for TermsMatchingStrategy {
     }
 }
 
-#[derive(Debug, Default, Clone, PartialEq, Eq, Deserr)]
-#[deserr(rename_all = camelCase)]
-pub enum FacetValuesSort {
-    /// Facet values are sorted in alphabetical order, ascending from A to Z.
-    #[default]
-    Alpha,
-    /// Facet values are sorted by decreasing count.
-    /// The count is the number of records containing this facet value in the results of the query.
-    Count,
-}
-
-impl From<FacetValuesSort> for OrderBy {
-    fn from(val: FacetValuesSort) -> Self {
-        match val {
-            FacetValuesSort::Alpha => OrderBy::Lexicographic,
-            FacetValuesSort::Count => OrderBy::Count,
-        }
-    }
-}
-
-#[derive(Debug, Clone, Serialize, PartialEq)]
+#[derive(Debug, Clone, Serialize, PartialEq, Eq)]
 pub struct SearchHit {
     #[serde(flatten)]
     pub document: Document,
@@ -255,12 +208,6 @@ pub struct SearchHit {
     pub formatted: Document,
     #[serde(rename = "_matchesPosition", skip_serializing_if = "Option::is_none")]
     pub matches_position: Option<MatchesPosition>,
-    #[serde(rename = "_rankingScore", skip_serializing_if = "Option::is_none")]
-    pub ranking_score: Option<f64>,
-    #[serde(rename = "_rankingScoreDetails", skip_serializing_if = "Option::is_none")]
-    pub ranking_score_details: Option<serde_json::Map<String, serde_json::Value>>,
-    #[serde(rename = "_semanticScore", skip_serializing_if = "Option::is_none")]
-    pub semantic_score: Option<f32>,
 }
 
 #[derive(Serialize, Debug, Clone, PartialEq)]
@@ -268,13 +215,11 @@ pub struct SearchHit {
 pub struct SearchResult {
     pub hits: Vec<SearchHit>,
     pub query: String,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub vector: Option<Vec<f32>>,
     pub processing_time_ms: u128,
     #[serde(flatten)]
     pub hits_info: HitsInfo,
     #[serde(skip_serializing_if = "Option::is_none")]
-    pub facet_distribution: Option<BTreeMap<String, IndexMap<String, u64>>>,
+    pub facet_distribution: Option<BTreeMap<String, BTreeMap<String, u64>>>,
     #[serde(skip_serializing_if = "Option::is_none")]
     pub facet_stats: Option<BTreeMap<String, FacetStats>>,
 }
@@ -302,14 +247,6 @@ pub struct FacetStats {
     pub max: f64,
 }
 
-#[derive(Serialize, Debug, Clone, PartialEq)]
-#[serde(rename_all = "camelCase")]
-pub struct FacetSearchResult {
-    pub facet_hits: Vec<FacetValueHit>,
-    pub facet_query: Option<String>,
-    pub processing_time_ms: u128,
-}
-
 /// Incorporate search rules in search query
 pub fn add_search_rules(query: &mut SearchQuery, rules: IndexSearchRules) {
     query.filter = match (query.filter.take(), rules.filter) {
@@ -330,17 +267,14 @@ pub fn add_search_rules(query: &mut SearchQuery, rules: IndexSearchRules) {
     }
 }
 
-fn prepare_search<'t>(
-    index: &'t Index,
-    rtxn: &'t RoTxn,
-    query: &'t SearchQuery,
-    features: RoFeatures,
-) -> Result<(milli::Search<'t>, bool, usize, usize), MeilisearchHttpError> {
-    let mut search = index.search(rtxn);
+pub fn perform_search(
+    index: &Index,
+    query: SearchQuery,
+) -> Result<SearchResult, MeilisearchHttpError> {
+    let before_search = Instant::now();
+    let rtxn = index.read_txn()?;
 
-    if query.vector.is_some() && query.q.is_some() {
-        warn!("Ignoring the query string `q` when used with the `vector` parameter.");
-    }
+    let mut search = index.search(&rtxn);
 
     if let Some(ref vector) = query.vector {
         search.vector(vector.clone());
@@ -350,32 +284,15 @@ fn prepare_search<'t>(
         search.query(query);
     }
 
-    if let Some(ref searchable) = query.attributes_to_search_on {
-        search.searchable_attributes(searchable);
-    }
-
     let is_finite_pagination = query.is_finite_pagination();
     search.terms_matching_strategy(query.matching_strategy.into());
 
     let max_total_hits = index
-        .pagination_max_total_hits(rtxn)
+        .pagination_max_total_hits(&rtxn)
         .map_err(milli::Error::from)?
         .unwrap_or(DEFAULT_PAGINATION_MAX_TOTAL_HITS);
 
     search.exhaustive_number_hits(is_finite_pagination);
-    search.scoring_strategy(if query.show_ranking_score || query.show_ranking_score_details {
-        ScoringStrategy::Detailed
-    } else {
-        ScoringStrategy::Skip
-    });
-
-    if query.show_ranking_score_details {
-        features.check_score_details()?;
-    }
-
-    if query.vector.is_some() {
-        features.check_vector()?;
-    }
 
     // compute the offset on the limit depending on the pagination mode.
     let (offset, limit) = if is_finite_pagination {
@@ -413,22 +330,7 @@ fn prepare_search<'t>(
         search.sort_criteria(sort);
     }
 
-    Ok((search, is_finite_pagination, max_total_hits, offset))
-}
-
-pub fn perform_search(
-    index: &Index,
-    query: SearchQuery,
-    features: RoFeatures,
-) -> Result<SearchResult, MeilisearchHttpError> {
-    let before_search = Instant::now();
-    let rtxn = index.read_txn()?;
-
-    let (search, is_finite_pagination, max_total_hits, offset) =
-        prepare_search(index, &rtxn, &query, features)?;
-
-    let milli::SearchResult { documents_ids, matching_words, candidates, document_scores, .. } =
-        search.execute()?;
+    let milli::SearchResult { documents_ids, matching_words, candidates, .. } = search.execute()?;
 
     let fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
 
@@ -497,9 +399,10 @@ pub fn perform_search(
     formatter_builder.highlight_suffix(query.highlight_post_tag);
 
     let mut documents = Vec::new();
+
     let documents_iter = index.documents(&rtxn, documents_ids)?;
 
-    for ((_id, obkv), score) in documents_iter.into_iter().zip(document_scores.into_iter()) {
+    for (_id, obkv) in documents_iter {
         // First generate a document with all the displayed fields
         let displayed_document = make_document(&displayed_ids, &fields_ids_map, obkv)?;
 
@@ -523,27 +426,7 @@ pub fn perform_search(
             insert_geo_distance(sort, &mut document);
         }
 
-        let semantic_score = match query.vector.as_ref() {
-            Some(vector) => match extract_field("_vectors", &fields_ids_map, obkv)? {
-                Some(vectors) => compute_semantic_score(vector, vectors)?,
-                None => None,
-            },
-            None => None,
-        };
-
-        let ranking_score =
-            query.show_ranking_score.then(|| ScoreDetails::global_score(score.iter()));
-        let ranking_score_details =
-            query.show_ranking_score_details.then(|| ScoreDetails::to_json_map(score.iter()));
-
-        let hit = SearchHit {
-            document,
-            formatted,
-            matches_position,
-            ranking_score_details,
-            ranking_score,
-            semantic_score,
-        };
+        let hit = SearchHit { document, formatted, matches_position };
         documents.push(hit);
     }
 
@@ -575,30 +458,10 @@ pub fn perform_search(
                 .unwrap_or(DEFAULT_VALUES_PER_FACET);
             facet_distribution.max_values_per_facet(max_values_by_facet);
 
-            let sort_facet_values_by =
-                index.sort_facet_values_by(&rtxn).map_err(milli::Error::from)?;
-            let default_sort_facet_values_by =
-                sort_facet_values_by.get("*").copied().unwrap_or_default();
-
             if fields.iter().all(|f| f != "*") {
-                let fields: Vec<_> = fields
-                    .iter()
-                    .map(|n| {
-                        (
-                            n,
-                            sort_facet_values_by
-                                .get(n)
-                                .copied()
-                                .unwrap_or(default_sort_facet_values_by),
-                        )
-                    })
-                    .collect();
                 facet_distribution.facets(fields);
             }
-            let distribution = facet_distribution
-                .candidates(candidates)
-                .default_order_by(default_sort_facet_values_by)
-                .execute()?;
+            let distribution = facet_distribution.candidates(candidates).execute()?;
             let stats = facet_distribution.compute_stats()?;
             (Some(distribution), Some(stats))
         }
@@ -612,8 +475,7 @@ pub fn perform_search(
     let result = SearchResult {
         hits: documents,
         hits_info,
-        query: query.q.unwrap_or_default(),
-        vector: query.vector,
+        query: query.q.clone().unwrap_or_default(),
         processing_time_ms: before_search.elapsed().as_millis(),
         facet_distribution,
         facet_stats,
@@ -621,29 +483,6 @@ pub fn perform_search(
     Ok(result)
 }
 
-pub fn perform_facet_search(
-    index: &Index,
-    search_query: SearchQuery,
-    facet_query: Option<String>,
-    facet_name: String,
-    features: RoFeatures,
-) -> Result<FacetSearchResult, MeilisearchHttpError> {
-    let before_search = Instant::now();
-    let rtxn = index.read_txn()?;
-
-    let (search, _, _, _) = prepare_search(index, &rtxn, &search_query, features)?;
-    let mut facet_search = SearchForFacetValues::new(facet_name, search);
-    if let Some(facet_query) = &facet_query {
-        facet_search.query(facet_query);
-    }
-
-    Ok(FacetSearchResult {
-        facet_hits: facet_search.execute()?,
-        facet_query,
-        processing_time_ms: before_search.elapsed().as_millis(),
-    })
-}
-
 fn insert_geo_distance(sorts: &[String], document: &mut Document) {
     lazy_static::lazy_static! {
         static ref GEO_REGEX: Regex =
@@ -660,17 +499,6 @@ fn insert_geo_distance(sorts: &[String], document: &mut Document) {
     }
 }
 
-fn compute_semantic_score(query: &[f32], vectors: Value) -> milli::Result<Option<f32>> {
-    let vectors = serde_json::from_value(vectors)
-        .map(VectorOrArrayOfVectors::into_array_of_vectors)
-        .map_err(InternalError::SerdeJson)?;
-    Ok(vectors
-        .into_iter()
-        .map(|v| OrderedFloat(dot_product_similarity(query, &v)))
-        .max()
-        .map(OrderedFloat::into_inner))
-}
-
 fn compute_formatted_options(
     attr_to_highlight: &HashSet<String>,
     attr_to_crop: &[String],
@@ -798,26 +626,10 @@ fn make_document(
     Ok(document)
 }
 
-/// Extract the JSON value under the field name specified
-/// but doesn't support nested objects.
-fn extract_field(
-    field_name: &str,
-    field_ids_map: &FieldsIdsMap,
-    obkv: obkv::KvReaderU16,
-) -> Result<Option<serde_json::Value>, MeilisearchHttpError> {
-    match field_ids_map.id(field_name) {
-        Some(fid) => match obkv.get(fid) {
-            Some(value) => Ok(serde_json::from_slice(value).map(Some)?),
-            None => Ok(None),
-        },
-        None => Ok(None),
-    }
-}
-
-fn format_fields<'a>(
+fn format_fields<A: AsRef<[u8]>>(
     document: &Document,
     field_ids_map: &FieldsIdsMap,
-    builder: &'a MatcherBuilder<'a>,
+    builder: &MatcherBuilder<'_, A>,
     formatted_options: &BTreeMap<FieldId, FormatOptions>,
     compute_matches: bool,
     displayable_ids: &BTreeSet<FieldId>,
@@ -862,9 +674,9 @@ fn format_fields<'a>(
     Ok((matches_position, document))
 }
 
-fn format_value<'a>(
+fn format_value<A: AsRef<[u8]>>(
     value: Value,
-    builder: &'a MatcherBuilder<'a>,
+    builder: &MatcherBuilder<'_, A>,
     format_options: Option<FormatOptions>,
     infos: &mut Vec<MatchBounds>,
     compute_matches: bool,

meilisearch/tests/auth/api_keys.rs

@@ -422,7 +422,7 @@ async fn error_add_api_key_invalid_parameters_actions() {
     meili_snap::snapshot!(code, @"400 Bad Request");
     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`, `version`, `keys.create`, `keys.get`, `keys.update`, `keys.delete`, `experimental.get`, `experimental.update`",
+      "message": "Unknown value `doc.add` at `.actions[0]`: expected one of `*`, `search`, `documents.*`, `documents.add`, `documents.get`, `documents.delete`, `indexes.*`, `indexes.create`, `indexes.get`, `indexes.update`, `indexes.delete`, `indexes.swap`, `tasks.*`, `tasks.cancel`, `tasks.delete`, `tasks.get`, `settings.*`, `settings.get`, `settings.update`, `stats.*`, `stats.get`, `metrics.*`, `metrics.get`, `dumps.*`, `dumps.create`, `version`, `keys.create`, `keys.get`, `keys.update`, `keys.delete`",
       "code": "invalid_api_key_actions",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_api_key_actions"

meilisearch/tests/auth/errors.rs

@@ -90,7 +90,7 @@ async fn create_api_key_bad_actions() {
     snapshot!(code, @"400 Bad Request");
     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`, `version`, `keys.create`, `keys.get`, `keys.update`, `keys.delete`, `experimental.get`, `experimental.update`",
+      "message": "Unknown value `doggo` at `.actions[0]`: expected one of `*`, `search`, `documents.*`, `documents.add`, `documents.get`, `documents.delete`, `indexes.*`, `indexes.create`, `indexes.get`, `indexes.update`, `indexes.delete`, `indexes.swap`, `tasks.*`, `tasks.cancel`, `tasks.delete`, `tasks.get`, `settings.*`, `settings.get`, `settings.update`, `stats.*`, `stats.get`, `metrics.*`, `metrics.get`, `dumps.*`, `dumps.create`, `version`, `keys.create`, `keys.get`, `keys.update`, `keys.delete`",
       "code": "invalid_api_key_actions",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_api_key_actions"

meilisearch/tests/common/index.rs

@@ -346,24 +346,17 @@ impl Index<'_> {
         query: Value,
         test: impl Fn(Value, StatusCode) + UnwindSafe + Clone,
     ) {
-        let post = self.search_post(query.clone()).await;
-
+        let (response, code) = self.search_post(query.clone()).await;
+        let t = test.clone();
+        if let Err(e) = catch_unwind(move || t(response, code)) {
+            eprintln!("Error with post search");
+            resume_unwind(e);
+        }
         let query = yaup::to_string(&query).unwrap();
-        let get = self.search_get(&query).await;
-
-        insta::allow_duplicates! {
-            let (response, code) = post;
-            let t = test.clone();
-            if let Err(e) = catch_unwind(move || t(response, code)) {
-                eprintln!("Error with post search");
-                resume_unwind(e);
-            }
-
-            let (response, code) = get;
-            if let Err(e) = catch_unwind(move || test(response, code)) {
-                eprintln!("Error with get search");
-                resume_unwind(e);
-            }
+        let (response, code) = self.search_get(&query).await;
+        if let Err(e) = catch_unwind(move || test(response, code)) {
+            eprintln!("Error with get search");
+            resume_unwind(e);
         }
     }
 
@@ -377,11 +370,6 @@ impl Index<'_> {
         self.service.get(url).await
     }
 
-    pub async fn facet_search(&self, query: Value) -> (Value, StatusCode) {
-        let url = format!("/indexes/{}/facet-search", urlencode(self.uid.as_ref()));
-        self.service.post_encoded(url, query, self.encoder).await
-    }
-
     pub async fn update_distinct_attribute(&self, value: Value) -> (Value, StatusCode) {
         let url =
             format!("/indexes/{}/settings/{}", urlencode(self.uid.as_ref()), "distinct-attribute");

meilisearch/tests/dumps/mod.rs

@@ -36,7 +36,7 @@ async fn import_dump_v1_movie_raw() {
     assert_eq!(code, 200);
     assert_eq!(
         settings,
-        json!({"displayedAttributes": ["*"], "searchableAttributes": ["*"], "filterableAttributes": [], "sortableAttributes": [], "rankingRules": ["typo", "words", "proximity", "attribute", "exactness"], "stopWords": [], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": {"oneTypo": 5, "twoTypos": 9}, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100, "sortFacetValuesBy": { "*": "alpha" } }, "pagination": { "maxTotalHits": 1000 } })
+        json!({"displayedAttributes": ["*"], "searchableAttributes": ["*"], "filterableAttributes": [], "sortableAttributes": [], "rankingRules": ["typo", "words", "proximity", "attribute", "exactness"], "stopWords": [], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": {"oneTypo": 5, "twoTypos": 9}, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100 }, "pagination": { "maxTotalHits": 1000 } })
     );
 
     let (tasks, code) = index.list_tasks().await;
@@ -128,7 +128,7 @@ async fn import_dump_v1_movie_with_settings() {
     assert_eq!(code, 200);
     assert_eq!(
         settings,
-        json!({ "displayedAttributes": ["genres", "id", "overview", "poster", "release_date", "title"], "searchableAttributes": ["title", "overview"], "filterableAttributes": ["genres"], "sortableAttributes": ["genres"], "rankingRules": ["typo", "words", "proximity", "attribute", "exactness"], "stopWords": ["of", "the"], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": { "oneTypo": 5, "twoTypos": 9 }, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100, "sortFacetValuesBy": { "*": "alpha" } }, "pagination": { "maxTotalHits": 1000 } })
+        json!({ "displayedAttributes": ["genres", "id", "overview", "poster", "release_date", "title"], "searchableAttributes": ["title", "overview"], "filterableAttributes": ["genres"], "sortableAttributes": ["genres"], "rankingRules": ["typo", "words", "proximity", "attribute", "exactness"], "stopWords": ["of", "the"], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": { "oneTypo": 5, "twoTypos": 9 }, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100 }, "pagination": { "maxTotalHits": 1000 } })
     );
 
     let (tasks, code) = index.list_tasks().await;
@@ -220,7 +220,7 @@ async fn import_dump_v1_rubygems_with_settings() {
     assert_eq!(code, 200);
     assert_eq!(
         settings,
-        json!({"displayedAttributes": ["description", "id", "name", "summary", "total_downloads", "version"], "searchableAttributes": ["name", "summary"], "filterableAttributes": ["version"], "sortableAttributes": ["version"], "rankingRules": ["typo", "words", "fame:desc", "proximity", "attribute", "exactness", "total_downloads:desc"], "stopWords": [], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": {"oneTypo": 5, "twoTypos": 9}, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100, "sortFacetValuesBy": { "*": "alpha" } }, "pagination": { "maxTotalHits": 1000 }})
+        json!({"displayedAttributes": ["description", "id", "name", "summary", "total_downloads", "version"], "searchableAttributes": ["name", "summary"], "filterableAttributes": ["version"], "sortableAttributes": ["version"], "rankingRules": ["typo", "words", "fame:desc", "proximity", "attribute", "exactness", "total_downloads:desc"], "stopWords": [], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": {"oneTypo": 5, "twoTypos": 9}, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100 }, "pagination": { "maxTotalHits": 1000 }})
     );
 
     let (tasks, code) = index.list_tasks().await;
@@ -310,7 +310,7 @@ async fn import_dump_v2_movie_raw() {
     assert_eq!(code, 200);
     assert_eq!(
         settings,
-        json!({"displayedAttributes": ["*"], "searchableAttributes": ["*"], "filterableAttributes": [], "sortableAttributes": [], "rankingRules": ["words", "typo", "proximity", "attribute", "exactness"], "stopWords": [], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": {"oneTypo": 5, "twoTypos": 9}, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100, "sortFacetValuesBy": { "*": "alpha" } }, "pagination": { "maxTotalHits": 1000 } })
+        json!({"displayedAttributes": ["*"], "searchableAttributes": ["*"], "filterableAttributes": [], "sortableAttributes": [], "rankingRules": ["words", "typo", "proximity", "attribute", "exactness"], "stopWords": [], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": {"oneTypo": 5, "twoTypos": 9}, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100 }, "pagination": { "maxTotalHits": 1000 } })
     );
 
     let (tasks, code) = index.list_tasks().await;
@@ -402,7 +402,7 @@ async fn import_dump_v2_movie_with_settings() {
     assert_eq!(code, 200);
     assert_eq!(
         settings,
-        json!({ "displayedAttributes": ["title", "genres", "overview", "poster", "release_date"], "searchableAttributes": ["title", "overview"], "filterableAttributes": ["genres"], "sortableAttributes": [], "rankingRules": ["words", "typo", "proximity", "attribute", "exactness"], "stopWords": ["of", "the"], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": { "oneTypo": 5, "twoTypos": 9 }, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100, "sortFacetValuesBy": { "*": "alpha" } }, "pagination": { "maxTotalHits": 1000 } })
+        json!({ "displayedAttributes": ["title", "genres", "overview", "poster", "release_date"], "searchableAttributes": ["title", "overview"], "filterableAttributes": ["genres"], "sortableAttributes": [], "rankingRules": ["words", "typo", "proximity", "attribute", "exactness"], "stopWords": ["of", "the"], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": { "oneTypo": 5, "twoTypos": 9 }, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100 }, "pagination": { "maxTotalHits": 1000 } })
     );
 
     let (tasks, code) = index.list_tasks().await;
@@ -494,7 +494,7 @@ async fn import_dump_v2_rubygems_with_settings() {
     assert_eq!(code, 200);
     assert_eq!(
         settings,
-        json!({"displayedAttributes": ["name", "summary", "description", "version", "total_downloads"], "searchableAttributes": ["name", "summary"], "filterableAttributes": ["version"], "sortableAttributes": [], "rankingRules": ["typo", "words", "fame:desc", "proximity", "attribute", "exactness", "total_downloads:desc"], "stopWords": [], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": {"oneTypo": 5, "twoTypos": 9}, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100, "sortFacetValuesBy": { "*": "alpha" } }, "pagination": { "maxTotalHits": 1000 }})
+        json!({"displayedAttributes": ["name", "summary", "description", "version", "total_downloads"], "searchableAttributes": ["name", "summary"], "filterableAttributes": ["version"], "sortableAttributes": [], "rankingRules": ["typo", "words", "fame:desc", "proximity", "attribute", "exactness", "total_downloads:desc"], "stopWords": [], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": {"oneTypo": 5, "twoTypos": 9}, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100 }, "pagination": { "maxTotalHits": 1000 }})
     );
 
     let (tasks, code) = index.list_tasks().await;
@@ -584,7 +584,7 @@ async fn import_dump_v3_movie_raw() {
     assert_eq!(code, 200);
     assert_eq!(
         settings,
-        json!({"displayedAttributes": ["*"], "searchableAttributes": ["*"], "filterableAttributes": [], "sortableAttributes": [], "rankingRules": ["words", "typo", "proximity", "attribute", "exactness"], "stopWords": [], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": {"oneTypo": 5, "twoTypos": 9}, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100, "sortFacetValuesBy": { "*": "alpha" } }, "pagination": { "maxTotalHits": 1000 } })
+        json!({"displayedAttributes": ["*"], "searchableAttributes": ["*"], "filterableAttributes": [], "sortableAttributes": [], "rankingRules": ["words", "typo", "proximity", "attribute", "exactness"], "stopWords": [], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": {"oneTypo": 5, "twoTypos": 9}, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100 }, "pagination": { "maxTotalHits": 1000 } })
     );
 
     let (tasks, code) = index.list_tasks().await;
@@ -676,7 +676,7 @@ async fn import_dump_v3_movie_with_settings() {
     assert_eq!(code, 200);
     assert_eq!(
         settings,
-        json!({ "displayedAttributes": ["title", "genres", "overview", "poster", "release_date"], "searchableAttributes": ["title", "overview"], "filterableAttributes": ["genres"], "sortableAttributes": [], "rankingRules": ["words", "typo", "proximity", "attribute", "exactness"], "stopWords": ["of", "the"], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": { "oneTypo": 5, "twoTypos": 9 }, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100, "sortFacetValuesBy": { "*": "alpha" } }, "pagination": { "maxTotalHits": 1000 } })
+        json!({ "displayedAttributes": ["title", "genres", "overview", "poster", "release_date"], "searchableAttributes": ["title", "overview"], "filterableAttributes": ["genres"], "sortableAttributes": [], "rankingRules": ["words", "typo", "proximity", "attribute", "exactness"], "stopWords": ["of", "the"], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": { "oneTypo": 5, "twoTypos": 9 }, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100 }, "pagination": { "maxTotalHits": 1000 } })
     );
 
     let (tasks, code) = index.list_tasks().await;
@@ -768,7 +768,7 @@ async fn import_dump_v3_rubygems_with_settings() {
     assert_eq!(code, 200);
     assert_eq!(
         settings,
-        json!({"displayedAttributes": ["name", "summary", "description", "version", "total_downloads"], "searchableAttributes": ["name", "summary"], "filterableAttributes": ["version"], "sortableAttributes": [], "rankingRules": ["typo", "words", "fame:desc", "proximity", "attribute", "exactness", "total_downloads:desc"], "stopWords": [], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": {"oneTypo": 5, "twoTypos": 9}, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100, "sortFacetValuesBy": { "*": "alpha" } }, "pagination": { "maxTotalHits": 1000 } })
+        json!({"displayedAttributes": ["name", "summary", "description", "version", "total_downloads"], "searchableAttributes": ["name", "summary"], "filterableAttributes": ["version"], "sortableAttributes": [], "rankingRules": ["typo", "words", "fame:desc", "proximity", "attribute", "exactness", "total_downloads:desc"], "stopWords": [], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": {"oneTypo": 5, "twoTypos": 9}, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100 }, "pagination": { "maxTotalHits": 1000 } })
     );
 
     let (tasks, code) = index.list_tasks().await;
@@ -858,7 +858,7 @@ async fn import_dump_v4_movie_raw() {
     assert_eq!(code, 200);
     assert_eq!(
         settings,
-        json!({ "displayedAttributes": ["*"], "searchableAttributes": ["*"], "filterableAttributes": [], "sortableAttributes": [], "rankingRules": ["words", "typo", "proximity", "attribute", "exactness"], "stopWords": [], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": {"oneTypo": 5, "twoTypos": 9}, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100, "sortFacetValuesBy": { "*": "alpha" } }, "pagination": { "maxTotalHits": 1000 } })
+        json!({ "displayedAttributes": ["*"], "searchableAttributes": ["*"], "filterableAttributes": [], "sortableAttributes": [], "rankingRules": ["words", "typo", "proximity", "attribute", "exactness"], "stopWords": [], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": {"oneTypo": 5, "twoTypos": 9}, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100 }, "pagination": { "maxTotalHits": 1000 } })
     );
 
     let (tasks, code) = index.list_tasks().await;
@@ -950,7 +950,7 @@ async fn import_dump_v4_movie_with_settings() {
     assert_eq!(code, 200);
     assert_eq!(
         settings,
-        json!({ "displayedAttributes": ["title", "genres", "overview", "poster", "release_date"], "searchableAttributes": ["title", "overview"], "filterableAttributes": ["genres"], "sortableAttributes": [], "rankingRules": ["words", "typo", "proximity", "attribute", "exactness"], "stopWords": ["of", "the"], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": { "oneTypo": 5, "twoTypos": 9 }, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100, "sortFacetValuesBy": { "*": "alpha" } }, "pagination": { "maxTotalHits": 1000 } })
+        json!({ "displayedAttributes": ["title", "genres", "overview", "poster", "release_date"], "searchableAttributes": ["title", "overview"], "filterableAttributes": ["genres"], "sortableAttributes": [], "rankingRules": ["words", "typo", "proximity", "attribute", "exactness"], "stopWords": ["of", "the"], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": { "oneTypo": 5, "twoTypos": 9 }, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100 }, "pagination": { "maxTotalHits": 1000 } })
     );
 
     let (tasks, code) = index.list_tasks().await;
@@ -1042,7 +1042,7 @@ async fn import_dump_v4_rubygems_with_settings() {
     assert_eq!(code, 200);
     assert_eq!(
         settings,
-        json!({ "displayedAttributes": ["name", "summary", "description", "version", "total_downloads"], "searchableAttributes": ["name", "summary"], "filterableAttributes": ["version"], "sortableAttributes": [], "rankingRules": ["typo", "words", "fame:desc", "proximity", "attribute", "exactness", "total_downloads:desc"], "stopWords": [], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": {"oneTypo": 5, "twoTypos": 9}, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100, "sortFacetValuesBy": { "*": "alpha" } }, "pagination": { "maxTotalHits": 1000 } })
+        json!({ "displayedAttributes": ["name", "summary", "description", "version", "total_downloads"], "searchableAttributes": ["name", "summary"], "filterableAttributes": ["version"], "sortableAttributes": [], "rankingRules": ["typo", "words", "fame:desc", "proximity", "attribute", "exactness", "total_downloads:desc"], "stopWords": [], "synonyms": {}, "distinctAttribute": null, "typoTolerance": {"enabled": true, "minWordSizeForTypos": {"oneTypo": 5, "twoTypos": 9}, "disableOnWords": [], "disableOnAttributes": [] }, "faceting": { "maxValuesPerFacet": 100 }, "pagination": { "maxTotalHits": 1000 } })
     );
 
     let (tasks, code) = index.list_tasks().await;

meilisearch/tests/search/errors.rs

@@ -963,29 +963,3 @@ async fn sort_unset_ranking_rule() {
         )
         .await;
 }
-
-#[actix_rt::test]
-async fn search_on_unknown_field() {
-    let server = Server::new().await;
-    let index = server.index("test");
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(0).await;
-
-    index
-        .search(
-            json!({"q": "Captain Marvel", "attributesToSearchOn": ["unknown"]}),
-            |response, code| {
-                snapshot!(code, @"400 Bad Request");
-                snapshot!(json_string!(response), @r###"
-                {
-                  "message": "Attribute `unknown` is not searchable. Available searchable attributes are: `id, title`.",
-                  "code": "invalid_search_attributes_to_search_on",
-                  "type": "invalid_request",
-                  "link": "https://docs.meilisearch.com/errors#invalid_search_attributes_to_search_on"
-                }
-                "###);
-            },
-        )
-        .await;
-}

meilisearch/tests/search/facet_search.rs

@@ -1,92 +0,0 @@
-use once_cell::sync::Lazy;
-use serde_json::{json, Value};
-
-use crate::common::Server;
-
-pub(self) static DOCUMENTS: Lazy<Value> = Lazy::new(|| {
-    json!([
-        {
-            "title": "Shazam!",
-            "genres": ["Action", "Adventure"],
-            "id": "287947",
-        },
-        {
-            "title": "Captain Marvel",
-            "genres": ["Action", "Adventure"],
-            "id": "299537",
-        },
-        {
-            "title": "Escape Room",
-            "genres": ["Horror", "Thriller", "Multiple Words"],
-            "id": "522681",
-        },
-        {
-            "title": "How to Train Your Dragon: The Hidden World",
-            "genres": ["Action", "Comedy"],
-            "id": "166428",
-        },
-        {
-            "title": "Gläss",
-            "genres": ["Thriller"],
-            "id": "450465",
-        }
-    ])
-});
-
-#[actix_rt::test]
-async fn simple_facet_search() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
-    let documents = DOCUMENTS.clone();
-    index.update_settings_filterable_attributes(json!(["genres"])).await;
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
-
-    let (response, code) =
-        index.facet_search(json!({"facetName": "genres", "facetQuery": "a"})).await;
-
-    assert_eq!(code, 200, "{}", response);
-    assert_eq!(dbg!(response)["facetHits"].as_array().unwrap().len(), 2);
-
-    let (response, code) =
-        index.facet_search(json!({"facetName": "genres", "facetQuery": "adventure"})).await;
-
-    assert_eq!(code, 200, "{}", response);
-    assert_eq!(response["facetHits"].as_array().unwrap().len(), 1);
-}
-
-#[actix_rt::test]
-async fn non_filterable_facet_search_error() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
-    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(0).await;
-
-    let (response, code) =
-        index.facet_search(json!({"facetName": "genres", "facetQuery": "a"})).await;
-    assert_eq!(code, 400, "{}", response);
-
-    let (response, code) =
-        index.facet_search(json!({"facetName": "genres", "facetQuery": "adv"})).await;
-    assert_eq!(code, 400, "{}", response);
-}
-
-#[actix_rt::test]
-async fn facet_search_dont_support_words() {
-    let server = Server::new().await;
-    let index = server.index("test");
-
-    let documents = DOCUMENTS.clone();
-    index.update_settings_filterable_attributes(json!(["genres"])).await;
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
-
-    let (response, code) =
-        index.facet_search(json!({"facetName": "genres", "facetQuery": "words"})).await;
-
-    assert_eq!(code, 200, "{}", response);
-    assert_eq!(response["facetHits"].as_array().unwrap().len(), 0);
-}

meilisearch/tests/search/formatted.rs

@@ -1,4 +1,3 @@
-use insta::{allow_duplicates, assert_json_snapshot};
 use serde_json::json;
 
 use super::*;
@@ -19,43 +18,30 @@ async fn formatted_contain_wildcard() {
         |response, code|
         {
             assert_eq!(code, 200, "{}", response);
-            allow_duplicates! {
-              assert_json_snapshot!(response["hits"][0],
-                    { "._rankingScore" => "[score]" },
-                    @r###"
-              {
-                "_formatted": {
-                  "id": "852",
-                  "cattos": "<em>pésti</em>"
-                },
-                "_matchesPosition": {
-                  "cattos": [
-                    {
-                      "start": 0,
-                      "length": 5
-                    }
-                  ]
-                }
-              }
-              "###);
-            }
-    }
+            assert_eq!(
+                response["hits"][0],
+                json!({
+                    "_formatted": {
+                        "id": "852",
+                        "cattos": "<em>pésti</em>",
+                    },
+                    "_matchesPosition": {"cattos": [{"start": 0, "length": 5}]},
+                })
+            );
+        }
     )
     .await;
 
     index
         .search(json!({ "q": "pésti", "attributesToRetrieve": ["*"] }), |response, code| {
             assert_eq!(code, 200, "{}", response);
-            allow_duplicates! {
-                assert_json_snapshot!(response["hits"][0],
-                { "._rankingScore" => "[score]" },
-                @r###"
-                {
-                  "id": 852,
-                  "cattos": "pésti"
-                }
-                "###)
-            }
+            assert_eq!(
+                response["hits"][0],
+                json!({
+                    "id": 852,
+                    "cattos": "pésti",
+                })
+            );
         })
         .await;
 
@@ -64,29 +50,20 @@ async fn formatted_contain_wildcard() {
             json!({ "q": "pésti", "attributesToRetrieve": ["*"], "attributesToHighlight": ["id"], "showMatchesPosition": true }),
             |response, code| {
                 assert_eq!(code, 200, "{}", response);
-                allow_duplicates! {
-                  assert_json_snapshot!(response["hits"][0],
-                 { "._rankingScore" => "[score]" },
-                 @r###"
-                  {
-                    "id": 852,
-                    "cattos": "pésti",
-                    "_formatted": {
-                      "id": "852",
-                      "cattos": "pésti"
-                    },
-                    "_matchesPosition": {
-                      "cattos": [
-                        {
-                          "start": 0,
-                          "length": 5
-                        }
-                      ]
-                    }
-                  }
-                  "###)
-             }
-        })
+                assert_eq!(
+                    response["hits"][0],
+                    json!({
+                        "id": 852,
+                        "cattos": "pésti",
+                        "_formatted": {
+                            "id": "852",
+                            "cattos": "pésti",
+                        },
+                        "_matchesPosition": {"cattos": [{"start": 0, "length": 5}]},
+                    })
+                );
+            }
+        )
         .await;
 
     index
@@ -94,20 +71,17 @@ async fn formatted_contain_wildcard() {
             json!({ "q": "pésti", "attributesToRetrieve": ["*"], "attributesToCrop": ["*"] }),
             |response, code| {
                 assert_eq!(code, 200, "{}", response);
-                allow_duplicates! {
-                    assert_json_snapshot!(response["hits"][0],
-                    { "._rankingScore" => "[score]" },
-                    @r###"
-                    {
-                      "id": 852,
-                      "cattos": "pésti",
-                      "_formatted": {
-                        "id": "852",
-                        "cattos": "pésti"
-                      }
-                    }
-                    "###);
-                }
+                assert_eq!(
+                    response["hits"][0],
+                    json!({
+                        "id": 852,
+                        "cattos": "pésti",
+                        "_formatted": {
+                            "id": "852",
+                            "cattos": "pésti",
+                        }
+                    })
+                );
             },
         )
         .await;
@@ -115,20 +89,17 @@ async fn formatted_contain_wildcard() {
     index
         .search(json!({ "q": "pésti", "attributesToCrop": ["*"] }), |response, code| {
             assert_eq!(code, 200, "{}", response);
-            allow_duplicates! {
-                assert_json_snapshot!(response["hits"][0],
-                { "._rankingScore" => "[score]" },
-                @r###"
-                {
-                  "id": 852,
-                  "cattos": "pésti",
-                  "_formatted": {
-                    "id": "852",
-                    "cattos": "pésti"
-                  }
-                }
-                "###)
-            }
+            assert_eq!(
+                response["hits"][0],
+                json!({
+                    "id": 852,
+                    "cattos": "pésti",
+                    "_formatted": {
+                        "id": "852",
+                        "cattos": "pésti",
+                    }
+                })
+            );
         })
         .await;
 }
@@ -145,24 +116,21 @@ async fn format_nested() {
     index
         .search(json!({ "q": "pésti", "attributesToRetrieve": ["doggos"] }), |response, code| {
             assert_eq!(code, 200, "{}", response);
-            allow_duplicates! {
-                assert_json_snapshot!(response["hits"][0],
-                { "._rankingScore" => "[score]" },
-                @r###"
-                {
-                  "doggos": [
-                    {
-                      "name": "bobby",
-                      "age": 2
-                    },
-                    {
-                      "name": "buddy",
-                      "age": 4
-                    }
-                  ]
-                }
-                "###)
-            }
+            assert_eq!(
+                response["hits"][0],
+                json!({
+                    "doggos": [
+                        {
+                            "name": "bobby",
+                            "age": 2,
+                        },
+                        {
+                            "name": "buddy",
+                            "age": 4,
+                        },
+                    ],
+                })
+            );
         })
         .await;
 
@@ -171,22 +139,19 @@ async fn format_nested() {
             json!({ "q": "pésti", "attributesToRetrieve": ["doggos.name"] }),
             |response, code| {
                 assert_eq!(code, 200, "{}", response);
-                allow_duplicates! {
-                    assert_json_snapshot!(response["hits"][0],
-                    { "._rankingScore" => "[score]" },
-                    @r###"
-                    {
-                      "doggos": [
-                        {
-                          "name": "bobby"
-                        },
-                        {
-                          "name": "buddy"
-                        }
-                      ]
-                    }
-                    "###)
-                }
+                assert_eq!(
+                    response["hits"][0],
+                    json!({
+                        "doggos": [
+                            {
+                                "name": "bobby",
+                            },
+                            {
+                                "name": "buddy",
+                            },
+                        ],
+                    })
+                );
             },
         )
         .await;
@@ -196,30 +161,20 @@ async fn format_nested() {
             json!({ "q": "bobby", "attributesToRetrieve": ["doggos.name"], "showMatchesPosition": true }),
             |response, code| {
                 assert_eq!(code, 200, "{}", response);
-                allow_duplicates! {
-                    assert_json_snapshot!(response["hits"][0],
-                    { "._rankingScore" => "[score]" },
-                    @r###"
-                    {
-                      "doggos": [
-                        {
-                          "name": "bobby"
-                        },
-                        {
-                          "name": "buddy"
-                        }
-                      ],
-                      "_matchesPosition": {
-                        "doggos.name": [
-                          {
-                            "start": 0,
-                            "length": 5
-                          }
-                        ]
-                      }
-                    }
-                    "###)
-                }
+                assert_eq!(
+                    response["hits"][0],
+                    json!({
+                        "doggos": [
+                            {
+                                "name": "bobby",
+                            },
+                            {
+                                "name": "buddy",
+                            },
+                        ],
+                        "_matchesPosition": {"doggos.name": [{"start": 0, "length": 5}]},
+                    })
+                );
             }
         )
         .await;
@@ -228,24 +183,21 @@ async fn format_nested() {
         .search(json!({ "q": "pésti", "attributesToRetrieve": [], "attributesToHighlight": ["doggos.name"] }),
         |response, code| {
             assert_eq!(code, 200, "{}", response);
-            allow_duplicates! {
-                assert_json_snapshot!(response["hits"][0],
-                { "._rankingScore" => "[score]" },
-                @r###"
-                {
-                  "_formatted": {
-                    "doggos": [
-                      {
-                        "name": "bobby"
-                      },
-                      {
-                        "name": "buddy"
-                      }
-                    ]
-                  }
-                }
-                "###)
-            }
+            assert_eq!(
+                response["hits"][0],
+                json!({
+                    "_formatted": {
+                        "doggos": [
+                            {
+                                "name": "bobby",
+                            },
+                            {
+                                "name": "buddy",
+                            },
+                        ],
+                    },
+                })
+            );
         })
         .await;
 
@@ -253,24 +205,21 @@ async fn format_nested() {
         .search(json!({ "q": "pésti", "attributesToRetrieve": [], "attributesToCrop": ["doggos.name"] }),
         |response, code| {
             assert_eq!(code, 200, "{}", response);
-            allow_duplicates! {
-                assert_json_snapshot!(response["hits"][0],
-                { "._rankingScore" => "[score]" },
-                @r###"
-                {
-                  "_formatted": {
-                    "doggos": [
-                      {
-                        "name": "bobby"
-                      },
-                      {
-                        "name": "buddy"
-                      }
-                    ]
-                  }
-                }
-                "###)
-            }
+            assert_eq!(
+                response["hits"][0],
+                json!({
+                    "_formatted": {
+                        "doggos": [
+                            {
+                                "name": "bobby",
+                            },
+                            {
+                                "name": "buddy",
+                            },
+                        ],
+                    },
+                })
+            );
         })
         .await;
 
@@ -278,61 +227,55 @@ async fn format_nested() {
         .search(json!({ "q": "pésti", "attributesToRetrieve": ["doggos.name"], "attributesToHighlight": ["doggos.age"] }),
         |response, code| {
     assert_eq!(code, 200, "{}", response);
-    allow_duplicates! {
-        assert_json_snapshot!(response["hits"][0],
-        { "._rankingScore" => "[score]" },
-        @r###"
-        {
-          "doggos": [
-            {
-              "name": "bobby"
-            },
-            {
-              "name": "buddy"
-            }
-          ],
-          "_formatted": {
+    assert_eq!(
+        response["hits"][0],
+        json!({
             "doggos": [
-              {
-                "name": "bobby",
-                "age": "2"
-              },
-              {
-                "name": "buddy",
-                "age": "4"
-              }
-            ]
-          }
-        }
-        "###)
-    }
-    })
+                {
+                    "name": "bobby",
+                },
+                {
+                    "name": "buddy",
+                },
+            ],
+            "_formatted": {
+                "doggos": [
+                    {
+                        "name": "bobby",
+                        "age": "2",
+                    },
+                    {
+                        "name": "buddy",
+                        "age": "4",
+                    },
+                ],
+            },
+        })
+    );
+        })
         .await;
 
     index
         .search(json!({ "q": "pésti", "attributesToRetrieve": [], "attributesToHighlight": ["doggos.age"], "attributesToCrop": ["doggos.name"] }),
         |response, code| {
                 assert_eq!(code, 200, "{}", response);
-                allow_duplicates! {
-                    assert_json_snapshot!(response["hits"][0],
-                    { "._rankingScore" => "[score]" },
-                    @r###"
+    assert_eq!(
+        response["hits"][0],
+        json!({
+            "_formatted": {
+                "doggos": [
                     {
-                      "_formatted": {
-                        "doggos": [
-                          {
-                            "name": "bobby",
-                            "age": "2"
-                          },
-                          {
-                            "name": "buddy",
-                            "age": "4"
-                          }
-                        ]
-                      }
-                    }
-                    "###)
-                }
+                        "name": "bobby",
+                        "age": "2",
+                    },
+                    {
+                        "name": "buddy",
+                        "age": "4",
+                    },
+                ],
+            },
+        })
+    );
             }
         )
         .await;
@@ -354,66 +297,54 @@ async fn displayedattr_2_smol() {
         .search(json!({ "attributesToRetrieve": ["father", "id"], "attributesToHighlight": ["mother"], "attributesToCrop": ["cattos"] }),
         |response, code| {
     assert_eq!(code, 200, "{}", response);
-    allow_duplicates! {
-        assert_json_snapshot!(response["hits"][0],
-        { "._rankingScore" => "[score]" },
-        @r###"
-        {
-          "id": 852
-        }
-        "###)
-    }
+    assert_eq!(
+        response["hits"][0],
+        json!({
+            "id": 852,
+        })
+    );
         })
         .await;
 
     index
         .search(json!({ "attributesToRetrieve": ["id"] }), |response, code| {
             assert_eq!(code, 200, "{}", response);
-            allow_duplicates! {
-                assert_json_snapshot!(response["hits"][0],
-                { "._rankingScore" => "[score]" },
-                @r###"
-                {
-                  "id": 852
-                }
-                "###)
-            }
+            assert_eq!(
+                response["hits"][0],
+                json!({
+                    "id": 852,
+                })
+            );
         })
         .await;
 
     index
         .search(json!({ "attributesToHighlight": ["id"] }), |response, code| {
             assert_eq!(code, 200, "{}", response);
-            allow_duplicates! {
-                assert_json_snapshot!(response["hits"][0],
-                { "._rankingScore" => "[score]" },
-                @r###"
-                {
-                  "id": 852,
-                  "_formatted": {
-                    "id": "852"
-                  }
-                }
-                "###)
-            }
+            assert_eq!(
+                response["hits"][0],
+                json!({
+                    "id": 852,
+                    "_formatted": {
+                        "id": "852",
+                    }
+                })
+            );
         })
         .await;
 
     index
         .search(json!({ "attributesToCrop": ["id"] }), |response, code| {
             assert_eq!(code, 200, "{}", response);
-            allow_duplicates! {
-                assert_json_snapshot!(response["hits"][0],
-                { "._rankingScore" => "[score]" },
-                @r###"
-                {
-                  "id": 852,
-                  "_formatted": {
-                    "id": "852"
-                  }
-                }
-                "###)
-            }
+            assert_eq!(
+                response["hits"][0],
+                json!({
+                    "id": 852,
+                    "_formatted": {
+                        "id": "852",
+                    }
+                })
+            );
         })
         .await;
 
@@ -422,18 +353,15 @@ async fn displayedattr_2_smol() {
             json!({ "attributesToHighlight": ["id"], "attributesToCrop": ["id"] }),
             |response, code| {
                 assert_eq!(code, 200, "{}", response);
-                allow_duplicates! {
-                    assert_json_snapshot!(response["hits"][0],
-                    { "._rankingScore" => "[score]" },
-                    @r###"
-                    {
-                      "id": 852,
-                      "_formatted": {
-                        "id": "852"
-                      }
-                    }
-                    "###)
-                }
+                assert_eq!(
+                    response["hits"][0],
+                    json!({
+                        "id": 852,
+                        "_formatted": {
+                            "id": "852",
+                        }
+                    })
+                );
             },
         )
         .await;
@@ -441,41 +369,31 @@ async fn displayedattr_2_smol() {
     index
         .search(json!({ "attributesToHighlight": ["cattos"] }), |response, code| {
             assert_eq!(code, 200, "{}", response);
-            allow_duplicates! {
-                assert_json_snapshot!(response["hits"][0],
-                { "._rankingScore" => "[score]" },
-                @r###"
-                {
-                  "id": 852
-                }
-                "###)
-            }
+            assert_eq!(
+                response["hits"][0],
+                json!({
+                    "id": 852,
+                })
+            );
         })
         .await;
 
     index
         .search(json!({ "attributesToCrop": ["cattos"] }), |response, code| {
             assert_eq!(code, 200, "{}", response);
-            allow_duplicates! {
-                assert_json_snapshot!(response["hits"][0],
-                { "._rankingScore" => "[score]" },
-                @r###"
-                {
-                  "id": 852
-                }
-                "###)
-            }
+            assert_eq!(
+                response["hits"][0],
+                json!({
+                    "id": 852,
+                })
+            );
         })
         .await;
 
     index
         .search(json!({ "attributesToRetrieve": ["cattos"] }), |response, code| {
             assert_eq!(code, 200, "{}", response);
-            allow_duplicates! {
-                assert_json_snapshot!(response["hits"][0],
-                { "._rankingScore" => "[score]" },
-                @"{}")
-            }
+            assert_eq!(response["hits"][0], json!({}));
         })
         .await;
 
@@ -484,11 +402,7 @@ async fn displayedattr_2_smol() {
             json!({ "attributesToRetrieve": ["cattos"], "attributesToHighlight": ["cattos"], "attributesToCrop": ["cattos"] }),
             |response, code| {
     assert_eq!(code, 200, "{}", response);
-    allow_duplicates! {
-        assert_json_snapshot!(response["hits"][0],
-        { "._rankingScore" => "[score]" },
-        @"{}")
-    }
+    assert_eq!(response["hits"][0], json!({}));
 
             }
         )
@@ -499,17 +413,14 @@ async fn displayedattr_2_smol() {
             json!({ "attributesToRetrieve": ["cattos"], "attributesToHighlight": ["id"] }),
             |response, code| {
                 assert_eq!(code, 200, "{}", response);
-                allow_duplicates! {
-                    assert_json_snapshot!(response["hits"][0],
-                    { "._rankingScore" => "[score]" },
-                    @r###"
-                    {
-                      "_formatted": {
-                        "id": "852"
-                      }
-                    }
-                    "###)
-                }
+                assert_eq!(
+                    response["hits"][0],
+                    json!({
+                        "_formatted": {
+                            "id": "852",
+                        }
+                    })
+                );
             },
         )
         .await;
@@ -519,17 +430,14 @@ async fn displayedattr_2_smol() {
             json!({ "attributesToRetrieve": ["cattos"], "attributesToCrop": ["id"] }),
             |response, code| {
                 assert_eq!(code, 200, "{}", response);
-                allow_duplicates! {
-                    assert_json_snapshot!(response["hits"][0],
-                    { "._rankingScore" => "[score]" },
-                    @r###"
-                    {
-                      "_formatted": {
-                        "id": "852"
-                      }
-                    }
-                    "###)
-                }
+                assert_eq!(
+                    response["hits"][0],
+                    json!({
+                        "_formatted": {
+                            "id": "852",
+                        }
+                    })
+                );
             },
         )
         .await;

meilisearch/tests/search/mod.rs

@@ -2,11 +2,9 @@
 // should be tested in its own module to isolate tests and keep the tests readable.
 
 mod errors;
-mod facet_search;
 mod formatted;
 mod multi;
 mod pagination;
-mod restrict_searchable;
 
 use once_cell::sync::Lazy;
 use serde_json::{json, Value};

meilisearch/tests/search/multi.rs

@@ -65,7 +65,7 @@ async fn simple_search_single_index() {
         ]}))
         .await;
     snapshot!(code, @"200 OK");
-    insta::assert_json_snapshot!(response["results"], { "[].processingTimeMs" => "[time]", ".**._rankingScore" => "[score]" }, @r###"
+    insta::assert_json_snapshot!(response["results"], { "[].processingTimeMs" => "[time]" }, @r###"
     [
       {
         "indexUid": "test",
@@ -170,7 +170,7 @@ async fn simple_search_two_indexes() {
         ]}))
         .await;
     snapshot!(code, @"200 OK");
-    insta::assert_json_snapshot!(response["results"], { "[].processingTimeMs" => "[time]", ".**._rankingScore" => "[score]" }, @r###"
+    insta::assert_json_snapshot!(response["results"], { "[].processingTimeMs" => "[time]" }, @r###"
     [
       {
         "indexUid": "test",

meilisearch/tests/search/restrict_searchable.rs

@@ -1,267 +0,0 @@
-use meili_snap::{json_string, snapshot};
-use once_cell::sync::Lazy;
-use serde_json::{json, Value};
-
-use crate::common::index::Index;
-use crate::common::Server;
-
-async fn index_with_documents<'a>(server: &'a Server, documents: &Value) -> Index<'a> {
-    let index = server.index("test");
-
-    index.add_documents(documents.clone(), None).await;
-    index.wait_task(0).await;
-    index
-}
-
-static SIMPLE_SEARCH_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
-    json!([
-    {
-        "title": "Shazam!",
-        "desc": "a Captain Marvel ersatz",
-        "id": "1",
-    },
-    {
-        "title": "Captain Planet",
-        "desc": "He's not part of the Marvel Cinematic Universe",
-        "id": "2",
-    },
-    {
-        "title": "Captain Marvel",
-        "desc": "a Shazam ersatz",
-        "id": "3",
-    }])
-});
-
-#[actix_rt::test]
-async fn simple_search_on_title() {
-    let server = Server::new().await;
-    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
-
-    // simple search should return 2 documents (ids: 2 and 3).
-    index
-        .search(
-            json!({"q": "Captain Marvel", "attributesToSearchOn": ["title"]}),
-            |response, code| {
-                snapshot!(code, @"200 OK");
-                snapshot!(response["hits"].as_array().unwrap().len(), @"2");
-            },
-        )
-        .await;
-}
-
-#[actix_rt::test]
-async fn simple_prefix_search_on_title() {
-    let server = Server::new().await;
-    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
-
-    // simple search should return 2 documents (ids: 2 and 3).
-    index
-        .search(json!({"q": "Captain Mar", "attributesToSearchOn": ["title"]}), |response, code| {
-            snapshot!(code, @"200 OK");
-            snapshot!(response["hits"].as_array().unwrap().len(), @"2");
-        })
-        .await;
-}
-
-#[actix_rt::test]
-async fn simple_search_on_title_matching_strategy_all() {
-    let server = Server::new().await;
-    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
-    // simple search matching strategy all should only return 1 document (ids: 2).
-    index
-        .search(json!({"q": "Captain Marvel", "attributesToSearchOn": ["title"], "matchingStrategy": "all"}), |response, code| {
-            snapshot!(code, @"200 OK");
-            snapshot!(response["hits"].as_array().unwrap().len(), @"1");
-        })
-        .await;
-}
-
-#[actix_rt::test]
-async fn simple_search_on_no_field() {
-    let server = Server::new().await;
-    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
-    // simple search on no field shouldn't return any document.
-    index
-        .search(json!({"q": "Captain Marvel", "attributesToSearchOn": []}), |response, code| {
-            snapshot!(code, @"200 OK");
-            snapshot!(response["hits"].as_array().unwrap().len(), @"0");
-        })
-        .await;
-}
-
-#[actix_rt::test]
-async fn word_ranking_rule_order() {
-    let server = Server::new().await;
-    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
-
-    // Document 3 should appear before document 2.
-    index
-        .search(
-            json!({"q": "Captain Marvel", "attributesToSearchOn": ["title"], "attributesToRetrieve": ["id"]}),
-            |response, code| {
-                snapshot!(code, @"200 OK");
-                snapshot!(json_string!(response["hits"]),
-                    @r###"
-                [
-                  {
-                    "id": "3"
-                  },
-                  {
-                    "id": "2"
-                  }
-                ]
-                "###
-                );
-            },
-        )
-        .await;
-}
-
-#[actix_rt::test]
-async fn word_ranking_rule_order_exact_words() {
-    let server = Server::new().await;
-    let index = index_with_documents(&server, &SIMPLE_SEARCH_DOCUMENTS).await;
-    index.update_settings_typo_tolerance(json!({"disableOnWords": ["Captain", "Marvel"]})).await;
-    index.wait_task(1).await;
-
-    // simple search should return 2 documents (ids: 2 and 3).
-    index
-        .search(
-            json!({"q": "Captain Marvel", "attributesToSearchOn": ["title"], "attributesToRetrieve": ["id"]}),
-            |response, code| {
-                snapshot!(code, @"200 OK");
-                snapshot!(json_string!(response["hits"]),
-                    @r###"
-                [
-                  {
-                    "id": "3"
-                  },
-                  {
-                    "id": "2"
-                  }
-                ]
-                "###
-                );
-            },
-        )
-        .await;
-}
-
-#[actix_rt::test]
-async fn typo_ranking_rule_order() {
-    let server = Server::new().await;
-    let index = index_with_documents(
-        &server,
-        &json!([
-        {
-            "title": "Capitain Marivel",
-            "desc": "Captain Marvel",
-            "id": "1",
-        },
-        {
-            "title": "Captain Marivel",
-            "desc": "a Shazam ersatz",
-            "id": "2",
-        }]),
-    )
-    .await;
-
-    // Document 2 should appear before document 1.
-    index
-        .search(json!({"q": "Captain Marvel", "attributesToSearchOn": ["title"], "attributesToRetrieve": ["id"]}), |response, code| {
-            snapshot!(code, @"200 OK");
-            snapshot!(json_string!(response["hits"]),
-                @r###"
-            [
-              {
-                "id": "2"
-              },
-              {
-                "id": "1"
-              }
-            ]
-            "###
-            );
-        })
-        .await;
-}
-
-#[actix_rt::test]
-async fn attributes_ranking_rule_order() {
-    let server = Server::new().await;
-    let index = index_with_documents(
-        &server,
-        &json!([
-        {
-            "title": "Captain Marvel",
-            "desc": "a Shazam ersatz",
-            "footer": "The story of Captain Marvel",
-            "id": "1",
-        },
-        {
-            "title": "The Avengers",
-            "desc": "Captain Marvel is far from the earth",
-            "footer": "A super hero team",
-            "id": "2",
-        }]),
-    )
-    .await;
-
-    // Document 2 should appear before document 1.
-    index
-        .search(json!({"q": "Captain Marvel", "attributesToSearchOn": ["desc", "footer"], "attributesToRetrieve": ["id"]}), |response, code| {
-            snapshot!(code, @"200 OK");
-            snapshot!(json_string!(response["hits"]),
-                @r###"
-            [
-              {
-                "id": "2"
-              },
-              {
-                "id": "1"
-              }
-            ]
-            "###
-            );
-        })
-        .await;
-}
-
-#[actix_rt::test]
-async fn exactness_ranking_rule_order() {
-    let server = Server::new().await;
-    let index = index_with_documents(
-        &server,
-        &json!([
-        {
-            "title": "Captain Marvel",
-            "desc": "Captain Marivel",
-            "id": "1",
-        },
-        {
-            "title": "Captain Marvel",
-            "desc": "CaptainMarvel",
-            "id": "2",
-        }]),
-    )
-    .await;
-
-    // Document 2 should appear before document 1.
-    index
-        .search(json!({"q": "Captain Marvel", "attributesToRetrieve": ["id"], "attributesToSearchOn": ["desc"]}), |response, code| {
-            snapshot!(code, @"200 OK");
-            snapshot!(json_string!(response["hits"]),
-                @r###"
-            [
-              {
-                "id": "2"
-              },
-              {
-                "id": "1"
-              }
-            ]
-            "###
-            );
-        })
-        .await;
-}

meilisearch/tests/settings/get_settings.rs

@@ -21,9 +21,6 @@ static DEFAULT_SETTINGS_VALUES: Lazy<HashMap<&'static str, Value>> = Lazy::new(|
         "faceting",
         json!({
             "maxValuesPerFacet": json!(100),
-            "sortFacetValuesBy": {
-                "*": "alpha"
-            }
         }),
     );
     map.insert(
@@ -66,9 +63,6 @@ async fn get_settings() {
         settings["faceting"],
         json!({
             "maxValuesPerFacet": 100,
-            "sortFacetValuesBy": {
-                "*": "alpha"
-            }
         })
     );
     assert_eq!(

milli/Cargo.toml

@@ -17,7 +17,7 @@ bincode = "1.3.3"
 bstr = "1.4.0"
 bytemuck = { version = "1.13.1", features = ["extern_crate_alloc"] }
 byteorder = "1.4.3"
-charabia = { version = "0.8.1", default-features = false }
+charabia = { version = "0.7.2", default-features = false }
 concat-arrays = "0.1.2"
 crossbeam-channel = "0.5.8"
 deserr = "0.5.0"
@@ -34,7 +34,6 @@ heed = { git = "https://github.com/meilisearch/heed", tag = "v0.12.6", default-f
     "sync-read-txn",
 ] }
 hnsw = { version = "0.11.0", features = ["serde1"] }
-indexmap = { version = "1.9.3", features = ["serde"] }
 json-depth-checker = { path = "../json-depth-checker" }
 levenshtein_automata = { version = "0.2.1", features = ["fst_automaton"] }
 memmap2 = "0.5.10"
@@ -80,6 +79,9 @@ maplit = "1.0.2"
 md5 = "0.7.0"
 rand = { version = "0.8.5", features = ["small_rng"] }
 
+[target.'cfg(fuzzing)'.dev-dependencies]
+fuzzcheck = "0.12.1"
+
 [features]
 all-tokenizations = ["charabia/default"]
 

milli/examples/search.rs

@@ -54,7 +54,6 @@ fn main() -> Result<(), Box<dyn Error>> {
                 &(!query.trim().is_empty()).then(|| query.trim().to_owned()),
                 &None,
                 TermsMatchingStrategy::Last,
-                milli::score_details::ScoringStrategy::Skip,
                 false,
                 &None,
                 &None,

milli/src/distance.rs

@@ -7,19 +7,28 @@ pub struct DotProduct;
 impl Metric<Vec<f32>> for DotProduct {
     type Unit = u32;
 
-    // Following <https://docs.rs/space/0.17.0/space/trait.Metric.html>.
+    // TODO explain me this function, I don't understand why f32.to_bits is ordered.
+    // I tried to do this and it wasn't OK <https://stackoverflow.com/a/43305015/1941280>
     //
-    // Here is a playground that validate the ordering of the bit representation of floats in range 0.0..=1.0:
-    // <https://play.rust-lang.org/?version=stable&mode=debug&edition=2021&gist=6c59e31a3cc5036b32edf51e8937b56e>
+    // Following <https://docs.rs/space/0.17.0/space/trait.Metric.html>.
     fn distance(&self, a: &Vec<f32>, b: &Vec<f32>) -> Self::Unit {
-        let dist = 1.0 - dot_product_similarity(a, b);
+        let dist: f32 = a.iter().zip(b).map(|(a, b)| a * b).sum();
+        let dist = 1.0 - dist;
         debug_assert!(!dist.is_nan());
         dist.to_bits()
     }
 }
 
-/// Returns the dot product similarity score that will between 0.0 and 1.0
-/// if both vectors are normalized. The higher the more similar the vectors are.
-pub fn dot_product_similarity(a: &[f32], b: &[f32]) -> f32 {
-    a.iter().zip(b).map(|(a, b)| a * b).sum()
+#[derive(Debug, Default, Clone, Copy, Serialize, Deserialize)]
+pub struct Euclidean;
+
+impl Metric<Vec<f32>> for Euclidean {
+    type Unit = u32;
+
+    fn distance(&self, a: &Vec<f32>, b: &Vec<f32>) -> Self::Unit {
+        let squared: f32 = a.iter().zip(b).map(|(a, b)| (a - b).powi(2)).sum();
+        let dist = squared.sqrt();
+        debug_assert!(!dist.is_nan());
+        dist.to_bits()
+    }
 }

milli/src/documents/mod.rs

@@ -111,6 +111,7 @@ pub enum Error {
     Io(#[from] io::Error),
 }
 
+#[cfg(test)]
 pub fn objects_from_json_value(json: serde_json::Value) -> Vec<crate::Object> {
     let documents = match json {
         object @ serde_json::Value::Object(_) => vec![object],
@@ -140,6 +141,7 @@ macro_rules! documents {
     }};
 }
 
+#[cfg(test)]
 pub fn documents_batch_reader_from_objects(
     objects: impl IntoIterator<Item = Object>,
 ) -> DocumentsBatchReader<std::io::Cursor<Vec<u8>>> {

milli/src/error.rs

@@ -112,8 +112,6 @@ only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and undersco
     InvalidGeoField(#[from] GeoError),
     #[error("Invalid vector dimensions: expected: `{}`, found: `{}`.", .expected, .found)]
     InvalidVectorDimensions { expected: usize, found: usize },
-    #[error("The `_vectors` field in the document with the id: `{document_id}` is not an array. Was expecting an array of floats or an array of arrays of floats but instead got `{value}`.")]
-    InvalidVectorsType { document_id: Value, value: Value },
     #[error("{0}")]
     InvalidFilter(String),
     #[error("Invalid type for filter subexpression: expected: {}, found: {1}.", .0.join(", "))]
@@ -128,26 +126,6 @@ only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and undersco
         }
     )]
     InvalidSortableAttribute { field: String, valid_fields: BTreeSet<String> },
-    #[error("Attribute `{}` is not facet-searchable. {}",
-        .field,
-        match .valid_fields.is_empty() {
-            true => "This index does not have configured facet-searchable attributes. To make it facet-searchable add it to the `filterableAttributes` index settings.".to_string(),
-            false => format!("Available facet-searchable attributes are: `{}`. To make it facet-searchable add it to the `filterableAttributes` index settings.",
-                    valid_fields.iter().map(AsRef::as_ref).collect::<Vec<&str>>().join(", ")
-                ),
-        }
-    )]
-    InvalidFacetSearchFacetName { field: String, valid_fields: BTreeSet<String> },
-    #[error("Attribute `{}` is not searchable. Available searchable attributes are: `{}{}`.",
-        .field,
-        .valid_fields.iter().map(AsRef::as_ref).collect::<Vec<&str>>().join(", "),
-        .hidden_fields.then_some(", <..hidden-attributes>").unwrap_or(""),
-    )]
-    InvalidSearchableAttribute {
-        field: String,
-        valid_fields: BTreeSet<String>,
-        hidden_fields: bool,
-    },
     #[error("{}", HeedError::BadOpenOptions)]
     InvalidLmdbOpenOptions,
     #[error("You must specify where `sort` is listed in the rankingRules setting to use the sort parameter at search time.")]

milli/src/external_documents_ids.rs

@@ -106,30 +106,22 @@ impl<'a> ExternalDocumentsIds<'a> {
         map
     }
 
-    /// Return an fst of the combined hard and soft deleted ID.
-    pub fn to_fst<'b>(&'b self) -> fst::Result<Cow<'b, fst::Map<Cow<'a, [u8]>>>> {
-        if self.soft.is_empty() {
-            return Ok(Cow::Borrowed(&self.hard));
-        }
-        let union_op = self.hard.op().add(&self.soft).r#union();
-
-        let mut iter = union_op.into_stream();
-        let mut new_hard_builder = fst::MapBuilder::memory();
-        while let Some((external_id, marked_docids)) = iter.next() {
-            let value = indexed_last_value(marked_docids).unwrap();
-            if value != DELETED_ID {
-                new_hard_builder.insert(external_id, value)?;
-            }
-        }
-
-        drop(iter);
-
-        Ok(Cow::Owned(new_hard_builder.into_map().map_data(Cow::Owned)?))
-    }
-
     fn merge_soft_into_hard(&mut self) -> fst::Result<()> {
         if self.soft.len() >= self.hard.len() / 2 {
-            self.hard = self.to_fst()?.into_owned();
+            let union_op = self.hard.op().add(&self.soft).r#union();
+
+            let mut iter = union_op.into_stream();
+            let mut new_hard_builder = fst::MapBuilder::memory();
+            while let Some((external_id, marked_docids)) = iter.next() {
+                let value = indexed_last_value(marked_docids).unwrap();
+                if value != DELETED_ID {
+                    new_hard_builder.insert(external_id, value)?;
+                }
+            }
+
+            drop(iter);
+
+            self.hard = new_hard_builder.into_map().map_data(Cow::Owned)?;
             self.soft = fst::Map::default().map_data(Cow::Owned)?;
         }
 

milli/src/heed_codec/fst_set_codec.rs

@@ -1,23 +0,0 @@
-use std::borrow::Cow;
-
-use fst::Set;
-use heed::{BytesDecode, BytesEncode};
-
-/// A codec for values of type `Set<&[u8]>`.
-pub struct FstSetCodec;
-
-impl<'a> BytesEncode<'a> for FstSetCodec {
-    type EItem = Set<Vec<u8>>;
-
-    fn bytes_encode(item: &'a Self::EItem) -> Option<Cow<'a, [u8]>> {
-        Some(Cow::Borrowed(item.as_fst().as_bytes()))
-    }
-}
-
-impl<'a> BytesDecode<'a> for FstSetCodec {
-    type DItem = Set<&'a [u8]>;
-
-    fn bytes_decode(bytes: &'a [u8]) -> Option<Self::DItem> {
-        Set::new(bytes).ok()
-    }
-}

milli/src/heed_codec/mod.rs

@@ -2,7 +2,6 @@ mod beu32_str_codec;
 mod byte_slice_ref;
 pub mod facet;
 mod field_id_word_count_codec;
-mod fst_set_codec;
 mod obkv_codec;
 mod roaring_bitmap;
 mod roaring_bitmap_length;
@@ -16,7 +15,6 @@ pub use str_ref::StrRefCodec;
 
 pub use self::beu32_str_codec::BEU32StrCodec;
 pub use self::field_id_word_count_codec::FieldIdWordCountCodec;
-pub use self::fst_set_codec::FstSetCodec;
 pub use self::obkv_codec::ObkvCodec;
 pub use self::roaring_bitmap::{BoRoaringBitmapCodec, CboRoaringBitmapCodec, RoaringBitmapCodec};
 pub use self::roaring_bitmap_length::{
@@ -25,9 +23,3 @@ pub use self::roaring_bitmap_length::{
 pub use self::script_language_codec::ScriptLanguageCodec;
 pub use self::str_beu32_codec::{StrBEU16Codec, StrBEU32Codec};
 pub use self::str_str_u8_codec::{U8StrStrCodec, UncheckedU8StrStrCodec};
-
-pub trait BytesDecodeOwned {
-    type DItem;
-
-    fn bytes_decode_owned(bytes: &[u8]) -> Option<Self::DItem>;
-}

milli/src/heed_codec/roaring_bitmap/bo_roaring_bitmap_codec.rs

@@ -2,11 +2,8 @@ use std::borrow::Cow;
 use std::convert::TryInto;
 use std::mem::size_of;
 
-use heed::BytesDecode;
 use roaring::RoaringBitmap;
 
-use crate::heed_codec::BytesDecodeOwned;
-
 pub struct BoRoaringBitmapCodec;
 
 impl BoRoaringBitmapCodec {
@@ -16,7 +13,7 @@ impl BoRoaringBitmapCodec {
     }
 }
 
-impl BytesDecode<'_> for BoRoaringBitmapCodec {
+impl heed::BytesDecode<'_> for BoRoaringBitmapCodec {
     type DItem = RoaringBitmap;
 
     fn bytes_decode(bytes: &[u8]) -> Option<Self::DItem> {
@@ -31,14 +28,6 @@ impl BytesDecode<'_> for BoRoaringBitmapCodec {
     }
 }
 
-impl BytesDecodeOwned for BoRoaringBitmapCodec {
-    type DItem = RoaringBitmap;
-
-    fn bytes_decode_owned(bytes: &[u8]) -> Option<Self::DItem> {
-        Self::bytes_decode(bytes)
-    }
-}
-
 impl heed::BytesEncode<'_> for BoRoaringBitmapCodec {
     type EItem = RoaringBitmap;
 

milli/src/heed_codec/roaring_bitmap/cbo_roaring_bitmap_codec.rs

@@ -5,8 +5,6 @@ use std::mem::size_of;
 use byteorder::{NativeEndian, ReadBytesExt, WriteBytesExt};
 use roaring::RoaringBitmap;
 
-use crate::heed_codec::BytesDecodeOwned;
-
 /// This is the limit where using a byteorder became less size efficient
 /// than using a direct roaring encoding, it is also the point where we are able
 /// to determine the encoding used only by using the array of bytes length.
@@ -105,14 +103,6 @@ impl heed::BytesDecode<'_> for CboRoaringBitmapCodec {
     }
 }
 
-impl BytesDecodeOwned for CboRoaringBitmapCodec {
-    type DItem = RoaringBitmap;
-
-    fn bytes_decode_owned(bytes: &[u8]) -> Option<Self::DItem> {
-        Self::deserialize_from(bytes).ok()
-    }
-}
-
 impl heed::BytesEncode<'_> for CboRoaringBitmapCodec {
     type EItem = RoaringBitmap;
 

milli/src/heed_codec/roaring_bitmap/roaring_bitmap_codec.rs

@@ -2,8 +2,6 @@ use std::borrow::Cow;
 
 use roaring::RoaringBitmap;
 
-use crate::heed_codec::BytesDecodeOwned;
-
 pub struct RoaringBitmapCodec;
 
 impl heed::BytesDecode<'_> for RoaringBitmapCodec {
@@ -14,14 +12,6 @@ impl heed::BytesDecode<'_> for RoaringBitmapCodec {
     }
 }
 
-impl BytesDecodeOwned for RoaringBitmapCodec {
-    type DItem = RoaringBitmap;
-
-    fn bytes_decode_owned(bytes: &[u8]) -> Option<Self::DItem> {
-        RoaringBitmap::deserialize_from(bytes).ok()
-    }
-}
-
 impl heed::BytesEncode<'_> for RoaringBitmapCodec {
     type EItem = RoaringBitmap;
 

milli/src/heed_codec/roaring_bitmap_length/bo_roaring_bitmap_len_codec.rs

@@ -1,23 +1,11 @@
 use std::mem;
 
-use heed::BytesDecode;
-
-use crate::heed_codec::BytesDecodeOwned;
-
 pub struct BoRoaringBitmapLenCodec;
 
-impl BytesDecode<'_> for BoRoaringBitmapLenCodec {
+impl heed::BytesDecode<'_> for BoRoaringBitmapLenCodec {
     type DItem = u64;
 
     fn bytes_decode(bytes: &[u8]) -> Option<Self::DItem> {
         Some((bytes.len() / mem::size_of::<u32>()) as u64)
     }
 }
-
-impl BytesDecodeOwned for BoRoaringBitmapLenCodec {
-    type DItem = u64;
-
-    fn bytes_decode_owned(bytes: &[u8]) -> Option<Self::DItem> {
-        Self::bytes_decode(bytes)
-    }
-}

milli/src/heed_codec/roaring_bitmap_length/cbo_roaring_bitmap_len_codec.rs

@@ -1,14 +1,11 @@
 use std::mem;
 
-use heed::BytesDecode;
-
 use super::{BoRoaringBitmapLenCodec, RoaringBitmapLenCodec};
 use crate::heed_codec::roaring_bitmap::cbo_roaring_bitmap_codec::THRESHOLD;
-use crate::heed_codec::BytesDecodeOwned;
 
 pub struct CboRoaringBitmapLenCodec;
 
-impl BytesDecode<'_> for CboRoaringBitmapLenCodec {
+impl heed::BytesDecode<'_> for CboRoaringBitmapLenCodec {
     type DItem = u64;
 
     fn bytes_decode(bytes: &[u8]) -> Option<Self::DItem> {
@@ -23,11 +20,3 @@ impl BytesDecode<'_> for CboRoaringBitmapLenCodec {
         }
     }
 }
-
-impl BytesDecodeOwned for CboRoaringBitmapLenCodec {
-    type DItem = u64;
-
-    fn bytes_decode_owned(bytes: &[u8]) -> Option<Self::DItem> {
-        Self::bytes_decode(bytes)
-    }
-}

milli/src/heed_codec/roaring_bitmap_length/roaring_bitmap_len_codec.rs

@@ -3,8 +3,6 @@ use std::mem;
 
 use byteorder::{LittleEndian, ReadBytesExt};
 
-use crate::heed_codec::BytesDecodeOwned;
-
 const SERIAL_COOKIE_NO_RUNCONTAINER: u32 = 12346;
 const SERIAL_COOKIE: u16 = 12347;
 
@@ -61,14 +59,6 @@ impl heed::BytesDecode<'_> for RoaringBitmapLenCodec {
     }
 }
 
-impl BytesDecodeOwned for RoaringBitmapLenCodec {
-    type DItem = u64;
-
-    fn bytes_decode_owned(bytes: &[u8]) -> Option<Self::DItem> {
-        RoaringBitmapLenCodec::deserialize_from_slice(bytes).ok()
-    }
-}
-
 #[cfg(test)]
 mod tests {
     use heed::BytesEncode;

milli/src/index.rs

@@ -21,13 +21,11 @@ use crate::heed_codec::facet::{
     FacetGroupKeyCodec, FacetGroupValueCodec, FieldDocIdFacetF64Codec, FieldDocIdFacetStringCodec,
     FieldIdCodec, OrderedF64Codec,
 };
-use crate::heed_codec::{FstSetCodec, ScriptLanguageCodec, StrBEU16Codec, StrRefCodec};
-use crate::readable_slices::ReadableSlices;
+use crate::heed_codec::{ScriptLanguageCodec, StrBEU16Codec, StrRefCodec};
 use crate::{
     default_criteria, CboRoaringBitmapCodec, Criterion, DocumentId, ExternalDocumentsIds,
     FacetDistribution, FieldDistribution, FieldId, FieldIdWordCountCodec, GeoPoint, ObkvCodec,
-    OrderBy, Result, RoaringBitmapCodec, RoaringBitmapLenCodec, Search, U8StrStrCodec, BEU16,
-    BEU32,
+    Result, RoaringBitmapCodec, RoaringBitmapLenCodec, Search, U8StrStrCodec, BEU16, BEU32,
 };
 
 /// The HNSW data-structure that we serialize, fill and search in.
@@ -49,10 +47,7 @@ pub mod main_key {
     pub const FIELDS_IDS_MAP_KEY: &str = "fields-ids-map";
     pub const GEO_FACETED_DOCUMENTS_IDS_KEY: &str = "geo-faceted-documents-ids";
     pub const GEO_RTREE_KEY: &str = "geo-rtree";
-    /// The prefix of the key that is used to store the, potential big, HNSW structure.
-    /// It is concatenated with a big-endian encoded number (non-human readable).
-    /// e.g. vector-hnsw0x0032.
-    pub const VECTOR_HNSW_KEY_PREFIX: &str = "vector-hnsw";
+    pub const VECTOR_HNSW_KEY: &str = "vector-hnsw";
     pub const HARD_EXTERNAL_DOCUMENTS_IDS_KEY: &str = "hard-external-documents-ids";
     pub const NUMBER_FACETED_DOCUMENTS_IDS_PREFIX: &str = "number-faceted-documents-ids";
     pub const PRIMARY_KEY_KEY: &str = "primary-key";
@@ -72,7 +67,6 @@ pub mod main_key {
     pub const EXACT_WORDS: &str = "exact-words";
     pub const EXACT_ATTRIBUTES: &str = "exact-attributes";
     pub const MAX_VALUES_PER_FACET: &str = "max-values-per-facet";
-    pub const SORT_FACET_VALUES_BY: &str = "sort-facet-values-by";
     pub const PAGINATION_MAX_TOTAL_HITS: &str = "pagination-max-total-hits";
 }
 
@@ -96,7 +90,6 @@ pub mod db_name {
     pub const FACET_ID_IS_NULL_DOCIDS: &str = "facet-id-is-null-docids";
     pub const FACET_ID_IS_EMPTY_DOCIDS: &str = "facet-id-is-empty-docids";
     pub const FACET_ID_STRING_DOCIDS: &str = "facet-id-string-docids";
-    pub const FACET_ID_STRING_FST: &str = "facet-id-string-fst";
     pub const FIELD_ID_DOCID_FACET_F64S: &str = "field-id-docid-facet-f64s";
     pub const FIELD_ID_DOCID_FACET_STRINGS: &str = "field-id-docid-facet-strings";
     pub const VECTOR_ID_DOCID: &str = "vector-id-docids";
@@ -157,8 +150,6 @@ pub struct Index {
     pub facet_id_f64_docids: Database<FacetGroupKeyCodec<OrderedF64Codec>, FacetGroupValueCodec>,
     /// Maps the facet field id and ranges of strings with the docids that corresponds to them.
     pub facet_id_string_docids: Database<FacetGroupKeyCodec<StrRefCodec>, FacetGroupValueCodec>,
-    /// Maps the facet field id of the string facets with an FST containing all the facets values.
-    pub facet_id_string_fst: Database<OwnedType<BEU16>, FstSetCodec>,
 
     /// Maps the document id, the facet field id and the numbers.
     pub field_id_docid_facet_f64s: Database<FieldDocIdFacetF64Codec, Unit>,
@@ -211,7 +202,6 @@ impl Index {
         let facet_id_f64_docids = env.create_database(&mut wtxn, Some(FACET_ID_F64_DOCIDS))?;
         let facet_id_string_docids =
             env.create_database(&mut wtxn, Some(FACET_ID_STRING_DOCIDS))?;
-        let facet_id_string_fst = env.create_database(&mut wtxn, Some(FACET_ID_STRING_FST))?;
         let facet_id_exists_docids =
             env.create_database(&mut wtxn, Some(FACET_ID_EXISTS_DOCIDS))?;
         let facet_id_is_null_docids =
@@ -246,7 +236,6 @@ impl Index {
             field_id_word_count_docids,
             facet_id_f64_docids,
             facet_id_string_docids,
-            facet_id_string_fst,
             facet_id_exists_docids,
             facet_id_is_null_docids,
             facet_id_is_empty_docids,
@@ -528,49 +517,19 @@ impl Index {
 
     /// Writes the provided `hnsw`.
     pub(crate) fn put_vector_hnsw(&self, wtxn: &mut RwTxn, hnsw: &Hnsw) -> heed::Result<()> {
-        // We must delete all the chunks before we write the new HNSW chunks.
-        self.delete_vector_hnsw(wtxn)?;
-
-        let chunk_size = 1024 * 1024 * (1024 + 512); // 1.5 GiB
-        let bytes = bincode::serialize(hnsw).map_err(|_| heed::Error::Encoding)?;
-        for (i, chunk) in bytes.chunks(chunk_size).enumerate() {
-            let i = i as u32;
-            let mut key = main_key::VECTOR_HNSW_KEY_PREFIX.as_bytes().to_vec();
-            key.extend_from_slice(&i.to_be_bytes());
-            self.main.put::<_, ByteSlice, ByteSlice>(wtxn, &key, chunk)?;
-        }
-        Ok(())
+        self.main.put::<_, Str, SerdeBincode<Hnsw>>(wtxn, main_key::VECTOR_HNSW_KEY, hnsw)
     }
 
     /// Delete the `hnsw`.
     pub(crate) fn delete_vector_hnsw(&self, wtxn: &mut RwTxn) -> heed::Result<bool> {
-        let mut iter = self.main.prefix_iter_mut::<_, ByteSlice, DecodeIgnore>(
-            wtxn,
-            main_key::VECTOR_HNSW_KEY_PREFIX.as_bytes(),
-        )?;
-        let mut deleted = false;
-        while iter.next().transpose()?.is_some() {
-            // We do not keep a reference to the key or the value.
-            unsafe { deleted |= iter.del_current()? };
-        }
-        Ok(deleted)
+        self.main.delete::<_, Str>(wtxn, main_key::VECTOR_HNSW_KEY)
     }
 
     /// Returns the `hnsw`.
     pub fn vector_hnsw(&self, rtxn: &RoTxn) -> Result<Option<Hnsw>> {
-        let mut slices = Vec::new();
-        for result in
-            self.main.prefix_iter::<_, Str, ByteSlice>(rtxn, main_key::VECTOR_HNSW_KEY_PREFIX)?
-        {
-            let (_, slice) = result?;
-            slices.push(slice);
-        }
-
-        if slices.is_empty() {
-            Ok(None)
-        } else {
-            let readable_slices: ReadableSlices<_> = slices.into_iter().collect();
-            Ok(Some(bincode::deserialize_from(readable_slices).map_err(|_| heed::Error::Decoding)?))
+        match self.main.get::<_, Str, SerdeBincode<Hnsw>>(rtxn, main_key::VECTOR_HNSW_KEY)? {
+            Some(hnsw) => Ok(Some(hnsw)),
+            None => Ok(None),
         }
     }
 
@@ -1300,31 +1259,6 @@ impl Index {
         self.main.delete::<_, Str>(txn, main_key::MAX_VALUES_PER_FACET)
     }
 
-    pub fn sort_facet_values_by(&self, txn: &RoTxn) -> heed::Result<HashMap<String, OrderBy>> {
-        let mut orders = self
-            .main
-            .get::<_, Str, SerdeJson<HashMap<String, OrderBy>>>(
-                txn,
-                main_key::SORT_FACET_VALUES_BY,
-            )?
-            .unwrap_or_default();
-        // Insert the default ordering if it is not already overwritten by the user.
-        orders.entry("*".to_string()).or_insert(OrderBy::Lexicographic);
-        Ok(orders)
-    }
-
-    pub(crate) fn put_sort_facet_values_by(
-        &self,
-        txn: &mut RwTxn,
-        val: &HashMap<String, OrderBy>,
-    ) -> heed::Result<()> {
-        self.main.put::<_, Str, SerdeJson<_>>(txn, main_key::SORT_FACET_VALUES_BY, &val)
-    }
-
-    pub(crate) fn delete_sort_facet_values_by(&self, txn: &mut RwTxn) -> heed::Result<bool> {
-        self.main.delete::<_, Str>(txn, main_key::SORT_FACET_VALUES_BY)
-    }
-
     pub fn pagination_max_total_hits(&self, txn: &RoTxn) -> heed::Result<Option<usize>> {
         self.main.get::<_, Str, OwnedType<usize>>(txn, main_key::PAGINATION_MAX_TOTAL_HITS)
     }
@@ -2585,12 +2519,8 @@ pub(crate) mod tests {
 
         let rtxn = index.read_txn().unwrap();
         let search = Search::new(&rtxn, &index);
-        let SearchResult {
-            matching_words: _,
-            candidates: _,
-            document_scores: _,
-            mut documents_ids,
-        } = search.execute().unwrap();
+        let SearchResult { matching_words: _, candidates: _, mut documents_ids } =
+            search.execute().unwrap();
         let primary_key_id = index.fields_ids_map(&rtxn).unwrap().id("primary_key").unwrap();
         documents_ids.sort_unstable();
         let docs = index.documents(&rtxn, documents_ids).unwrap();

milli/src/lib.rs

@@ -18,8 +18,6 @@ mod fields_ids_map;
 pub mod heed_codec;
 pub mod index;
 pub mod proximity;
-mod readable_slices;
-pub mod score_details;
 mod search;
 pub mod update;
 
@@ -32,7 +30,6 @@ use std::convert::{TryFrom, TryInto};
 use std::hash::BuildHasherDefault;
 
 use charabia::normalizer::{CharNormalizer, CompatibilityDecompositionNormalizer};
-pub use distance::dot_product_similarity;
 pub use filter_parser::{Condition, FilterCondition, Span, Token};
 use fxhash::{FxHasher32, FxHasher64};
 pub use grenad::CompressionType;
@@ -57,9 +54,8 @@ pub use self::heed_codec::{
 };
 pub use self::index::Index;
 pub use self::search::{
-    FacetDistribution, FacetValueHit, Filter, FormatOptions, MatchBounds, MatcherBuilder,
-    MatchingWords, OrderBy, Search, SearchForFacetValues, SearchResult, TermsMatchingStrategy,
-    DEFAULT_VALUES_PER_FACET,
+    FacetDistribution, Filter, FormatOptions, MatchBounds, MatcherBuilder, MatchingWords, Search,
+    SearchResult, TermsMatchingStrategy, DEFAULT_VALUES_PER_FACET,
 };
 
 pub type Result<T> = std::result::Result<T, error::Error>;
@@ -288,35 +284,6 @@ pub fn normalize_facet(original: &str) -> String {
     CompatibilityDecompositionNormalizer.normalize_str(original.trim()).to_lowercase()
 }
 
-/// Represents either a vector or an array of multiple vectors.
-#[derive(serde::Serialize, serde::Deserialize, Debug)]
-#[serde(transparent)]
-pub struct VectorOrArrayOfVectors {
-    #[serde(with = "either::serde_untagged")]
-    inner: either::Either<Vec<f32>, Vec<Vec<f32>>>,
-}
-
-impl VectorOrArrayOfVectors {
-    pub fn into_array_of_vectors(self) -> Vec<Vec<f32>> {
-        match self.inner {
-            either::Either::Left(vector) => vec![vector],
-            either::Either::Right(vectors) => vectors,
-        }
-    }
-}
-
-/// Normalize a vector by dividing the dimensions by the length of it.
-pub fn normalize_vector(mut vector: Vec<f32>) -> Vec<f32> {
-    let squared: f32 = vector.iter().map(|x| x * x).sum();
-    let length = squared.sqrt();
-    if length <= f32::EPSILON {
-        vector
-    } else {
-        vector.iter_mut().for_each(|x| *x /= length);
-        vector
-    }
-}
-
 #[cfg(test)]
 mod tests {
     use serde_json::json;

milli/src/readable_slices.rs

@@ -1,85 +0,0 @@
-use std::io::{self, Read};
-use std::iter::FromIterator;
-
-pub struct ReadableSlices<A> {
-    inner: Vec<A>,
-    pos: u64,
-}
-
-impl<A> FromIterator<A> for ReadableSlices<A> {
-    fn from_iter<T: IntoIterator<Item = A>>(iter: T) -> Self {
-        ReadableSlices { inner: iter.into_iter().collect(), pos: 0 }
-    }
-}
-
-impl<A: AsRef<[u8]>> Read for ReadableSlices<A> {
-    fn read(&mut self, mut buf: &mut [u8]) -> io::Result<usize> {
-        let original_buf_len = buf.len();
-
-        // We explore the list of slices to find the one where we must start reading.
-        let mut pos = self.pos;
-        let index = match self
-            .inner
-            .iter()
-            .map(|s| s.as_ref().len() as u64)
-            .position(|size| pos.checked_sub(size).map(|p| pos = p).is_none())
-        {
-            Some(index) => index,
-            None => return Ok(0),
-        };
-
-        let mut inner_pos = pos as usize;
-        for slice in &self.inner[index..] {
-            let slice = &slice.as_ref()[inner_pos..];
-
-            if buf.len() > slice.len() {
-                // We must exhaust the current slice and go to the next one there is not enough here.
-                buf[..slice.len()].copy_from_slice(slice);
-                buf = &mut buf[slice.len()..];
-                inner_pos = 0;
-            } else {
-                // There is enough in this slice to fill the remaining bytes of the buffer.
-                // Let's break just after filling it.
-                buf.copy_from_slice(&slice[..buf.len()]);
-                buf = &mut [];
-                break;
-            }
-        }
-
-        let written = original_buf_len - buf.len();
-        self.pos += written as u64;
-        Ok(written)
-    }
-}
-
-#[cfg(test)]
-mod test {
-    use std::io::Read;
-
-    use super::ReadableSlices;
-
-    #[test]
-    fn basic() {
-        let data: Vec<_> = (0..100).collect();
-        let splits: Vec<_> = data.chunks(3).collect();
-        let mut rdslices: ReadableSlices<_> = splits.into_iter().collect();
-
-        let mut output = Vec::new();
-        let length = rdslices.read_to_end(&mut output).unwrap();
-        assert_eq!(length, data.len());
-        assert_eq!(output, data);
-    }
-
-    #[test]
-    fn small_reads() {
-        let data: Vec<_> = (0..u8::MAX).collect();
-        let splits: Vec<_> = data.chunks(27).collect();
-        let mut rdslices: ReadableSlices<_> = splits.into_iter().collect();
-
-        let buffer = &mut [0; 45];
-        let length = rdslices.read(buffer).unwrap();
-        let expected: Vec<_> = (0..buffer.len() as u8).collect();
-        assert_eq!(length, buffer.len());
-        assert_eq!(buffer, &expected[..]);
-    }
-}

milli/src/score_details.rs

@@ -1,313 +0,0 @@
-use serde::Serialize;
-
-use crate::distance_between_two_points;
-
-#[derive(Debug, Clone, PartialEq)]
-pub enum ScoreDetails {
-    Words(Words),
-    Typo(Typo),
-    Proximity(Rank),
-    Fid(Rank),
-    Position(Rank),
-    ExactAttribute(ExactAttribute),
-    Exactness(Rank),
-    Sort(Sort),
-    GeoSort(GeoSort),
-}
-
-impl ScoreDetails {
-    pub fn local_score(&self) -> Option<f64> {
-        self.rank().map(Rank::local_score)
-    }
-
-    pub fn rank(&self) -> Option<Rank> {
-        match self {
-            ScoreDetails::Words(details) => Some(details.rank()),
-            ScoreDetails::Typo(details) => Some(details.rank()),
-            ScoreDetails::Proximity(details) => Some(*details),
-            ScoreDetails::Fid(details) => Some(*details),
-            ScoreDetails::Position(details) => Some(*details),
-            ScoreDetails::ExactAttribute(details) => Some(details.rank()),
-            ScoreDetails::Exactness(details) => Some(*details),
-            ScoreDetails::Sort(_) => None,
-            ScoreDetails::GeoSort(_) => None,
-        }
-    }
-
-    pub fn global_score<'a>(details: impl Iterator<Item = &'a Self>) -> f64 {
-        Rank::global_score(details.filter_map(Self::rank))
-    }
-
-    /// Panics
-    ///
-    /// - If Position is not preceded by Fid
-    /// - If Exactness is not preceded by ExactAttribute
-    pub fn to_json_map<'a>(
-        details: impl Iterator<Item = &'a Self>,
-    ) -> serde_json::Map<String, serde_json::Value> {
-        let mut order = 0;
-        let mut fid_details = None;
-        let mut details_map = serde_json::Map::default();
-        for details in details {
-            match details {
-                ScoreDetails::Words(words) => {
-                    let words_details = serde_json::json!({
-                            "order": order,
-                            "matchingWords": words.matching_words,
-                            "maxMatchingWords": words.max_matching_words,
-                            "score": words.rank().local_score(),
-                    });
-                    details_map.insert("words".into(), words_details);
-                    order += 1;
-                }
-                ScoreDetails::Typo(typo) => {
-                    let typo_details = serde_json::json!({
-                        "order": order,
-                        "typoCount": typo.typo_count,
-                        "maxTypoCount": typo.max_typo_count,
-                        "score": typo.rank().local_score(),
-                    });
-                    details_map.insert("typo".into(), typo_details);
-                    order += 1;
-                }
-                ScoreDetails::Proximity(proximity) => {
-                    let proximity_details = serde_json::json!({
-                        "order": order,
-                        "score": proximity.local_score(),
-                    });
-                    details_map.insert("proximity".into(), proximity_details);
-                    order += 1;
-                }
-                ScoreDetails::Fid(fid) => {
-                    // copy the rank for future use in Position.
-                    fid_details = Some(*fid);
-                    // For now, fid is a virtual rule always followed by the "position" rule
-                    let fid_details = serde_json::json!({
-                        "order": order,
-                        "attribute_ranking_order_score": fid.local_score(),
-                    });
-                    details_map.insert("attribute".into(), fid_details);
-                    order += 1;
-                }
-                ScoreDetails::Position(position) => {
-                    // For now, position is a virtual rule always preceded by the "fid" rule
-                    let attribute_details = details_map
-                        .get_mut("attribute")
-                        .expect("position not preceded by attribute");
-                    let attribute_details = attribute_details
-                        .as_object_mut()
-                        .expect("attribute details was not an object");
-                    let Some(fid_details) = fid_details else {
-                        unimplemented!("position not preceded by attribute");
-                    };
-
-                    attribute_details
-                        .insert("query_word_distance_score".into(), position.local_score().into());
-                    let score = Rank::global_score([fid_details, *position].iter().copied());
-                    attribute_details.insert("score".into(), score.into());
-
-                    // do not update the order since this was already done by fid
-                }
-                ScoreDetails::ExactAttribute(exact_attribute) => {
-                    let exactness_details = serde_json::json!({
-                        "order": order,
-                        "matchType": exact_attribute,
-                        "score": exact_attribute.rank().local_score(),
-                    });
-                    details_map.insert("exactness".into(), exactness_details);
-                    order += 1;
-                }
-                ScoreDetails::Exactness(details) => {
-                    // For now, exactness is a virtual rule always preceded by the "ExactAttribute" rule
-                    let exactness_details = details_map
-                        .get_mut("exactness")
-                        .expect("Exactness not preceded by exactAttribute");
-                    let exactness_details = exactness_details
-                        .as_object_mut()
-                        .expect("exactness details was not an object");
-                    if exactness_details.get("matchType").expect("missing 'matchType'")
-                        == &serde_json::json!(ExactAttribute::NoExactMatch)
-                    {
-                        let score = Rank::global_score(
-                            [ExactAttribute::NoExactMatch.rank(), *details].iter().copied(),
-                        );
-                        *exactness_details.get_mut("score").expect("missing score") = score.into();
-                    }
-                    // do not update the order since this was already done by exactAttribute
-                }
-                ScoreDetails::Sort(details) => {
-                    let sort = if details.redacted {
-                        format!("<hidden-rule-{order}>")
-                    } else {
-                        format!(
-                            "{}:{}",
-                            details.field_name,
-                            if details.ascending { "asc" } else { "desc" }
-                        )
-                    };
-                    let value =
-                        if details.redacted { "<hidden>".into() } else { details.value.clone() };
-                    let sort_details = serde_json::json!({
-                        "order": order,
-                        "value": value,
-                    });
-                    details_map.insert(sort, sort_details);
-                    order += 1;
-                }
-                ScoreDetails::GeoSort(details) => {
-                    let sort = format!(
-                        "_geoPoint({}, {}):{}",
-                        details.target_point[0],
-                        details.target_point[1],
-                        if details.ascending { "asc" } else { "desc" }
-                    );
-                    let point = if let Some(value) = details.value {
-                        serde_json::json!({ "lat": value[0], "lng": value[1]})
-                    } else {
-                        serde_json::Value::Null
-                    };
-                    let sort_details = serde_json::json!({
-                        "order": order,
-                        "value": point,
-                        "distance": details.distance(),
-                    });
-                    details_map.insert(sort, sort_details);
-                    order += 1;
-                }
-            }
-        }
-        details_map
-    }
-}
-
-/// The strategy to compute scores.
-///
-/// It makes sense to pass down this strategy to the internals of the search, because
-/// some optimizations (today, mainly skipping ranking rules for universes of a single document)
-/// are not correct to do when computing the scores.
-///
-/// This strategy could feasibly be extended to differentiate between the normalized score and the
-/// detailed scores, but it is not useful today as the normalized score is *derived from* the
-/// detailed scores.
-#[derive(Debug, Clone, Copy, PartialEq, Eq, Default)]
-pub enum ScoringStrategy {
-    /// Don't compute scores
-    #[default]
-    Skip,
-    /// Compute detailed scores
-    Detailed,
-}
-
-#[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord, Hash)]
-pub struct Words {
-    pub matching_words: u32,
-    pub max_matching_words: u32,
-}
-
-impl Words {
-    pub fn rank(&self) -> Rank {
-        Rank { rank: self.matching_words, max_rank: self.max_matching_words }
-    }
-
-    pub(crate) fn from_rank(rank: Rank) -> Words {
-        Words { matching_words: rank.rank, max_matching_words: rank.max_rank }
-    }
-}
-
-#[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord, Hash)]
-pub struct Typo {
-    pub typo_count: u32,
-    pub max_typo_count: u32,
-}
-
-impl Typo {
-    pub fn rank(&self) -> Rank {
-        Rank {
-            rank: self.max_typo_count - self.typo_count + 1,
-            max_rank: (self.max_typo_count + 1),
-        }
-    }
-
-    // max_rank = max_typo + 1
-    // max_typo = max_rank - 1
-    //
-    // rank = max_typo - typo + 1
-    // rank = max_rank - 1 - typo + 1
-    // rank + typo = max_rank
-    // typo = max_rank - rank
-    pub fn from_rank(rank: Rank) -> Typo {
-        Typo { typo_count: rank.max_rank - rank.rank, max_typo_count: rank.max_rank - 1 }
-    }
-}
-
-#[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord, Hash)]
-pub struct Rank {
-    /// The ordinal rank, such that `max_rank` is the first rank, and 0 is the last rank.
-    ///
-    /// The higher the better. Documents with a rank of 0 have a score of 0 and are typically never returned
-    /// (they don't match the query).
-    pub rank: u32,
-    /// The maximum possible rank. Documents with this rank have a score of 1.
-    ///
-    /// The max rank should not be 0.
-    pub max_rank: u32,
-}
-
-impl Rank {
-    pub fn local_score(self) -> f64 {
-        self.rank as f64 / self.max_rank as f64
-    }
-
-    pub fn global_score(details: impl Iterator<Item = Self>) -> f64 {
-        let mut rank = Rank { rank: 1, max_rank: 1 };
-        for inner_rank in details {
-            rank.rank -= 1;
-
-            rank.rank *= inner_rank.max_rank;
-            rank.max_rank *= inner_rank.max_rank;
-
-            rank.rank += inner_rank.rank;
-        }
-        rank.local_score()
-    }
-}
-
-#[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord, Hash, Serialize)]
-#[serde(rename_all = "camelCase")]
-pub enum ExactAttribute {
-    ExactMatch,
-    MatchesStart,
-    NoExactMatch,
-}
-
-impl ExactAttribute {
-    pub fn rank(&self) -> Rank {
-        let rank = match self {
-            ExactAttribute::ExactMatch => 3,
-            ExactAttribute::MatchesStart => 2,
-            ExactAttribute::NoExactMatch => 1,
-        };
-        Rank { rank, max_rank: 3 }
-    }
-}
-
-#[derive(Debug, Clone, PartialEq)]
-pub struct Sort {
-    pub field_name: String,
-    pub ascending: bool,
-    pub redacted: bool,
-    pub value: serde_json::Value,
-}
-
-#[derive(Debug, Clone, Copy, PartialEq, PartialOrd)]
-pub struct GeoSort {
-    pub target_point: [f64; 2],
-    pub ascending: bool,
-    pub value: Option<[f64; 2]>,
-}
-
-impl GeoSort {
-    pub fn distance(&self) -> Option<f64> {
-        self.value.map(|value| distance_between_two_points(&self.target_point, &value))
-    }
-}

milli/src/search/facet/facet_distribution.rs

@@ -1,22 +1,19 @@
-use std::collections::{BTreeMap, HashMap, HashSet};
+use std::collections::{BTreeMap, HashSet};
 use std::ops::ControlFlow;
 use std::{fmt, mem};
 
 use heed::types::ByteSlice;
 use heed::BytesDecode;
-use indexmap::IndexMap;
 use roaring::RoaringBitmap;
-use serde::{Deserialize, Serialize};
 
 use crate::error::UserError;
 use crate::facet::FacetType;
 use crate::heed_codec::facet::{
-    FacetGroupKeyCodec, FieldDocIdFacetF64Codec, FieldDocIdFacetStringCodec, OrderedF64Codec,
+    FacetGroupKeyCodec, FacetGroupValueCodec, FieldDocIdFacetF64Codec, FieldDocIdFacetStringCodec,
+    OrderedF64Codec,
 };
 use crate::heed_codec::{ByteSliceRefCodec, StrRefCodec};
-use crate::search::facet::facet_distribution_iter::{
-    count_iterate_over_facet_distribution, lexicographically_iterate_over_facet_distribution,
-};
+use crate::search::facet::facet_distribution_iter;
 use crate::{FieldId, Index, Result};
 
 /// The default number of values by facets that will
@@ -27,21 +24,10 @@ pub const DEFAULT_VALUES_PER_FACET: usize = 100;
 /// the system to choose between one algorithm or another.
 const CANDIDATES_THRESHOLD: u64 = 3000;
 
-/// How should we fetch the facets?
-#[derive(Debug, Default, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
-pub enum OrderBy {
-    /// By lexicographic order...
-    #[default]
-    Lexicographic,
-    /// Or by number of docids in common?
-    Count,
-}
-
 pub struct FacetDistribution<'a> {
-    facets: Option<HashMap<String, OrderBy>>,
+    facets: Option<HashSet<String>>,
     candidates: Option<RoaringBitmap>,
     max_values_per_facet: usize,
-    default_order_by: OrderBy,
     rtxn: &'a heed::RoTxn<'a>,
     index: &'a Index,
 }
@@ -52,22 +38,13 @@ impl<'a> FacetDistribution<'a> {
             facets: None,
             candidates: None,
             max_values_per_facet: DEFAULT_VALUES_PER_FACET,
-            default_order_by: OrderBy::default(),
             rtxn,
             index,
         }
     }
 
-    pub fn facets<I: IntoIterator<Item = (A, OrderBy)>, A: AsRef<str>>(
-        &mut self,
-        names_ordered_by: I,
-    ) -> &mut Self {
-        self.facets = Some(
-            names_ordered_by
-                .into_iter()
-                .map(|(name, order_by)| (name.as_ref().to_string(), order_by))
-                .collect(),
-        );
+    pub fn facets<I: IntoIterator<Item = A>, A: AsRef<str>>(&mut self, names: I) -> &mut Self {
+        self.facets = Some(names.into_iter().map(|s| s.as_ref().to_string()).collect());
         self
     }
 
@@ -76,11 +53,6 @@ impl<'a> FacetDistribution<'a> {
         self
     }
 
-    pub fn default_order_by(&mut self, order_by: OrderBy) -> &mut Self {
-        self.default_order_by = order_by;
-        self
-    }
-
     pub fn candidates(&mut self, candidates: RoaringBitmap) -> &mut Self {
         self.candidates = Some(candidates);
         self
@@ -93,7 +65,7 @@ impl<'a> FacetDistribution<'a> {
         field_id: FieldId,
         facet_type: FacetType,
         candidates: &RoaringBitmap,
-        distribution: &mut IndexMap<String, u64>,
+        distribution: &mut BTreeMap<String, u64>,
     ) -> heed::Result<()> {
         match facet_type {
             FacetType::Number => {
@@ -162,15 +134,9 @@ impl<'a> FacetDistribution<'a> {
         &self,
         field_id: FieldId,
         candidates: &RoaringBitmap,
-        order_by: OrderBy,
-        distribution: &mut IndexMap<String, u64>,
+        distribution: &mut BTreeMap<String, u64>,
     ) -> heed::Result<()> {
-        let search_function = match order_by {
-            OrderBy::Lexicographic => lexicographically_iterate_over_facet_distribution,
-            OrderBy::Count => count_iterate_over_facet_distribution,
-        };
-
-        search_function(
+        facet_distribution_iter::iterate_over_facet_distribution(
             self.rtxn,
             self.index
                 .facet_id_f64_docids
@@ -193,15 +159,9 @@ impl<'a> FacetDistribution<'a> {
         &self,
         field_id: FieldId,
         candidates: &RoaringBitmap,
-        order_by: OrderBy,
-        distribution: &mut IndexMap<String, u64>,
+        distribution: &mut BTreeMap<String, u64>,
     ) -> heed::Result<()> {
-        let search_function = match order_by {
-            OrderBy::Lexicographic => lexicographically_iterate_over_facet_distribution,
-            OrderBy::Count => count_iterate_over_facet_distribution,
-        };
-
-        search_function(
+        facet_distribution_iter::iterate_over_facet_distribution(
             self.rtxn,
             self.index
                 .facet_id_string_docids
@@ -229,49 +189,95 @@ impl<'a> FacetDistribution<'a> {
         )
     }
 
-    fn facet_values(
+    /// Placeholder search, a.k.a. no candidates were specified. We iterate throught the
+    /// facet values one by one and iterate on the facet level 0 for numbers.
+    fn facet_values_from_raw_facet_database(
         &self,
         field_id: FieldId,
-        order_by: OrderBy,
-    ) -> heed::Result<IndexMap<String, u64>> {
-        use FacetType::{Number, String};
+    ) -> heed::Result<BTreeMap<String, u64>> {
+        let mut distribution = BTreeMap::new();
 
-        let mut distribution = IndexMap::new();
-        match (order_by, &self.candidates) {
-            (OrderBy::Lexicographic, Some(cnd)) if cnd.len() <= CANDIDATES_THRESHOLD => {
-                // Classic search, candidates were specified, we must return facet values only related
-                // to those candidates. We also enter here for facet strings for performance reasons.
-                self.facet_distribution_from_documents(field_id, Number, cnd, &mut distribution)?;
-                self.facet_distribution_from_documents(field_id, String, cnd, &mut distribution)?;
-            }
-            _ => {
-                let universe;
-                let candidates = match &self.candidates {
-                    Some(cnd) => cnd,
-                    None => {
-                        universe = self.index.documents_ids(self.rtxn)?;
-                        &universe
-                    }
-                };
+        let db = self.index.facet_id_f64_docids;
+        let mut prefix = vec![];
+        prefix.extend_from_slice(&field_id.to_be_bytes());
+        prefix.push(0); // read values from level 0 only
 
-                self.facet_numbers_distribution_from_facet_levels(
-                    field_id,
-                    candidates,
-                    order_by,
-                    &mut distribution,
-                )?;
-                self.facet_strings_distribution_from_facet_levels(
-                    field_id,
-                    candidates,
-                    order_by,
-                    &mut distribution,
-                )?;
+        let iter = db
+            .as_polymorph()
+            .prefix_iter::<_, ByteSlice, ByteSlice>(self.rtxn, prefix.as_slice())?
+            .remap_types::<FacetGroupKeyCodec<OrderedF64Codec>, FacetGroupValueCodec>();
+
+        for result in iter {
+            let (key, value) = result?;
+            distribution.insert(key.left_bound.to_string(), value.bitmap.len());
+            if distribution.len() == self.max_values_per_facet {
+                break;
             }
-        };
+        }
+
+        let iter = self
+            .index
+            .facet_id_string_docids
+            .as_polymorph()
+            .prefix_iter::<_, ByteSlice, ByteSlice>(self.rtxn, prefix.as_slice())?
+            .remap_types::<FacetGroupKeyCodec<StrRefCodec>, FacetGroupValueCodec>();
+
+        for result in iter {
+            let (key, value) = result?;
+
+            let docid = value.bitmap.iter().next().unwrap();
+            let key: (FieldId, _, &'a str) = (field_id, docid, key.left_bound);
+            let original_string =
+                self.index.field_id_docid_facet_strings.get(self.rtxn, &key)?.unwrap().to_owned();
+
+            distribution.insert(original_string, value.bitmap.len());
+            if distribution.len() == self.max_values_per_facet {
+                break;
+            }
+        }
 
         Ok(distribution)
     }
 
+    fn facet_values(&self, field_id: FieldId) -> heed::Result<BTreeMap<String, u64>> {
+        use FacetType::{Number, String};
+
+        match self.candidates {
+            Some(ref candidates) => {
+                // Classic search, candidates were specified, we must return facet values only related
+                // to those candidates. We also enter here for facet strings for performance reasons.
+                let mut distribution = BTreeMap::new();
+                if candidates.len() <= CANDIDATES_THRESHOLD {
+                    self.facet_distribution_from_documents(
+                        field_id,
+                        Number,
+                        candidates,
+                        &mut distribution,
+                    )?;
+                    self.facet_distribution_from_documents(
+                        field_id,
+                        String,
+                        candidates,
+                        &mut distribution,
+                    )?;
+                } else {
+                    self.facet_numbers_distribution_from_facet_levels(
+                        field_id,
+                        candidates,
+                        &mut distribution,
+                    )?;
+                    self.facet_strings_distribution_from_facet_levels(
+                        field_id,
+                        candidates,
+                        &mut distribution,
+                    )?;
+                }
+                Ok(distribution)
+            }
+            None => self.facet_values_from_raw_facet_database(field_id),
+        }
+    }
+
     pub fn compute_stats(&self) -> Result<BTreeMap<String, (f64, f64)>> {
         let fields_ids_map = self.index.fields_ids_map(self.rtxn)?;
         let filterable_fields = self.index.filterable_fields(self.rtxn)?;
@@ -285,7 +291,6 @@ impl<'a> FacetDistribution<'a> {
             Some(facets) => {
                 let invalid_fields: HashSet<_> = facets
                     .iter()
-                    .map(|(name, _)| name)
                     .filter(|facet| !crate::is_faceted(facet, &filterable_fields))
                     .collect();
                 if !invalid_fields.is_empty() {
@@ -295,7 +300,7 @@ impl<'a> FacetDistribution<'a> {
                     }
                     .into());
                 } else {
-                    facets.iter().map(|(name, _)| name).cloned().collect()
+                    facets.clone()
                 }
             }
             None => filterable_fields,
@@ -332,7 +337,7 @@ impl<'a> FacetDistribution<'a> {
         Ok(distribution)
     }
 
-    pub fn execute(&self) -> Result<BTreeMap<String, IndexMap<String, u64>>> {
+    pub fn execute(&self) -> Result<BTreeMap<String, BTreeMap<String, u64>>> {
         let fields_ids_map = self.index.fields_ids_map(self.rtxn)?;
         let filterable_fields = self.index.filterable_fields(self.rtxn)?;
 
@@ -340,7 +345,6 @@ impl<'a> FacetDistribution<'a> {
             Some(ref facets) => {
                 let invalid_fields: HashSet<_> = facets
                     .iter()
-                    .map(|(name, _)| name)
                     .filter(|facet| !crate::is_faceted(facet, &filterable_fields))
                     .collect();
                 if !invalid_fields.is_empty() {
@@ -350,7 +354,7 @@ impl<'a> FacetDistribution<'a> {
                     }
                     .into());
                 } else {
-                    facets.iter().map(|(name, _)| name).cloned().collect()
+                    facets.clone()
                 }
             }
             None => filterable_fields,
@@ -359,12 +363,7 @@ impl<'a> FacetDistribution<'a> {
         let mut distribution = BTreeMap::new();
         for (fid, name) in fields_ids_map.iter() {
             if crate::is_faceted(name, &fields) {
-                let order_by = self
-                    .facets
-                    .as_ref()
-                    .and_then(|facets| facets.get(name).copied())
-                    .unwrap_or(self.default_order_by);
-                let values = self.facet_values(fid, order_by)?;
+                let values = self.facet_values(fid)?;
                 distribution.insert(name.to_string(), values);
             }
         }
@@ -375,34 +374,25 @@ impl<'a> FacetDistribution<'a> {
 
 impl fmt::Debug for FacetDistribution<'_> {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        let FacetDistribution {
-            facets,
-            candidates,
-            max_values_per_facet,
-            default_order_by,
-            rtxn: _,
-            index: _,
-        } = self;
+        let FacetDistribution { facets, candidates, max_values_per_facet, rtxn: _, index: _ } =
+            self;
 
         f.debug_struct("FacetDistribution")
             .field("facets", facets)
             .field("candidates", candidates)
             .field("max_values_per_facet", max_values_per_facet)
-            .field("default_order_by", default_order_by)
             .finish()
     }
 }
 
 #[cfg(test)]
 mod tests {
-    use std::iter;
-
     use big_s::S;
     use maplit::hashset;
 
     use crate::documents::documents_batch_reader_from_objects;
     use crate::index::tests::TempIndex;
-    use crate::{milli_snap, FacetDistribution, OrderBy};
+    use crate::{milli_snap, FacetDistribution};
 
     #[test]
     fn few_candidates_few_facet_values() {
@@ -427,14 +417,14 @@ mod tests {
         let txn = index.read_txn().unwrap();
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(iter::once(("colour", OrderBy::default())))
+            .facets(std::iter::once("colour"))
             .execute()
             .unwrap();
 
         milli_snap!(format!("{map:?}"), @r###"{"colour": {"Blue": 2, "RED": 1}}"###);
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(iter::once(("colour", OrderBy::default())))
+            .facets(std::iter::once("colour"))
             .candidates([0, 1, 2].iter().copied().collect())
             .execute()
             .unwrap();
@@ -442,7 +432,7 @@ mod tests {
         milli_snap!(format!("{map:?}"), @r###"{"colour": {"Blue": 2, "RED": 1}}"###);
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(iter::once(("colour", OrderBy::default())))
+            .facets(std::iter::once("colour"))
             .candidates([1, 2].iter().copied().collect())
             .execute()
             .unwrap();
@@ -453,7 +443,7 @@ mod tests {
         milli_snap!(format!("{map:?}"), @r###"{"colour": {"  blue": 1, "RED": 1}}"###);
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(iter::once(("colour", OrderBy::default())))
+            .facets(std::iter::once("colour"))
             .candidates([2].iter().copied().collect())
             .execute()
             .unwrap();
@@ -461,22 +451,13 @@ mod tests {
         milli_snap!(format!("{map:?}"), @r###"{"colour": {"RED": 1}}"###);
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(iter::once(("colour", OrderBy::default())))
+            .facets(std::iter::once("colour"))
             .candidates([0, 1, 2].iter().copied().collect())
             .max_values_per_facet(1)
             .execute()
             .unwrap();
 
         milli_snap!(format!("{map:?}"), @r###"{"colour": {"Blue": 1}}"###);
-
-        let map = FacetDistribution::new(&txn, &index)
-            .facets(iter::once(("colour", OrderBy::Count)))
-            .candidates([0, 1, 2].iter().copied().collect())
-            .max_values_per_facet(1)
-            .execute()
-            .unwrap();
-
-        milli_snap!(format!("{map:?}"), @r###"{"colour": {"Blue": 2}}"###);
     }
 
     #[test]
@@ -508,14 +489,14 @@ mod tests {
         let txn = index.read_txn().unwrap();
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(iter::once(("colour", OrderBy::default())))
+            .facets(std::iter::once("colour"))
             .execute()
             .unwrap();
 
         milli_snap!(format!("{map:?}"), @r###"{"colour": {"Blue": 4000, "Red": 6000}}"###);
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(iter::once(("colour", OrderBy::default())))
+            .facets(std::iter::once("colour"))
             .max_values_per_facet(1)
             .execute()
             .unwrap();
@@ -523,7 +504,7 @@ mod tests {
         milli_snap!(format!("{map:?}"), @r###"{"colour": {"Blue": 4000}}"###);
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(iter::once(("colour", OrderBy::default())))
+            .facets(std::iter::once("colour"))
             .candidates((0..10_000).collect())
             .execute()
             .unwrap();
@@ -531,7 +512,7 @@ mod tests {
         milli_snap!(format!("{map:?}"), @r###"{"colour": {"Blue": 4000, "Red": 6000}}"###);
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(iter::once(("colour", OrderBy::default())))
+            .facets(std::iter::once("colour"))
             .candidates((0..5_000).collect())
             .execute()
             .unwrap();
@@ -539,7 +520,7 @@ mod tests {
         milli_snap!(format!("{map:?}"), @r###"{"colour": {"Blue": 2000, "Red": 3000}}"###);
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(iter::once(("colour", OrderBy::default())))
+            .facets(std::iter::once("colour"))
             .candidates((0..5_000).collect())
             .execute()
             .unwrap();
@@ -547,22 +528,13 @@ mod tests {
         milli_snap!(format!("{map:?}"), @r###"{"colour": {"Blue": 2000, "Red": 3000}}"###);
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(iter::once(("colour", OrderBy::default())))
+            .facets(std::iter::once("colour"))
             .candidates((0..5_000).collect())
             .max_values_per_facet(1)
             .execute()
             .unwrap();
 
         milli_snap!(format!("{map:?}"), @r###"{"colour": {"Blue": 2000}}"###);
-
-        let map = FacetDistribution::new(&txn, &index)
-            .facets(iter::once(("colour", OrderBy::Count)))
-            .candidates((0..5_000).collect())
-            .max_values_per_facet(1)
-            .execute()
-            .unwrap();
-
-        milli_snap!(format!("{map:?}"), @r###"{"colour": {"Red": 3000}}"###);
     }
 
     #[test]
@@ -594,14 +566,14 @@ mod tests {
         let txn = index.read_txn().unwrap();
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(iter::once(("colour", OrderBy::default())))
+            .facets(std::iter::once("colour"))
             .execute()
             .unwrap();
 
         milli_snap!(format!("{map:?}"), "no_candidates", @"ac9229ed5964d893af96a7076e2f8af5");
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(iter::once(("colour", OrderBy::default())))
+            .facets(std::iter::once("colour"))
             .max_values_per_facet(2)
             .execute()
             .unwrap();
@@ -609,7 +581,7 @@ mod tests {
         milli_snap!(format!("{map:?}"), "no_candidates_with_max_2", @r###"{"colour": {"0": 10, "1": 10}}"###);
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(iter::once(("colour", OrderBy::default())))
+            .facets(std::iter::once("colour"))
             .candidates((0..10_000).collect())
             .execute()
             .unwrap();
@@ -617,7 +589,7 @@ mod tests {
         milli_snap!(format!("{map:?}"), "candidates_0_10_000", @"ac9229ed5964d893af96a7076e2f8af5");
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(iter::once(("colour", OrderBy::default())))
+            .facets(std::iter::once("colour"))
             .candidates((0..5_000).collect())
             .execute()
             .unwrap();
@@ -654,14 +626,14 @@ mod tests {
         let txn = index.read_txn().unwrap();
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(iter::once(("colour", OrderBy::default())))
+            .facets(std::iter::once("colour"))
             .compute_stats()
             .unwrap();
 
         milli_snap!(format!("{map:?}"), "no_candidates", @"{}");
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(iter::once(("colour", OrderBy::default())))
+            .facets(std::iter::once("colour"))
             .candidates((0..1000).collect())
             .compute_stats()
             .unwrap();
@@ -669,7 +641,7 @@ mod tests {
         milli_snap!(format!("{map:?}"), "candidates_0_1000", @r###"{"colour": (0.0, 999.0)}"###);
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(iter::once(("colour", OrderBy::default())))
+            .facets(std::iter::once("colour"))
             .candidates((217..777).collect())
             .compute_stats()
             .unwrap();
@@ -706,14 +678,14 @@ mod tests {
         let txn = index.read_txn().unwrap();
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(iter::once(("colour", OrderBy::default())))
+            .facets(std::iter::once("colour"))
             .compute_stats()
             .unwrap();
 
         milli_snap!(format!("{map:?}"), "no_candidates", @"{}");
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(iter::once(("colour", OrderBy::default())))
+            .facets(std::iter::once("colour"))
             .candidates((0..1000).collect())
             .compute_stats()
             .unwrap();
@@ -721,7 +693,7 @@ mod tests {
         milli_snap!(format!("{map:?}"), "candidates_0_1000", @r###"{"colour": (0.0, 1999.0)}"###);
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(iter::once(("colour", OrderBy::default())))
+            .facets(std::iter::once("colour"))
             .candidates((217..777).collect())
             .compute_stats()
             .unwrap();
@@ -758,14 +730,14 @@ mod tests {
         let txn = index.read_txn().unwrap();
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(iter::once(("colour", OrderBy::default())))
+            .facets(std::iter::once("colour"))
             .compute_stats()
             .unwrap();
 
         milli_snap!(format!("{map:?}"), "no_candidates", @"{}");
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(iter::once(("colour", OrderBy::default())))
+            .facets(std::iter::once("colour"))
             .candidates((0..1000).collect())
             .compute_stats()
             .unwrap();
@@ -773,7 +745,7 @@ mod tests {
         milli_snap!(format!("{map:?}"), "candidates_0_1000", @r###"{"colour": (0.0, 999.0)}"###);
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(iter::once(("colour", OrderBy::default())))
+            .facets(std::iter::once("colour"))
             .candidates((217..777).collect())
             .compute_stats()
             .unwrap();
@@ -814,14 +786,14 @@ mod tests {
         let txn = index.read_txn().unwrap();
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(iter::once(("colour", OrderBy::default())))
+            .facets(std::iter::once("colour"))
             .compute_stats()
             .unwrap();
 
         milli_snap!(format!("{map:?}"), "no_candidates", @"{}");
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(iter::once(("colour", OrderBy::default())))
+            .facets(std::iter::once("colour"))
             .candidates((0..1000).collect())
             .compute_stats()
             .unwrap();
@@ -829,7 +801,7 @@ mod tests {
         milli_snap!(format!("{map:?}"), "candidates_0_1000", @r###"{"colour": (0.0, 1998.0)}"###);
 
         let map = FacetDistribution::new(&txn, &index)
-            .facets(iter::once(("colour", OrderBy::default())))
+            .facets(std::iter::once("colour"))
             .candidates((217..777).collect())
             .compute_stats()
             .unwrap();

milli/src/search/facet/facet_distribution_iter.rs

@@ -1,5 +1,3 @@
-use std::cmp::Reverse;
-use std::collections::BinaryHeap;
 use std::ops::ControlFlow;
 
 use heed::Result;
@@ -21,7 +19,7 @@ use crate::DocumentId;
 ///
 /// The return value of the closure is a `ControlFlow<()>` which indicates whether we should
 /// keep iterating over the different facet values or stop.
-pub fn lexicographically_iterate_over_facet_distribution<'t, CB>(
+pub fn iterate_over_facet_distribution<'t, CB>(
     rtxn: &'t heed::RoTxn<'t>,
     db: heed::Database<FacetGroupKeyCodec<ByteSliceRefCodec>, FacetGroupValueCodec>,
     field_id: u16,
@@ -31,7 +29,7 @@ pub fn lexicographically_iterate_over_facet_distribution<'t, CB>(
 where
     CB: FnMut(&'t [u8], u64, DocumentId) -> Result<ControlFlow<()>>,
 {
-    let mut fd = LexicographicFacetDistribution { rtxn, db, field_id, callback };
+    let mut fd = FacetDistribution { rtxn, db, field_id, callback };
     let highest_level = get_highest_level(
         rtxn,
         db.remap_key_type::<FacetGroupKeyCodec<ByteSliceRefCodec>>(),
@@ -46,102 +44,7 @@ where
     }
 }
 
-pub fn count_iterate_over_facet_distribution<'t, CB>(
-    rtxn: &'t heed::RoTxn<'t>,
-    db: heed::Database<FacetGroupKeyCodec<ByteSliceRefCodec>, FacetGroupValueCodec>,
-    field_id: u16,
-    candidates: &RoaringBitmap,
-    mut callback: CB,
-) -> Result<()>
-where
-    CB: FnMut(&'t [u8], u64, DocumentId) -> Result<ControlFlow<()>>,
-{
-    /// # Important
-    /// The order of the fields determines the order in which the facet values will be returned.
-    /// This struct is inserted in a BinaryHeap and popped later on.
-    #[derive(Debug, PartialOrd, Ord, PartialEq, Eq)]
-    struct LevelEntry<'t> {
-        /// The number of candidates in this entry.
-        count: u64,
-        /// The key level of the entry.
-        level: Reverse<u8>,
-        /// The left bound key.
-        left_bound: &'t [u8],
-        /// The number of keys we must look for after `left_bound`.
-        group_size: u8,
-        /// Any docid in the set of matching documents. Used to find the original facet string.
-        any_docid: u32,
-    }
-
-    // Represents the list of keys that we must explore.
-    let mut heap = BinaryHeap::new();
-    let highest_level = get_highest_level(
-        rtxn,
-        db.remap_key_type::<FacetGroupKeyCodec<ByteSliceRefCodec>>(),
-        field_id,
-    )?;
-
-    if let Some(first_bound) = get_first_facet_value::<ByteSliceRefCodec>(rtxn, db, field_id)? {
-        // We first fill the heap with values from the highest level
-        let starting_key =
-            FacetGroupKey { field_id, level: highest_level, left_bound: first_bound };
-        for el in db.range(rtxn, &(&starting_key..))?.take(usize::MAX) {
-            let (key, value) = el?;
-            // The range is unbounded on the right and the group size for the highest level is MAX,
-            // so we need to check that we are not iterating over the next field id
-            if key.field_id != field_id {
-                break;
-            }
-            let intersection = value.bitmap & candidates;
-            let count = intersection.len();
-            if count != 0 {
-                heap.push(LevelEntry {
-                    count,
-                    level: Reverse(key.level),
-                    left_bound: key.left_bound,
-                    group_size: value.size,
-                    any_docid: intersection.min().unwrap(),
-                });
-            }
-        }
-
-        while let Some(LevelEntry { count, level, left_bound, group_size, any_docid }) = heap.pop()
-        {
-            if let Reverse(0) = level {
-                match (callback)(left_bound, count, any_docid)? {
-                    ControlFlow::Continue(_) => (),
-                    ControlFlow::Break(_) => return Ok(()),
-                }
-            } else {
-                let starting_key = FacetGroupKey { field_id, level: level.0 - 1, left_bound };
-                for el in db.range(rtxn, &(&starting_key..))?.take(group_size as usize) {
-                    let (key, value) = el?;
-                    // The range is unbounded on the right and the group size for the highest level is MAX,
-                    // so we need to check that we are not iterating over the next field id
-                    if key.field_id != field_id {
-                        break;
-                    }
-                    let intersection = value.bitmap & candidates;
-                    let count = intersection.len();
-                    if count != 0 {
-                        heap.push(LevelEntry {
-                            count,
-                            level: Reverse(key.level),
-                            left_bound: key.left_bound,
-                            group_size: value.size,
-                            any_docid: intersection.min().unwrap(),
-                        });
-                    }
-                }
-            }
-        }
-    }
-
-    Ok(())
-}
-
-/// Iterate over the facets values by lexicographic order.
-struct LexicographicFacetDistribution<'t, CB>
+struct FacetDistribution<'t, CB>
 where
     CB: FnMut(&'t [u8], u64, DocumentId) -> Result<ControlFlow<()>>,
 {
@@ -151,7 +54,7 @@ where
     callback: CB,
 }
 
-impl<'t, CB> LexicographicFacetDistribution<'t, CB>
+impl<'t, CB> FacetDistribution<'t, CB>
 where
     CB: FnMut(&'t [u8], u64, DocumentId) -> Result<ControlFlow<()>>,
 {
@@ -183,7 +86,6 @@ where
         }
         Ok(ControlFlow::Continue(()))
     }
-
     fn iterate(
         &mut self,
         candidates: &RoaringBitmap,
@@ -196,10 +98,10 @@ where
         }
         let starting_key =
             FacetGroupKey { field_id: self.field_id, level, left_bound: starting_bound };
-        let iter = self.db.range(self.rtxn, &(&starting_key..))?.take(group_size);
+        let iter = self.db.range(self.rtxn, &(&starting_key..)).unwrap().take(group_size);
 
         for el in iter {
-            let (key, value) = el?;
+            let (key, value) = el.unwrap();
             // The range is unbounded on the right and the group size for the highest level is MAX,
             // so we need to check that we are not iterating over the next field id
             if key.field_id != self.field_id {
@@ -214,7 +116,7 @@ where
                     value.size as usize,
                 )?;
                 match cf {
-                    ControlFlow::Continue(_) => (),
+                    ControlFlow::Continue(_) => {}
                     ControlFlow::Break(_) => return Ok(ControlFlow::Break(())),
                 }
             }
@@ -230,7 +132,7 @@ mod tests {
     use heed::BytesDecode;
     use roaring::RoaringBitmap;
 
-    use super::lexicographically_iterate_over_facet_distribution;
+    use super::iterate_over_facet_distribution;
     use crate::heed_codec::facet::OrderedF64Codec;
     use crate::milli_snap;
     use crate::search::facet::tests::{get_random_looking_index, get_simple_index};
@@ -242,7 +144,7 @@ mod tests {
             let txn = index.env.read_txn().unwrap();
             let candidates = (0..=255).collect::<RoaringBitmap>();
             let mut results = String::new();
-            lexicographically_iterate_over_facet_distribution(
+            iterate_over_facet_distribution(
                 &txn,
                 index.content,
                 0,
@@ -259,7 +161,6 @@ mod tests {
             txn.commit().unwrap();
         }
     }
-
     #[test]
     fn filter_distribution_all_stop_early() {
         let indexes = [get_simple_index(), get_random_looking_index()];
@@ -268,7 +169,7 @@ mod tests {
             let candidates = (0..=255).collect::<RoaringBitmap>();
             let mut results = String::new();
             let mut nbr_facets = 0;
-            lexicographically_iterate_over_facet_distribution(
+            iterate_over_facet_distribution(
                 &txn,
                 index.content,
                 0,

milli/src/search/facet/mod.rs

@@ -4,7 +4,7 @@ use heed::types::{ByteSlice, DecodeIgnore};
 use heed::{BytesDecode, RoTxn};
 use roaring::RoaringBitmap;
 
-pub use self::facet_distribution::{FacetDistribution, OrderBy, DEFAULT_VALUES_PER_FACET};
+pub use self::facet_distribution::{FacetDistribution, DEFAULT_VALUES_PER_FACET};
 pub use self::filter::{BadGeoError, Filter};
 use crate::heed_codec::facet::{FacetGroupKeyCodec, FacetGroupValueCodec, OrderedF64Codec};
 use crate::heed_codec::ByteSliceRefCodec;

milli/src/search/mod.rs

@@ -1,21 +1,14 @@
 use std::fmt;
 
-use fst::automaton::{Automaton, Str};
-use fst::{IntoStreamer, Streamer};
 use levenshtein_automata::{LevenshteinAutomatonBuilder as LevBuilder, DFA};
-use log::error;
 use once_cell::sync::Lazy;
 use roaring::bitmap::RoaringBitmap;
 
-pub use self::facet::{FacetDistribution, Filter, OrderBy, DEFAULT_VALUES_PER_FACET};
+pub use self::facet::{FacetDistribution, Filter, DEFAULT_VALUES_PER_FACET};
 pub use self::new::matches::{FormatOptions, MatchBounds, Matcher, MatcherBuilder, MatchingWords};
 use self::new::PartialSearchResult;
-use crate::error::UserError;
-use crate::heed_codec::facet::{FacetGroupKey, FacetGroupValue};
-use crate::score_details::{ScoreDetails, ScoringStrategy};
 use crate::{
-    execute_search, normalize_facet, AscDesc, DefaultSearchLogger, DocumentId, FieldId, Index,
-    Result, SearchContext, BEU16,
+    execute_search, AscDesc, DefaultSearchLogger, DocumentId, Index, Result, SearchContext,
 };
 
 // Building these factories is not free.
@@ -23,9 +16,6 @@ static LEVDIST0: Lazy<LevBuilder> = Lazy::new(|| LevBuilder::new(0, true));
 static LEVDIST1: Lazy<LevBuilder> = Lazy::new(|| LevBuilder::new(1, true));
 static LEVDIST2: Lazy<LevBuilder> = Lazy::new(|| LevBuilder::new(2, true));
 
-/// The maximum number of facets returned by the facet search route.
-const MAX_NUMBER_OF_FACETS: usize = 100;
-
 pub mod facet;
 mod fst_utils;
 pub mod new;
@@ -38,10 +28,8 @@ pub struct Search<'a> {
     offset: usize,
     limit: usize,
     sort_criteria: Option<Vec<AscDesc>>,
-    searchable_attributes: Option<&'a [String]>,
     geo_strategy: new::GeoSortStrategy,
     terms_matching_strategy: TermsMatchingStrategy,
-    scoring_strategy: ScoringStrategy,
     words_limit: usize,
     exhaustive_number_hits: bool,
     rtxn: &'a heed::RoTxn<'a>,
@@ -57,10 +45,8 @@ impl<'a> Search<'a> {
             offset: 0,
             limit: 20,
             sort_criteria: None,
-            searchable_attributes: None,
             geo_strategy: new::GeoSortStrategy::default(),
             terms_matching_strategy: TermsMatchingStrategy::default(),
-            scoring_strategy: Default::default(),
             exhaustive_number_hits: false,
             words_limit: 10,
             rtxn,
@@ -93,21 +79,11 @@ impl<'a> Search<'a> {
         self
     }
 
-    pub fn searchable_attributes(&mut self, searchable: &'a [String]) -> &mut Search<'a> {
-        self.searchable_attributes = Some(searchable);
-        self
-    }
-
     pub fn terms_matching_strategy(&mut self, value: TermsMatchingStrategy) -> &mut Search<'a> {
         self.terms_matching_strategy = value;
         self
     }
 
-    pub fn scoring_strategy(&mut self, value: ScoringStrategy) -> &mut Search<'a> {
-        self.scoring_strategy = value;
-        self
-    }
-
     pub fn words_limit(&mut self, value: usize) -> &mut Search<'a> {
         self.words_limit = value;
         self
@@ -124,7 +100,7 @@ impl<'a> Search<'a> {
         self
     }
 
-    /// Forces the search to exhaustively compute the number of candidates,
+    /// Force the search to exhastivelly compute the number of candidates,
     /// this will increase the search time but allows finite pagination.
     pub fn exhaustive_number_hits(&mut self, exhaustive_number_hits: bool) -> &mut Search<'a> {
         self.exhaustive_number_hits = exhaustive_number_hits;
@@ -133,18 +109,12 @@ impl<'a> Search<'a> {
 
     pub fn execute(&self) -> Result<SearchResult> {
         let mut ctx = SearchContext::new(self.index, self.rtxn);
-
-        if let Some(searchable_attributes) = self.searchable_attributes {
-            ctx.searchable_attributes(searchable_attributes)?;
-        }
-
-        let PartialSearchResult { located_query_terms, candidates, documents_ids, document_scores } =
+        let PartialSearchResult { located_query_terms, candidates, documents_ids } =
             execute_search(
                 &mut ctx,
                 &self.query,
                 &self.vector,
                 self.terms_matching_strategy,
-                self.scoring_strategy,
                 self.exhaustive_number_hits,
                 &self.filter,
                 &self.sort_criteria,
@@ -162,7 +132,7 @@ impl<'a> Search<'a> {
             None => MatchingWords::default(),
         };
 
-        Ok(SearchResult { matching_words, candidates, document_scores, documents_ids })
+        Ok(SearchResult { matching_words, candidates, documents_ids })
     }
 }
 
@@ -175,10 +145,8 @@ impl fmt::Debug for Search<'_> {
             offset,
             limit,
             sort_criteria,
-            searchable_attributes,
             geo_strategy: _,
             terms_matching_strategy,
-            scoring_strategy,
             words_limit,
             exhaustive_number_hits,
             rtxn: _,
@@ -191,9 +159,7 @@ impl fmt::Debug for Search<'_> {
             .field("offset", offset)
             .field("limit", limit)
             .field("sort_criteria", sort_criteria)
-            .field("searchable_attributes", searchable_attributes)
             .field("terms_matching_strategy", terms_matching_strategy)
-            .field("scoring_strategy", scoring_strategy)
             .field("exhaustive_number_hits", exhaustive_number_hits)
             .field("words_limit", words_limit)
             .finish()
@@ -204,8 +170,8 @@ impl fmt::Debug for Search<'_> {
 pub struct SearchResult {
     pub matching_words: MatchingWords,
     pub candidates: RoaringBitmap,
+    // TODO those documents ids should be associated with their criteria scores.
     pub documents_ids: Vec<DocumentId>,
-    pub document_scores: Vec<Vec<ScoreDetails>>,
 }
 
 #[derive(Debug, Clone, Copy, PartialEq, Eq)]
@@ -243,195 +209,6 @@ pub fn build_dfa(word: &str, typos: u8, is_prefix: bool) -> DFA {
     }
 }
 
-pub struct SearchForFacetValues<'a> {
-    query: Option<String>,
-    facet: String,
-    search_query: Search<'a>,
-}
-
-impl<'a> SearchForFacetValues<'a> {
-    pub fn new(facet: String, search_query: Search<'a>) -> SearchForFacetValues<'a> {
-        SearchForFacetValues { query: None, facet, search_query }
-    }
-
-    pub fn query(&mut self, query: impl Into<String>) -> &mut Self {
-        self.query = Some(query.into());
-        self
-    }
-
-    fn one_original_value_of(
-        &self,
-        field_id: FieldId,
-        facet_str: &str,
-        any_docid: DocumentId,
-    ) -> Result<Option<String>> {
-        let index = self.search_query.index;
-        let rtxn = self.search_query.rtxn;
-        let key: (FieldId, _, &str) = (field_id, any_docid, facet_str);
-        Ok(index.field_id_docid_facet_strings.get(rtxn, &key)?.map(|v| v.to_owned()))
-    }
-
-    pub fn execute(&self) -> Result<Vec<FacetValueHit>> {
-        let index = self.search_query.index;
-        let rtxn = self.search_query.rtxn;
-
-        let filterable_fields = index.filterable_fields(rtxn)?;
-        if !filterable_fields.contains(&self.facet) {
-            return Err(UserError::InvalidFacetSearchFacetName {
-                field: self.facet.clone(),
-                valid_fields: filterable_fields.into_iter().collect(),
-            }
-            .into());
-        }
-
-        let fields_ids_map = index.fields_ids_map(rtxn)?;
-        let fid = match fields_ids_map.id(&self.facet) {
-            Some(fid) => fid,
-            // we return an empty list of results when the attribute has been
-            // set as filterable but no document contains this field (yet).
-            None => return Ok(Vec::new()),
-        };
-
-        let fst = match self.search_query.index.facet_id_string_fst.get(rtxn, &BEU16::new(fid))? {
-            Some(fst) => fst,
-            None => return Ok(vec![]),
-        };
-
-        let search_candidates = self.search_query.execute()?.candidates;
-
-        match self.query.as_ref() {
-            Some(query) => {
-                let query = normalize_facet(query);
-                let query = query.as_str();
-                let authorize_typos = self.search_query.index.authorize_typos(rtxn)?;
-                let field_authorizes_typos =
-                    !self.search_query.index.exact_attributes_ids(rtxn)?.contains(&fid);
-
-                if authorize_typos && field_authorizes_typos {
-                    let mut results = vec![];
-
-                    let exact_words_fst = self.search_query.index.exact_words(rtxn)?;
-                    if exact_words_fst.map_or(false, |fst| fst.contains(query)) {
-                        let key = FacetGroupKey { field_id: fid, level: 0, left_bound: query };
-                        if let Some(FacetGroupValue { bitmap, .. }) =
-                            index.facet_id_string_docids.get(rtxn, &key)?
-                        {
-                            let count = search_candidates.intersection_len(&bitmap);
-                            if count != 0 {
-                                let value = self
-                                    .one_original_value_of(fid, query, bitmap.min().unwrap())?
-                                    .unwrap_or_else(|| query.to_string());
-                                results.push(FacetValueHit { value, count });
-                            }
-                        }
-                    } else {
-                        let one_typo = self.search_query.index.min_word_len_one_typo(rtxn)?;
-                        let two_typos = self.search_query.index.min_word_len_two_typos(rtxn)?;
-
-                        let is_prefix = true;
-                        let automaton = if query.len() < one_typo as usize {
-                            build_dfa(query, 0, is_prefix)
-                        } else if query.len() < two_typos as usize {
-                            build_dfa(query, 1, is_prefix)
-                        } else {
-                            build_dfa(query, 2, is_prefix)
-                        };
-
-                        let mut stream = fst.search(automaton).into_stream();
-                        let mut length = 0;
-                        while let Some(facet_value) = stream.next() {
-                            let value = std::str::from_utf8(facet_value)?;
-                            let key = FacetGroupKey { field_id: fid, level: 0, left_bound: value };
-                            let docids = match index.facet_id_string_docids.get(rtxn, &key)? {
-                                Some(FacetGroupValue { bitmap, .. }) => bitmap,
-                                None => {
-                                    error!(
-                                        "the facet value is missing from the facet database: {key:?}"
-                                    );
-                                    continue;
-                                }
-                            };
-                            let count = search_candidates.intersection_len(&docids);
-                            if count != 0 {
-                                let value = self
-                                    .one_original_value_of(fid, value, docids.min().unwrap())?
-                                    .unwrap_or_else(|| query.to_string());
-                                results.push(FacetValueHit { value, count });
-                                length += 1;
-                            }
-                            if length >= MAX_NUMBER_OF_FACETS {
-                                break;
-                            }
-                        }
-                    }
-
-                    Ok(results)
-                } else {
-                    let automaton = Str::new(query).starts_with();
-                    let mut stream = fst.search(automaton).into_stream();
-                    let mut results = vec![];
-                    let mut length = 0;
-                    while let Some(facet_value) = stream.next() {
-                        let value = std::str::from_utf8(facet_value)?;
-                        let key = FacetGroupKey { field_id: fid, level: 0, left_bound: value };
-                        let docids = match index.facet_id_string_docids.get(rtxn, &key)? {
-                            Some(FacetGroupValue { bitmap, .. }) => bitmap,
-                            None => {
-                                error!(
-                                    "the facet value is missing from the facet database: {key:?}"
-                                );
-                                continue;
-                            }
-                        };
-                        let count = search_candidates.intersection_len(&docids);
-                        if count != 0 {
-                            let value = self
-                                .one_original_value_of(fid, value, docids.min().unwrap())?
-                                .unwrap_or_else(|| query.to_string());
-                            results.push(FacetValueHit { value, count });
-                            length += 1;
-                        }
-                        if length >= MAX_NUMBER_OF_FACETS {
-                            break;
-                        }
-                    }
-
-                    Ok(results)
-                }
-            }
-            None => {
-                let mut results = vec![];
-                let mut length = 0;
-                let prefix = FacetGroupKey { field_id: fid, level: 0, left_bound: "" };
-                for result in index.facet_id_string_docids.prefix_iter(rtxn, &prefix)? {
-                    let (FacetGroupKey { left_bound, .. }, FacetGroupValue { bitmap, .. }) =
-                        result?;
-                    let count = search_candidates.intersection_len(&bitmap);
-                    if count != 0 {
-                        let value = self
-                            .one_original_value_of(fid, left_bound, bitmap.min().unwrap())?
-                            .unwrap_or_else(|| left_bound.to_string());
-                        results.push(FacetValueHit { value, count });
-                        length += 1;
-                    }
-                    if length >= MAX_NUMBER_OF_FACETS {
-                        break;
-                    }
-                }
-                Ok(results)
-            }
-        }
-    }
-}
-
-#[derive(Debug, Clone, serde::Serialize, PartialEq)]
-pub struct FacetValueHit {
-    /// The original facet value
-    pub value: String,
-    /// The number of documents associated to this facet
-    pub count: u64,
-}
-
 #[cfg(test)]
 mod test {
     #[allow(unused_imports)]

milli/src/search/new/bucket_sort.rs

@@ -3,18 +3,14 @@ use roaring::RoaringBitmap;
 use super::logger::SearchLogger;
 use super::ranking_rules::{BoxRankingRule, RankingRuleQueryTrait};
 use super::SearchContext;
-use crate::score_details::{ScoreDetails, ScoringStrategy};
 use crate::search::new::distinct::{apply_distinct_rule, distinct_single_docid, DistinctOutput};
 use crate::Result;
 
 pub struct BucketSortOutput {
     pub docids: Vec<u32>,
-    pub scores: Vec<Vec<ScoreDetails>>,
     pub all_candidates: RoaringBitmap,
 }
 
-// TODO: would probably be good to regroup some of these inside of a struct?
-#[allow(clippy::too_many_arguments)]
 pub fn bucket_sort<'ctx, Q: RankingRuleQueryTrait>(
     ctx: &mut SearchContext<'ctx>,
     mut ranking_rules: Vec<BoxRankingRule<'ctx, Q>>,
@@ -22,7 +18,6 @@ pub fn bucket_sort<'ctx, Q: RankingRuleQueryTrait>(
     universe: &RoaringBitmap,
     from: usize,
     length: usize,
-    scoring_strategy: ScoringStrategy,
     logger: &mut dyn SearchLogger<Q>,
 ) -> Result<BucketSortOutput> {
     logger.initial_query(query);
@@ -36,11 +31,7 @@ pub fn bucket_sort<'ctx, Q: RankingRuleQueryTrait>(
     };
 
     if universe.len() < from as u64 {
-        return Ok(BucketSortOutput {
-            docids: vec![],
-            scores: vec![],
-            all_candidates: universe.clone(),
-        });
+        return Ok(BucketSortOutput { docids: vec![], all_candidates: universe.clone() });
     }
     if ranking_rules.is_empty() {
         if let Some(distinct_fid) = distinct_fid {
@@ -58,32 +49,22 @@ pub fn bucket_sort<'ctx, Q: RankingRuleQueryTrait>(
             }
             let mut all_candidates = universe - excluded;
             all_candidates.extend(results.iter().copied());
-            return Ok(BucketSortOutput {
-                scores: vec![Default::default(); results.len()],
-                docids: results,
-                all_candidates,
-            });
+            return Ok(BucketSortOutput { docids: results, all_candidates });
         } else {
-            let docids: Vec<u32> = universe.iter().skip(from).take(length).collect();
-            return Ok(BucketSortOutput {
-                scores: vec![Default::default(); docids.len()],
-                docids,
-                all_candidates: universe.clone(),
-            });
+            let docids = universe.iter().skip(from).take(length).collect();
+            return Ok(BucketSortOutput { docids, all_candidates: universe.clone() });
         };
     }
 
     let ranking_rules_len = ranking_rules.len();
 
     logger.start_iteration_ranking_rule(0, ranking_rules[0].as_ref(), query, universe);
-
     ranking_rules[0].start_iteration(ctx, logger, universe, query)?;
 
-    let mut ranking_rule_scores: Vec<ScoreDetails> = vec![];
-
     let mut ranking_rule_universes: Vec<RoaringBitmap> =
         vec![RoaringBitmap::default(); ranking_rules_len];
     ranking_rule_universes[0] = universe.clone();
+
     let mut cur_ranking_rule_index = 0;
 
     /// Finish iterating over the current ranking rule, yielding
@@ -108,15 +89,11 @@ pub fn bucket_sort<'ctx, Q: RankingRuleQueryTrait>(
             } else {
                 cur_ranking_rule_index -= 1;
             }
-            if ranking_rule_scores.len() > cur_ranking_rule_index {
-                ranking_rule_scores.pop();
-            }
         };
     }
 
     let mut all_candidates = universe.clone();
     let mut valid_docids = vec![];
-    let mut valid_scores = vec![];
     let mut cur_offset = 0usize;
 
     macro_rules! maybe_add_to_results {
@@ -127,44 +104,32 @@ pub fn bucket_sort<'ctx, Q: RankingRuleQueryTrait>(
                 length,
                 logger,
                 &mut valid_docids,
-                &mut valid_scores,
                 &mut all_candidates,
                 &mut ranking_rule_universes,
                 &mut ranking_rules,
                 cur_ranking_rule_index,
                 &mut cur_offset,
                 distinct_fid,
-                &ranking_rule_scores,
                 $candidates,
             )?;
         };
     }
 
     while valid_docids.len() < length {
-        // The universe for this bucket is zero, so we don't need to sort
-        // anything, just go back to the parent ranking rule.
-        if ranking_rule_universes[cur_ranking_rule_index].is_empty()
-            || (scoring_strategy == ScoringStrategy::Skip
-                && ranking_rule_universes[cur_ranking_rule_index].len() == 1)
-        {
+        // The universe for this bucket is zero or one element, so we don't need to sort
+        // anything, just extend the results and go back to the parent ranking rule.
+        if ranking_rule_universes[cur_ranking_rule_index].len() <= 1 {
             let bucket = std::mem::take(&mut ranking_rule_universes[cur_ranking_rule_index]);
             maybe_add_to_results!(bucket);
             back!();
             continue;
         }
 
-        let Some(next_bucket) = ranking_rules[cur_ranking_rule_index].next_bucket(
-            ctx,
-            logger,
-            &ranking_rule_universes[cur_ranking_rule_index],
-        )?
-        else {
+        let Some(next_bucket) = ranking_rules[cur_ranking_rule_index].next_bucket(ctx, logger, &ranking_rule_universes[cur_ranking_rule_index])? else {
             back!();
             continue;
         };
 
-        ranking_rule_scores.push(next_bucket.score);
-
         logger.next_bucket_ranking_rule(
             cur_ranking_rule_index,
             ranking_rules[cur_ranking_rule_index].as_ref(),
@@ -178,11 +143,10 @@ pub fn bucket_sort<'ctx, Q: RankingRuleQueryTrait>(
         ranking_rule_universes[cur_ranking_rule_index] -= &next_bucket.candidates;
 
         if cur_ranking_rule_index == ranking_rules_len - 1
-            || (scoring_strategy == ScoringStrategy::Skip && next_bucket.candidates.len() <= 1)
+            || next_bucket.candidates.len() <= 1
             || cur_offset + (next_bucket.candidates.len() as usize) < from
         {
             maybe_add_to_results!(next_bucket.candidates);
-            ranking_rule_scores.pop();
             continue;
         }
 
@@ -202,7 +166,7 @@ pub fn bucket_sort<'ctx, Q: RankingRuleQueryTrait>(
         )?;
     }
 
-    Ok(BucketSortOutput { docids: valid_docids, scores: valid_scores, all_candidates })
+    Ok(BucketSortOutput { docids: valid_docids, all_candidates })
 }
 
 /// Add the candidates to the results. Take `distinct`, `from`, `length`, and `cur_offset`
@@ -215,18 +179,14 @@ fn maybe_add_to_results<'ctx, Q: RankingRuleQueryTrait>(
     logger: &mut dyn SearchLogger<Q>,
 
     valid_docids: &mut Vec<u32>,
-    valid_scores: &mut Vec<Vec<ScoreDetails>>,
     all_candidates: &mut RoaringBitmap,
 
     ranking_rule_universes: &mut [RoaringBitmap],
     ranking_rules: &mut [BoxRankingRule<'ctx, Q>],
-
     cur_ranking_rule_index: usize,
 
     cur_offset: &mut usize,
-
     distinct_fid: Option<u16>,
-    ranking_rule_scores: &[ScoreDetails],
     candidates: RoaringBitmap,
 ) -> Result<()> {
     // First apply the distinct rule on the candidates, reducing the universes if necessary
@@ -271,17 +231,13 @@ fn maybe_add_to_results<'ctx, Q: RankingRuleQueryTrait>(
             let candidates =
                 candidates.iter().take(length - valid_docids.len()).copied().collect::<Vec<_>>();
             logger.add_to_results(&candidates);
-            valid_docids.extend_from_slice(&candidates);
-            valid_scores
-                .extend(std::iter::repeat(ranking_rule_scores.to_owned()).take(candidates.len()));
+            valid_docids.extend(&candidates);
         }
     } else {
         // if we have passed the offset already, add some of the documents (up to the limit)
         let candidates = candidates.iter().take(length - valid_docids.len()).collect::<Vec<u32>>();
         logger.add_to_results(&candidates);
-        valid_docids.extend_from_slice(&candidates);
-        valid_scores
-            .extend(std::iter::repeat(ranking_rule_scores.to_owned()).take(candidates.len()));
+        valid_docids.extend(&candidates);
     }
 
     *cur_offset += candidates.len() as usize;

milli/src/search/new/db_cache.rs

@@ -4,13 +4,12 @@ use std::hash::Hash;
 
 use fxhash::FxHashMap;
 use heed::types::ByteSlice;
-use heed::{BytesEncode, Database, RoTxn};
+use heed::{BytesDecode, BytesEncode, Database, RoTxn};
 use roaring::RoaringBitmap;
 
 use super::interner::Interned;
 use super::Word;
-use crate::heed_codec::{BytesDecodeOwned, StrBEU16Codec};
-use crate::update::{merge_cbo_roaring_bitmaps, MergeFn};
+use crate::heed_codec::StrBEU16Codec;
 use crate::{
     CboRoaringBitmapCodec, CboRoaringBitmapLenCodec, Result, RoaringBitmapCodec, SearchContext,
 };
@@ -23,104 +22,50 @@ use crate::{
 #[derive(Default)]
 pub struct DatabaseCache<'ctx> {
     pub word_pair_proximity_docids:
-        FxHashMap<(u8, Interned<String>, Interned<String>), Option<Cow<'ctx, [u8]>>>,
+        FxHashMap<(u8, Interned<String>, Interned<String>), Option<&'ctx [u8]>>,
     pub word_prefix_pair_proximity_docids:
-        FxHashMap<(u8, Interned<String>, Interned<String>), Option<Cow<'ctx, [u8]>>>,
+        FxHashMap<(u8, Interned<String>, Interned<String>), Option<&'ctx [u8]>>,
     pub prefix_word_pair_proximity_docids:
-        FxHashMap<(u8, Interned<String>, Interned<String>), Option<Cow<'ctx, [u8]>>>,
-    pub word_docids: FxHashMap<Interned<String>, Option<Cow<'ctx, [u8]>>>,
-    pub exact_word_docids: FxHashMap<Interned<String>, Option<Cow<'ctx, [u8]>>>,
-    pub word_prefix_docids: FxHashMap<Interned<String>, Option<Cow<'ctx, [u8]>>>,
-    pub exact_word_prefix_docids: FxHashMap<Interned<String>, Option<Cow<'ctx, [u8]>>>,
+        FxHashMap<(u8, Interned<String>, Interned<String>), Option<&'ctx [u8]>>,
+    pub word_docids: FxHashMap<Interned<String>, Option<&'ctx [u8]>>,
+    pub exact_word_docids: FxHashMap<Interned<String>, Option<&'ctx [u8]>>,
+    pub word_prefix_docids: FxHashMap<Interned<String>, Option<&'ctx [u8]>>,
+    pub exact_word_prefix_docids: FxHashMap<Interned<String>, Option<&'ctx [u8]>>,
 
     pub words_fst: Option<fst::Set<Cow<'ctx, [u8]>>>,
-    pub word_position_docids: FxHashMap<(Interned<String>, u16), Option<Cow<'ctx, [u8]>>>,
-    pub word_prefix_position_docids: FxHashMap<(Interned<String>, u16), Option<Cow<'ctx, [u8]>>>,
+    pub word_position_docids: FxHashMap<(Interned<String>, u16), Option<&'ctx [u8]>>,
+    pub word_prefix_position_docids: FxHashMap<(Interned<String>, u16), Option<&'ctx [u8]>>,
     pub word_positions: FxHashMap<Interned<String>, Vec<u16>>,
     pub word_prefix_positions: FxHashMap<Interned<String>, Vec<u16>>,
 
-    pub word_fid_docids: FxHashMap<(Interned<String>, u16), Option<Cow<'ctx, [u8]>>>,
-    pub word_prefix_fid_docids: FxHashMap<(Interned<String>, u16), Option<Cow<'ctx, [u8]>>>,
+    pub word_fid_docids: FxHashMap<(Interned<String>, u16), Option<&'ctx [u8]>>,
+    pub word_prefix_fid_docids: FxHashMap<(Interned<String>, u16), Option<&'ctx [u8]>>,
     pub word_fids: FxHashMap<Interned<String>, Vec<u16>>,
     pub word_prefix_fids: FxHashMap<Interned<String>, Vec<u16>>,
 }
 impl<'ctx> DatabaseCache<'ctx> {
-    fn get_value<'v, K1, KC, DC>(
+    fn get_value<'v, K1, KC>(
         txn: &'ctx RoTxn,
         cache_key: K1,
         db_key: &'v KC::EItem,
-        cache: &mut FxHashMap<K1, Option<Cow<'ctx, [u8]>>>,
+        cache: &mut FxHashMap<K1, Option<&'ctx [u8]>>,
         db: Database<KC, ByteSlice>,
-    ) -> Result<Option<DC::DItem>>
+    ) -> Result<Option<&'ctx [u8]>>
     where
         K1: Copy + Eq + Hash,
         KC: BytesEncode<'v>,
-        DC: BytesDecodeOwned,
     {
-        if let Entry::Vacant(entry) = cache.entry(cache_key) {
-            let bitmap_ptr = db.get(txn, db_key)?.map(Cow::Borrowed);
-            entry.insert(bitmap_ptr);
-        }
-
-        match cache.get(&cache_key).unwrap() {
-            Some(Cow::Borrowed(bytes)) => {
-                DC::bytes_decode_owned(bytes).ok_or(heed::Error::Decoding.into()).map(Some)
+        let bitmap_ptr = match cache.entry(cache_key) {
+            Entry::Occupied(bitmap_ptr) => *bitmap_ptr.get(),
+            Entry::Vacant(entry) => {
+                let bitmap_ptr = db.get(txn, db_key)?;
+                entry.insert(bitmap_ptr);
+                bitmap_ptr
             }
-            Some(Cow::Owned(bytes)) => {
-                DC::bytes_decode_owned(bytes).ok_or(heed::Error::Decoding.into()).map(Some)
-            }
-            None => Ok(None),
-        }
-    }
-
-    fn get_value_from_keys<'v, K1, KC, DC>(
-        txn: &'ctx RoTxn,
-        cache_key: K1,
-        db_keys: &'v [KC::EItem],
-        cache: &mut FxHashMap<K1, Option<Cow<'ctx, [u8]>>>,
-        db: Database<KC, ByteSlice>,
-        merger: MergeFn,
-    ) -> Result<Option<DC::DItem>>
-    where
-        K1: Copy + Eq + Hash,
-        KC: BytesEncode<'v>,
-        DC: BytesDecodeOwned,
-        KC::EItem: Sized,
-    {
-        if let Entry::Vacant(entry) = cache.entry(cache_key) {
-            let bitmap_ptr: Option<Cow<'ctx, [u8]>> = match db_keys {
-                [] => None,
-                [key] => db.get(txn, key)?.map(Cow::Borrowed),
-                keys => {
-                    let bitmaps = keys
-                        .iter()
-                        .filter_map(|key| db.get(txn, key).transpose())
-                        .map(|v| v.map(Cow::Borrowed))
-                        .collect::<std::result::Result<Vec<Cow<[u8]>>, _>>()?;
-
-                    if bitmaps.is_empty() {
-                        None
-                    } else {
-                        Some(merger(&[], &bitmaps[..])?)
-                    }
-                }
-            };
-
-            entry.insert(bitmap_ptr);
-        }
-
-        match cache.get(&cache_key).unwrap() {
-            Some(Cow::Borrowed(bytes)) => {
-                DC::bytes_decode_owned(bytes).ok_or(heed::Error::Decoding.into()).map(Some)
-            }
-            Some(Cow::Owned(bytes)) => {
-                DC::bytes_decode_owned(bytes).ok_or(heed::Error::Decoding.into()).map(Some)
-            }
-            None => Ok(None),
-        }
+        };
+        Ok(bitmap_ptr)
     }
 }
-
 impl<'ctx> SearchContext<'ctx> {
     pub fn get_words_fst(&mut self) -> Result<fst::Set<Cow<'ctx, [u8]>>> {
         if let Some(fst) = self.db_cache.words_fst.clone() {
@@ -154,41 +99,30 @@ impl<'ctx> SearchContext<'ctx> {
 
     /// Retrieve or insert the given value in the `word_docids` database.
     fn get_db_word_docids(&mut self, word: Interned<String>) -> Result<Option<RoaringBitmap>> {
-        match &self.restricted_fids {
-            Some(restricted_fids) => {
-                let interned = self.word_interner.get(word).as_str();
-                let keys: Vec<_> = restricted_fids.iter().map(|fid| (interned, *fid)).collect();
-
-                DatabaseCache::get_value_from_keys::<_, _, CboRoaringBitmapCodec>(
-                    self.txn,
-                    word,
-                    &keys[..],
-                    &mut self.db_cache.word_docids,
-                    self.index.word_fid_docids.remap_data_type::<ByteSlice>(),
-                    merge_cbo_roaring_bitmaps,
-                )
-            }
-            None => DatabaseCache::get_value::<_, _, RoaringBitmapCodec>(
-                self.txn,
-                word,
-                self.word_interner.get(word).as_str(),
-                &mut self.db_cache.word_docids,
-                self.index.word_docids.remap_data_type::<ByteSlice>(),
-            ),
-        }
+        DatabaseCache::get_value(
+            self.txn,
+            word,
+            self.word_interner.get(word).as_str(),
+            &mut self.db_cache.word_docids,
+            self.index.word_docids.remap_data_type::<ByteSlice>(),
+        )?
+        .map(|bytes| RoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     fn get_db_exact_word_docids(
         &mut self,
         word: Interned<String>,
     ) -> Result<Option<RoaringBitmap>> {
-        DatabaseCache::get_value::<_, _, RoaringBitmapCodec>(
+        DatabaseCache::get_value(
             self.txn,
             word,
             self.word_interner.get(word).as_str(),
             &mut self.db_cache.exact_word_docids,
             self.index.exact_word_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| RoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     pub fn word_prefix_docids(&mut self, prefix: Word) -> Result<Option<RoaringBitmap>> {
@@ -216,41 +150,30 @@ impl<'ctx> SearchContext<'ctx> {
         &mut self,
         prefix: Interned<String>,
     ) -> Result<Option<RoaringBitmap>> {
-        match &self.restricted_fids {
-            Some(restricted_fids) => {
-                let interned = self.word_interner.get(prefix).as_str();
-                let keys: Vec<_> = restricted_fids.iter().map(|fid| (interned, *fid)).collect();
-
-                DatabaseCache::get_value_from_keys::<_, _, CboRoaringBitmapCodec>(
-                    self.txn,
-                    prefix,
-                    &keys[..],
-                    &mut self.db_cache.word_prefix_docids,
-                    self.index.word_prefix_fid_docids.remap_data_type::<ByteSlice>(),
-                    merge_cbo_roaring_bitmaps,
-                )
-            }
-            None => DatabaseCache::get_value::<_, _, RoaringBitmapCodec>(
-                self.txn,
-                prefix,
-                self.word_interner.get(prefix).as_str(),
-                &mut self.db_cache.word_prefix_docids,
-                self.index.word_prefix_docids.remap_data_type::<ByteSlice>(),
-            ),
-        }
+        DatabaseCache::get_value(
+            self.txn,
+            prefix,
+            self.word_interner.get(prefix).as_str(),
+            &mut self.db_cache.word_prefix_docids,
+            self.index.word_prefix_docids.remap_data_type::<ByteSlice>(),
+        )?
+        .map(|bytes| RoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     fn get_db_exact_word_prefix_docids(
         &mut self,
         prefix: Interned<String>,
     ) -> Result<Option<RoaringBitmap>> {
-        DatabaseCache::get_value::<_, _, RoaringBitmapCodec>(
+        DatabaseCache::get_value(
             self.txn,
             prefix,
             self.word_interner.get(prefix).as_str(),
             &mut self.db_cache.exact_word_prefix_docids,
             self.index.exact_word_prefix_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| RoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     pub fn get_db_word_pair_proximity_docids(
@@ -259,7 +182,7 @@ impl<'ctx> SearchContext<'ctx> {
         word2: Interned<String>,
         proximity: u8,
     ) -> Result<Option<RoaringBitmap>> {
-        DatabaseCache::get_value::<_, _, CboRoaringBitmapCodec>(
+        DatabaseCache::get_value(
             self.txn,
             (proximity, word1, word2),
             &(
@@ -269,7 +192,9 @@ impl<'ctx> SearchContext<'ctx> {
             ),
             &mut self.db_cache.word_pair_proximity_docids,
             self.index.word_pair_proximity_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| CboRoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     pub fn get_db_word_pair_proximity_docids_len(
@@ -278,7 +203,7 @@ impl<'ctx> SearchContext<'ctx> {
         word2: Interned<String>,
         proximity: u8,
     ) -> Result<Option<u64>> {
-        DatabaseCache::get_value::<_, _, CboRoaringBitmapLenCodec>(
+        DatabaseCache::get_value(
             self.txn,
             (proximity, word1, word2),
             &(
@@ -288,7 +213,11 @@ impl<'ctx> SearchContext<'ctx> {
             ),
             &mut self.db_cache.word_pair_proximity_docids,
             self.index.word_pair_proximity_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| {
+            CboRoaringBitmapLenCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into())
+        })
+        .transpose()
     }
 
     pub fn get_db_word_prefix_pair_proximity_docids(
@@ -297,7 +226,7 @@ impl<'ctx> SearchContext<'ctx> {
         prefix2: Interned<String>,
         proximity: u8,
     ) -> Result<Option<RoaringBitmap>> {
-        DatabaseCache::get_value::<_, _, CboRoaringBitmapCodec>(
+        DatabaseCache::get_value(
             self.txn,
             (proximity, word1, prefix2),
             &(
@@ -307,7 +236,9 @@ impl<'ctx> SearchContext<'ctx> {
             ),
             &mut self.db_cache.word_prefix_pair_proximity_docids,
             self.index.word_prefix_pair_proximity_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| CboRoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
     pub fn get_db_prefix_word_pair_proximity_docids(
         &mut self,
@@ -315,7 +246,7 @@ impl<'ctx> SearchContext<'ctx> {
         right: Interned<String>,
         proximity: u8,
     ) -> Result<Option<RoaringBitmap>> {
-        DatabaseCache::get_value::<_, _, CboRoaringBitmapCodec>(
+        DatabaseCache::get_value(
             self.txn,
             (proximity, left_prefix, right),
             &(
@@ -325,7 +256,9 @@ impl<'ctx> SearchContext<'ctx> {
             ),
             &mut self.db_cache.prefix_word_pair_proximity_docids,
             self.index.prefix_word_pair_proximity_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| CboRoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     pub fn get_db_word_fid_docids(
@@ -333,18 +266,15 @@ impl<'ctx> SearchContext<'ctx> {
         word: Interned<String>,
         fid: u16,
     ) -> Result<Option<RoaringBitmap>> {
-        // if the requested fid isn't in the restricted list, return None.
-        if self.restricted_fids.as_ref().map_or(false, |fids| !fids.contains(&fid)) {
-            return Ok(None);
-        }
-
-        DatabaseCache::get_value::<_, _, CboRoaringBitmapCodec>(
+        DatabaseCache::get_value(
             self.txn,
             (word, fid),
             &(self.word_interner.get(word).as_str(), fid),
             &mut self.db_cache.word_fid_docids,
             self.index.word_fid_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| CboRoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     pub fn get_db_word_prefix_fid_docids(
@@ -352,18 +282,15 @@ impl<'ctx> SearchContext<'ctx> {
         word_prefix: Interned<String>,
         fid: u16,
     ) -> Result<Option<RoaringBitmap>> {
-        // if the requested fid isn't in the restricted list, return None.
-        if self.restricted_fids.as_ref().map_or(false, |fids| !fids.contains(&fid)) {
-            return Ok(None);
-        }
-
-        DatabaseCache::get_value::<_, _, CboRoaringBitmapCodec>(
+        DatabaseCache::get_value(
             self.txn,
             (word_prefix, fid),
             &(self.word_interner.get(word_prefix).as_str(), fid),
             &mut self.db_cache.word_prefix_fid_docids,
             self.index.word_prefix_fid_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| CboRoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     pub fn get_db_word_fids(&mut self, word: Interned<String>) -> Result<Vec<u16>> {
@@ -382,7 +309,7 @@ impl<'ctx> SearchContext<'ctx> {
                 for result in remap_key_type {
                     let ((_, fid), value) = result?;
                     // filling other caches to avoid searching for them again
-                    self.db_cache.word_fid_docids.insert((word, fid), Some(Cow::Borrowed(value)));
+                    self.db_cache.word_fid_docids.insert((word, fid), Some(value));
                     fids.push(fid);
                 }
                 entry.insert(fids.clone());
@@ -408,9 +335,7 @@ impl<'ctx> SearchContext<'ctx> {
                 for result in remap_key_type {
                     let ((_, fid), value) = result?;
                     // filling other caches to avoid searching for them again
-                    self.db_cache
-                        .word_prefix_fid_docids
-                        .insert((word_prefix, fid), Some(Cow::Borrowed(value)));
+                    self.db_cache.word_prefix_fid_docids.insert((word_prefix, fid), Some(value));
                     fids.push(fid);
                 }
                 entry.insert(fids.clone());
@@ -425,13 +350,15 @@ impl<'ctx> SearchContext<'ctx> {
         word: Interned<String>,
         position: u16,
     ) -> Result<Option<RoaringBitmap>> {
-        DatabaseCache::get_value::<_, _, CboRoaringBitmapCodec>(
+        DatabaseCache::get_value(
             self.txn,
             (word, position),
             &(self.word_interner.get(word).as_str(), position),
             &mut self.db_cache.word_position_docids,
             self.index.word_position_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| CboRoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     pub fn get_db_word_prefix_position_docids(
@@ -439,13 +366,15 @@ impl<'ctx> SearchContext<'ctx> {
         word_prefix: Interned<String>,
         position: u16,
     ) -> Result<Option<RoaringBitmap>> {
-        DatabaseCache::get_value::<_, _, CboRoaringBitmapCodec>(
+        DatabaseCache::get_value(
             self.txn,
             (word_prefix, position),
             &(self.word_interner.get(word_prefix).as_str(), position),
             &mut self.db_cache.word_prefix_position_docids,
             self.index.word_prefix_position_docids.remap_data_type::<ByteSlice>(),
-        )
+        )?
+        .map(|bytes| CboRoaringBitmapCodec::bytes_decode(bytes).ok_or(heed::Error::Decoding.into()))
+        .transpose()
     }
 
     pub fn get_db_word_positions(&mut self, word: Interned<String>) -> Result<Vec<u16>> {
@@ -464,9 +393,7 @@ impl<'ctx> SearchContext<'ctx> {
                 for result in remap_key_type {
                     let ((_, position), value) = result?;
                     // filling other caches to avoid searching for them again
-                    self.db_cache
-                        .word_position_docids
-                        .insert((word, position), Some(Cow::Borrowed(value)));
+                    self.db_cache.word_position_docids.insert((word, position), Some(value));
                     positions.push(position);
                 }
                 entry.insert(positions.clone());
@@ -497,7 +424,7 @@ impl<'ctx> SearchContext<'ctx> {
                     // filling other caches to avoid searching for them again
                     self.db_cache
                         .word_prefix_position_docids
-                        .insert((word_prefix, position), Some(Cow::Borrowed(value)));
+                        .insert((word_prefix, position), Some(value));
                     positions.push(position);
                 }
                 entry.insert(positions.clone());

milli/src/search/new/distinct.rs

@@ -26,6 +26,7 @@ pub fn apply_distinct_rule(
     ctx: &mut SearchContext,
     field_id: u16,
     candidates: &RoaringBitmap,
+    // TODO: add a universe here, such that the `excluded` are a subset of the universe?
 ) -> Result<DistinctOutput> {
     let mut excluded = RoaringBitmap::new();
     let mut remaining = RoaringBitmap::new();

milli/src/search/new/exact_attribute.rs

@@ -2,7 +2,6 @@ use roaring::{MultiOps, RoaringBitmap};
 
 use super::query_graph::QueryGraph;
 use super::ranking_rules::{RankingRule, RankingRuleOutput};
-use crate::score_details::{self, ScoreDetails};
 use crate::search::new::query_graph::QueryNodeData;
 use crate::search::new::query_term::ExactTerm;
 use crate::{Result, SearchContext, SearchLogger};
@@ -207,7 +206,7 @@ impl State {
             )?;
             intersection &= &candidates;
             if !intersection.is_empty() {
-                // Although not really worth it in terms of performance,
+                // TODO: although not really worth it in terms of performance,
                 // if would be good to put this in cache for the sake of consistency
                 let candidates_with_exact_word_count = if count_all_positions < u8::MAX as usize {
                     ctx.index
@@ -245,13 +244,7 @@ impl State {
                 candidates &= universe;
                 (
                     State::AttributeStarts(query_graph.clone(), candidates_per_attribute),
-                    Some(RankingRuleOutput {
-                        query: query_graph,
-                        candidates,
-                        score: ScoreDetails::ExactAttribute(
-                            score_details::ExactAttribute::ExactMatch,
-                        ),
-                    }),
+                    Some(RankingRuleOutput { query: query_graph, candidates }),
                 )
             }
             State::AttributeStarts(query_graph, candidates_per_attribute) => {
@@ -264,24 +257,12 @@ impl State {
                 candidates &= universe;
                 (
                     State::Empty(query_graph.clone()),
-                    Some(RankingRuleOutput {
-                        query: query_graph,
-                        candidates,
-                        score: ScoreDetails::ExactAttribute(
-                            score_details::ExactAttribute::MatchesStart,
-                        ),
-                    }),
+                    Some(RankingRuleOutput { query: query_graph, candidates }),
                 )
             }
             State::Empty(query_graph) => (
                 State::Empty(query_graph.clone()),
-                Some(RankingRuleOutput {
-                    query: query_graph,
-                    candidates: universe.clone(),
-                    score: ScoreDetails::ExactAttribute(
-                        score_details::ExactAttribute::NoExactMatch,
-                    ),
-                }),
+                Some(RankingRuleOutput { query: query_graph, candidates: universe.clone() }),
             ),
         };
         (state, output)

milli/src/search/new/geo_sort.rs

@@ -8,7 +8,6 @@ use rstar::RTree;
 
 use super::ranking_rules::{RankingRule, RankingRuleOutput, RankingRuleQueryTrait};
 use crate::heed_codec::facet::{FieldDocIdFacetCodec, OrderedF64Codec};
-use crate::score_details::{self, ScoreDetails};
 use crate::{
     distance_between_two_points, lat_lng_to_xyz, GeoPoint, Index, Result, SearchContext,
     SearchLogger,
@@ -81,7 +80,7 @@ pub struct GeoSort<Q: RankingRuleQueryTrait> {
     field_ids: Option<[u16; 2]>,
     rtree: Option<RTree<GeoPoint>>,
 
-    cached_sorted_docids: VecDeque<(u32, [f64; 2])>,
+    cached_sorted_docids: VecDeque<u32>,
     geo_candidates: RoaringBitmap,
 }
 
@@ -131,7 +130,7 @@ impl<Q: RankingRuleQueryTrait> GeoSort<Q> {
                 let point = lat_lng_to_xyz(&self.point);
                 for point in rtree.nearest_neighbor_iter(&point) {
                     if self.geo_candidates.contains(point.data.0) {
-                        self.cached_sorted_docids.push_back(point.data);
+                        self.cached_sorted_docids.push_back(point.data.0);
                         if self.cached_sorted_docids.len() >= cache_size {
                             break;
                         }
@@ -143,7 +142,7 @@ impl<Q: RankingRuleQueryTrait> GeoSort<Q> {
                 let point = lat_lng_to_xyz(&opposite_of(self.point));
                 for point in rtree.nearest_neighbor_iter(&point) {
                     if self.geo_candidates.contains(point.data.0) {
-                        self.cached_sorted_docids.push_front(point.data);
+                        self.cached_sorted_docids.push_front(point.data.0);
                         if self.cached_sorted_docids.len() >= cache_size {
                             break;
                         }
@@ -178,7 +177,7 @@ impl<Q: RankingRuleQueryTrait> GeoSort<Q> {
             // 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.into_iter());
+            self.cached_sorted_docids.extend(documents.into_iter().map(|(doc_id, _)| doc_id));
         };
 
         Ok(())
@@ -221,19 +220,12 @@ impl<'ctx, Q: RankingRuleQueryTrait> RankingRule<'ctx, Q> for GeoSort<Q> {
         logger: &mut dyn SearchLogger<Q>,
         universe: &RoaringBitmap,
     ) -> Result<Option<RankingRuleOutput<Q>>> {
+        assert!(universe.len() > 1);
         let query = self.query.as_ref().unwrap().clone();
         self.geo_candidates &= universe;
 
         if self.geo_candidates.is_empty() {
-            return Ok(Some(RankingRuleOutput {
-                query,
-                candidates: universe.clone(),
-                score: ScoreDetails::GeoSort(score_details::GeoSort {
-                    target_point: self.point,
-                    ascending: self.ascending,
-                    value: None,
-                }),
-            }));
+            return Ok(Some(RankingRuleOutput { query, candidates: universe.clone() }));
         }
 
         let ascending = self.ascending;
@@ -244,16 +236,11 @@ impl<'ctx, Q: RankingRuleQueryTrait> RankingRule<'ctx, Q> for GeoSort<Q> {
                 cache.pop_back()
             }
         };
-        while let Some((id, point)) = next(&mut self.cached_sorted_docids) {
+        while let Some(id) = next(&mut self.cached_sorted_docids) {
             if self.geo_candidates.contains(id) {
                 return Ok(Some(RankingRuleOutput {
                     query,
                     candidates: RoaringBitmap::from_iter([id]),
-                    score: ScoreDetails::GeoSort(score_details::GeoSort {
-                        target_point: self.point,
-                        ascending: self.ascending,
-                        value: Some(point),
-                    }),
                 }));
             }
         }

milli/src/search/new/graph_based_ranking_rule.rs

@@ -50,7 +50,6 @@ use super::ranking_rule_graph::{
 };
 use super::small_bitmap::SmallBitmap;
 use super::{QueryGraph, RankingRule, RankingRuleOutput, SearchContext};
-use crate::score_details::Rank;
 use crate::search::new::query_term::LocatedQueryTermSubset;
 use crate::search::new::ranking_rule_graph::PathVisitor;
 use crate::{Result, TermsMatchingStrategy};
@@ -119,8 +118,6 @@ pub struct GraphBasedRankingRuleState<G: RankingRuleGraphTrait> {
     all_costs: MappedInterner<QueryNode, Vec<u64>>,
     /// An index in the first element of `all_distances`, giving the cost of the next bucket
     cur_cost: u64,
-    /// One above the highest possible cost for this rule
-    next_max_cost: u64,
 }
 
 impl<'ctx, G: RankingRuleGraphTrait> RankingRule<'ctx, QueryGraph> for GraphBasedRankingRule<G> {
@@ -134,20 +131,7 @@ impl<'ctx, G: RankingRuleGraphTrait> RankingRule<'ctx, QueryGraph> for GraphBase
         _universe: &RoaringBitmap,
         query_graph: &QueryGraph,
     ) -> Result<()> {
-        // the `next_max_cost` is the successor integer to the maximum cost of the paths in the graph.
-        //
-        // When there is a matching strategy, it also factors the additional costs of:
-        // 1. The words that are matched in phrases
-        // 2. Skipping words (by adding them to the paths with a cost)
-        let mut next_max_cost = 1;
         let removal_cost = if let Some(terms_matching_strategy) = self.terms_matching_strategy {
-            // add the cost of the phrase to the next_max_cost
-            next_max_cost += query_graph
-                .words_in_phrases_count(ctx)
-                // remove 1 from the words in phrases count, because when there is a phrase we can now have a document
-                // where only the phrase is matching, and none of the non-phrase words.
-                // With the `1` that `next_max_cost` is initialized with, this gets counted twice.
-                .saturating_sub(1) as u64;
             match terms_matching_strategy {
                 TermsMatchingStrategy::Last => {
                     let removal_order =
@@ -155,12 +139,13 @@ impl<'ctx, G: RankingRuleGraphTrait> RankingRule<'ctx, QueryGraph> for GraphBase
                     let mut forbidden_nodes =
                         SmallBitmap::for_interned_values_in(&query_graph.nodes);
                     let mut costs = query_graph.nodes.map(|_| None);
-                    // FIXME: this works because only words uses termsmatchingstrategy at the moment.
+                    let mut cost = 100;
                     for ns in removal_order {
                         for n in ns.iter() {
-                            *costs.get_mut(n) = Some((1, forbidden_nodes.clone()));
+                            *costs.get_mut(n) = Some((cost, forbidden_nodes.clone()));
                         }
                         forbidden_nodes.union(&ns);
+                        cost += 100;
                     }
                     costs
                 }
@@ -177,16 +162,12 @@ impl<'ctx, G: RankingRuleGraphTrait> RankingRule<'ctx, QueryGraph> for GraphBase
         // Then pre-compute the cost of all paths from each node to the end node
         let all_costs = graph.find_all_costs_to_end();
 
-        next_max_cost +=
-            all_costs.get(graph.query_graph.root_node).iter().copied().max().unwrap_or(0);
-
         let state = GraphBasedRankingRuleState {
             graph,
             conditions_cache: condition_docids_cache,
             dead_ends_cache,
             all_costs,
             cur_cost: 0,
-            next_max_cost,
         };
 
         self.state = Some(state);
@@ -200,15 +181,21 @@ impl<'ctx, G: RankingRuleGraphTrait> RankingRule<'ctx, QueryGraph> for GraphBase
         logger: &mut dyn SearchLogger<QueryGraph>,
         universe: &RoaringBitmap,
     ) -> Result<Option<RankingRuleOutput<QueryGraph>>> {
+        // If universe.len() <= 1, the bucket sort algorithm
+        // should not have called this function.
+        assert!(universe.len() > 1);
         // Will crash if `next_bucket` is called before `start_iteration` or after `end_iteration`,
         // should never happen
         let mut state = self.state.take().unwrap();
 
-        let all_costs = state.all_costs.get(state.graph.query_graph.root_node);
         // Retrieve the cost of the paths to compute
-        let Some(&cost) = all_costs.iter().find(|c| **c >= state.cur_cost) else {
-            self.state = None;
-            return Ok(None);
+        let Some(&cost) = state
+            .all_costs
+            .get(state.graph.query_graph.root_node)
+            .iter()
+            .find(|c| **c >= state.cur_cost) else {
+                self.state = None;
+                return Ok(None);
         };
         state.cur_cost = cost + 1;
 
@@ -220,12 +207,8 @@ impl<'ctx, G: RankingRuleGraphTrait> RankingRule<'ctx, QueryGraph> for GraphBase
             dead_ends_cache,
             all_costs,
             cur_cost: _,
-            next_max_cost,
         } = &mut state;
 
-        let rank = *next_max_cost - cost;
-        let score = G::rank_to_score(Rank { rank: rank as u32, max_rank: *next_max_cost as u32 });
-
         let mut universe = universe.clone();
 
         let mut used_conditions = SmallBitmap::for_interned_values_in(&graph.conditions_interner);
@@ -312,6 +295,8 @@ impl<'ctx, G: RankingRuleGraphTrait> RankingRule<'ctx, QueryGraph> for GraphBase
 
         // We modify the next query graph so that it only contains the subgraph
         // that was used to compute this bucket
+        // But we only do it in case the bucket length is >1, because otherwise
+        // we know the child ranking rule won't be called anyway
 
         let paths: Vec<Vec<(Option<LocatedQueryTermSubset>, LocatedQueryTermSubset)>> = good_paths
             .into_iter()
@@ -340,7 +325,7 @@ impl<'ctx, G: RankingRuleGraphTrait> RankingRule<'ctx, QueryGraph> for GraphBase
 
         self.state = Some(state);
 
-        Ok(Some(RankingRuleOutput { query: next_query_graph, candidates: bucket, score }))
+        Ok(Some(RankingRuleOutput { query: next_query_graph, candidates: bucket }))
     }
 
     fn end_iteration(

milli/src/search/new/interner.rs

@@ -32,7 +32,7 @@ impl<T> Interned<T> {
 #[derive(Clone)]
 pub struct DedupInterner<T> {
     stable_store: Vec<T>,
-    lookup: FxHashMap<T, Interned<T>>,
+    lookup: FxHashMap<T, Interned<T>>, // TODO: Arc
 }
 impl<T> Default for DedupInterner<T> {
     fn default() -> Self {

milli/src/search/new/limits.rs

@@ -1,4 +1,5 @@
 /// Maximum number of tokens we consider in a single search.
+// TODO: Loic, find proper value here so we don't overflow the interner.
 pub const MAX_TOKEN_COUNT: usize = 1_000;
 
 /// Maximum number of prefixes that can be derived from a single word.

milli/src/search/new/matches/matching_words.rs

@@ -80,9 +80,7 @@ impl MatchingWords {
                 let word = self.word_interner.get(*word);
                 // if the word is a prefix we match using starts_with.
                 if located_words.is_prefix && token.lemma().starts_with(word) {
-                    let Some((char_index, c)) =
-                        word.char_indices().take(located_words.original_char_count).last()
-                    else {
+                    let Some((char_index, c)) = word.char_indices().take(located_words.original_char_count).last() else {
                         continue;
                     };
                     let prefix_length = char_index + c.len_utf8();
@@ -258,8 +256,7 @@ pub(crate) mod tests {
         let temp_index = temp_index_with_documents();
         let rtxn = temp_index.read_txn().unwrap();
         let mut ctx = SearchContext::new(&temp_index, &rtxn);
-        let mut builder = TokenizerBuilder::default();
-        let tokenizer = builder.build();
+        let tokenizer = TokenizerBuilder::new().build();
         let tokens = tokenizer.tokenize("split this world");
         let query_terms = located_query_terms_from_tokens(&mut ctx, tokens, None).unwrap();
         let matching_words = MatchingWords::new(ctx, query_terms);