3699: Search for Facet Values r=Kerollmops a=Kerollmops

This PR introduces the first version of [the _Search for Facet Values_ feature](https://github.com/meilisearch/product/discussions/515) that allows a user to search for facets, by optionally using a prefix string and optionally specifying the `q` and `filter` original search parameters to restrict the candidates to search in.

The steps to merge it into Meilisearch will first start by providing prototype Docker images. This way users will be able to test the prototypes before using them.

The current route to use the _Search for Facet Values_ feature is the `POST /indexes/{index}/facet-search` where the body is a JSON object that looks like the following:
```json5
{
  "q": "spiderman", // optional
  "filter": "rating > 10", // optional
  "facetName": "genres",
  "facetQuery": "a" // optional
}
```

## What is missing?

 - [x] Send some analytics.
 - [x] Support the `matchingStrategy` parameter.
 - [x] Make sure that the errors are the right ones.
 - [x] Use the [Index typo tolerance settings](https://www.meilisearch.com/docs/learn/configuration/typo_tolerance#minwordsizefortypos) when matching facet values.
    - [x] minWordSizeForTypos.oneTypo
    - [x] minWordSizeForTypos.twoTypo
 - [x] Add tests
 - [x] Log the time it took to compute the results.
 - [x] Fix the compilation warnings.
 - [x] [Create an issue to fix potential performance issues when indexing](https://github.com/meilisearch/meilisearch/issues/3862).


Co-authored-by: Clément Renault <clement@meilisearch.com>
Co-authored-by: Kerollmops <clement@meilisearch.com>
This commit is contained in:
meili-bors[bot] 2023-06-29 09:08:55 +00:00 committed by GitHub
commit 73bb080a26
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
21 changed files with 774 additions and 50 deletions

View File

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

View File

@ -233,6 +233,7 @@ InvalidSearchAttributesToRetrieve , InvalidRequest , BAD_REQUEST ;
InvalidSearchCropLength , InvalidRequest , BAD_REQUEST ;
InvalidSearchCropMarker , InvalidRequest , BAD_REQUEST ;
InvalidSearchFacets , InvalidRequest , BAD_REQUEST ;
InvalidFacetSearchFacetName , InvalidRequest , BAD_REQUEST ;
InvalidSearchFilter , InvalidRequest , BAD_REQUEST ;
InvalidSearchHighlightPostTag , InvalidRequest , BAD_REQUEST ;
InvalidSearchHighlightPreTag , InvalidRequest , BAD_REQUEST ;
@ -242,6 +243,8 @@ InvalidSearchMatchingStrategy , InvalidRequest , BAD_REQUEST ;
InvalidSearchOffset , InvalidRequest , BAD_REQUEST ;
InvalidSearchPage , InvalidRequest , BAD_REQUEST ;
InvalidSearchQ , InvalidRequest , BAD_REQUEST ;
InvalidFacetSearchQuery , InvalidRequest , BAD_REQUEST ;
InvalidFacetSearchName , InvalidRequest , BAD_REQUEST ;
InvalidSearchVector , InvalidRequest , BAD_REQUEST ;
InvalidSearchShowMatchesPosition , InvalidRequest , BAD_REQUEST ;
InvalidSearchShowRankingScore , InvalidRequest , BAD_REQUEST ;
@ -284,6 +287,7 @@ MissingApiKeyIndexes , InvalidRequest , BAD_REQUEST ;
MissingAuthorizationHeader , Auth , UNAUTHORIZED ;
MissingContentType , InvalidRequest , UNSUPPORTED_MEDIA_TYPE ;
MissingDocumentId , InvalidRequest , BAD_REQUEST ;
MissingFacetSearchFacetName , InvalidRequest , BAD_REQUEST ;
MissingIndexUid , InvalidRequest , BAD_REQUEST ;
MissingMasterKey , Auth , UNAUTHORIZED ;
MissingPayload , InvalidRequest , BAD_REQUEST ;
@ -340,6 +344,9 @@ impl ErrorCode for milli::Error {
UserError::InvalidSearchableAttribute { .. } => {
Code::InvalidAttributesToSearchOn
}
UserError::InvalidFacetSearchFacetName { .. } => {
Code::InvalidFacetSearchFacetName
}
UserError::CriterionError(_) => Code::InvalidSettingsRankingRules,
UserError::InvalidGeoField { .. } => Code::InvalidDocumentGeoField,
UserError::InvalidVectorDimensions { .. } => Code::InvalidVectorDimensions,

View File

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

View File

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

View File

@ -1,5 +1,6 @@
use std::collections::{BinaryHeap, HashMap, HashSet};
use std::fs;
use std::mem::take;
use std::path::{Path, PathBuf};
use std::sync::Arc;
use std::time::{Duration, Instant};
@ -29,11 +30,13 @@ use super::{
use crate::analytics::Analytics;
use crate::option::{default_http_addr, IndexerOpts, MaxMemory, MaxThreads, ScheduleSnapshot};
use crate::routes::indexes::documents::UpdateDocumentsQuery;
use crate::routes::indexes::facet_search::FacetSearchQuery;
use crate::routes::tasks::TasksFilterQuery;
use crate::routes::{create_all_stats, Stats};
use crate::search::{
SearchQuery, SearchQueryWithIndex, SearchResult, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER,
DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT,
FacetSearchResult, MatchingStrategy, SearchQuery, SearchQueryWithIndex, SearchResult,
DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT,
};
use crate::Opt;
@ -71,6 +74,7 @@ pub enum AnalyticsMsg {
AggregateGetSearch(SearchAggregator),
AggregatePostSearch(SearchAggregator),
AggregatePostMultiSearch(MultiSearchAggregator),
AggregatePostFacetSearch(FacetSearchAggregator),
AggregateAddDocuments(DocumentsAggregator),
AggregateDeleteDocuments(DocumentsDeletionAggregator),
AggregateUpdateDocuments(DocumentsAggregator),
@ -139,6 +143,7 @@ impl SegmentAnalytics {
batcher,
post_search_aggregator: SearchAggregator::default(),
post_multi_search_aggregator: MultiSearchAggregator::default(),
post_facet_search_aggregator: FacetSearchAggregator::default(),
get_search_aggregator: SearchAggregator::default(),
add_documents_aggregator: DocumentsAggregator::default(),
delete_documents_aggregator: DocumentsDeletionAggregator::default(),
@ -182,6 +187,10 @@ impl super::Analytics for SegmentAnalytics {
let _ = self.sender.try_send(AnalyticsMsg::AggregatePostSearch(aggregate));
}
fn post_facet_search(&self, aggregate: FacetSearchAggregator) {
let _ = self.sender.try_send(AnalyticsMsg::AggregatePostFacetSearch(aggregate));
}
fn post_multi_search(&self, aggregate: MultiSearchAggregator) {
let _ = self.sender.try_send(AnalyticsMsg::AggregatePostMultiSearch(aggregate));
}
@ -354,6 +363,7 @@ pub struct Segment {
get_search_aggregator: SearchAggregator,
post_search_aggregator: SearchAggregator,
post_multi_search_aggregator: MultiSearchAggregator,
post_facet_search_aggregator: FacetSearchAggregator,
add_documents_aggregator: DocumentsAggregator,
delete_documents_aggregator: DocumentsDeletionAggregator,
update_documents_aggregator: DocumentsAggregator,
@ -418,6 +428,7 @@ impl Segment {
Some(AnalyticsMsg::AggregateGetSearch(agreg)) => self.get_search_aggregator.aggregate(agreg),
Some(AnalyticsMsg::AggregatePostSearch(agreg)) => self.post_search_aggregator.aggregate(agreg),
Some(AnalyticsMsg::AggregatePostMultiSearch(agreg)) => self.post_multi_search_aggregator.aggregate(agreg),
Some(AnalyticsMsg::AggregatePostFacetSearch(agreg)) => self.post_facet_search_aggregator.aggregate(agreg),
Some(AnalyticsMsg::AggregateAddDocuments(agreg)) => self.add_documents_aggregator.aggregate(agreg),
Some(AnalyticsMsg::AggregateDeleteDocuments(agreg)) => self.delete_documents_aggregator.aggregate(agreg),
Some(AnalyticsMsg::AggregateUpdateDocuments(agreg)) => self.update_documents_aggregator.aggregate(agreg),
@ -461,55 +472,74 @@ impl Segment {
})
.await;
}
let get_search = std::mem::take(&mut self.get_search_aggregator)
.into_event(&self.user, "Documents Searched GET");
let post_search = std::mem::take(&mut self.post_search_aggregator)
.into_event(&self.user, "Documents Searched POST");
let post_multi_search = std::mem::take(&mut self.post_multi_search_aggregator)
.into_event(&self.user, "Documents Searched by Multi-Search POST");
let add_documents = std::mem::take(&mut self.add_documents_aggregator)
.into_event(&self.user, "Documents Added");
let delete_documents = std::mem::take(&mut self.delete_documents_aggregator)
.into_event(&self.user, "Documents Deleted");
let update_documents = std::mem::take(&mut self.update_documents_aggregator)
.into_event(&self.user, "Documents Updated");
let get_fetch_documents = std::mem::take(&mut self.get_fetch_documents_aggregator)
.into_event(&self.user, "Documents Fetched GET");
let post_fetch_documents = std::mem::take(&mut self.post_fetch_documents_aggregator)
.into_event(&self.user, "Documents Fetched POST");
let get_tasks =
std::mem::take(&mut self.get_tasks_aggregator).into_event(&self.user, "Tasks Seen");
let health =
std::mem::take(&mut self.health_aggregator).into_event(&self.user, "Health Seen");
if let Some(get_search) = get_search {
let Segment {
inbox: _,
opt: _,
batcher: _,
user,
get_search_aggregator,
post_search_aggregator,
post_multi_search_aggregator,
post_facet_search_aggregator,
add_documents_aggregator,
delete_documents_aggregator,
update_documents_aggregator,
get_fetch_documents_aggregator,
post_fetch_documents_aggregator,
get_tasks_aggregator,
health_aggregator,
} = self;
if let Some(get_search) =
take(get_search_aggregator).into_event(&user, "Documents Searched GET")
{
let _ = self.batcher.push(get_search).await;
}
if let Some(post_search) = post_search {
if let Some(post_search) =
take(post_search_aggregator).into_event(&user, "Documents Searched POST")
{
let _ = self.batcher.push(post_search).await;
}
if let Some(post_multi_search) = post_multi_search {
if let Some(post_multi_search) = take(post_multi_search_aggregator)
.into_event(&user, "Documents Searched by Multi-Search POST")
{
let _ = self.batcher.push(post_multi_search).await;
}
if let Some(add_documents) = add_documents {
if let Some(post_facet_search) =
take(post_facet_search_aggregator).into_event(&user, "Facet Searched POST")
{
let _ = self.batcher.push(post_facet_search).await;
}
if let Some(add_documents) =
take(add_documents_aggregator).into_event(&user, "Documents Added")
{
let _ = self.batcher.push(add_documents).await;
}
if let Some(delete_documents) = delete_documents {
if let Some(delete_documents) =
take(delete_documents_aggregator).into_event(&user, "Documents Deleted")
{
let _ = self.batcher.push(delete_documents).await;
}
if let Some(update_documents) = update_documents {
if let Some(update_documents) =
take(update_documents_aggregator).into_event(&user, "Documents Updated")
{
let _ = self.batcher.push(update_documents).await;
}
if let Some(get_fetch_documents) = get_fetch_documents {
if let Some(get_fetch_documents) =
take(get_fetch_documents_aggregator).into_event(&user, "Documents Fetched GET")
{
let _ = self.batcher.push(get_fetch_documents).await;
}
if let Some(post_fetch_documents) = post_fetch_documents {
if let Some(post_fetch_documents) =
take(post_fetch_documents_aggregator).into_event(&user, "Documents Fetched POST")
{
let _ = self.batcher.push(post_fetch_documents).await;
}
if let Some(get_tasks) = get_tasks {
if let Some(get_tasks) = take(get_tasks_aggregator).into_event(&user, "Tasks Seen") {
let _ = self.batcher.push(get_tasks).await;
}
if let Some(health) = health {
if let Some(health) = take(health_aggregator).into_event(&user, "Health Seen") {
let _ = self.batcher.push(health).await;
}
let _ = self.batcher.flush().await;
@ -909,6 +939,120 @@ impl MultiSearchAggregator {
}
}
#[derive(Default)]
pub struct FacetSearchAggregator {
timestamp: Option<OffsetDateTime>,
// context
user_agents: HashSet<String>,
// requests
total_received: usize,
total_succeeded: usize,
time_spent: BinaryHeap<usize>,
// The set of all facetNames that were used
facet_names: HashSet<String>,
// As there been any other parameter than the facetName or facetQuery ones?
additional_search_parameters_provided: bool,
}
impl FacetSearchAggregator {
pub fn from_query(query: &FacetSearchQuery, request: &HttpRequest) -> Self {
let FacetSearchQuery {
facet_query: _,
facet_name,
vector,
q,
filter,
matching_strategy,
attributes_to_search_on,
} = query;
let mut ret = Self::default();
ret.timestamp = Some(OffsetDateTime::now_utc());
ret.total_received = 1;
ret.user_agents = extract_user_agents(request).into_iter().collect();
ret.facet_names = Some(facet_name.clone()).into_iter().collect();
ret.additional_search_parameters_provided = q.is_some()
|| vector.is_some()
|| filter.is_some()
|| *matching_strategy != MatchingStrategy::default()
|| attributes_to_search_on.is_some();
ret
}
pub fn succeed(&mut self, result: &FacetSearchResult) {
self.total_succeeded = self.total_succeeded.saturating_add(1);
self.time_spent.push(result.processing_time_ms as usize);
}
/// Aggregate one [SearchAggregator] into another.
pub fn aggregate(&mut self, mut other: Self) {
if self.timestamp.is_none() {
self.timestamp = other.timestamp;
}
// context
for user_agent in other.user_agents.into_iter() {
self.user_agents.insert(user_agent);
}
// request
self.total_received = self.total_received.saturating_add(other.total_received);
self.total_succeeded = self.total_succeeded.saturating_add(other.total_succeeded);
self.time_spent.append(&mut other.time_spent);
// facet_names
for facet_name in other.facet_names.into_iter() {
self.facet_names.insert(facet_name);
}
// additional_search_parameters_provided
self.additional_search_parameters_provided = self.additional_search_parameters_provided
| other.additional_search_parameters_provided;
}
pub fn into_event(self, user: &User, event_name: &str) -> Option<Track> {
if self.total_received == 0 {
None
} else {
// the index of the 99th percentage of value
let percentile_99th = 0.99 * (self.total_succeeded as f64 - 1.) + 1.;
// we get all the values in a sorted manner
let time_spent = self.time_spent.into_sorted_vec();
// We are only interested by the slowest value of the 99th fastest results
let time_spent = time_spent.get(percentile_99th as usize);
let properties = json!({
"user-agent": self.user_agents,
"requests": {
"99th_response_time": time_spent.map(|t| format!("{:.2}", t)),
"total_succeeded": self.total_succeeded,
"total_failed": self.total_received.saturating_sub(self.total_succeeded), // just to be sure we never panics
"total_received": self.total_received,
},
"facets": {
"total_distinct_facet_count": self.facet_names.len(),
"additional_search_parameters_provided": self.additional_search_parameters_provided,
},
});
Some(Track {
timestamp: self.timestamp,
user: user.clone(),
event: event_name.to_string(),
properties,
..Default::default()
})
}
}
}
#[derive(Default)]
pub struct DocumentsAggregator {
timestamp: Option<OffsetDateTime>,

View File

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

View File

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

View File

@ -10,9 +10,12 @@ use log::warn;
use meilisearch_auth::IndexSearchRules;
use meilisearch_types::deserr::DeserrJsonError;
use meilisearch_types::error::deserr_codes::*;
use meilisearch_types::heed::RoTxn;
use meilisearch_types::index_uid::IndexUid;
use meilisearch_types::milli::score_details::{ScoreDetails, ScoringStrategy};
use meilisearch_types::milli::{dot_product_similarity, InternalError};
use meilisearch_types::milli::{
dot_product_similarity, FacetValueHit, InternalError, SearchForFacetValues,
};
use meilisearch_types::settings::DEFAULT_PAGINATION_MAX_TOTAL_HITS;
use meilisearch_types::{milli, Document};
use milli::tokenizer::TokenizerBuilder;
@ -199,7 +202,7 @@ impl SearchQueryWithIndex {
}
}
#[derive(Debug, Clone, PartialEq, Eq, Deserr)]
#[derive(Debug, Copy, Clone, PartialEq, Eq, Deserr)]
#[deserr(rename_all = camelCase)]
pub enum MatchingStrategy {
/// Remove query words from last to first
@ -278,6 +281,14 @@ pub struct FacetStats {
pub max: f64,
}
#[derive(Serialize, Debug, Clone, PartialEq)]
#[serde(rename_all = "camelCase")]
pub struct FacetSearchResult {
pub facet_hits: Vec<FacetValueHit>,
pub facet_query: Option<String>,
pub processing_time_ms: u128,
}
/// Incorporate search rules in search query
pub fn add_search_rules(query: &mut SearchQuery, rules: IndexSearchRules) {
query.filter = match (query.filter.take(), rules.filter) {
@ -298,15 +309,13 @@ pub fn add_search_rules(query: &mut SearchQuery, rules: IndexSearchRules) {
}
}
pub fn perform_search(
index: &Index,
query: SearchQuery,
fn prepare_search<'t>(
index: &'t Index,
rtxn: &'t RoTxn,
query: &'t SearchQuery,
features: RoFeatures,
) -> Result<SearchResult, MeilisearchHttpError> {
let before_search = Instant::now();
let rtxn = index.read_txn()?;
let mut search = index.search(&rtxn);
) -> Result<(milli::Search<'t>, bool, usize, usize), MeilisearchHttpError> {
let mut search = index.search(rtxn);
if query.vector.is_some() && query.q.is_some() {
warn!("Ignoring the query string `q` when used with the `vector` parameter.");
@ -328,7 +337,7 @@ pub fn perform_search(
search.terms_matching_strategy(query.matching_strategy.into());
let max_total_hits = index
.pagination_max_total_hits(&rtxn)
.pagination_max_total_hits(rtxn)
.map_err(milli::Error::from)?
.unwrap_or(DEFAULT_PAGINATION_MAX_TOTAL_HITS);
@ -383,6 +392,20 @@ pub fn perform_search(
search.sort_criteria(sort);
}
Ok((search, is_finite_pagination, max_total_hits, offset))
}
pub fn perform_search(
index: &Index,
query: SearchQuery,
features: RoFeatures,
) -> Result<SearchResult, MeilisearchHttpError> {
let before_search = Instant::now();
let rtxn = index.read_txn()?;
let (search, is_finite_pagination, max_total_hits, offset) =
prepare_search(index, &rtxn, &query, features)?;
let milli::SearchResult { documents_ids, matching_words, candidates, document_scores, .. } =
search.execute()?;
@ -557,6 +580,29 @@ pub fn perform_search(
Ok(result)
}
pub fn perform_facet_search(
index: &Index,
search_query: SearchQuery,
facet_query: Option<String>,
facet_name: String,
features: RoFeatures,
) -> Result<FacetSearchResult, MeilisearchHttpError> {
let before_search = Instant::now();
let rtxn = index.read_txn()?;
let (search, _, _, _) = prepare_search(index, &rtxn, &search_query, features)?;
let mut facet_search = SearchForFacetValues::new(facet_name, search);
if let Some(facet_query) = &facet_query {
facet_search.query(facet_query);
}
Ok(FacetSearchResult {
facet_hits: facet_search.execute()?,
facet_query,
processing_time_ms: before_search.elapsed().as_millis(),
})
}
fn insert_geo_distance(sorts: &[String], document: &mut Document) {
lazy_static::lazy_static! {
static ref GEO_REGEX: Regex =

View File

@ -377,6 +377,11 @@ impl Index<'_> {
self.service.get(url).await
}
pub async fn facet_search(&self, query: Value) -> (Value, StatusCode) {
let url = format!("/indexes/{}/facet-search", urlencode(self.uid.as_ref()));
self.service.post_encoded(url, query, self.encoder).await
}
pub async fn update_distinct_attribute(&self, value: Value) -> (Value, StatusCode) {
let url =
format!("/indexes/{}/settings/{}", urlencode(self.uid.as_ref()), "distinct-attribute");

View File

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

View File

@ -2,6 +2,7 @@
// should be tested in its own module to isolate tests and keep the tests readable.
mod errors;
mod facet_search;
mod formatted;
mod multi;
mod pagination;

View File

@ -128,6 +128,16 @@ only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and undersco
}
)]
InvalidSortableAttribute { field: String, valid_fields: BTreeSet<String> },
#[error("Attribute `{}` is not facet-searchable. {}",
.field,
match .valid_fields.is_empty() {
true => "This index does not have configured facet-searchable attributes. To make it facet-searchable add it to the `filterableAttributes` index settings.".to_string(),
false => format!("Available facet-searchable attributes are: `{}`. To make it facet-searchable add it to the `filterableAttributes` index settings.",
valid_fields.iter().map(AsRef::as_ref).collect::<Vec<&str>>().join(", ")
),
}
)]
InvalidFacetSearchFacetName { field: String, valid_fields: BTreeSet<String> },
#[error("Attribute `{}` is not searchable. Available searchable attributes are: `{}{}`.",
.field,
.valid_fields.iter().map(AsRef::as_ref).collect::<Vec<&str>>().join(", "),

View File

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

View File

@ -2,6 +2,7 @@ mod beu32_str_codec;
mod byte_slice_ref;
pub mod facet;
mod field_id_word_count_codec;
mod fst_set_codec;
mod obkv_codec;
mod roaring_bitmap;
mod roaring_bitmap_length;
@ -15,6 +16,7 @@ pub use str_ref::StrRefCodec;
pub use self::beu32_str_codec::BEU32StrCodec;
pub use self::field_id_word_count_codec::FieldIdWordCountCodec;
pub use self::fst_set_codec::FstSetCodec;
pub use self::obkv_codec::ObkvCodec;
pub use self::roaring_bitmap::{BoRoaringBitmapCodec, CboRoaringBitmapCodec, RoaringBitmapCodec};
pub use self::roaring_bitmap_length::{

View File

@ -21,7 +21,7 @@ use crate::heed_codec::facet::{
FacetGroupKeyCodec, FacetGroupValueCodec, FieldDocIdFacetF64Codec, FieldDocIdFacetStringCodec,
FieldIdCodec, OrderedF64Codec,
};
use crate::heed_codec::{ScriptLanguageCodec, StrBEU16Codec, StrRefCodec};
use crate::heed_codec::{FstSetCodec, ScriptLanguageCodec, StrBEU16Codec, StrRefCodec};
use crate::readable_slices::ReadableSlices;
use crate::{
default_criteria, CboRoaringBitmapCodec, Criterion, DocumentId, ExternalDocumentsIds,
@ -94,6 +94,7 @@ pub mod db_name {
pub const FACET_ID_IS_NULL_DOCIDS: &str = "facet-id-is-null-docids";
pub const FACET_ID_IS_EMPTY_DOCIDS: &str = "facet-id-is-empty-docids";
pub const FACET_ID_STRING_DOCIDS: &str = "facet-id-string-docids";
pub const FACET_ID_STRING_FST: &str = "facet-id-string-fst";
pub const FIELD_ID_DOCID_FACET_F64S: &str = "field-id-docid-facet-f64s";
pub const FIELD_ID_DOCID_FACET_STRINGS: &str = "field-id-docid-facet-strings";
pub const VECTOR_ID_DOCID: &str = "vector-id-docids";
@ -154,6 +155,8 @@ pub struct Index {
pub facet_id_f64_docids: Database<FacetGroupKeyCodec<OrderedF64Codec>, FacetGroupValueCodec>,
/// Maps the facet field id and ranges of strings with the docids that corresponds to them.
pub facet_id_string_docids: Database<FacetGroupKeyCodec<StrRefCodec>, FacetGroupValueCodec>,
/// Maps the facet field id of the string facets with an FST containing all the facets values.
pub facet_id_string_fst: Database<OwnedType<BEU16>, FstSetCodec>,
/// Maps the document id, the facet field id and the numbers.
pub field_id_docid_facet_f64s: Database<FieldDocIdFacetF64Codec, Unit>,
@ -206,6 +209,7 @@ impl Index {
let facet_id_f64_docids = env.create_database(&mut wtxn, Some(FACET_ID_F64_DOCIDS))?;
let facet_id_string_docids =
env.create_database(&mut wtxn, Some(FACET_ID_STRING_DOCIDS))?;
let facet_id_string_fst = env.create_database(&mut wtxn, Some(FACET_ID_STRING_FST))?;
let facet_id_exists_docids =
env.create_database(&mut wtxn, Some(FACET_ID_EXISTS_DOCIDS))?;
let facet_id_is_null_docids =
@ -240,6 +244,7 @@ impl Index {
field_id_word_count_docids,
facet_id_f64_docids,
facet_id_string_docids,
facet_id_string_fst,
facet_id_exists_docids,
facet_id_is_null_docids,
facet_id_is_empty_docids,

View File

@ -57,8 +57,9 @@ pub use self::heed_codec::{
};
pub use self::index::Index;
pub use self::search::{
FacetDistribution, Filter, FormatOptions, MatchBounds, MatcherBuilder, MatchingWords, Search,
SearchResult, TermsMatchingStrategy, DEFAULT_VALUES_PER_FACET,
FacetDistribution, FacetValueHit, Filter, FormatOptions, MatchBounds, MatcherBuilder,
MatchingWords, Search, SearchForFacetValues, SearchResult, TermsMatchingStrategy,
DEFAULT_VALUES_PER_FACET,
};
pub type Result<T> = std::result::Result<T, error::Error>;

View File

@ -1,15 +1,21 @@
use std::fmt;
use fst::automaton::{Automaton, Str};
use fst::{IntoStreamer, Streamer};
use levenshtein_automata::{LevenshteinAutomatonBuilder as LevBuilder, DFA};
use log::error;
use once_cell::sync::Lazy;
use roaring::bitmap::RoaringBitmap;
pub use self::facet::{FacetDistribution, Filter, DEFAULT_VALUES_PER_FACET};
pub use self::new::matches::{FormatOptions, MatchBounds, Matcher, MatcherBuilder, MatchingWords};
use self::new::PartialSearchResult;
use crate::error::UserError;
use crate::heed_codec::facet::{FacetGroupKey, FacetGroupValue};
use crate::score_details::{ScoreDetails, ScoringStrategy};
use crate::{
execute_search, AscDesc, DefaultSearchLogger, DocumentId, Index, Result, SearchContext,
execute_search, normalize_facet, AscDesc, DefaultSearchLogger, DocumentId, FieldId, Index,
Result, SearchContext, BEU16,
};
// Building these factories is not free.
@ -17,6 +23,9 @@ static LEVDIST0: Lazy<LevBuilder> = Lazy::new(|| LevBuilder::new(0, true));
static LEVDIST1: Lazy<LevBuilder> = Lazy::new(|| LevBuilder::new(1, true));
static LEVDIST2: Lazy<LevBuilder> = Lazy::new(|| LevBuilder::new(2, true));
/// The maximum number of facets returned by the facet search route.
const MAX_NUMBER_OF_FACETS: usize = 100;
pub mod facet;
mod fst_utils;
pub mod new;
@ -234,6 +243,195 @@ pub fn build_dfa(word: &str, typos: u8, is_prefix: bool) -> DFA {
}
}
pub struct SearchForFacetValues<'a> {
query: Option<String>,
facet: String,
search_query: Search<'a>,
}
impl<'a> SearchForFacetValues<'a> {
pub fn new(facet: String, search_query: Search<'a>) -> SearchForFacetValues<'a> {
SearchForFacetValues { query: None, facet, search_query }
}
pub fn query(&mut self, query: impl Into<String>) -> &mut Self {
self.query = Some(query.into());
self
}
fn one_original_value_of(
&self,
field_id: FieldId,
facet_str: &str,
any_docid: DocumentId,
) -> Result<Option<String>> {
let index = self.search_query.index;
let rtxn = self.search_query.rtxn;
let key: (FieldId, _, &str) = (field_id, any_docid, facet_str);
Ok(index.field_id_docid_facet_strings.get(rtxn, &key)?.map(|v| v.to_owned()))
}
pub fn execute(&self) -> Result<Vec<FacetValueHit>> {
let index = self.search_query.index;
let rtxn = self.search_query.rtxn;
let filterable_fields = index.filterable_fields(rtxn)?;
if !filterable_fields.contains(&self.facet) {
return Err(UserError::InvalidFacetSearchFacetName {
field: self.facet.clone(),
valid_fields: filterable_fields.into_iter().collect(),
}
.into());
}
let fields_ids_map = index.fields_ids_map(rtxn)?;
let fid = match fields_ids_map.id(&self.facet) {
Some(fid) => fid,
// we return an empty list of results when the attribute has been
// set as filterable but no document contains this field (yet).
None => return Ok(Vec::new()),
};
let fst = match self.search_query.index.facet_id_string_fst.get(rtxn, &BEU16::new(fid))? {
Some(fst) => fst,
None => return Ok(vec![]),
};
let search_candidates = self.search_query.execute()?.candidates;
match self.query.as_ref() {
Some(query) => {
let query = normalize_facet(query);
let query = query.as_str();
let authorize_typos = self.search_query.index.authorize_typos(rtxn)?;
let field_authorizes_typos =
!self.search_query.index.exact_attributes_ids(rtxn)?.contains(&fid);
if authorize_typos && field_authorizes_typos {
let mut results = vec![];
let exact_words_fst = self.search_query.index.exact_words(rtxn)?;
if exact_words_fst.map_or(false, |fst| fst.contains(query)) {
let key = FacetGroupKey { field_id: fid, level: 0, left_bound: query };
if let Some(FacetGroupValue { bitmap, .. }) =
index.facet_id_string_docids.get(rtxn, &key)?
{
let count = search_candidates.intersection_len(&bitmap);
if count != 0 {
let value = self
.one_original_value_of(fid, query, bitmap.min().unwrap())?
.unwrap_or_else(|| query.to_string());
results.push(FacetValueHit { value, count });
}
}
} else {
let one_typo = self.search_query.index.min_word_len_one_typo(rtxn)?;
let two_typos = self.search_query.index.min_word_len_two_typos(rtxn)?;
let is_prefix = true;
let automaton = if query.len() < one_typo as usize {
build_dfa(query, 0, is_prefix)
} else if query.len() < two_typos as usize {
build_dfa(query, 1, is_prefix)
} else {
build_dfa(query, 2, is_prefix)
};
let mut stream = fst.search(automaton).into_stream();
let mut length = 0;
while let Some(facet_value) = stream.next() {
let value = std::str::from_utf8(facet_value)?;
let key = FacetGroupKey { field_id: fid, level: 0, left_bound: value };
let docids = match index.facet_id_string_docids.get(rtxn, &key)? {
Some(FacetGroupValue { bitmap, .. }) => bitmap,
None => {
error!(
"the facet value is missing from the facet database: {key:?}"
);
continue;
}
};
let count = search_candidates.intersection_len(&docids);
if count != 0 {
let value = self
.one_original_value_of(fid, value, docids.min().unwrap())?
.unwrap_or_else(|| query.to_string());
results.push(FacetValueHit { value, count });
length += 1;
}
if length >= MAX_NUMBER_OF_FACETS {
break;
}
}
}
Ok(results)
} else {
let automaton = Str::new(query).starts_with();
let mut stream = fst.search(automaton).into_stream();
let mut results = vec![];
let mut length = 0;
while let Some(facet_value) = stream.next() {
let value = std::str::from_utf8(facet_value)?;
let key = FacetGroupKey { field_id: fid, level: 0, left_bound: value };
let docids = match index.facet_id_string_docids.get(rtxn, &key)? {
Some(FacetGroupValue { bitmap, .. }) => bitmap,
None => {
error!(
"the facet value is missing from the facet database: {key:?}"
);
continue;
}
};
let count = search_candidates.intersection_len(&docids);
if count != 0 {
let value = self
.one_original_value_of(fid, value, docids.min().unwrap())?
.unwrap_or_else(|| query.to_string());
results.push(FacetValueHit { value, count });
length += 1;
}
if length >= MAX_NUMBER_OF_FACETS {
break;
}
}
Ok(results)
}
}
None => {
let mut results = vec![];
let mut length = 0;
let prefix = FacetGroupKey { field_id: fid, level: 0, left_bound: "" };
for result in index.facet_id_string_docids.prefix_iter(rtxn, &prefix)? {
let (FacetGroupKey { left_bound, .. }, FacetGroupValue { bitmap, .. }) =
result?;
let count = search_candidates.intersection_len(&bitmap);
if count != 0 {
let value = self
.one_original_value_of(fid, left_bound, bitmap.min().unwrap())?
.unwrap_or_else(|| left_bound.to_string());
results.push(FacetValueHit { value, count });
length += 1;
}
if length >= MAX_NUMBER_OF_FACETS {
break;
}
}
Ok(results)
}
}
}
}
#[derive(Debug, Clone, serde::Serialize, PartialEq)]
pub struct FacetValueHit {
/// The original facet value
pub value: String,
/// The number of documents associated to this facet
pub count: u64,
}
#[cfg(test)]
mod test {
#[allow(unused_imports)]

View File

@ -34,6 +34,7 @@ impl<'t, 'u, 'i> ClearDocuments<'t, 'u, 'i> {
script_language_docids,
facet_id_f64_docids,
facet_id_string_docids,
facet_id_string_fst,
facet_id_exists_docids,
facet_id_is_null_docids,
facet_id_is_empty_docids,
@ -91,6 +92,7 @@ impl<'t, 'u, 'i> ClearDocuments<'t, 'u, 'i> {
word_prefix_fid_docids.clear(self.wtxn)?;
script_language_docids.clear(self.wtxn)?;
facet_id_f64_docids.clear(self.wtxn)?;
facet_id_string_fst.clear(self.wtxn)?;
facet_id_exists_docids.clear(self.wtxn)?;
facet_id_is_null_docids.clear(self.wtxn)?;
facet_id_is_empty_docids.clear(self.wtxn)?;

View File

@ -237,6 +237,7 @@ impl<'t, 'u, 'i> DeleteDocuments<'t, 'u, 'i> {
word_prefix_fid_docids,
facet_id_f64_docids: _,
facet_id_string_docids: _,
facet_id_string_fst: _,
field_id_docid_facet_f64s: _,
field_id_docid_facet_strings: _,
script_language_docids,

View File

@ -78,15 +78,16 @@ pub const FACET_MIN_LEVEL_SIZE: u8 = 5;
use std::fs::File;
use heed::types::DecodeIgnore;
use log::debug;
use time::OffsetDateTime;
use self::incremental::FacetsUpdateIncremental;
use super::FacetsUpdateBulk;
use crate::facet::FacetType;
use crate::heed_codec::facet::{FacetGroupKeyCodec, FacetGroupValueCodec};
use crate::heed_codec::facet::{FacetGroupKey, FacetGroupKeyCodec, FacetGroupValueCodec};
use crate::heed_codec::ByteSliceRefCodec;
use crate::{Index, Result};
use crate::{Index, Result, BEU16};
pub mod bulk;
pub mod delete;
@ -157,6 +158,43 @@ impl<'i> FacetsUpdate<'i> {
);
incremental_update.execute(wtxn)?;
}
// We compute one FST by string facet
let mut text_fsts = vec![];
let mut current_fst: Option<(u16, fst::SetBuilder<Vec<u8>>)> = None;
let database = self.index.facet_id_string_docids.remap_data_type::<DecodeIgnore>();
for result in database.iter(wtxn)? {
let (facet_group_key, _) = result?;
if let FacetGroupKey { field_id, level: 0, left_bound } = facet_group_key {
current_fst = match current_fst.take() {
Some((fid, fst_builder)) if fid != field_id => {
let fst = fst_builder.into_set();
text_fsts.push((fid, fst));
Some((field_id, fst::SetBuilder::memory()))
}
Some((field_id, fst_builder)) => Some((field_id, fst_builder)),
None => Some((field_id, fst::SetBuilder::memory())),
};
if let Some((_, fst_builder)) = current_fst.as_mut() {
fst_builder.insert(left_bound)?;
}
}
}
if let Some((field_id, fst_builder)) = current_fst {
let fst = fst_builder.into_set();
text_fsts.push((field_id, fst));
}
// We remove all of the previous FSTs that were in this database
self.index.facet_id_string_fst.clear(wtxn)?;
// We write those FSTs in LMDB now
for (field_id, fst) in text_fsts {
self.index.facet_id_string_fst.put(wtxn, &BEU16::new(field_id), &fst)?;
}
Ok(())
}
}

View File

@ -1 +0,0 @@