Merge branch 'main' into tmp-release-v1.11.0

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

@@ -0,0 +1,260 @@
+use std::collections::{BinaryHeap, HashSet};
+
+use actix_web::web::Data;
+use actix_web::{web, HttpRequest, HttpResponse};
+use deserr::actix_web::AwebJson;
+use index_scheduler::IndexScheduler;
+use meilisearch_types::deserr::DeserrJsonError;
+use meilisearch_types::error::deserr_codes::*;
+use meilisearch_types::error::ResponseError;
+use meilisearch_types::index_uid::IndexUid;
+use meilisearch_types::locales::Locale;
+use serde_json::Value;
+use tracing::debug;
+
+use crate::analytics::{Aggregate, Analytics};
+use crate::extractors::authentication::policies::*;
+use crate::extractors::authentication::GuardedData;
+use crate::routes::indexes::search::search_kind;
+use crate::search::{
+    add_search_rules, perform_facet_search, FacetSearchResult, HybridQuery, MatchingStrategy,
+    RankingScoreThreshold, SearchQuery, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER,
+    DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT,
+    DEFAULT_SEARCH_OFFSET,
+};
+use crate::search_queue::SearchQueue;
+
+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<InvalidHybridQuery>)]
+    pub hybrid: Option<HybridQuery>,
+    #[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>>,
+    #[deserr(default, error = DeserrJsonError<InvalidSearchRankingScoreThreshold>, default)]
+    pub ranking_score_threshold: Option<RankingScoreThreshold>,
+    #[deserr(default, error = DeserrJsonError<InvalidSearchLocales>, default)]
+    pub locales: Option<Vec<Locale>>,
+}
+
+#[derive(Default)]
+pub struct FacetSearchAggregator {
+    // 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 {
+    #[allow(clippy::field_reassign_with_default)]
+    pub fn from_query(query: &FacetSearchQuery) -> Self {
+        let FacetSearchQuery {
+            facet_query: _,
+            facet_name,
+            vector,
+            q,
+            filter,
+            matching_strategy,
+            attributes_to_search_on,
+            hybrid,
+            ranking_score_threshold,
+            locales,
+        } = query;
+
+        Self {
+            total_received: 1,
+            facet_names: Some(facet_name.clone()).into_iter().collect(),
+            additional_search_parameters_provided: q.is_some()
+                || vector.is_some()
+                || filter.is_some()
+                || *matching_strategy != MatchingStrategy::default()
+                || attributes_to_search_on.is_some()
+                || hybrid.is_some()
+                || ranking_score_threshold.is_some()
+                || locales.is_some(),
+            ..Default::default()
+        }
+    }
+
+    pub fn succeed(&mut self, result: &FacetSearchResult) {
+        let FacetSearchResult { facet_hits: _, facet_query: _, processing_time_ms } = result;
+        self.total_succeeded = 1;
+        self.time_spent.push(*processing_time_ms as usize);
+    }
+}
+
+impl Aggregate for FacetSearchAggregator {
+    fn event_name(&self) -> &'static str {
+        "Facet Searched POST"
+    }
+
+    fn aggregate(mut self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        for time in new.time_spent {
+            self.time_spent.push(time);
+        }
+
+        Box::new(Self {
+            total_received: self.total_received.saturating_add(new.total_received),
+            total_succeeded: self.total_succeeded.saturating_add(new.total_succeeded),
+            time_spent: self.time_spent,
+            facet_names: self.facet_names.union(&new.facet_names).cloned().collect(),
+            additional_search_parameters_provided: self.additional_search_parameters_provided
+                | new.additional_search_parameters_provided,
+        })
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        let Self {
+            total_received,
+            total_succeeded,
+            time_spent,
+            facet_names,
+            additional_search_parameters_provided,
+        } = *self;
+        // the index of the 99th percentage of value
+        let percentile_99th = 0.99 * (total_succeeded as f64 - 1.) + 1.;
+        // we get all the values in a sorted manner
+        let time_spent = 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);
+
+        serde_json::json!({
+            "requests": {
+                "99th_response_time":  time_spent.map(|t| format!("{:.2}", t)),
+                "total_succeeded": total_succeeded,
+                "total_failed": total_received.saturating_sub(total_succeeded), // just to be sure we never panics
+                "total_received": total_received,
+            },
+            "facets": {
+                "total_distinct_facet_count": facet_names.len(),
+                "additional_search_parameters_provided": additional_search_parameters_provided,
+            },
+        })
+    }
+}
+
+pub async fn search(
+    index_scheduler: GuardedData<ActionPolicy<{ actions::SEARCH }>, Data<IndexScheduler>>,
+    search_queue: Data<SearchQueue>,
+    index_uid: web::Path<String>,
+    params: AwebJson<FacetSearchQuery, DeserrJsonError>,
+    req: HttpRequest,
+    analytics: web::Data<Analytics>,
+) -> Result<HttpResponse, ResponseError> {
+    let index_uid = IndexUid::try_from(index_uid.into_inner())?;
+
+    let query = params.into_inner();
+    debug!(parameters = ?query, "Facet search");
+
+    let mut aggregate = FacetSearchAggregator::from_query(&query);
+
+    let facet_query = query.facet_query.clone();
+    let facet_name = query.facet_name.clone();
+    let locales = query.locales.clone().map(|l| l.into_iter().map(Into::into).collect());
+    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.filter, search_rules);
+    }
+
+    let index = index_scheduler.index(&index_uid)?;
+    let features = index_scheduler.features();
+    let search_kind = search_kind(&search_query, &index_scheduler, &index, features)?;
+    let permit = search_queue.try_get_search_permit().await?;
+    let search_result = tokio::task::spawn_blocking(move || {
+        perform_facet_search(
+            &index,
+            search_query,
+            facet_query,
+            facet_name,
+            search_kind,
+            index_scheduler.features(),
+            locales,
+        )
+    })
+    .await;
+    permit.drop().await;
+    let search_result = search_result?;
+
+    if let Ok(ref search_result) = search_result {
+        aggregate.succeed(search_result);
+    }
+    analytics.publish(aggregate, &req);
+
+    let search_result = search_result?;
+
+    debug!(returns = ?search_result, "Facet search");
+    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,
+            hybrid,
+            ranking_score_threshold,
+            locales,
+        } = value;
+
+        SearchQuery {
+            q,
+            offset: DEFAULT_SEARCH_OFFSET(),
+            limit: DEFAULT_SEARCH_LIMIT(),
+            page: None,
+            hits_per_page: None,
+            attributes_to_retrieve: None,
+            retrieve_vectors: false,
+            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,
+            distinct: 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,
+            hybrid,
+            ranking_score_threshold,
+            locales,
+        }
+    }
+}

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

@@ -0,0 +1,318 @@
+use std::collections::BTreeSet;
+use std::convert::Infallible;
+
+use actix_web::web::Data;
+use actix_web::{web, HttpRequest, HttpResponse};
+use deserr::actix_web::{AwebJson, AwebQueryParameter};
+use deserr::{DeserializeError, Deserr, ValuePointerRef};
+use index_scheduler::IndexScheduler;
+use meilisearch_types::deserr::query_params::Param;
+use meilisearch_types::deserr::{immutable_field_error, DeserrJsonError, DeserrQueryParamError};
+use meilisearch_types::error::deserr_codes::*;
+use meilisearch_types::error::{Code, ResponseError};
+use meilisearch_types::index_uid::IndexUid;
+use meilisearch_types::milli::{self, FieldDistribution, Index};
+use meilisearch_types::tasks::KindWithContent;
+use serde::Serialize;
+use time::OffsetDateTime;
+use tracing::debug;
+
+use super::{get_task_id, Pagination, SummarizedTaskView, PAGINATION_DEFAULT_LIMIT};
+use crate::analytics::{Aggregate, Analytics};
+use crate::extractors::authentication::policies::*;
+use crate::extractors::authentication::{AuthenticationError, GuardedData};
+use crate::extractors::sequential_extractor::SeqHandler;
+use crate::routes::is_dry_run;
+use crate::Opt;
+
+pub mod documents;
+pub mod facet_search;
+pub mod search;
+mod search_analytics;
+pub mod settings;
+mod settings_analytics;
+pub mod similar;
+mod similar_analytics;
+
+pub fn configure(cfg: &mut web::ServiceConfig) {
+    cfg.service(
+        web::resource("")
+            .route(web::get().to(list_indexes))
+            .route(web::post().to(SeqHandler(create_index))),
+    )
+    .service(
+        web::scope("/{index_uid}")
+            .service(
+                web::resource("")
+                    .route(web::get().to(SeqHandler(get_index)))
+                    .route(web::patch().to(SeqHandler(update_index)))
+                    .route(web::delete().to(SeqHandler(delete_index))),
+            )
+            .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("/similar").configure(similar::configure))
+            .service(web::scope("/settings").configure(settings::configure)),
+    );
+}
+
+#[derive(Debug, Serialize, Clone)]
+#[serde(rename_all = "camelCase")]
+pub struct IndexView {
+    pub uid: String,
+    #[serde(with = "time::serde::rfc3339")]
+    pub created_at: OffsetDateTime,
+    #[serde(with = "time::serde::rfc3339")]
+    pub updated_at: OffsetDateTime,
+    pub primary_key: Option<String>,
+}
+
+impl IndexView {
+    fn new(uid: String, index: &Index) -> Result<IndexView, milli::Error> {
+        // It is important that this function does not keep the Index handle or a clone of it, because
+        // `list_indexes` relies on this property to avoid opening all indexes at once.
+        let rtxn = index.read_txn()?;
+        Ok(IndexView {
+            uid,
+            created_at: index.created_at(&rtxn)?,
+            updated_at: index.updated_at(&rtxn)?,
+            primary_key: index.primary_key(&rtxn)?.map(String::from),
+        })
+    }
+}
+
+#[derive(Deserr, Debug, Clone, Copy)]
+#[deserr(error = DeserrQueryParamError, rename_all = camelCase, deny_unknown_fields)]
+pub struct ListIndexes {
+    #[deserr(default, error = DeserrQueryParamError<InvalidIndexOffset>)]
+    pub offset: Param<usize>,
+    #[deserr(default = Param(PAGINATION_DEFAULT_LIMIT), error = DeserrQueryParamError<InvalidIndexLimit>)]
+    pub limit: Param<usize>,
+}
+impl ListIndexes {
+    fn as_pagination(self) -> Pagination {
+        Pagination { offset: self.offset.0, limit: self.limit.0 }
+    }
+}
+
+pub async fn list_indexes(
+    index_scheduler: GuardedData<ActionPolicy<{ actions::INDEXES_GET }>, Data<IndexScheduler>>,
+    paginate: AwebQueryParameter<ListIndexes, DeserrQueryParamError>,
+) -> Result<HttpResponse, ResponseError> {
+    debug!(parameters = ?paginate, "List indexes");
+    let filters = index_scheduler.filters();
+    let indexes: Vec<Option<IndexView>> =
+        index_scheduler.try_for_each_index(|uid, index| -> Result<Option<IndexView>, _> {
+            if !filters.is_index_authorized(uid) {
+                return Ok(None);
+            }
+            Ok(Some(IndexView::new(uid.to_string(), index)?))
+        })?;
+    // Won't cause to open all indexes because IndexView doesn't keep the `Index` opened.
+    let indexes: Vec<IndexView> = indexes.into_iter().flatten().collect();
+    let ret = paginate.as_pagination().auto_paginate_sized(indexes.into_iter());
+
+    debug!(returns = ?ret, "List indexes");
+    Ok(HttpResponse::Ok().json(ret))
+}
+
+#[derive(Deserr, Debug)]
+#[deserr(error = DeserrJsonError, rename_all = camelCase, deny_unknown_fields)]
+pub struct IndexCreateRequest {
+    #[deserr(error = DeserrJsonError<InvalidIndexUid>, missing_field_error = DeserrJsonError::missing_index_uid)]
+    uid: IndexUid,
+    #[deserr(default, error = DeserrJsonError<InvalidIndexPrimaryKey>)]
+    primary_key: Option<String>,
+}
+
+#[derive(Serialize)]
+struct IndexCreatedAggregate {
+    primary_key: BTreeSet<String>,
+}
+
+impl Aggregate for IndexCreatedAggregate {
+    fn event_name(&self) -> &'static str {
+        "Index Created"
+    }
+
+    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        Box::new(Self { primary_key: self.primary_key.union(&new.primary_key).cloned().collect() })
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        serde_json::to_value(*self).unwrap_or_default()
+    }
+}
+
+pub async fn create_index(
+    index_scheduler: GuardedData<ActionPolicy<{ actions::INDEXES_CREATE }>, Data<IndexScheduler>>,
+    body: AwebJson<IndexCreateRequest, DeserrJsonError>,
+    req: HttpRequest,
+    opt: web::Data<Opt>,
+    analytics: web::Data<Analytics>,
+) -> Result<HttpResponse, ResponseError> {
+    debug!(parameters = ?body, "Create index");
+    let IndexCreateRequest { primary_key, uid } = body.into_inner();
+
+    let allow_index_creation = index_scheduler.filters().allow_index_creation(&uid);
+    if allow_index_creation {
+        analytics.publish(
+            IndexCreatedAggregate { primary_key: primary_key.iter().cloned().collect() },
+            &req,
+        );
+
+        let task = KindWithContent::IndexCreation { index_uid: uid.to_string(), primary_key };
+        let uid = get_task_id(&req, &opt)?;
+        let dry_run = is_dry_run(&req, &opt)?;
+        let task: SummarizedTaskView =
+            tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run))
+                .await??
+                .into();
+        debug!(returns = ?task, "Create index");
+
+        Ok(HttpResponse::Accepted().json(task))
+    } else {
+        Err(AuthenticationError::InvalidToken.into())
+    }
+}
+
+fn deny_immutable_fields_index(
+    field: &str,
+    accepted: &[&str],
+    location: ValuePointerRef,
+) -> DeserrJsonError {
+    match field {
+        "uid" => immutable_field_error(field, accepted, Code::ImmutableIndexUid),
+        "createdAt" => immutable_field_error(field, accepted, Code::ImmutableIndexCreatedAt),
+        "updatedAt" => immutable_field_error(field, accepted, Code::ImmutableIndexUpdatedAt),
+        _ => deserr::take_cf_content(DeserrJsonError::<BadRequest>::error::<Infallible>(
+            None,
+            deserr::ErrorKind::UnknownKey { key: field, accepted },
+            location,
+        )),
+    }
+}
+
+#[derive(Deserr, Debug)]
+#[deserr(error = DeserrJsonError, rename_all = camelCase, deny_unknown_fields = deny_immutable_fields_index)]
+pub struct UpdateIndexRequest {
+    #[deserr(default, error = DeserrJsonError<InvalidIndexPrimaryKey>)]
+    primary_key: Option<String>,
+}
+
+pub async fn get_index(
+    index_scheduler: GuardedData<ActionPolicy<{ actions::INDEXES_GET }>, Data<IndexScheduler>>,
+    index_uid: web::Path<String>,
+) -> Result<HttpResponse, ResponseError> {
+    let index_uid = IndexUid::try_from(index_uid.into_inner())?;
+
+    let index = index_scheduler.index(&index_uid)?;
+    let index_view = IndexView::new(index_uid.into_inner(), &index)?;
+
+    debug!(returns = ?index_view, "Get index");
+
+    Ok(HttpResponse::Ok().json(index_view))
+}
+
+#[derive(Serialize)]
+struct IndexUpdatedAggregate {
+    primary_key: BTreeSet<String>,
+}
+
+impl Aggregate for IndexUpdatedAggregate {
+    fn event_name(&self) -> &'static str {
+        "Index Updated"
+    }
+
+    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        Box::new(Self { primary_key: self.primary_key.union(&new.primary_key).cloned().collect() })
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        serde_json::to_value(*self).unwrap_or_default()
+    }
+}
+pub async fn update_index(
+    index_scheduler: GuardedData<ActionPolicy<{ actions::INDEXES_UPDATE }>, Data<IndexScheduler>>,
+    index_uid: web::Path<String>,
+    body: AwebJson<UpdateIndexRequest, DeserrJsonError>,
+    req: HttpRequest,
+    opt: web::Data<Opt>,
+    analytics: web::Data<Analytics>,
+) -> Result<HttpResponse, ResponseError> {
+    debug!(parameters = ?body, "Update index");
+    let index_uid = IndexUid::try_from(index_uid.into_inner())?;
+    let body = body.into_inner();
+    analytics.publish(
+        IndexUpdatedAggregate { primary_key: body.primary_key.iter().cloned().collect() },
+        &req,
+    );
+
+    let task = KindWithContent::IndexUpdate {
+        index_uid: index_uid.into_inner(),
+        primary_key: body.primary_key,
+    };
+
+    let uid = get_task_id(&req, &opt)?;
+    let dry_run = is_dry_run(&req, &opt)?;
+    let task: SummarizedTaskView =
+        tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run))
+            .await??
+            .into();
+
+    debug!(returns = ?task, "Update index");
+    Ok(HttpResponse::Accepted().json(task))
+}
+
+pub async fn delete_index(
+    index_scheduler: GuardedData<ActionPolicy<{ actions::INDEXES_DELETE }>, Data<IndexScheduler>>,
+    index_uid: web::Path<String>,
+    req: HttpRequest,
+    opt: web::Data<Opt>,
+) -> Result<HttpResponse, ResponseError> {
+    let index_uid = IndexUid::try_from(index_uid.into_inner())?;
+    let task = KindWithContent::IndexDeletion { index_uid: index_uid.into_inner() };
+    let uid = get_task_id(&req, &opt)?;
+    let dry_run = is_dry_run(&req, &opt)?;
+    let task: SummarizedTaskView =
+        tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run))
+            .await??
+            .into();
+    debug!(returns = ?task, "Delete index");
+
+    Ok(HttpResponse::Accepted().json(task))
+}
+
+/// Stats of an `Index`, as known to the `stats` route.
+#[derive(Serialize, Debug)]
+#[serde(rename_all = "camelCase")]
+pub struct IndexStats {
+    /// Number of documents in the index
+    pub number_of_documents: u64,
+    /// Whether the index is currently performing indexation, according to the scheduler.
+    pub is_indexing: bool,
+    /// Association of every field name with the number of times it occurs in the documents.
+    pub field_distribution: FieldDistribution,
+}
+
+impl From<index_scheduler::IndexStats> for IndexStats {
+    fn from(stats: index_scheduler::IndexStats) -> Self {
+        IndexStats {
+            number_of_documents: stats.inner_stats.number_of_documents,
+            is_indexing: stats.is_indexing,
+            field_distribution: stats.inner_stats.field_distribution,
+        }
+    }
+}
+
+pub async fn get_index_stats(
+    index_scheduler: GuardedData<ActionPolicy<{ actions::STATS_GET }>, Data<IndexScheduler>>,
+    index_uid: web::Path<String>,
+) -> Result<HttpResponse, ResponseError> {
+    let index_uid = IndexUid::try_from(index_uid.into_inner())?;
+    let stats = IndexStats::from(index_scheduler.index_stats(&index_uid)?);
+
+    debug!(returns = ?stats, "Get index stats");
+    Ok(HttpResponse::Ok().json(stats))
+}

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

@@ -0,0 +1,385 @@
+use actix_web::web::Data;
+use actix_web::{web, HttpRequest, HttpResponse};
+use deserr::actix_web::{AwebJson, AwebQueryParameter};
+use index_scheduler::{IndexScheduler, RoFeatures};
+use meilisearch_types::deserr::query_params::Param;
+use meilisearch_types::deserr::{DeserrJsonError, DeserrQueryParamError};
+use meilisearch_types::error::deserr_codes::*;
+use meilisearch_types::error::ResponseError;
+use meilisearch_types::index_uid::IndexUid;
+use meilisearch_types::locales::Locale;
+use meilisearch_types::milli;
+use meilisearch_types::serde_cs::vec::CS;
+use serde_json::Value;
+use tracing::debug;
+
+use crate::analytics::Analytics;
+use crate::error::MeilisearchHttpError;
+use crate::extractors::authentication::policies::*;
+use crate::extractors::authentication::GuardedData;
+use crate::extractors::sequential_extractor::SeqHandler;
+use crate::metrics::MEILISEARCH_DEGRADED_SEARCH_REQUESTS;
+use crate::routes::indexes::search_analytics::{SearchAggregator, SearchGET, SearchPOST};
+use crate::search::{
+    add_search_rules, perform_search, HybridQuery, MatchingStrategy, RankingScoreThreshold,
+    RetrieveVectors, SearchKind, SearchQuery, SemanticRatio, DEFAULT_CROP_LENGTH,
+    DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG,
+    DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET, DEFAULT_SEMANTIC_RATIO,
+};
+use crate::search_queue::SearchQueue;
+
+pub fn configure(cfg: &mut web::ServiceConfig) {
+    cfg.service(
+        web::resource("")
+            .route(web::get().to(SeqHandler(search_with_url_query)))
+            .route(web::post().to(SeqHandler(search_with_post))),
+    );
+}
+
+#[derive(Debug, deserr::Deserr)]
+#[deserr(error = DeserrQueryParamError, rename_all = camelCase, deny_unknown_fields)]
+pub struct SearchQueryGet {
+    #[deserr(default, error = DeserrQueryParamError<InvalidSearchQ>)]
+    q: Option<String>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSearchVector>)]
+    vector: Option<CS<f32>>,
+    #[deserr(default = Param(DEFAULT_SEARCH_OFFSET()), error = DeserrQueryParamError<InvalidSearchOffset>)]
+    offset: Param<usize>,
+    #[deserr(default = Param(DEFAULT_SEARCH_LIMIT()), error = DeserrQueryParamError<InvalidSearchLimit>)]
+    limit: Param<usize>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSearchPage>)]
+    page: Option<Param<usize>>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSearchHitsPerPage>)]
+    hits_per_page: Option<Param<usize>>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSearchAttributesToRetrieve>)]
+    attributes_to_retrieve: Option<CS<String>>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSearchRetrieveVectors>)]
+    retrieve_vectors: Param<bool>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSearchAttributesToCrop>)]
+    attributes_to_crop: Option<CS<String>>,
+    #[deserr(default = Param(DEFAULT_CROP_LENGTH()), error = DeserrQueryParamError<InvalidSearchCropLength>)]
+    crop_length: Param<usize>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSearchAttributesToHighlight>)]
+    attributes_to_highlight: Option<CS<String>>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSearchFilter>)]
+    filter: Option<String>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSearchSort>)]
+    sort: Option<String>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSearchDistinct>)]
+    distinct: 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>)]
+    highlight_pre_tag: String,
+    #[deserr( default = DEFAULT_HIGHLIGHT_POST_TAG(), error = DeserrQueryParamError<InvalidSearchHighlightPostTag>)]
+    highlight_post_tag: String,
+    #[deserr(default = DEFAULT_CROP_MARKER(), error = DeserrQueryParamError<InvalidSearchCropMarker>)]
+    crop_marker: String,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSearchMatchingStrategy>)]
+    matching_strategy: MatchingStrategy,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSearchAttributesToSearchOn>)]
+    pub attributes_to_search_on: Option<CS<String>>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidEmbedder>)]
+    pub hybrid_embedder: Option<String>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSearchSemanticRatio>)]
+    pub hybrid_semantic_ratio: Option<SemanticRatioGet>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSearchRankingScoreThreshold>)]
+    pub ranking_score_threshold: Option<RankingScoreThresholdGet>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSearchLocales>)]
+    pub locales: Option<CS<Locale>>,
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, deserr::Deserr)]
+#[deserr(try_from(String) = TryFrom::try_from -> InvalidSearchRankingScoreThreshold)]
+pub struct RankingScoreThresholdGet(RankingScoreThreshold);
+
+impl std::convert::TryFrom<String> for RankingScoreThresholdGet {
+    type Error = InvalidSearchRankingScoreThreshold;
+
+    fn try_from(s: String) -> Result<Self, Self::Error> {
+        let f: f64 = s.parse().map_err(|_| InvalidSearchRankingScoreThreshold)?;
+        Ok(RankingScoreThresholdGet(RankingScoreThreshold::try_from(f)?))
+    }
+}
+
+#[derive(Debug, Clone, Copy, Default, PartialEq, deserr::Deserr)]
+#[deserr(try_from(String) = TryFrom::try_from -> InvalidSearchSemanticRatio)]
+pub struct SemanticRatioGet(SemanticRatio);
+
+impl std::convert::TryFrom<String> for SemanticRatioGet {
+    type Error = InvalidSearchSemanticRatio;
+
+    fn try_from(s: String) -> Result<Self, Self::Error> {
+        let f: f32 = s.parse().map_err(|_| InvalidSearchSemanticRatio)?;
+        Ok(SemanticRatioGet(SemanticRatio::try_from(f)?))
+    }
+}
+
+impl std::ops::Deref for SemanticRatioGet {
+    type Target = SemanticRatio;
+
+    fn deref(&self) -> &Self::Target {
+        &self.0
+    }
+}
+
+impl TryFrom<SearchQueryGet> for SearchQuery {
+    type Error = ResponseError;
+
+    fn try_from(other: SearchQueryGet) -> Result<Self, Self::Error> {
+        let filter = match other.filter {
+            Some(f) => match serde_json::from_str(&f) {
+                Ok(v) => Some(v),
+                _ => Some(Value::String(f)),
+            },
+            None => None,
+        };
+
+        let hybrid = match (other.hybrid_embedder, other.hybrid_semantic_ratio) {
+            (None, None) => None,
+            (None, Some(_)) => {
+                return Err(ResponseError::from_msg(
+                    "`hybridEmbedder` is mandatory when `hybridSemanticRatio` is present".into(),
+                    meilisearch_types::error::Code::InvalidHybridQuery,
+                ));
+            }
+            (Some(embedder), None) => {
+                Some(HybridQuery { semantic_ratio: DEFAULT_SEMANTIC_RATIO(), embedder })
+            }
+            (Some(embedder), Some(semantic_ratio)) => {
+                Some(HybridQuery { semantic_ratio: *semantic_ratio, embedder })
+            }
+        };
+
+        if other.vector.is_some() && hybrid.is_none() {
+            return Err(ResponseError::from_msg(
+                "`hybridEmbedder` is mandatory when `vector` is present".into(),
+                meilisearch_types::error::Code::MissingSearchHybrid,
+            ));
+        }
+
+        Ok(Self {
+            q: other.q,
+            vector: other.vector.map(CS::into_inner),
+            offset: other.offset.0,
+            limit: other.limit.0,
+            page: other.page.as_deref().copied(),
+            hits_per_page: other.hits_per_page.as_deref().copied(),
+            attributes_to_retrieve: other.attributes_to_retrieve.map(|o| o.into_iter().collect()),
+            retrieve_vectors: other.retrieve_vectors.0,
+            attributes_to_crop: other.attributes_to_crop.map(|o| o.into_iter().collect()),
+            crop_length: other.crop_length.0,
+            attributes_to_highlight: other.attributes_to_highlight.map(|o| o.into_iter().collect()),
+            filter,
+            sort: other.sort.map(|attr| fix_sort_query_parameters(&attr)),
+            distinct: other.distinct,
+            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()),
+            hybrid,
+            ranking_score_threshold: other.ranking_score_threshold.map(|o| o.0),
+            locales: other.locales.map(|o| o.into_iter().collect()),
+        })
+    }
+}
+
+// TODO: TAMO: split on :asc, and :desc, instead of doing some weird things
+
+/// Transform the sort query parameter into something that matches the post expected format.
+fn fix_sort_query_parameters(sort_query: &str) -> Vec<String> {
+    let mut sort_parameters = Vec::new();
+    let mut merge = false;
+    for current_sort in sort_query.trim_matches('"').split(',').map(|s| s.trim()) {
+        if current_sort.starts_with("_geoPoint(") {
+            sort_parameters.push(current_sort.to_string());
+            merge = true;
+        } else if merge && !sort_parameters.is_empty() {
+            let s = sort_parameters.last_mut().unwrap();
+            s.push(',');
+            s.push_str(current_sort);
+            if current_sort.ends_with("):desc") || current_sort.ends_with("):asc") {
+                merge = false;
+            }
+        } else {
+            sort_parameters.push(current_sort.to_string());
+            merge = false;
+        }
+    }
+    sort_parameters
+}
+
+pub async fn search_with_url_query(
+    index_scheduler: GuardedData<ActionPolicy<{ actions::SEARCH }>, Data<IndexScheduler>>,
+    search_queue: web::Data<SearchQueue>,
+    index_uid: web::Path<String>,
+    params: AwebQueryParameter<SearchQueryGet, DeserrQueryParamError>,
+    req: HttpRequest,
+    analytics: web::Data<Analytics>,
+) -> Result<HttpResponse, ResponseError> {
+    debug!(parameters = ?params, "Search get");
+    let index_uid = IndexUid::try_from(index_uid.into_inner())?;
+
+    let mut query: SearchQuery = params.into_inner().try_into()?;
+
+    // Tenant token search_rules.
+    if let Some(search_rules) = index_scheduler.filters().get_index_search_rules(&index_uid) {
+        add_search_rules(&mut query.filter, search_rules);
+    }
+
+    let mut aggregate = SearchAggregator::<SearchGET>::from_query(&query);
+
+    let index = index_scheduler.index(&index_uid)?;
+    let features = index_scheduler.features();
+
+    let search_kind = search_kind(&query, index_scheduler.get_ref(), &index, features)?;
+    let retrieve_vector = RetrieveVectors::new(query.retrieve_vectors, features)?;
+    let permit = search_queue.try_get_search_permit().await?;
+    let search_result = tokio::task::spawn_blocking(move || {
+        perform_search(&index, query, search_kind, retrieve_vector, index_scheduler.features())
+    })
+    .await;
+    permit.drop().await;
+    let search_result = search_result?;
+    if let Ok(ref search_result) = search_result {
+        aggregate.succeed(search_result);
+    }
+    analytics.publish(aggregate, &req);
+
+    let search_result = search_result?;
+
+    debug!(returns = ?search_result, "Search get");
+    Ok(HttpResponse::Ok().json(search_result))
+}
+
+pub async fn search_with_post(
+    index_scheduler: GuardedData<ActionPolicy<{ actions::SEARCH }>, Data<IndexScheduler>>,
+    search_queue: web::Data<SearchQueue>,
+    index_uid: web::Path<String>,
+    params: AwebJson<SearchQuery, DeserrJsonError>,
+    req: HttpRequest,
+    analytics: web::Data<Analytics>,
+) -> Result<HttpResponse, ResponseError> {
+    let index_uid = IndexUid::try_from(index_uid.into_inner())?;
+
+    let mut query = params.into_inner();
+    debug!(parameters = ?query, "Search post");
+
+    // Tenant token search_rules.
+    if let Some(search_rules) = index_scheduler.filters().get_index_search_rules(&index_uid) {
+        add_search_rules(&mut query.filter, search_rules);
+    }
+
+    let mut aggregate = SearchAggregator::<SearchPOST>::from_query(&query);
+
+    let index = index_scheduler.index(&index_uid)?;
+
+    let features = index_scheduler.features();
+
+    let search_kind = search_kind(&query, index_scheduler.get_ref(), &index, features)?;
+    let retrieve_vectors = RetrieveVectors::new(query.retrieve_vectors, features)?;
+
+    let permit = search_queue.try_get_search_permit().await?;
+    let search_result = tokio::task::spawn_blocking(move || {
+        perform_search(&index, query, search_kind, retrieve_vectors, index_scheduler.features())
+    })
+    .await;
+    permit.drop().await;
+    let search_result = search_result?;
+    if let Ok(ref search_result) = search_result {
+        aggregate.succeed(search_result);
+        if search_result.degraded {
+            MEILISEARCH_DEGRADED_SEARCH_REQUESTS.inc();
+        }
+    }
+    analytics.publish(aggregate, &req);
+
+    let search_result = search_result?;
+
+    debug!(returns = ?search_result, "Search post");
+    Ok(HttpResponse::Ok().json(search_result))
+}
+
+pub fn search_kind(
+    query: &SearchQuery,
+    index_scheduler: &IndexScheduler,
+    index: &milli::Index,
+    features: RoFeatures,
+) -> Result<SearchKind, ResponseError> {
+    if query.vector.is_some() {
+        features.check_vector("Passing `vector` as a parameter")?;
+    }
+    if query.hybrid.is_some() {
+        features.check_vector("Passing `hybrid` as a parameter")?;
+    }
+
+    // handle with care, the order of cases matters, the semantics is subtle
+    match (query.q.as_deref(), &query.hybrid, query.vector.as_deref()) {
+        // empty query, no vector => placeholder search
+        (Some(q), _, None) if q.trim().is_empty() => Ok(SearchKind::KeywordOnly),
+        // no query, no vector => placeholder search
+        (None, _, None) => Ok(SearchKind::KeywordOnly),
+        // hybrid.semantic_ratio == 1.0 => vector
+        (_, Some(HybridQuery { semantic_ratio, embedder }), v) if **semantic_ratio == 1.0 => {
+            SearchKind::semantic(index_scheduler, index, embedder, v.map(|v| v.len()))
+        }
+        // hybrid.semantic_ratio == 0.0 => keyword
+        (_, Some(HybridQuery { semantic_ratio, embedder: _ }), _) if **semantic_ratio == 0.0 => {
+            Ok(SearchKind::KeywordOnly)
+        }
+        // no query, hybrid, vector => semantic
+        (None, Some(HybridQuery { semantic_ratio: _, embedder }), Some(v)) => {
+            SearchKind::semantic(index_scheduler, index, embedder, Some(v.len()))
+        }
+        // query, no hybrid, no vector => keyword
+        (Some(_), None, None) => Ok(SearchKind::KeywordOnly),
+        // query, hybrid, maybe vector => hybrid
+        (Some(_), Some(HybridQuery { semantic_ratio, embedder }), v) => SearchKind::hybrid(
+            index_scheduler,
+            index,
+            embedder,
+            **semantic_ratio,
+            v.map(|v| v.len()),
+        ),
+
+        (_, None, Some(_)) => Err(MeilisearchHttpError::MissingSearchHybrid.into()),
+    }
+}
+
+#[cfg(test)]
+mod test {
+    use super::*;
+
+    #[test]
+    fn test_fix_sort_query_parameters() {
+        let sort = fix_sort_query_parameters("_geoPoint(12, 13):asc");
+        assert_eq!(sort, vec!["_geoPoint(12,13):asc".to_string()]);
+        let sort = fix_sort_query_parameters("doggo:asc,_geoPoint(12.45,13.56):desc");
+        assert_eq!(sort, vec!["doggo:asc".to_string(), "_geoPoint(12.45,13.56):desc".to_string(),]);
+        let sort = fix_sort_query_parameters(
+            "doggo:asc , _geoPoint(12.45, 13.56, 2590352):desc , catto:desc",
+        );
+        assert_eq!(
+            sort,
+            vec![
+                "doggo:asc".to_string(),
+                "_geoPoint(12.45,13.56,2590352):desc".to_string(),
+                "catto:desc".to_string(),
+            ]
+        );
+        let sort = fix_sort_query_parameters("doggo:asc , _geoPoint(1, 2), catto:desc");
+        // This is ugly but eh, I don't want to write a full parser just for this unused route
+        assert_eq!(sort, vec!["doggo:asc".to_string(), "_geoPoint(1,2),catto:desc".to_string(),]);
+    }
+}

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

@@ -0,0 +1,485 @@
+use once_cell::sync::Lazy;
+use regex::Regex;
+use serde_json::{json, Value};
+use std::collections::{BTreeSet, BinaryHeap, HashMap};
+
+use meilisearch_types::locales::Locale;
+
+use crate::{
+    aggregate_methods,
+    analytics::{Aggregate, AggregateMethod},
+    search::{
+        SearchQuery, SearchResult, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER,
+        DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT,
+        DEFAULT_SEMANTIC_RATIO,
+    },
+};
+
+aggregate_methods!(
+    SearchGET => "Documents Searched GET",
+    SearchPOST => "Documents Searched POST",
+);
+
+#[derive(Default)]
+pub struct SearchAggregator<Method: AggregateMethod> {
+    // requests
+    total_received: usize,
+    total_succeeded: usize,
+    total_degraded: usize,
+    total_used_negative_operator: usize,
+    time_spent: BinaryHeap<usize>,
+
+    // sort
+    sort_with_geo_point: bool,
+    // every time a request has a filter, this field must be incremented by the number of terms it contains
+    sort_sum_of_criteria_terms: usize,
+    // every time a request has a filter, this field must be incremented by one
+    sort_total_number_of_criteria: usize,
+
+    // distinct
+    distinct: bool,
+
+    // filter
+    filter_with_geo_radius: bool,
+    filter_with_geo_bounding_box: bool,
+    // every time a request has a filter, this field must be incremented by the number of terms it contains
+    filter_sum_of_criteria_terms: usize,
+    // every time a request has a filter, this field must be incremented by one
+    filter_total_number_of_criteria: usize,
+    used_syntax: HashMap<String, usize>,
+
+    // attributes_to_search_on
+    // every time a search is done using attributes_to_search_on
+    attributes_to_search_on_total_number_of_uses: usize,
+
+    // q
+    // 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,
+    // Whether the semantic ratio passed to a hybrid search equals the default ratio.
+    semantic_ratio: bool,
+    hybrid: bool,
+    retrieve_vectors: bool,
+
+    // every time a search is done, we increment the counter linked to the used settings
+    matching_strategy: HashMap<String, usize>,
+
+    // List of the unique Locales passed as parameter
+    locales: BTreeSet<Locale>,
+
+    // pagination
+    max_limit: usize,
+    max_offset: usize,
+    finite_pagination: usize,
+
+    // formatting
+    max_attributes_to_retrieve: usize,
+    max_attributes_to_highlight: usize,
+    highlight_pre_tag: bool,
+    highlight_post_tag: bool,
+    max_attributes_to_crop: usize,
+    crop_marker: bool,
+    show_matches_position: bool,
+    crop_length: bool,
+
+    // facets
+    facets_sum_of_terms: usize,
+    facets_total_number_of_facets: usize,
+
+    // scoring
+    show_ranking_score: bool,
+    show_ranking_score_details: bool,
+    ranking_score_threshold: bool,
+
+    marker: std::marker::PhantomData<Method>,
+}
+
+impl<Method: AggregateMethod> SearchAggregator<Method> {
+    #[allow(clippy::field_reassign_with_default)]
+    pub fn from_query(query: &SearchQuery) -> Self {
+        let SearchQuery {
+            q,
+            vector,
+            offset,
+            limit,
+            page,
+            hits_per_page,
+            attributes_to_retrieve: _,
+            retrieve_vectors,
+            attributes_to_crop: _,
+            crop_length,
+            attributes_to_highlight: _,
+            show_matches_position,
+            show_ranking_score,
+            show_ranking_score_details,
+            filter,
+            sort,
+            distinct,
+            facets: _,
+            highlight_pre_tag,
+            highlight_post_tag,
+            crop_marker,
+            matching_strategy,
+            attributes_to_search_on,
+            hybrid,
+            ranking_score_threshold,
+            locales,
+        } = query;
+
+        let mut ret = Self::default();
+
+        ret.total_received = 1;
+
+        if let Some(ref sort) = sort {
+            ret.sort_total_number_of_criteria = 1;
+            ret.sort_with_geo_point = sort.iter().any(|s| s.contains("_geoPoint("));
+            ret.sort_sum_of_criteria_terms = sort.len();
+        }
+
+        ret.distinct = distinct.is_some();
+
+        if let Some(ref filter) = filter {
+            static RE: Lazy<Regex> = Lazy::new(|| Regex::new("AND | OR").unwrap());
+            ret.filter_total_number_of_criteria = 1;
+
+            let syntax = match filter {
+                Value::String(_) => "string".to_string(),
+                Value::Array(values) => {
+                    if values.iter().map(|v| v.to_string()).any(|s| RE.is_match(&s)) {
+                        "mixed".to_string()
+                    } else {
+                        "array".to_string()
+                    }
+                }
+                _ => "none".to_string(),
+            };
+            // convert the string to a HashMap
+            ret.used_syntax.insert(syntax, 1);
+
+            let stringified_filters = filter.to_string();
+            ret.filter_with_geo_radius = stringified_filters.contains("_geoRadius(");
+            ret.filter_with_geo_bounding_box = stringified_filters.contains("_geoBoundingBox(");
+            ret.filter_sum_of_criteria_terms = RE.split(&stringified_filters).count();
+        }
+
+        // attributes_to_search_on
+        if attributes_to_search_on.is_some() {
+            ret.attributes_to_search_on_total_number_of_uses = 1;
+        }
+
+        if let Some(ref q) = q {
+            ret.max_terms_number = q.split_whitespace().count();
+        }
+
+        if let Some(ref vector) = vector {
+            ret.max_vector_size = vector.len();
+        }
+        ret.retrieve_vectors |= retrieve_vectors;
+
+        if query.is_finite_pagination() {
+            let limit = hits_per_page.unwrap_or_else(DEFAULT_SEARCH_LIMIT);
+            ret.max_limit = limit;
+            ret.max_offset = page.unwrap_or(1).saturating_sub(1) * limit;
+            ret.finite_pagination = 1;
+        } else {
+            ret.max_limit = *limit;
+            ret.max_offset = *offset;
+            ret.finite_pagination = 0;
+        }
+
+        ret.matching_strategy.insert(format!("{:?}", matching_strategy), 1);
+
+        if let Some(locales) = locales {
+            ret.locales = locales.iter().copied().collect();
+        }
+
+        ret.highlight_pre_tag = *highlight_pre_tag != DEFAULT_HIGHLIGHT_PRE_TAG();
+        ret.highlight_post_tag = *highlight_post_tag != DEFAULT_HIGHLIGHT_POST_TAG();
+        ret.crop_marker = *crop_marker != DEFAULT_CROP_MARKER();
+        ret.crop_length = *crop_length != DEFAULT_CROP_LENGTH();
+        ret.show_matches_position = *show_matches_position;
+
+        ret.show_ranking_score = *show_ranking_score;
+        ret.show_ranking_score_details = *show_ranking_score_details;
+        ret.ranking_score_threshold = ranking_score_threshold.is_some();
+
+        if let Some(hybrid) = hybrid {
+            ret.semantic_ratio = hybrid.semantic_ratio != DEFAULT_SEMANTIC_RATIO();
+            ret.hybrid = true;
+        }
+
+        ret
+    }
+
+    pub fn succeed(&mut self, result: &SearchResult) {
+        let SearchResult {
+            hits: _,
+            query: _,
+            processing_time_ms,
+            hits_info: _,
+            semantic_hit_count: _,
+            facet_distribution: _,
+            facet_stats: _,
+            degraded,
+            used_negative_operator,
+        } = result;
+
+        self.total_succeeded = self.total_succeeded.saturating_add(1);
+        if *degraded {
+            self.total_degraded = self.total_degraded.saturating_add(1);
+        }
+        if *used_negative_operator {
+            self.total_used_negative_operator = self.total_used_negative_operator.saturating_add(1);
+        }
+        self.time_spent.push(*processing_time_ms as usize);
+    }
+}
+
+impl<Method: AggregateMethod> Aggregate for SearchAggregator<Method> {
+    fn event_name(&self) -> &'static str {
+        Method::event_name()
+    }
+
+    fn aggregate(mut self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        let Self {
+            total_received,
+            total_succeeded,
+            mut time_spent,
+            sort_with_geo_point,
+            sort_sum_of_criteria_terms,
+            sort_total_number_of_criteria,
+            distinct,
+            filter_with_geo_radius,
+            filter_with_geo_bounding_box,
+            filter_sum_of_criteria_terms,
+            filter_total_number_of_criteria,
+            used_syntax,
+            attributes_to_search_on_total_number_of_uses,
+            max_terms_number,
+            max_vector_size,
+            retrieve_vectors,
+            matching_strategy,
+            max_limit,
+            max_offset,
+            finite_pagination,
+            max_attributes_to_retrieve,
+            max_attributes_to_highlight,
+            highlight_pre_tag,
+            highlight_post_tag,
+            max_attributes_to_crop,
+            crop_marker,
+            show_matches_position,
+            crop_length,
+            facets_sum_of_terms,
+            facets_total_number_of_facets,
+            show_ranking_score,
+            show_ranking_score_details,
+            semantic_ratio,
+            hybrid,
+            total_degraded,
+            total_used_negative_operator,
+            ranking_score_threshold,
+            mut locales,
+            marker: _,
+        } = *new;
+
+        // request
+        self.total_received = self.total_received.saturating_add(total_received);
+        self.total_succeeded = self.total_succeeded.saturating_add(total_succeeded);
+        self.total_degraded = self.total_degraded.saturating_add(total_degraded);
+        self.total_used_negative_operator =
+            self.total_used_negative_operator.saturating_add(total_used_negative_operator);
+        self.time_spent.append(&mut time_spent);
+
+        // sort
+        self.sort_with_geo_point |= sort_with_geo_point;
+        self.sort_sum_of_criteria_terms =
+            self.sort_sum_of_criteria_terms.saturating_add(sort_sum_of_criteria_terms);
+        self.sort_total_number_of_criteria =
+            self.sort_total_number_of_criteria.saturating_add(sort_total_number_of_criteria);
+
+        // distinct
+        self.distinct |= distinct;
+
+        // filter
+        self.filter_with_geo_radius |= filter_with_geo_radius;
+        self.filter_with_geo_bounding_box |= filter_with_geo_bounding_box;
+        self.filter_sum_of_criteria_terms =
+            self.filter_sum_of_criteria_terms.saturating_add(filter_sum_of_criteria_terms);
+        self.filter_total_number_of_criteria =
+            self.filter_total_number_of_criteria.saturating_add(filter_total_number_of_criteria);
+        for (key, value) in used_syntax.into_iter() {
+            let used_syntax = self.used_syntax.entry(key).or_insert(0);
+            *used_syntax = used_syntax.saturating_add(value);
+        }
+
+        // attributes_to_search_on
+        self.attributes_to_search_on_total_number_of_uses = self
+            .attributes_to_search_on_total_number_of_uses
+            .saturating_add(attributes_to_search_on_total_number_of_uses);
+
+        // q
+        self.max_terms_number = self.max_terms_number.max(max_terms_number);
+
+        // vector
+        self.max_vector_size = self.max_vector_size.max(max_vector_size);
+        self.retrieve_vectors |= retrieve_vectors;
+        self.semantic_ratio |= semantic_ratio;
+        self.hybrid |= hybrid;
+
+        // pagination
+        self.max_limit = self.max_limit.max(max_limit);
+        self.max_offset = self.max_offset.max(max_offset);
+        self.finite_pagination += finite_pagination;
+
+        // formatting
+        self.max_attributes_to_retrieve =
+            self.max_attributes_to_retrieve.max(max_attributes_to_retrieve);
+        self.max_attributes_to_highlight =
+            self.max_attributes_to_highlight.max(max_attributes_to_highlight);
+        self.highlight_pre_tag |= highlight_pre_tag;
+        self.highlight_post_tag |= highlight_post_tag;
+        self.max_attributes_to_crop = self.max_attributes_to_crop.max(max_attributes_to_crop);
+        self.crop_marker |= crop_marker;
+        self.show_matches_position |= show_matches_position;
+        self.crop_length |= crop_length;
+
+        // facets
+        self.facets_sum_of_terms = self.facets_sum_of_terms.saturating_add(facets_sum_of_terms);
+        self.facets_total_number_of_facets =
+            self.facets_total_number_of_facets.saturating_add(facets_total_number_of_facets);
+
+        // matching strategy
+        for (key, value) in matching_strategy.into_iter() {
+            let matching_strategy = self.matching_strategy.entry(key).or_insert(0);
+            *matching_strategy = matching_strategy.saturating_add(value);
+        }
+
+        // scoring
+        self.show_ranking_score |= show_ranking_score;
+        self.show_ranking_score_details |= show_ranking_score_details;
+        self.ranking_score_threshold |= ranking_score_threshold;
+
+        // locales
+        self.locales.append(&mut locales);
+
+        self
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        let Self {
+            total_received,
+            total_succeeded,
+            time_spent,
+            sort_with_geo_point,
+            sort_sum_of_criteria_terms,
+            sort_total_number_of_criteria,
+            distinct,
+            filter_with_geo_radius,
+            filter_with_geo_bounding_box,
+            filter_sum_of_criteria_terms,
+            filter_total_number_of_criteria,
+            used_syntax,
+            attributes_to_search_on_total_number_of_uses,
+            max_terms_number,
+            max_vector_size,
+            retrieve_vectors,
+            matching_strategy,
+            max_limit,
+            max_offset,
+            finite_pagination,
+            max_attributes_to_retrieve,
+            max_attributes_to_highlight,
+            highlight_pre_tag,
+            highlight_post_tag,
+            max_attributes_to_crop,
+            crop_marker,
+            show_matches_position,
+            crop_length,
+            facets_sum_of_terms,
+            facets_total_number_of_facets,
+            show_ranking_score,
+            show_ranking_score_details,
+            semantic_ratio,
+            hybrid,
+            total_degraded,
+            total_used_negative_operator,
+            ranking_score_threshold,
+            locales,
+            marker: _,
+        } = *self;
+
+        // we get all the values in a sorted manner
+        let time_spent = time_spent.into_sorted_vec();
+        // the index of the 99th percentage of value
+        let percentile_99th = time_spent.len() * 99 / 100;
+        // We are only interested by the slowest value of the 99th fastest results
+        let time_spent = time_spent.get(percentile_99th);
+
+        json!({
+            "requests": {
+                "99th_response_time": time_spent.map(|t| format!("{:.2}", t)),
+                "total_succeeded": total_succeeded,
+                "total_failed": total_received.saturating_sub(total_succeeded), // just to be sure we never panics
+                "total_received": total_received,
+                "total_degraded": total_degraded,
+                "total_used_negative_operator": total_used_negative_operator,
+            },
+            "sort": {
+                "with_geoPoint": sort_with_geo_point,
+                "avg_criteria_number": format!("{:.2}", sort_sum_of_criteria_terms as f64 / sort_total_number_of_criteria as f64),
+            },
+            "distinct": distinct,
+            "filter": {
+               "with_geoRadius": filter_with_geo_radius,
+               "with_geoBoundingBox": filter_with_geo_bounding_box,
+               "avg_criteria_number": format!("{:.2}", filter_sum_of_criteria_terms as f64 / filter_total_number_of_criteria as f64),
+               "most_used_syntax": used_syntax.iter().max_by_key(|(_, v)| *v).map(|(k, _)| json!(k)).unwrap_or_else(|| json!(null)),
+            },
+            "attributes_to_search_on": {
+               "total_number_of_uses": attributes_to_search_on_total_number_of_uses,
+            },
+            "q": {
+               "max_terms_number": max_terms_number,
+            },
+            "vector": {
+                "max_vector_size": max_vector_size,
+                "retrieve_vectors": retrieve_vectors,
+            },
+            "hybrid": {
+                "enabled": hybrid,
+                "semantic_ratio": semantic_ratio,
+            },
+            "pagination": {
+               "max_limit": max_limit,
+               "max_offset": max_offset,
+               "most_used_navigation": if finite_pagination > (total_received / 2) { "exhaustive" } else { "estimated" },
+            },
+            "formatting": {
+                "max_attributes_to_retrieve": max_attributes_to_retrieve,
+                "max_attributes_to_highlight": max_attributes_to_highlight,
+                "highlight_pre_tag": highlight_pre_tag,
+                "highlight_post_tag": highlight_post_tag,
+                "max_attributes_to_crop": max_attributes_to_crop,
+                "crop_marker": crop_marker,
+                "show_matches_position": show_matches_position,
+                "crop_length": crop_length,
+            },
+            "facets": {
+                "avg_facets_number": format!("{:.2}", facets_sum_of_terms as f64 / facets_total_number_of_facets as f64),
+            },
+            "matching_strategy": {
+                "most_used_strategy": matching_strategy.iter().max_by_key(|(_, v)| *v).map(|(k, _)| json!(k)).unwrap_or_else(|| json!(null)),
+            },
+            "locales": locales,
+            "scoring": {
+                "show_ranking_score": show_ranking_score,
+                "show_ranking_score_details": show_ranking_score_details,
+                "ranking_score_threshold": ranking_score_threshold,
+            },
+        })
+    }
+}

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

@@ -0,0 +1,532 @@
+use super::settings_analytics::*;
+use actix_web::web::Data;
+use actix_web::{web, HttpRequest, HttpResponse};
+use deserr::actix_web::AwebJson;
+use index_scheduler::IndexScheduler;
+use meilisearch_types::deserr::DeserrJsonError;
+use meilisearch_types::error::ResponseError;
+use meilisearch_types::index_uid::IndexUid;
+use meilisearch_types::milli::update::Setting;
+use meilisearch_types::settings::{settings, SecretPolicy, Settings, Unchecked};
+use meilisearch_types::tasks::KindWithContent;
+use tracing::debug;
+
+use crate::analytics::Analytics;
+use crate::extractors::authentication::policies::*;
+use crate::extractors::authentication::GuardedData;
+use crate::routes::{get_task_id, is_dry_run, SummarizedTaskView};
+use crate::Opt;
+
+#[macro_export]
+macro_rules! make_setting_route {
+    ($route:literal, $update_verb:ident, $type:ty, $err_ty:ty, $attr:ident, $camelcase_attr:literal, $analytics:ident) => {
+        pub mod $attr {
+            use actix_web::web::Data;
+            use actix_web::{web, HttpRequest, HttpResponse, Resource};
+            use index_scheduler::IndexScheduler;
+            use meilisearch_types::error::ResponseError;
+            use meilisearch_types::index_uid::IndexUid;
+            use meilisearch_types::milli::update::Setting;
+            use meilisearch_types::settings::{settings, Settings};
+            use meilisearch_types::tasks::KindWithContent;
+            use tracing::debug;
+            use $crate::analytics::Analytics;
+            use $crate::extractors::authentication::policies::*;
+            use $crate::extractors::authentication::GuardedData;
+            use $crate::extractors::sequential_extractor::SeqHandler;
+            use $crate::Opt;
+            use $crate::routes::{is_dry_run, get_task_id, SummarizedTaskView};
+
+            pub async fn delete(
+                index_scheduler: GuardedData<
+                    ActionPolicy<{ actions::SETTINGS_UPDATE }>,
+                    Data<IndexScheduler>,
+                >,
+                index_uid: web::Path<String>,
+                req: HttpRequest,
+                opt: web::Data<Opt>,
+            ) -> Result<HttpResponse, ResponseError> {
+                let index_uid = IndexUid::try_from(index_uid.into_inner())?;
+
+                let new_settings = Settings { $attr: Setting::Reset.into(), ..Default::default() };
+
+                let allow_index_creation =
+                    index_scheduler.filters().allow_index_creation(&index_uid);
+
+                let task = KindWithContent::SettingsUpdate {
+                    index_uid: index_uid.to_string(),
+                    new_settings: Box::new(new_settings),
+                    is_deletion: true,
+                    allow_index_creation,
+                };
+                let uid = get_task_id(&req, &opt)?;
+                let dry_run = is_dry_run(&req, &opt)?;
+                let task: SummarizedTaskView =
+                    tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run))
+                        .await??
+                        .into();
+
+                debug!(returns = ?task, "Delete settings");
+                Ok(HttpResponse::Accepted().json(task))
+            }
+
+            pub async fn update(
+                index_scheduler: GuardedData<
+                    ActionPolicy<{ actions::SETTINGS_UPDATE }>,
+                    Data<IndexScheduler>,
+                >,
+                index_uid: actix_web::web::Path<String>,
+                body: deserr::actix_web::AwebJson<Option<$type>, $err_ty>,
+                req: HttpRequest,
+                opt: web::Data<Opt>,
+                analytics: web::Data<Analytics>,
+            ) -> std::result::Result<HttpResponse, ResponseError> {
+                let index_uid = IndexUid::try_from(index_uid.into_inner())?;
+
+                let body = body.into_inner();
+                debug!(parameters = ?body, "Update settings");
+
+                #[allow(clippy::redundant_closure_call)]
+                analytics.publish(
+                    $crate::routes::indexes::settings_analytics::$analytics::new(body.as_ref()).into_settings(),
+                    &req,
+                );
+
+                let new_settings = Settings {
+                    $attr: match body {
+                        Some(inner_body) => Setting::Set(inner_body).into(),
+                        None => Setting::Reset.into(),
+                    },
+                    ..Default::default()
+                };
+
+                let new_settings = $crate::routes::indexes::settings::validate_settings(
+                    new_settings,
+                    &index_scheduler,
+                )?;
+
+                let allow_index_creation =
+                    index_scheduler.filters().allow_index_creation(&index_uid);
+
+                let task = KindWithContent::SettingsUpdate {
+                    index_uid: index_uid.to_string(),
+                    new_settings: Box::new(new_settings),
+                    is_deletion: false,
+                    allow_index_creation,
+                };
+                let uid = get_task_id(&req, &opt)?;
+                let dry_run = is_dry_run(&req, &opt)?;
+                let task: SummarizedTaskView =
+                    tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run))
+                        .await??
+                        .into();
+
+                debug!(returns = ?task, "Update settings");
+                Ok(HttpResponse::Accepted().json(task))
+            }
+
+            pub async fn get(
+                index_scheduler: GuardedData<
+                    ActionPolicy<{ actions::SETTINGS_GET }>,
+                    Data<IndexScheduler>,
+                >,
+                index_uid: actix_web::web::Path<String>,
+            ) -> std::result::Result<HttpResponse, ResponseError> {
+                let index_uid = IndexUid::try_from(index_uid.into_inner())?;
+
+                let index = index_scheduler.index(&index_uid)?;
+                let rtxn = index.read_txn()?;
+                let settings = settings(&index, &rtxn, meilisearch_types::settings::SecretPolicy::HideSecrets)?;
+
+                debug!(returns = ?settings, "Update settings");
+
+                Ok(HttpResponse::Ok().json(settings.$attr))
+            }
+
+            pub fn resources() -> Resource {
+                Resource::new($route)
+                    .route(web::get().to(SeqHandler(get)))
+                    .route(web::$update_verb().to(SeqHandler(update)))
+                    .route(web::delete().to(SeqHandler(delete)))
+            }
+        }
+    };
+}
+
+make_setting_route!(
+    "/filterable-attributes",
+    put,
+    std::collections::BTreeSet<String>,
+    meilisearch_types::deserr::DeserrJsonError<
+        meilisearch_types::error::deserr_codes::InvalidSettingsFilterableAttributes,
+    >,
+    filterable_attributes,
+    "filterableAttributes",
+    FilterableAttributesAnalytics
+);
+
+make_setting_route!(
+    "/sortable-attributes",
+    put,
+    std::collections::BTreeSet<String>,
+    meilisearch_types::deserr::DeserrJsonError<
+        meilisearch_types::error::deserr_codes::InvalidSettingsSortableAttributes,
+    >,
+    sortable_attributes,
+    "sortableAttributes",
+    SortableAttributesAnalytics
+);
+
+make_setting_route!(
+    "/displayed-attributes",
+    put,
+    Vec<String>,
+    meilisearch_types::deserr::DeserrJsonError<
+        meilisearch_types::error::deserr_codes::InvalidSettingsDisplayedAttributes,
+    >,
+    displayed_attributes,
+    "displayedAttributes",
+    DisplayedAttributesAnalytics
+);
+
+make_setting_route!(
+    "/typo-tolerance",
+    patch,
+    meilisearch_types::settings::TypoSettings,
+    meilisearch_types::deserr::DeserrJsonError<
+        meilisearch_types::error::deserr_codes::InvalidSettingsTypoTolerance,
+    >,
+    typo_tolerance,
+    "typoTolerance",
+    TypoToleranceAnalytics
+);
+
+make_setting_route!(
+    "/searchable-attributes",
+    put,
+    Vec<String>,
+    meilisearch_types::deserr::DeserrJsonError<
+        meilisearch_types::error::deserr_codes::InvalidSettingsSearchableAttributes,
+    >,
+    searchable_attributes,
+    "searchableAttributes",
+    SearchableAttributesAnalytics
+);
+
+make_setting_route!(
+    "/stop-words",
+    put,
+    std::collections::BTreeSet<String>,
+    meilisearch_types::deserr::DeserrJsonError<
+        meilisearch_types::error::deserr_codes::InvalidSettingsStopWords,
+    >,
+    stop_words,
+    "stopWords",
+    StopWordsAnalytics
+);
+
+make_setting_route!(
+    "/non-separator-tokens",
+    put,
+    std::collections::BTreeSet<String>,
+    meilisearch_types::deserr::DeserrJsonError<
+        meilisearch_types::error::deserr_codes::InvalidSettingsNonSeparatorTokens,
+    >,
+    non_separator_tokens,
+    "nonSeparatorTokens",
+    NonSeparatorTokensAnalytics
+);
+
+make_setting_route!(
+    "/separator-tokens",
+    put,
+    std::collections::BTreeSet<String>,
+    meilisearch_types::deserr::DeserrJsonError<
+        meilisearch_types::error::deserr_codes::InvalidSettingsSeparatorTokens,
+    >,
+    separator_tokens,
+    "separatorTokens",
+    SeparatorTokensAnalytics
+);
+
+make_setting_route!(
+    "/dictionary",
+    put,
+    std::collections::BTreeSet<String>,
+    meilisearch_types::deserr::DeserrJsonError<
+        meilisearch_types::error::deserr_codes::InvalidSettingsDictionary,
+    >,
+    dictionary,
+    "dictionary",
+    DictionaryAnalytics
+);
+
+make_setting_route!(
+    "/synonyms",
+    put,
+    std::collections::BTreeMap<String, Vec<String>>,
+    meilisearch_types::deserr::DeserrJsonError<
+        meilisearch_types::error::deserr_codes::InvalidSettingsSynonyms,
+    >,
+    synonyms,
+    "synonyms",
+    SynonymsAnalytics
+);
+
+make_setting_route!(
+    "/distinct-attribute",
+    put,
+    String,
+    meilisearch_types::deserr::DeserrJsonError<
+        meilisearch_types::error::deserr_codes::InvalidSettingsDistinctAttribute,
+    >,
+    distinct_attribute,
+    "distinctAttribute",
+    DistinctAttributeAnalytics
+);
+
+make_setting_route!(
+    "/proximity-precision",
+    put,
+    meilisearch_types::settings::ProximityPrecisionView,
+    meilisearch_types::deserr::DeserrJsonError<
+        meilisearch_types::error::deserr_codes::InvalidSettingsProximityPrecision,
+    >,
+    proximity_precision,
+    "proximityPrecision",
+    ProximityPrecisionAnalytics
+);
+
+make_setting_route!(
+    "/localized-attributes",
+    put,
+    Vec<meilisearch_types::locales::LocalizedAttributesRuleView>,
+    meilisearch_types::deserr::DeserrJsonError<
+        meilisearch_types::error::deserr_codes::InvalidSettingsLocalizedAttributes,
+    >,
+    localized_attributes,
+    "localizedAttributes",
+    LocalesAnalytics
+);
+
+make_setting_route!(
+    "/ranking-rules",
+    put,
+    Vec<meilisearch_types::settings::RankingRuleView>,
+    meilisearch_types::deserr::DeserrJsonError<
+        meilisearch_types::error::deserr_codes::InvalidSettingsRankingRules,
+    >,
+    ranking_rules,
+    "rankingRules",
+    RankingRulesAnalytics
+);
+
+make_setting_route!(
+    "/faceting",
+    patch,
+    meilisearch_types::settings::FacetingSettings,
+    meilisearch_types::deserr::DeserrJsonError<
+        meilisearch_types::error::deserr_codes::InvalidSettingsFaceting,
+    >,
+    faceting,
+    "faceting",
+    FacetingAnalytics
+);
+
+make_setting_route!(
+    "/pagination",
+    patch,
+    meilisearch_types::settings::PaginationSettings,
+    meilisearch_types::deserr::DeserrJsonError<
+        meilisearch_types::error::deserr_codes::InvalidSettingsPagination,
+    >,
+    pagination,
+    "pagination",
+    PaginationAnalytics
+);
+
+make_setting_route!(
+    "/embedders",
+    patch,
+    std::collections::BTreeMap<String, Setting<meilisearch_types::milli::vector::settings::EmbeddingSettings>>,
+    meilisearch_types::deserr::DeserrJsonError<
+        meilisearch_types::error::deserr_codes::InvalidSettingsEmbedders,
+    >,
+    embedders,
+    "embedders",
+    EmbeddersAnalytics
+);
+
+make_setting_route!(
+    "/search-cutoff-ms",
+    put,
+    u64,
+    meilisearch_types::deserr::DeserrJsonError<
+        meilisearch_types::error::deserr_codes::InvalidSettingsSearchCutoffMs,
+    >,
+    search_cutoff_ms,
+    "searchCutoffMs",
+    SearchCutoffMsAnalytics
+);
+
+macro_rules! generate_configure {
+    ($($mod:ident),*) => {
+        pub fn configure(cfg: &mut web::ServiceConfig) {
+            use crate::extractors::sequential_extractor::SeqHandler;
+            cfg.service(
+                web::resource("")
+                .route(web::patch().to(SeqHandler(update_all)))
+                .route(web::get().to(SeqHandler(get_all)))
+                .route(web::delete().to(SeqHandler(delete_all))))
+                $(.service($mod::resources()))*;
+        }
+    };
+}
+
+generate_configure!(
+    filterable_attributes,
+    sortable_attributes,
+    displayed_attributes,
+    localized_attributes,
+    searchable_attributes,
+    distinct_attribute,
+    proximity_precision,
+    stop_words,
+    separator_tokens,
+    non_separator_tokens,
+    dictionary,
+    synonyms,
+    ranking_rules,
+    typo_tolerance,
+    pagination,
+    faceting,
+    embedders,
+    search_cutoff_ms
+);
+
+pub async fn update_all(
+    index_scheduler: GuardedData<ActionPolicy<{ actions::SETTINGS_UPDATE }>, Data<IndexScheduler>>,
+    index_uid: web::Path<String>,
+    body: AwebJson<Settings<Unchecked>, DeserrJsonError>,
+    req: HttpRequest,
+    opt: web::Data<Opt>,
+    analytics: web::Data<Analytics>,
+) -> Result<HttpResponse, ResponseError> {
+    let index_uid = IndexUid::try_from(index_uid.into_inner())?;
+
+    let new_settings = body.into_inner();
+    debug!(parameters = ?new_settings, "Update all settings");
+    let new_settings = validate_settings(new_settings, &index_scheduler)?;
+
+    analytics.publish(
+        SettingsAnalytics {
+            ranking_rules: RankingRulesAnalytics::new(new_settings.ranking_rules.as_ref().set()),
+            searchable_attributes: SearchableAttributesAnalytics::new(
+                new_settings.searchable_attributes.as_ref().set(),
+            ),
+            displayed_attributes: DisplayedAttributesAnalytics::new(
+                new_settings.displayed_attributes.as_ref().set(),
+            ),
+            sortable_attributes: SortableAttributesAnalytics::new(
+                new_settings.sortable_attributes.as_ref().set(),
+            ),
+            filterable_attributes: FilterableAttributesAnalytics::new(
+                new_settings.filterable_attributes.as_ref().set(),
+            ),
+            distinct_attribute: DistinctAttributeAnalytics::new(
+                new_settings.distinct_attribute.as_ref().set(),
+            ),
+            proximity_precision: ProximityPrecisionAnalytics::new(
+                new_settings.proximity_precision.as_ref().set(),
+            ),
+            typo_tolerance: TypoToleranceAnalytics::new(new_settings.typo_tolerance.as_ref().set()),
+            faceting: FacetingAnalytics::new(new_settings.faceting.as_ref().set()),
+            pagination: PaginationAnalytics::new(new_settings.pagination.as_ref().set()),
+            stop_words: StopWordsAnalytics::new(new_settings.stop_words.as_ref().set()),
+            synonyms: SynonymsAnalytics::new(new_settings.synonyms.as_ref().set()),
+            embedders: EmbeddersAnalytics::new(new_settings.embedders.as_ref().set()),
+            search_cutoff_ms: SearchCutoffMsAnalytics::new(
+                new_settings.search_cutoff_ms.as_ref().set(),
+            ),
+            locales: LocalesAnalytics::new(new_settings.localized_attributes.as_ref().set()),
+            dictionary: DictionaryAnalytics::new(new_settings.dictionary.as_ref().set()),
+            separator_tokens: SeparatorTokensAnalytics::new(
+                new_settings.separator_tokens.as_ref().set(),
+            ),
+            non_separator_tokens: NonSeparatorTokensAnalytics::new(
+                new_settings.non_separator_tokens.as_ref().set(),
+            ),
+        },
+        &req,
+    );
+
+    let allow_index_creation = index_scheduler.filters().allow_index_creation(&index_uid);
+    let index_uid = IndexUid::try_from(index_uid.into_inner())?.into_inner();
+    let task = KindWithContent::SettingsUpdate {
+        index_uid,
+        new_settings: Box::new(new_settings),
+        is_deletion: false,
+        allow_index_creation,
+    };
+    let uid = get_task_id(&req, &opt)?;
+    let dry_run = is_dry_run(&req, &opt)?;
+    let task: SummarizedTaskView =
+        tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run))
+            .await??
+            .into();
+
+    debug!(returns = ?task, "Update all settings");
+    Ok(HttpResponse::Accepted().json(task))
+}
+
+pub async fn get_all(
+    index_scheduler: GuardedData<ActionPolicy<{ actions::SETTINGS_GET }>, Data<IndexScheduler>>,
+    index_uid: web::Path<String>,
+) -> Result<HttpResponse, ResponseError> {
+    let index_uid = IndexUid::try_from(index_uid.into_inner())?;
+
+    let index = index_scheduler.index(&index_uid)?;
+    let rtxn = index.read_txn()?;
+    let new_settings = settings(&index, &rtxn, SecretPolicy::HideSecrets)?;
+    debug!(returns = ?new_settings, "Get all settings");
+    Ok(HttpResponse::Ok().json(new_settings))
+}
+
+pub async fn delete_all(
+    index_scheduler: GuardedData<ActionPolicy<{ actions::SETTINGS_UPDATE }>, Data<IndexScheduler>>,
+    index_uid: web::Path<String>,
+    req: HttpRequest,
+    opt: web::Data<Opt>,
+) -> Result<HttpResponse, ResponseError> {
+    let index_uid = IndexUid::try_from(index_uid.into_inner())?;
+
+    let new_settings = Settings::cleared().into_unchecked();
+
+    let allow_index_creation = index_scheduler.filters().allow_index_creation(&index_uid);
+    let index_uid = IndexUid::try_from(index_uid.into_inner())?.into_inner();
+    let task = KindWithContent::SettingsUpdate {
+        index_uid,
+        new_settings: Box::new(new_settings),
+        is_deletion: true,
+        allow_index_creation,
+    };
+    let uid = get_task_id(&req, &opt)?;
+    let dry_run = is_dry_run(&req, &opt)?;
+    let task: SummarizedTaskView =
+        tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run))
+            .await??
+            .into();
+
+    debug!(returns = ?task, "Delete all settings");
+    Ok(HttpResponse::Accepted().json(task))
+}
+
+fn validate_settings(
+    settings: Settings<Unchecked>,
+    index_scheduler: &IndexScheduler,
+) -> Result<Settings<Unchecked>, ResponseError> {
+    if matches!(settings.embedders, Setting::Set(_)) {
+        index_scheduler.features().check_vector("Passing `embedders` in settings")?
+    }
+    Ok(settings.validate()?)
+}

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

@@ -0,0 +1,621 @@
+//! All the structures used to make the analytics on the settings works.
+//! The signatures of the `new` functions are not very rust idiomatic because they must match the types received
+//! through the sub-settings route directly without any manipulation.
+//! This is why we often use a `Option<&Vec<_>>` instead of a `Option<&[_]>`.
+
+use meilisearch_types::locales::{Locale, LocalizedAttributesRuleView};
+use meilisearch_types::milli::update::Setting;
+use meilisearch_types::milli::vector::settings::EmbeddingSettings;
+use meilisearch_types::settings::{
+    FacetingSettings, PaginationSettings, ProximityPrecisionView, TypoSettings,
+};
+use meilisearch_types::{facet_values_sort::FacetValuesSort, settings::RankingRuleView};
+use serde::Serialize;
+use std::collections::{BTreeMap, BTreeSet, HashSet};
+
+use crate::analytics::Aggregate;
+
+#[derive(Serialize, Default)]
+pub struct SettingsAnalytics {
+    pub ranking_rules: RankingRulesAnalytics,
+    pub searchable_attributes: SearchableAttributesAnalytics,
+    pub displayed_attributes: DisplayedAttributesAnalytics,
+    pub sortable_attributes: SortableAttributesAnalytics,
+    pub filterable_attributes: FilterableAttributesAnalytics,
+    pub distinct_attribute: DistinctAttributeAnalytics,
+    pub proximity_precision: ProximityPrecisionAnalytics,
+    pub typo_tolerance: TypoToleranceAnalytics,
+    pub faceting: FacetingAnalytics,
+    pub pagination: PaginationAnalytics,
+    pub stop_words: StopWordsAnalytics,
+    pub synonyms: SynonymsAnalytics,
+    pub embedders: EmbeddersAnalytics,
+    pub search_cutoff_ms: SearchCutoffMsAnalytics,
+    pub locales: LocalesAnalytics,
+    pub dictionary: DictionaryAnalytics,
+    pub separator_tokens: SeparatorTokensAnalytics,
+    pub non_separator_tokens: NonSeparatorTokensAnalytics,
+}
+
+impl Aggregate for SettingsAnalytics {
+    fn event_name(&self) -> &'static str {
+        "Settings Updated"
+    }
+
+    fn aggregate(self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        Box::new(Self {
+            ranking_rules: RankingRulesAnalytics {
+                words_position: new
+                    .ranking_rules
+                    .words_position
+                    .or(self.ranking_rules.words_position),
+                typo_position: new.ranking_rules.typo_position.or(self.ranking_rules.typo_position),
+                proximity_position: new
+                    .ranking_rules
+                    .proximity_position
+                    .or(self.ranking_rules.proximity_position),
+                attribute_position: new
+                    .ranking_rules
+                    .attribute_position
+                    .or(self.ranking_rules.attribute_position),
+                sort_position: new.ranking_rules.sort_position.or(self.ranking_rules.sort_position),
+                exactness_position: new
+                    .ranking_rules
+                    .exactness_position
+                    .or(self.ranking_rules.exactness_position),
+                values: new.ranking_rules.values.or(self.ranking_rules.values),
+            },
+            searchable_attributes: SearchableAttributesAnalytics {
+                total: new.searchable_attributes.total.or(self.searchable_attributes.total),
+                with_wildcard: new
+                    .searchable_attributes
+                    .with_wildcard
+                    .or(self.searchable_attributes.with_wildcard),
+            },
+            displayed_attributes: DisplayedAttributesAnalytics {
+                total: new.displayed_attributes.total.or(self.displayed_attributes.total),
+                with_wildcard: new
+                    .displayed_attributes
+                    .with_wildcard
+                    .or(self.displayed_attributes.with_wildcard),
+            },
+            sortable_attributes: SortableAttributesAnalytics {
+                total: new.sortable_attributes.total.or(self.sortable_attributes.total),
+                has_geo: new.sortable_attributes.has_geo.or(self.sortable_attributes.has_geo),
+            },
+            filterable_attributes: FilterableAttributesAnalytics {
+                total: new.filterable_attributes.total.or(self.filterable_attributes.total),
+                has_geo: new.filterable_attributes.has_geo.or(self.filterable_attributes.has_geo),
+            },
+            distinct_attribute: DistinctAttributeAnalytics {
+                set: self.distinct_attribute.set | new.distinct_attribute.set,
+            },
+            proximity_precision: ProximityPrecisionAnalytics {
+                set: self.proximity_precision.set | new.proximity_precision.set,
+                value: new.proximity_precision.value.or(self.proximity_precision.value),
+            },
+            typo_tolerance: TypoToleranceAnalytics {
+                enabled: new.typo_tolerance.enabled.or(self.typo_tolerance.enabled),
+                disable_on_attributes: new
+                    .typo_tolerance
+                    .disable_on_attributes
+                    .or(self.typo_tolerance.disable_on_attributes),
+                disable_on_words: new
+                    .typo_tolerance
+                    .disable_on_words
+                    .or(self.typo_tolerance.disable_on_words),
+                min_word_size_for_one_typo: new
+                    .typo_tolerance
+                    .min_word_size_for_one_typo
+                    .or(self.typo_tolerance.min_word_size_for_one_typo),
+                min_word_size_for_two_typos: new
+                    .typo_tolerance
+                    .min_word_size_for_two_typos
+                    .or(self.typo_tolerance.min_word_size_for_two_typos),
+            },
+            faceting: FacetingAnalytics {
+                max_values_per_facet: new
+                    .faceting
+                    .max_values_per_facet
+                    .or(self.faceting.max_values_per_facet),
+                sort_facet_values_by_star_count: new
+                    .faceting
+                    .sort_facet_values_by_star_count
+                    .or(self.faceting.sort_facet_values_by_star_count),
+                sort_facet_values_by_total: new
+                    .faceting
+                    .sort_facet_values_by_total
+                    .or(self.faceting.sort_facet_values_by_total),
+            },
+            pagination: PaginationAnalytics {
+                max_total_hits: new.pagination.max_total_hits.or(self.pagination.max_total_hits),
+            },
+            stop_words: StopWordsAnalytics {
+                total: new.stop_words.total.or(self.stop_words.total),
+            },
+            synonyms: SynonymsAnalytics { total: new.synonyms.total.or(self.synonyms.total) },
+            embedders: EmbeddersAnalytics {
+                total: new.embedders.total.or(self.embedders.total),
+                sources: match (self.embedders.sources, new.embedders.sources) {
+                    (None, None) => None,
+                    (Some(sources), None) | (None, Some(sources)) => Some(sources),
+                    (Some(this), Some(other)) => Some(this.union(&other).cloned().collect()),
+                },
+                document_template_used: match (
+                    self.embedders.document_template_used,
+                    new.embedders.document_template_used,
+                ) {
+                    (None, None) => None,
+                    (Some(used), None) | (None, Some(used)) => Some(used),
+                    (Some(this), Some(other)) => Some(this | other),
+                },
+                document_template_max_bytes: match (
+                    self.embedders.document_template_max_bytes,
+                    new.embedders.document_template_max_bytes,
+                ) {
+                    (None, None) => None,
+                    (Some(bytes), None) | (None, Some(bytes)) => Some(bytes),
+                    (Some(this), Some(other)) => Some(this.max(other)),
+                },
+                binary_quantization_used: match (
+                    self.embedders.binary_quantization_used,
+                    new.embedders.binary_quantization_used,
+                ) {
+                    (None, None) => None,
+                    (Some(bq), None) | (None, Some(bq)) => Some(bq),
+                    (Some(this), Some(other)) => Some(this | other),
+                },
+            },
+            search_cutoff_ms: SearchCutoffMsAnalytics {
+                search_cutoff_ms: new
+                    .search_cutoff_ms
+                    .search_cutoff_ms
+                    .or(self.search_cutoff_ms.search_cutoff_ms),
+            },
+            locales: LocalesAnalytics { locales: new.locales.locales.or(self.locales.locales) },
+            dictionary: DictionaryAnalytics {
+                total: new.dictionary.total.or(self.dictionary.total),
+            },
+            separator_tokens: SeparatorTokensAnalytics {
+                total: new.non_separator_tokens.total.or(self.separator_tokens.total),
+            },
+            non_separator_tokens: NonSeparatorTokensAnalytics {
+                total: new.non_separator_tokens.total.or(self.non_separator_tokens.total),
+            },
+        })
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        serde_json::to_value(*self).unwrap_or_default()
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct RankingRulesAnalytics {
+    pub words_position: Option<usize>,
+    pub typo_position: Option<usize>,
+    pub proximity_position: Option<usize>,
+    pub attribute_position: Option<usize>,
+    pub sort_position: Option<usize>,
+    pub exactness_position: Option<usize>,
+    pub values: Option<String>,
+}
+
+impl RankingRulesAnalytics {
+    pub fn new(rr: Option<&Vec<RankingRuleView>>) -> Self {
+        RankingRulesAnalytics {
+            words_position: rr.as_ref().and_then(|rr| {
+                rr.iter()
+                    .position(|s| matches!(s, meilisearch_types::settings::RankingRuleView::Words))
+            }),
+            typo_position: rr.as_ref().and_then(|rr| {
+                rr.iter()
+                    .position(|s| matches!(s, meilisearch_types::settings::RankingRuleView::Typo))
+            }),
+            proximity_position: rr.as_ref().and_then(|rr| {
+                rr.iter().position(|s| {
+                    matches!(s, meilisearch_types::settings::RankingRuleView::Proximity)
+                })
+            }),
+            attribute_position: rr.as_ref().and_then(|rr| {
+                rr.iter().position(|s| {
+                    matches!(s, meilisearch_types::settings::RankingRuleView::Attribute)
+                })
+            }),
+            sort_position: rr.as_ref().and_then(|rr| {
+                rr.iter()
+                    .position(|s| matches!(s, meilisearch_types::settings::RankingRuleView::Sort))
+            }),
+            exactness_position: rr.as_ref().and_then(|rr| {
+                rr.iter().position(|s| {
+                    matches!(s, meilisearch_types::settings::RankingRuleView::Exactness)
+                })
+            }),
+            values: rr.as_ref().map(|rr| {
+                rr.iter()
+                    .filter(|s| {
+                        matches!(
+                            s,
+                            meilisearch_types::settings::RankingRuleView::Asc(_)
+                                | meilisearch_types::settings::RankingRuleView::Desc(_)
+                        )
+                    })
+                    .map(|x| x.to_string())
+                    .collect::<Vec<_>>()
+                    .join(", ")
+            }),
+        }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { ranking_rules: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct SearchableAttributesAnalytics {
+    pub total: Option<usize>,
+    pub with_wildcard: Option<bool>,
+}
+
+impl SearchableAttributesAnalytics {
+    pub fn new(setting: Option<&Vec<String>>) -> Self {
+        Self {
+            total: setting.as_ref().map(|searchable| searchable.len()),
+            with_wildcard: setting
+                .as_ref()
+                .map(|searchable| searchable.iter().any(|searchable| searchable == "*")),
+        }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { searchable_attributes: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct DisplayedAttributesAnalytics {
+    pub total: Option<usize>,
+    pub with_wildcard: Option<bool>,
+}
+
+impl DisplayedAttributesAnalytics {
+    pub fn new(displayed: Option<&Vec<String>>) -> Self {
+        Self {
+            total: displayed.as_ref().map(|displayed| displayed.len()),
+            with_wildcard: displayed
+                .as_ref()
+                .map(|displayed| displayed.iter().any(|displayed| displayed == "*")),
+        }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { displayed_attributes: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct SortableAttributesAnalytics {
+    pub total: Option<usize>,
+    pub has_geo: Option<bool>,
+}
+
+impl SortableAttributesAnalytics {
+    pub fn new(setting: Option<&BTreeSet<String>>) -> Self {
+        Self {
+            total: setting.as_ref().map(|sort| sort.len()),
+            has_geo: setting.as_ref().map(|sort| sort.contains("_geo")),
+        }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { sortable_attributes: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct FilterableAttributesAnalytics {
+    pub total: Option<usize>,
+    pub has_geo: Option<bool>,
+}
+
+impl FilterableAttributesAnalytics {
+    pub fn new(setting: Option<&BTreeSet<String>>) -> Self {
+        Self {
+            total: setting.as_ref().map(|filter| filter.len()),
+            has_geo: setting.as_ref().map(|filter| filter.contains("_geo")),
+        }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { filterable_attributes: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct DistinctAttributeAnalytics {
+    pub set: bool,
+}
+
+impl DistinctAttributeAnalytics {
+    pub fn new(distinct: Option<&String>) -> Self {
+        Self { set: distinct.is_some() }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { distinct_attribute: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct ProximityPrecisionAnalytics {
+    pub set: bool,
+    pub value: Option<ProximityPrecisionView>,
+}
+
+impl ProximityPrecisionAnalytics {
+    pub fn new(precision: Option<&ProximityPrecisionView>) -> Self {
+        Self { set: precision.is_some(), value: precision.cloned() }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { proximity_precision: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct TypoToleranceAnalytics {
+    pub enabled: Option<bool>,
+    pub disable_on_attributes: Option<bool>,
+    pub disable_on_words: Option<bool>,
+    pub min_word_size_for_one_typo: Option<u8>,
+    pub min_word_size_for_two_typos: Option<u8>,
+}
+
+impl TypoToleranceAnalytics {
+    pub fn new(setting: Option<&TypoSettings>) -> Self {
+        Self {
+            enabled: setting.as_ref().map(|s| !matches!(s.enabled, Setting::Set(false))),
+            disable_on_attributes: setting
+                .as_ref()
+                .and_then(|s| s.disable_on_attributes.as_ref().set().map(|m| !m.is_empty())),
+            disable_on_words: setting
+                .as_ref()
+                .and_then(|s| s.disable_on_words.as_ref().set().map(|m| !m.is_empty())),
+            min_word_size_for_one_typo: setting
+                .as_ref()
+                .and_then(|s| s.min_word_size_for_typos.as_ref().set().map(|s| s.one_typo.set()))
+                .flatten(),
+            min_word_size_for_two_typos: setting
+                .as_ref()
+                .and_then(|s| s.min_word_size_for_typos.as_ref().set().map(|s| s.two_typos.set()))
+                .flatten(),
+        }
+    }
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { typo_tolerance: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct FacetingAnalytics {
+    pub max_values_per_facet: Option<usize>,
+    pub sort_facet_values_by_star_count: Option<bool>,
+    pub sort_facet_values_by_total: Option<usize>,
+}
+
+impl FacetingAnalytics {
+    pub fn new(setting: Option<&FacetingSettings>) -> Self {
+        Self {
+            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())),
+        }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { faceting: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct PaginationAnalytics {
+    pub max_total_hits: Option<usize>,
+}
+
+impl PaginationAnalytics {
+    pub fn new(setting: Option<&PaginationSettings>) -> Self {
+        Self { max_total_hits: setting.as_ref().and_then(|s| s.max_total_hits.set()) }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { pagination: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct StopWordsAnalytics {
+    pub total: Option<usize>,
+}
+
+impl StopWordsAnalytics {
+    pub fn new(stop_words: Option<&BTreeSet<String>>) -> Self {
+        Self { total: stop_words.as_ref().map(|stop_words| stop_words.len()) }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { stop_words: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct SynonymsAnalytics {
+    pub total: Option<usize>,
+}
+
+impl SynonymsAnalytics {
+    pub fn new(synonyms: Option<&BTreeMap<String, Vec<String>>>) -> Self {
+        Self { total: synonyms.as_ref().map(|synonyms| synonyms.len()) }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { synonyms: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct EmbeddersAnalytics {
+    // last
+    pub total: Option<usize>,
+    // Merge the sources
+    pub sources: Option<HashSet<String>>,
+    // |=
+    pub document_template_used: Option<bool>,
+    // max
+    pub document_template_max_bytes: Option<usize>,
+    // |=
+    pub binary_quantization_used: Option<bool>,
+}
+
+impl EmbeddersAnalytics {
+    pub fn new(setting: Option<&BTreeMap<String, Setting<EmbeddingSettings>>>) -> Self {
+        let mut sources = std::collections::HashSet::new();
+
+        if let Some(s) = &setting {
+            for source in s
+                .values()
+                .filter_map(|config| config.clone().set())
+                .filter_map(|config| config.source.set())
+            {
+                use meilisearch_types::milli::vector::settings::EmbedderSource;
+                match source {
+                    EmbedderSource::OpenAi => sources.insert("openAi".to_string()),
+                    EmbedderSource::HuggingFace => sources.insert("huggingFace".to_string()),
+                    EmbedderSource::UserProvided => sources.insert("userProvided".to_string()),
+                    EmbedderSource::Ollama => sources.insert("ollama".to_string()),
+                    EmbedderSource::Rest => sources.insert("rest".to_string()),
+                };
+            }
+        };
+
+        Self {
+            total: setting.as_ref().map(|s| s.len()),
+            sources: Some(sources),
+            document_template_used: setting.as_ref().map(|map| {
+                map.values()
+                    .filter_map(|config| config.clone().set())
+                    .any(|config| config.document_template.set().is_some())
+            }),
+            document_template_max_bytes: setting.as_ref().and_then(|map| {
+                map.values()
+                    .filter_map(|config| config.clone().set())
+                    .filter_map(|config| config.document_template_max_bytes.set())
+                    .max()
+            }),
+            binary_quantization_used: setting.as_ref().map(|map| {
+                map.values()
+                    .filter_map(|config| config.clone().set())
+                    .any(|config| config.binary_quantized.set().is_some())
+            }),
+        }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { embedders: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+#[serde(transparent)]
+pub struct SearchCutoffMsAnalytics {
+    pub search_cutoff_ms: Option<u64>,
+}
+
+impl SearchCutoffMsAnalytics {
+    pub fn new(setting: Option<&u64>) -> Self {
+        Self { search_cutoff_ms: setting.copied() }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { search_cutoff_ms: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+#[serde(transparent)]
+pub struct LocalesAnalytics {
+    pub locales: Option<BTreeSet<Locale>>,
+}
+
+impl LocalesAnalytics {
+    pub fn new(rules: Option<&Vec<LocalizedAttributesRuleView>>) -> Self {
+        LocalesAnalytics {
+            locales: rules.as_ref().map(|rules| {
+                rules
+                    .iter()
+                    .flat_map(|rule| rule.locales.iter().cloned())
+                    .collect::<std::collections::BTreeSet<_>>()
+            }),
+        }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { locales: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct DictionaryAnalytics {
+    pub total: Option<usize>,
+}
+
+impl DictionaryAnalytics {
+    pub fn new(dictionary: Option<&BTreeSet<String>>) -> Self {
+        Self { total: dictionary.as_ref().map(|dictionary| dictionary.len()) }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { dictionary: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct SeparatorTokensAnalytics {
+    pub total: Option<usize>,
+}
+
+impl SeparatorTokensAnalytics {
+    pub fn new(separator_tokens: Option<&BTreeSet<String>>) -> Self {
+        Self { total: separator_tokens.as_ref().map(|separator_tokens| separator_tokens.len()) }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { separator_tokens: self, ..Default::default() }
+    }
+}
+
+#[derive(Serialize, Default)]
+pub struct NonSeparatorTokensAnalytics {
+    pub total: Option<usize>,
+}
+
+impl NonSeparatorTokensAnalytics {
+    pub fn new(non_separator_tokens: Option<&BTreeSet<String>>) -> Self {
+        Self {
+            total: non_separator_tokens
+                .as_ref()
+                .map(|non_separator_tokens| non_separator_tokens.len()),
+        }
+    }
+
+    pub fn into_settings(self) -> SettingsAnalytics {
+        SettingsAnalytics { non_separator_tokens: self, ..Default::default() }
+    }
+}

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

@@ -0,0 +1,201 @@
+use actix_web::web::{self, Data};
+use actix_web::{HttpRequest, HttpResponse};
+use deserr::actix_web::{AwebJson, AwebQueryParameter};
+use index_scheduler::IndexScheduler;
+use meilisearch_types::deserr::query_params::Param;
+use meilisearch_types::deserr::{DeserrJsonError, DeserrQueryParamError};
+use meilisearch_types::error::deserr_codes::*;
+use meilisearch_types::error::{ErrorCode as _, ResponseError};
+use meilisearch_types::index_uid::IndexUid;
+use meilisearch_types::keys::actions;
+use meilisearch_types::serde_cs::vec::CS;
+use serde_json::Value;
+use tracing::debug;
+
+use super::ActionPolicy;
+use crate::analytics::Analytics;
+use crate::extractors::authentication::GuardedData;
+use crate::extractors::sequential_extractor::SeqHandler;
+use crate::routes::indexes::similar_analytics::{SimilarAggregator, SimilarGET, SimilarPOST};
+use crate::search::{
+    add_search_rules, perform_similar, RankingScoreThresholdSimilar, RetrieveVectors, SearchKind,
+    SimilarQuery, SimilarResult, DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET,
+};
+
+pub fn configure(cfg: &mut web::ServiceConfig) {
+    cfg.service(
+        web::resource("")
+            .route(web::get().to(SeqHandler(similar_get)))
+            .route(web::post().to(SeqHandler(similar_post))),
+    );
+}
+
+pub async fn similar_get(
+    index_scheduler: GuardedData<ActionPolicy<{ actions::SEARCH }>, Data<IndexScheduler>>,
+    index_uid: web::Path<String>,
+    params: AwebQueryParameter<SimilarQueryGet, DeserrQueryParamError>,
+    req: HttpRequest,
+    analytics: web::Data<Analytics>,
+) -> Result<HttpResponse, ResponseError> {
+    let index_uid = IndexUid::try_from(index_uid.into_inner())?;
+
+    let query = params.0.try_into()?;
+
+    let mut aggregate = SimilarAggregator::<SimilarGET>::from_query(&query);
+
+    debug!(parameters = ?query, "Similar get");
+
+    let similar = similar(index_scheduler, index_uid, query).await;
+
+    if let Ok(similar) = &similar {
+        aggregate.succeed(similar);
+    }
+    analytics.publish(aggregate, &req);
+
+    let similar = similar?;
+
+    debug!(returns = ?similar, "Similar get");
+    Ok(HttpResponse::Ok().json(similar))
+}
+
+pub async fn similar_post(
+    index_scheduler: GuardedData<ActionPolicy<{ actions::SEARCH }>, Data<IndexScheduler>>,
+    index_uid: web::Path<String>,
+    params: AwebJson<SimilarQuery, DeserrJsonError>,
+    req: HttpRequest,
+    analytics: web::Data<Analytics>,
+) -> Result<HttpResponse, ResponseError> {
+    let index_uid = IndexUid::try_from(index_uid.into_inner())?;
+
+    let query = params.into_inner();
+    debug!(parameters = ?query, "Similar post");
+
+    let mut aggregate = SimilarAggregator::<SimilarPOST>::from_query(&query);
+
+    let similar = similar(index_scheduler, index_uid, query).await;
+
+    if let Ok(similar) = &similar {
+        aggregate.succeed(similar);
+    }
+    analytics.publish(aggregate, &req);
+
+    let similar = similar?;
+
+    debug!(returns = ?similar, "Similar post");
+    Ok(HttpResponse::Ok().json(similar))
+}
+
+async fn similar(
+    index_scheduler: GuardedData<ActionPolicy<{ actions::SEARCH }>, Data<IndexScheduler>>,
+    index_uid: IndexUid,
+    mut query: SimilarQuery,
+) -> Result<SimilarResult, ResponseError> {
+    let features = index_scheduler.features();
+
+    features.check_vector("Using the similar API")?;
+
+    let retrieve_vectors = RetrieveVectors::new(query.retrieve_vectors, features)?;
+
+    // Tenant token search_rules.
+    if let Some(search_rules) = index_scheduler.filters().get_index_search_rules(&index_uid) {
+        add_search_rules(&mut query.filter, search_rules);
+    }
+
+    let index = index_scheduler.index(&index_uid)?;
+
+    let (embedder_name, embedder, quantized) =
+        SearchKind::embedder(&index_scheduler, &index, &query.embedder, None)?;
+
+    tokio::task::spawn_blocking(move || {
+        perform_similar(
+            &index,
+            query,
+            embedder_name,
+            embedder,
+            quantized,
+            retrieve_vectors,
+            index_scheduler.features(),
+        )
+    })
+    .await?
+}
+
+#[derive(Debug, deserr::Deserr)]
+#[deserr(error = DeserrQueryParamError, rename_all = camelCase, deny_unknown_fields)]
+pub struct SimilarQueryGet {
+    #[deserr(error = DeserrQueryParamError<InvalidSimilarId>)]
+    id: Param<String>,
+    #[deserr(default = Param(DEFAULT_SEARCH_OFFSET()), error = DeserrQueryParamError<InvalidSimilarOffset>)]
+    offset: Param<usize>,
+    #[deserr(default = Param(DEFAULT_SEARCH_LIMIT()), error = DeserrQueryParamError<InvalidSimilarLimit>)]
+    limit: Param<usize>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSimilarAttributesToRetrieve>)]
+    attributes_to_retrieve: Option<CS<String>>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSimilarRetrieveVectors>)]
+    retrieve_vectors: Param<bool>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSimilarFilter>)]
+    filter: Option<String>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSimilarShowRankingScore>)]
+    show_ranking_score: Param<bool>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSimilarShowRankingScoreDetails>)]
+    show_ranking_score_details: Param<bool>,
+    #[deserr(default, error = DeserrQueryParamError<InvalidSimilarRankingScoreThreshold>, default)]
+    pub ranking_score_threshold: Option<RankingScoreThresholdGet>,
+    #[deserr(error = DeserrQueryParamError<InvalidEmbedder>)]
+    pub embedder: String,
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, deserr::Deserr)]
+#[deserr(try_from(String) = TryFrom::try_from -> InvalidSimilarRankingScoreThreshold)]
+pub struct RankingScoreThresholdGet(RankingScoreThresholdSimilar);
+
+impl std::convert::TryFrom<String> for RankingScoreThresholdGet {
+    type Error = InvalidSimilarRankingScoreThreshold;
+
+    fn try_from(s: String) -> Result<Self, Self::Error> {
+        let f: f64 = s.parse().map_err(|_| InvalidSimilarRankingScoreThreshold)?;
+        Ok(RankingScoreThresholdGet(RankingScoreThresholdSimilar::try_from(f)?))
+    }
+}
+
+impl TryFrom<SimilarQueryGet> for SimilarQuery {
+    type Error = ResponseError;
+
+    fn try_from(
+        SimilarQueryGet {
+            id,
+            offset,
+            limit,
+            attributes_to_retrieve,
+            retrieve_vectors,
+            filter,
+            show_ranking_score,
+            show_ranking_score_details,
+            embedder,
+            ranking_score_threshold,
+        }: SimilarQueryGet,
+    ) -> Result<Self, Self::Error> {
+        let filter = match filter {
+            Some(f) => match serde_json::from_str(&f) {
+                Ok(v) => Some(v),
+                _ => Some(Value::String(f)),
+            },
+            None => None,
+        };
+
+        Ok(SimilarQuery {
+            id: id.0.try_into().map_err(|code: InvalidSimilarId| {
+                ResponseError::from_msg(code.to_string(), code.error_code())
+            })?,
+            offset: offset.0,
+            limit: limit.0,
+            filter,
+            embedder,
+            attributes_to_retrieve: attributes_to_retrieve.map(|o| o.into_iter().collect()),
+            retrieve_vectors: retrieve_vectors.0,
+            show_ranking_score: show_ranking_score.0,
+            show_ranking_score_details: show_ranking_score_details.0,
+            ranking_score_threshold: ranking_score_threshold.map(|x| x.0),
+        })
+    }
+}

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

@@ -0,0 +1,235 @@
+use std::collections::{BinaryHeap, HashMap};
+
+use once_cell::sync::Lazy;
+use regex::Regex;
+use serde_json::{json, Value};
+
+use crate::{
+    aggregate_methods,
+    analytics::{Aggregate, AggregateMethod},
+    search::{SimilarQuery, SimilarResult},
+};
+
+aggregate_methods!(
+    SimilarPOST => "Similar POST",
+    SimilarGET => "Similar GET",
+);
+
+#[derive(Default)]
+pub struct SimilarAggregator<Method: AggregateMethod> {
+    // requests
+    total_received: usize,
+    total_succeeded: usize,
+    time_spent: BinaryHeap<usize>,
+
+    // filter
+    filter_with_geo_radius: bool,
+    filter_with_geo_bounding_box: bool,
+    // every time a request has a filter, this field must be incremented by the number of terms it contains
+    filter_sum_of_criteria_terms: usize,
+    // every time a request has a filter, this field must be incremented by one
+    filter_total_number_of_criteria: usize,
+    used_syntax: HashMap<String, usize>,
+
+    // Whether a non-default embedder was specified
+    retrieve_vectors: bool,
+
+    // pagination
+    max_limit: usize,
+    max_offset: usize,
+
+    // formatting
+    max_attributes_to_retrieve: usize,
+
+    // scoring
+    show_ranking_score: bool,
+    show_ranking_score_details: bool,
+    ranking_score_threshold: bool,
+
+    marker: std::marker::PhantomData<Method>,
+}
+
+impl<Method: AggregateMethod> SimilarAggregator<Method> {
+    #[allow(clippy::field_reassign_with_default)]
+    pub fn from_query(query: &SimilarQuery) -> Self {
+        let SimilarQuery {
+            id: _,
+            embedder: _,
+            offset,
+            limit,
+            attributes_to_retrieve: _,
+            retrieve_vectors,
+            show_ranking_score,
+            show_ranking_score_details,
+            filter,
+            ranking_score_threshold,
+        } = query;
+
+        let mut ret = Self::default();
+
+        ret.total_received = 1;
+
+        if let Some(ref filter) = filter {
+            static RE: Lazy<Regex> = Lazy::new(|| Regex::new("AND | OR").unwrap());
+            ret.filter_total_number_of_criteria = 1;
+
+            let syntax = match filter {
+                Value::String(_) => "string".to_string(),
+                Value::Array(values) => {
+                    if values.iter().map(|v| v.to_string()).any(|s| RE.is_match(&s)) {
+                        "mixed".to_string()
+                    } else {
+                        "array".to_string()
+                    }
+                }
+                _ => "none".to_string(),
+            };
+            // convert the string to a HashMap
+            ret.used_syntax.insert(syntax, 1);
+
+            let stringified_filters = filter.to_string();
+            ret.filter_with_geo_radius = stringified_filters.contains("_geoRadius(");
+            ret.filter_with_geo_bounding_box = stringified_filters.contains("_geoBoundingBox(");
+            ret.filter_sum_of_criteria_terms = RE.split(&stringified_filters).count();
+        }
+
+        ret.max_limit = *limit;
+        ret.max_offset = *offset;
+
+        ret.show_ranking_score = *show_ranking_score;
+        ret.show_ranking_score_details = *show_ranking_score_details;
+        ret.ranking_score_threshold = ranking_score_threshold.is_some();
+
+        ret.retrieve_vectors = *retrieve_vectors;
+
+        ret
+    }
+
+    pub fn succeed(&mut self, result: &SimilarResult) {
+        let SimilarResult { id: _, hits: _, processing_time_ms, hits_info: _ } = result;
+
+        self.total_succeeded = self.total_succeeded.saturating_add(1);
+
+        self.time_spent.push(*processing_time_ms as usize);
+    }
+}
+
+impl<Method: AggregateMethod> Aggregate for SimilarAggregator<Method> {
+    fn event_name(&self) -> &'static str {
+        Method::event_name()
+    }
+
+    /// Aggregate one [SimilarAggregator] into another.
+    fn aggregate(mut self: Box<Self>, new: Box<Self>) -> Box<Self> {
+        let Self {
+            total_received,
+            total_succeeded,
+            mut time_spent,
+            filter_with_geo_radius,
+            filter_with_geo_bounding_box,
+            filter_sum_of_criteria_terms,
+            filter_total_number_of_criteria,
+            used_syntax,
+            max_limit,
+            max_offset,
+            max_attributes_to_retrieve,
+            show_ranking_score,
+            show_ranking_score_details,
+            ranking_score_threshold,
+            retrieve_vectors,
+            marker: _,
+        } = *new;
+
+        // request
+        self.total_received = self.total_received.saturating_add(total_received);
+        self.total_succeeded = self.total_succeeded.saturating_add(total_succeeded);
+        self.time_spent.append(&mut time_spent);
+
+        // filter
+        self.filter_with_geo_radius |= filter_with_geo_radius;
+        self.filter_with_geo_bounding_box |= filter_with_geo_bounding_box;
+        self.filter_sum_of_criteria_terms =
+            self.filter_sum_of_criteria_terms.saturating_add(filter_sum_of_criteria_terms);
+        self.filter_total_number_of_criteria =
+            self.filter_total_number_of_criteria.saturating_add(filter_total_number_of_criteria);
+        for (key, value) in used_syntax.into_iter() {
+            let used_syntax = self.used_syntax.entry(key).or_insert(0);
+            *used_syntax = used_syntax.saturating_add(value);
+        }
+
+        self.retrieve_vectors |= retrieve_vectors;
+
+        // pagination
+        self.max_limit = self.max_limit.max(max_limit);
+        self.max_offset = self.max_offset.max(max_offset);
+
+        // formatting
+        self.max_attributes_to_retrieve =
+            self.max_attributes_to_retrieve.max(max_attributes_to_retrieve);
+
+        // scoring
+        self.show_ranking_score |= show_ranking_score;
+        self.show_ranking_score_details |= show_ranking_score_details;
+        self.ranking_score_threshold |= ranking_score_threshold;
+
+        self
+    }
+
+    fn into_event(self: Box<Self>) -> serde_json::Value {
+        let Self {
+            total_received,
+            total_succeeded,
+            time_spent,
+            filter_with_geo_radius,
+            filter_with_geo_bounding_box,
+            filter_sum_of_criteria_terms,
+            filter_total_number_of_criteria,
+            used_syntax,
+            max_limit,
+            max_offset,
+            max_attributes_to_retrieve,
+            show_ranking_score,
+            show_ranking_score_details,
+            ranking_score_threshold,
+            retrieve_vectors,
+            marker: _,
+        } = *self;
+
+        // we get all the values in a sorted manner
+        let time_spent = time_spent.into_sorted_vec();
+        // the index of the 99th percentage of value
+        let percentile_99th = time_spent.len() * 99 / 100;
+        // We are only interested by the slowest value of the 99th fastest results
+        let time_spent = time_spent.get(percentile_99th);
+
+        json!({
+            "requests": {
+                "99th_response_time": time_spent.map(|t| format!("{:.2}", t)),
+                "total_succeeded": total_succeeded,
+                "total_failed": total_received.saturating_sub(total_succeeded), // just to be sure we never panics
+                "total_received": total_received,
+            },
+            "filter": {
+               "with_geoRadius": filter_with_geo_radius,
+               "with_geoBoundingBox": filter_with_geo_bounding_box,
+               "avg_criteria_number": format!("{:.2}", filter_sum_of_criteria_terms as f64 / filter_total_number_of_criteria as f64),
+               "most_used_syntax": used_syntax.iter().max_by_key(|(_, v)| *v).map(|(k, _)| json!(k)).unwrap_or_else(|| json!(null)),
+            },
+            "vector": {
+                "retrieve_vectors": retrieve_vectors,
+            },
+            "pagination": {
+               "max_limit": max_limit,
+               "max_offset": max_offset,
+            },
+            "formatting": {
+                "max_attributes_to_retrieve": max_attributes_to_retrieve,
+            },
+            "scoring": {
+                "show_ranking_score": show_ranking_score,
+                "show_ranking_score_details": show_ranking_score_details,
+                "ranking_score_threshold": ranking_score_threshold,
+            }
+        })
+    }
+}