searchengines-web/MeiliSearch
searchengines-web/MeiliSearch
1
0
Fork 0
mirror of https://github.com/meilisearch/MeiliSearch synced 2025-07-03 03:47:02 +02:00
Code Issues Releases Wiki Activity

Merge pull request #5509 from meilisearch/release-v1.14.0-tmp

Browse source 
Bring back changes from v1.14.0 to main
This commit is contained in:
Louis Dureuil 2025-04-14 13:59:23 +00:00 • committed by GitHub
commit a500fa053c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
43 changed files with 1047 additions and 508 deletions
Download patch file Download diff file Expand all files Collapse all files

12
crates/meilisearch/Cargo.toml
View file

@ -30,11 +30,7 @@ actix-web = { version = "4.9.0", default-features = false, features = [
anyhow = { version = "1.0.95", features = ["backtrace"] }
async-trait = "0.1.85"
bstr = "1.11.3"
byte-unit = { version = "5.1.6", default-features = false, features = [
"std",
"byte",
"serde",
] }
byte-unit = { version = "5.1.6", features = ["serde"] }
bytes = "1.9.0"
clap = { version = "4.5.24", features = ["derive", "env"] }
crossbeam-channel = "0.5.15"
@ -140,7 +136,7 @@ reqwest = { version = "0.12.12", features = [
sha-1 = { version = "0.10.1", optional = true }
static-files = { version = "0.2.4", optional = true }
tempfile = { version = "3.15.0", optional = true }
zip = { version = "2.2.2", optional = true }
zip = { version = "2.3.0", optional = true }
[features]
default = ["meilisearch-types/all-tokenizations", "mini-dashboard"]
@ -170,5 +166,5 @@ german = ["meilisearch-types/german"]
turkish = ["meilisearch-types/turkish"]
[package.metadata.mini-dashboard]
assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.18/build.zip"
sha1 = "b408a30dcb6e20cddb0c153c23385bcac4c8e912"
assets-url = "https://github.com/meilisearch/mini-dashboard/releases/download/v0.2.19/build.zip"
sha1 = "7974430d5277c97f67cf6e95eec6faaac2788834"

3
crates/meilisearch/src/analytics/segment_analytics.rs
View file

@ -329,7 +329,8 @@ impl Infos {
http_addr: http_addr != default_http_addr(),
http_payload_size_limit,
experimental_max_number_of_batched_tasks,
experimental_limit_batched_tasks_total_size,
experimental_limit_batched_tasks_total_size:
experimental_limit_batched_tasks_total_size.into(),
task_queue_webhook: task_webhook_url.is_some(),
task_webhook_authorization_header: task_webhook_authorization_header.is_some(),
log_level: log_level.to_string(),

2
crates/meilisearch/src/lib.rs
View file

@ -228,7 +228,7 @@ pub fn setup_meilisearch(opt: &Opt) -> anyhow::Result<(Arc<IndexScheduler>, Arc<
cleanup_enabled: !opt.experimental_replication_parameters,
max_number_of_tasks: 1_000_000,
max_number_of_batched_tasks: opt.experimental_max_number_of_batched_tasks,
batched_tasks_size_limit: opt.experimental_limit_batched_tasks_total_size,
batched_tasks_size_limit: opt.experimental_limit_batched_tasks_total_size.into(),
index_growth_amount: byte_unit::Byte::from_str("10GiB").unwrap().as_u64() as usize,
index_count: DEFAULT_INDEX_COUNT,
instance_features: opt.to_instance_features(),

6
crates/meilisearch/src/option.rs
View file

@ -445,7 +445,7 @@ pub struct Opt {
/// see: <https://github.com/orgs/meilisearch/discussions/801>
#[clap(long, env = MEILI_EXPERIMENTAL_LIMIT_BATCHED_TASKS_TOTAL_SIZE, default_value_t = default_limit_batched_tasks_total_size())]
#[serde(default = "default_limit_batched_tasks_total_size")]
pub experimental_limit_batched_tasks_total_size: u64,
pub experimental_limit_batched_tasks_total_size: Byte,
/// Enables experimental caching of search query embeddings. The value represents the maximal number of entries in the cache of each
/// distinct embedder.
@ -968,8 +968,8 @@ fn default_limit_batched_tasks() -> usize {
usize::MAX
}
fn default_limit_batched_tasks_total_size() -> u64 {
u64::MAX
fn default_limit_batched_tasks_total_size() -> Byte {
Byte::from_u64(u64::MAX)
}
fn default_embedding_cache_entries() -> usize {

2
crates/meilisearch/src/routes/indexes/mod.rs
View file

@ -518,7 +518,7 @@ impl From<index_scheduler::IndexStats> for IndexStats {
.inner_stats
.number_of_documents
.unwrap_or(stats.inner_stats.documents_database_stats.number_of_entries()),
raw_document_db_size: stats.inner_stats.documents_database_stats.total_value_size(),
raw_document_db_size: stats.inner_stats.documents_database_stats.total_size(),
avg_document_size: stats.inner_stats.documents_database_stats.average_value_size(),
is_indexing: stats.is_indexing,
number_of_embeddings: stats.inner_stats.number_of_embeddings,

24
crates/meilisearch/tests/batches/mod.rs
View file

@ -281,7 +281,8 @@ async fn test_summarized_document_addition_or_update() {
".startedAt" => "[date]",
".finishedAt" => "[date]",
".stats.progressTrace" => "[progressTrace]",
".stats.writeChannelCongestion" => "[writeChannelCongestion]"
".stats.writeChannelCongestion" => "[writeChannelCongestion]",
".stats.internalDatabaseSizes" => "[internalDatabaseSizes]"
},
@r###"
{
@ -303,7 +304,8 @@ async fn test_summarized_document_addition_or_update() {
"test": 1
},
"progressTrace": "[progressTrace]",
"writeChannelCongestion": "[writeChannelCongestion]"
"writeChannelCongestion": "[writeChannelCongestion]",
"internalDatabaseSizes": "[internalDatabaseSizes]"
},
"duration": "[duration]",
"startedAt": "[date]",
@ -322,7 +324,8 @@ async fn test_summarized_document_addition_or_update() {
".startedAt" => "[date]",
".finishedAt" => "[date]",
".stats.progressTrace" => "[progressTrace]",
".stats.writeChannelCongestion" => "[writeChannelCongestion]"
".stats.writeChannelCongestion" => "[writeChannelCongestion]",
".stats.internalDatabaseSizes" => "[internalDatabaseSizes]"
},
@r###"
{
@ -407,7 +410,8 @@ async fn test_summarized_delete_documents_by_batch() {
".startedAt" => "[date]",
".finishedAt" => "[date]",
".stats.progressTrace" => "[progressTrace]",
".stats.writeChannelCongestion" => "[writeChannelCongestion]"
".stats.writeChannelCongestion" => "[writeChannelCongestion]",
".stats.internalDatabaseSizes" => "[internalDatabaseSizes]"
},
@r###"
{
@ -495,7 +499,8 @@ async fn test_summarized_delete_documents_by_filter() {
".startedAt" => "[date]",
".finishedAt" => "[date]",
".stats.progressTrace" => "[progressTrace]",
".stats.writeChannelCongestion" => "[writeChannelCongestion]"
".stats.writeChannelCongestion" => "[writeChannelCongestion]",
".stats.internalDatabaseSizes" => "[internalDatabaseSizes]"
},
@r###"
{
@ -537,7 +542,8 @@ async fn test_summarized_delete_documents_by_filter() {
".startedAt" => "[date]",
".finishedAt" => "[date]",
".stats.progressTrace" => "[progressTrace]",
".stats.writeChannelCongestion" => "[writeChannelCongestion]"
".stats.writeChannelCongestion" => "[writeChannelCongestion]",
".stats.internalDatabaseSizes" => "[internalDatabaseSizes]"
},
@r#"
{
@ -623,7 +629,8 @@ async fn test_summarized_delete_document_by_id() {
".startedAt" => "[date]",
".finishedAt" => "[date]",
".stats.progressTrace" => "[progressTrace]",
".stats.writeChannelCongestion" => "[writeChannelCongestion]"
".stats.writeChannelCongestion" => "[writeChannelCongestion]",
".stats.internalDatabaseSizes" => "[internalDatabaseSizes]"
},
@r#"
{
@ -679,7 +686,8 @@ async fn test_summarized_settings_update() {
".startedAt" => "[date]",
".finishedAt" => "[date]",
".stats.progressTrace" => "[progressTrace]",
".stats.writeChannelCongestion" => "[writeChannelCongestion]"
".stats.writeChannelCongestion" => "[writeChannelCongestion]",
".stats.internalDatabaseSizes" => "[internalDatabaseSizes]"
},
@r###"
{

65
crates/meilisearch/tests/documents/add_documents.rs
View file

@ -1897,11 +1897,11 @@ async fn update_documents_with_geo_field() {
},
{
"id": "3",
"_geo": { "lat": 1, "lng": 1 },
"_geo": { "lat": 3, "lng": 0 },
},
{
"id": "4",
"_geo": { "lat": "1", "lng": "1" },
"_geo": { "lat": "4", "lng": "0" },
},
]);
@ -1928,9 +1928,7 @@ async fn update_documents_with_geo_field() {
}
"###);
let (response, code) = index
.search_post(json!({"sort": ["_geoPoint(50.629973371633746,3.0569447399419567):desc"]}))
.await;
let (response, code) = index.search_post(json!({"sort": ["_geoPoint(10,0):asc"]})).await;
snapshot!(code, @"200 OK");
// we are expecting docs 4 and 3 first as they have geo
snapshot!(json_string!(response, { ".processingTimeMs" => "[time]" }),
@ -1940,18 +1938,18 @@ async fn update_documents_with_geo_field() {
{
"id": "4",
"_geo": {
"lat": "1",
"lng": "1"
"lat": "4",
"lng": "0"
},
"_geoDistance": 5522018
"_geoDistance": 667170
},
{
"id": "3",
"_geo": {
"lat": 1,
"lng": 1
"lat": 3,
"lng": 0
},
"_geoDistance": 5522018
"_geoDistance": 778364
},
{
"id": "1"
@ -1969,10 +1967,13 @@ async fn update_documents_with_geo_field() {
}
"###);
let updated_documents = json!([{
"id": "3",
"doggo": "kefir",
}]);
let updated_documents = json!([
{
"id": "3",
"doggo": "kefir",
"_geo": { "lat": 5, "lng": 0 },
}
]);
let (task, _status_code) = index.update_documents(updated_documents, None).await;
let response = index.wait_task(task.uid()).await;
snapshot!(json_string!(response, { ".duration" => "[duration]", ".enqueuedAt" => "[date]", ".startedAt" => "[date]", ".finishedAt" => "[date]" }),
@ -2012,16 +2013,16 @@ async fn update_documents_with_geo_field() {
{
"id": "3",
"_geo": {
"lat": 1,
"lng": 1
"lat": 5,
"lng": 0
},
"doggo": "kefir"
},
{
"id": "4",
"_geo": {
"lat": "1",
"lng": "1"
"lat": "4",
"lng": "0"
}
}
],
@ -2031,31 +2032,29 @@ async fn update_documents_with_geo_field() {
}
"###);
let (response, code) = index
.search_post(json!({"sort": ["_geoPoint(50.629973371633746,3.0569447399419567):desc"]}))
.await;
let (response, code) = index.search_post(json!({"sort": ["_geoPoint(10,0):asc"]})).await;
snapshot!(code, @"200 OK");
// the search response should not have changed: we are expecting docs 4 and 3 first as they have geo
snapshot!(json_string!(response, { ".processingTimeMs" => "[time]" }),
@r###"
{
"hits": [
{
"id": "4",
"_geo": {
"lat": "1",
"lng": "1"
},
"_geoDistance": 5522018
},
{
"id": "3",
"_geo": {
"lat": 1,
"lng": 1
"lat": 5,
"lng": 0
},
"doggo": "kefir",
"_geoDistance": 5522018
"_geoDistance": 555975
},
{
"id": "4",
"_geo": {
"lat": "4",
"lng": "0"
},
"_geoDistance": 667170
},
{
"id": "1"

27
crates/meilisearch/tests/documents/delete_documents.rs
View file

@ -157,11 +157,14 @@ async fn delete_document_by_filter() {
index.wait_task(task.uid()).await.succeeded();
let (stats, _) = index.stats().await;
snapshot!(json_string!(stats), @r###"
snapshot!(json_string!(stats, {
".rawDocumentDbSize" => "[size]",
".avgDocumentSize" => "[size]",
}), @r###"
{
"numberOfDocuments": 4,
"rawDocumentDbSize": 42,
"avgDocumentSize": 10,
"rawDocumentDbSize": "[size]",
"avgDocumentSize": "[size]",
"isIndexing": false,
"numberOfEmbeddings": 0,
"numberOfEmbeddedDocuments": 0,
@ -208,11 +211,14 @@ async fn delete_document_by_filter() {
"###);
let (stats, _) = index.stats().await;
snapshot!(json_string!(stats), @r###"
snapshot!(json_string!(stats, {
".rawDocumentDbSize" => "[size]",
".avgDocumentSize" => "[size]",
}), @r###"
{
"numberOfDocuments": 2,
"rawDocumentDbSize": 16,
"avgDocumentSize": 8,
"rawDocumentDbSize": "[size]",
"avgDocumentSize": "[size]",
"isIndexing": false,
"numberOfEmbeddings": 0,
"numberOfEmbeddedDocuments": 0,
@ -278,11 +284,14 @@ async fn delete_document_by_filter() {
"###);
let (stats, _) = index.stats().await;
snapshot!(json_string!(stats), @r###"
snapshot!(json_string!(stats, {
".rawDocumentDbSize" => "[size]",
".avgDocumentSize" => "[size]",
}), @r###"
{
"numberOfDocuments": 1,
"rawDocumentDbSize": 12,
"avgDocumentSize": 12,
"rawDocumentDbSize": "[size]",
"avgDocumentSize": "[size]",
"isIndexing": false,
"numberOfEmbeddings": 0,
"numberOfEmbeddedDocuments": 0,

127
crates/meilisearch/tests/dumps/mod.rs
View file

@ -28,12 +28,15 @@ async fn import_dump_v1_movie_raw() {
let (stats, code) = index.stats().await;
snapshot!(code, @"200 OK");
snapshot!(
json_string!(stats),
json_string!(stats, {
".rawDocumentDbSize" => "[size]",
".avgDocumentSize" => "[size]",
}),
@r###"
{
"numberOfDocuments": 53,
"rawDocumentDbSize": 21965,
"avgDocumentSize": 414,
"rawDocumentDbSize": "[size]",
"avgDocumentSize": "[size]",
"isIndexing": false,
"numberOfEmbeddings": 0,
"numberOfEmbeddedDocuments": 0,
@ -185,12 +188,15 @@ async fn import_dump_v1_movie_with_settings() {
let (stats, code) = index.stats().await;
snapshot!(code, @"200 OK");
snapshot!(
json_string!(stats),
json_string!(stats, {
".rawDocumentDbSize" => "[size]",
".avgDocumentSize" => "[size]",
}),
@r###"
{
"numberOfDocuments": 53,
"rawDocumentDbSize": 21965,
"avgDocumentSize": 414,
"rawDocumentDbSize": "[size]",
"avgDocumentSize": "[size]",
"isIndexing": false,
"numberOfEmbeddings": 0,
"numberOfEmbeddedDocuments": 0,
@ -355,12 +361,15 @@ async fn import_dump_v1_rubygems_with_settings() {
let (stats, code) = index.stats().await;
snapshot!(code, @"200 OK");
snapshot!(
json_string!(stats),
json_string!(stats, {
".rawDocumentDbSize" => "[size]",
".avgDocumentSize" => "[size]",
}),
@r###"
{
"numberOfDocuments": 53,
"rawDocumentDbSize": 8606,
"avgDocumentSize": 162,
"rawDocumentDbSize": "[size]",
"avgDocumentSize": "[size]",
"isIndexing": false,
"numberOfEmbeddings": 0,
"numberOfEmbeddedDocuments": 0,
@ -522,12 +531,15 @@ async fn import_dump_v2_movie_raw() {
let (stats, code) = index.stats().await;
snapshot!(code, @"200 OK");
snapshot!(
json_string!(stats),
json_string!(stats, {
".rawDocumentDbSize" => "[size]",
".avgDocumentSize" => "[size]",
}),
@r###"
{
"numberOfDocuments": 53,
"rawDocumentDbSize": 21965,
"avgDocumentSize": 414,
"rawDocumentDbSize": "[size]",
"avgDocumentSize": "[size]",
"isIndexing": false,
"numberOfEmbeddings": 0,
"numberOfEmbeddedDocuments": 0,
@ -679,12 +691,15 @@ async fn import_dump_v2_movie_with_settings() {
let (stats, code) = index.stats().await;
snapshot!(code, @"200 OK");
snapshot!(
json_string!(stats),
json_string!(stats, {
".rawDocumentDbSize" => "[size]",
".avgDocumentSize" => "[size]",
}),
@r###"
{
"numberOfDocuments": 53,
"rawDocumentDbSize": 21965,
"avgDocumentSize": 414,
"rawDocumentDbSize": "[size]",
"avgDocumentSize": "[size]",
"isIndexing": false,
"numberOfEmbeddings": 0,
"numberOfEmbeddedDocuments": 0,
@ -846,12 +861,15 @@ async fn import_dump_v2_rubygems_with_settings() {
let (stats, code) = index.stats().await;
snapshot!(code, @"200 OK");
snapshot!(
json_string!(stats),
json_string!(stats, {
".rawDocumentDbSize" => "[size]",
".avgDocumentSize" => "[size]",
}),
@r###"
{
"numberOfDocuments": 53,
"rawDocumentDbSize": 8606,
"avgDocumentSize": 162,
"rawDocumentDbSize": "[size]",
"avgDocumentSize": "[size]",
"isIndexing": false,
"numberOfEmbeddings": 0,
"numberOfEmbeddedDocuments": 0,
@ -1010,12 +1028,15 @@ async fn import_dump_v3_movie_raw() {
let (stats, code) = index.stats().await;
snapshot!(code, @"200 OK");
snapshot!(
json_string!(stats),
json_string!(stats, {
".rawDocumentDbSize" => "[size]",
".avgDocumentSize" => "[size]",
}),
@r###"
{
"numberOfDocuments": 53,
"rawDocumentDbSize": 21965,
"avgDocumentSize": 414,
"rawDocumentDbSize": "[size]",
"avgDocumentSize": "[size]",
"isIndexing": false,
"numberOfEmbeddings": 0,
"numberOfEmbeddedDocuments": 0,
@ -1167,12 +1188,15 @@ async fn import_dump_v3_movie_with_settings() {
let (stats, code) = index.stats().await;
snapshot!(code, @"200 OK");
snapshot!(
json_string!(stats),
json_string!(stats, {
".rawDocumentDbSize" => "[size]",
".avgDocumentSize" => "[size]",
}),
@r###"
{
"numberOfDocuments": 53,
"rawDocumentDbSize": 21965,
"avgDocumentSize": 414,
"rawDocumentDbSize": "[size]",
"avgDocumentSize": "[size]",
"isIndexing": false,
"numberOfEmbeddings": 0,
"numberOfEmbeddedDocuments": 0,
@ -1334,12 +1358,15 @@ async fn import_dump_v3_rubygems_with_settings() {
let (stats, code) = index.stats().await;
snapshot!(code, @"200 OK");
snapshot!(
json_string!(stats),
json_string!(stats, {
".rawDocumentDbSize" => "[size]",
".avgDocumentSize" => "[size]",
}),
@r###"
{
"numberOfDocuments": 53,
"rawDocumentDbSize": 8606,
"avgDocumentSize": 162,
"rawDocumentDbSize": "[size]",
"avgDocumentSize": "[size]",
"isIndexing": false,
"numberOfEmbeddings": 0,
"numberOfEmbeddedDocuments": 0,
@ -1498,12 +1525,15 @@ async fn import_dump_v4_movie_raw() {
let (stats, code) = index.stats().await;
snapshot!(code, @"200 OK");
snapshot!(
json_string!(stats),
json_string!(stats, {
".rawDocumentDbSize" => "[size]",
".avgDocumentSize" => "[size]",
}),
@r###"
{
"numberOfDocuments": 53,
"rawDocumentDbSize": 21965,
"avgDocumentSize": 414,
"rawDocumentDbSize": "[size]",
"avgDocumentSize": "[size]",
"isIndexing": false,
"numberOfEmbeddings": 0,
"numberOfEmbeddedDocuments": 0,
@ -1655,12 +1685,15 @@ async fn import_dump_v4_movie_with_settings() {
let (stats, code) = index.stats().await;
snapshot!(code, @"200 OK");
snapshot!(
json_string!(stats),
json_string!(stats, {
".rawDocumentDbSize" => "[size]",
".avgDocumentSize" => "[size]",
}),
@r###"
{
"numberOfDocuments": 53,
"rawDocumentDbSize": 21965,
"avgDocumentSize": 414,
"rawDocumentDbSize": "[size]",
"avgDocumentSize": "[size]",
"isIndexing": false,
"numberOfEmbeddings": 0,
"numberOfEmbeddedDocuments": 0,
@ -1822,12 +1855,15 @@ async fn import_dump_v4_rubygems_with_settings() {
let (stats, code) = index.stats().await;
snapshot!(code, @"200 OK");
snapshot!(
json_string!(stats),
json_string!(stats, {
".rawDocumentDbSize" => "[size]",
".avgDocumentSize" => "[size]",
}),
@r###"
{
"numberOfDocuments": 53,
"rawDocumentDbSize": 8606,
"avgDocumentSize": 162,
"rawDocumentDbSize": "[size]",
"avgDocumentSize": "[size]",
"isIndexing": false,
"numberOfEmbeddings": 0,
"numberOfEmbeddedDocuments": 0,
@ -1994,11 +2030,14 @@ async fn import_dump_v5() {
let (stats, code) = index1.stats().await;
snapshot!(code, @"200 OK");
snapshot!(json_string!(stats), @r###"
snapshot!(json_string!(stats, {
".rawDocumentDbSize" => "[size]",
".avgDocumentSize" => "[size]",
}), @r###"
{
"numberOfDocuments": 10,
"rawDocumentDbSize": 6782,
"avgDocumentSize": 678,
"rawDocumentDbSize": "[size]",
"avgDocumentSize": "[size]",
"isIndexing": false,
"numberOfEmbeddings": 0,
"numberOfEmbeddedDocuments": 0,
@ -2031,12 +2070,15 @@ async fn import_dump_v5() {
let (stats, code) = index2.stats().await;
snapshot!(code, @"200 OK");
snapshot!(
json_string!(stats),
json_string!(stats, {
".rawDocumentDbSize" => "[size]",
".avgDocumentSize" => "[size]",
}),
@r###"
{
"numberOfDocuments": 10,
"rawDocumentDbSize": 6782,
"avgDocumentSize": 678,
"rawDocumentDbSize": "[size]",
"avgDocumentSize": "[size]",
"isIndexing": false,
"numberOfEmbeddings": 0,
"numberOfEmbeddedDocuments": 0,
@ -2237,6 +2279,7 @@ async fn import_dump_v6_containing_batches_and_enqueued_tasks() {
".results[0].duration" => "[date]",
".results[0].stats.progressTrace" => "[progressTrace]",
".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]",
".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]",
}), name: "batches");
let (indexes, code) = server.list_indexes(None, None).await;

140
crates/meilisearch/tests/search/mod.rs
View file

@ -1783,6 +1783,146 @@ async fn test_nested_fields() {
.await;
}
#[actix_rt::test]
async fn test_typo_settings() {
let documents = json!([
{
"id": 0,
"title": "The zeroth document",
},
{
"id": 1,
"title": "The first document",
"nested": {
"object": "field",
"machin": "bidule",
},
},
{
"id": 2,
"title": "The second document",
"nested": [
"array",
{
"object": "field",
},
{
"prout": "truc",
"machin": "lol",
},
],
},
{
"id": 3,
"title": "The third document",
"nested": "I lied",
},
]);
test_settings_documents_indexing_swapping_and_search(
&documents,
&json!({
"searchableAttributes": ["title", "nested.object", "nested.machin"],
"typoTolerance": {
"enabled": true,
"disableOnAttributes": ["title"]
}
}),
&json!({"q": "document"}),
|response, code| {
assert_eq!(code, 200, "{}", response);
snapshot!(json_string!(response["hits"]), @r###"
[
{
"id": 0,
"title": "The zeroth document"
},
{
"id": 1,
"title": "The first document",
"nested": {
"object": "field",
"machin": "bidule"
}
},
{
"id": 2,
"title": "The second document",
"nested": [
"array",
{
"object": "field"
},
{
"prout": "truc",
"machin": "lol"
}
]
},
{
"id": 3,
"title": "The third document",
"nested": "I lied"
}
]
"###);
},
)
.await;
// Test prefix search
test_settings_documents_indexing_swapping_and_search(
&documents,
&json!({
"searchableAttributes": ["title", "nested.object", "nested.machin"],
"typoTolerance": {
"enabled": true,
"disableOnAttributes": ["title"]
}
}),
&json!({"q": "docume"}),
|response, code| {
assert_eq!(code, 200, "{}", response);
snapshot!(json_string!(response["hits"]), @r###"
[
{
"id": 0,
"title": "The zeroth document"
},
{
"id": 1,
"title": "The first document",
"nested": {
"object": "field",
"machin": "bidule"
}
},
{
"id": 2,
"title": "The second document",
"nested": [
"array",
{
"object": "field"
},
{
"prout": "truc",
"machin": "lol"
}
]
},
{
"id": 3,
"title": "The third document",
"nested": "I lied"
}
]
"###);
},
)
.await;
}
/// Modifying facets with different casing should work correctly
#[actix_rt::test]
async fn change_facet_casing() {

72
crates/meilisearch/tests/stats/mod.rs
View file

@ -110,11 +110,14 @@ async fn add_remove_embeddings() {
index.wait_task(response.uid()).await.succeeded();
let (stats, _code) = index.stats().await;
snapshot!(json_string!(stats), @r###"
snapshot!(json_string!(stats, {
".rawDocumentDbSize" => "[size]",
".avgDocumentSize" => "[size]",
}), @r###"
{
"numberOfDocuments": 2,
"rawDocumentDbSize": 27,
"avgDocumentSize": 13,
"rawDocumentDbSize": "[size]",
"avgDocumentSize": "[size]",
"isIndexing": false,
"numberOfEmbeddings": 5,
"numberOfEmbeddedDocuments": 2,
@ -135,11 +138,14 @@ async fn add_remove_embeddings() {
index.wait_task(response.uid()).await.succeeded();
let (stats, _code) = index.stats().await;
snapshot!(json_string!(stats), @r###"
snapshot!(json_string!(stats, {
".rawDocumentDbSize" => "[size]",
".avgDocumentSize" => "[size]",
}), @r###"
{
"numberOfDocuments": 2,
"rawDocumentDbSize": 27,
"avgDocumentSize": 13,
"rawDocumentDbSize": "[size]",
"avgDocumentSize": "[size]",
"isIndexing": false,
"numberOfEmbeddings": 3,
"numberOfEmbeddedDocuments": 2,
@ -160,11 +166,14 @@ async fn add_remove_embeddings() {
index.wait_task(response.uid()).await.succeeded();
let (stats, _code) = index.stats().await;
snapshot!(json_string!(stats), @r###"
snapshot!(json_string!(stats, {
".rawDocumentDbSize" => "[size]",
".avgDocumentSize" => "[size]",
}), @r###"
{
"numberOfDocuments": 2,
"rawDocumentDbSize": 27,
"avgDocumentSize": 13,
"rawDocumentDbSize": "[size]",
"avgDocumentSize": "[size]",
"isIndexing": false,
"numberOfEmbeddings": 2,
"numberOfEmbeddedDocuments": 2,
@ -186,11 +195,14 @@ async fn add_remove_embeddings() {
index.wait_task(response.uid()).await.succeeded();
let (stats, _code) = index.stats().await;
snapshot!(json_string!(stats), @r###"
snapshot!(json_string!(stats, {
".rawDocumentDbSize" => "[size]",
".avgDocumentSize" => "[size]",
}), @r###"
{
"numberOfDocuments": 2,
"rawDocumentDbSize": 27,
"avgDocumentSize": 13,
"rawDocumentDbSize": "[size]",
"avgDocumentSize": "[size]",
"isIndexing": false,
"numberOfEmbeddings": 2,
"numberOfEmbeddedDocuments": 1,
@ -236,11 +248,14 @@ async fn add_remove_embedded_documents() {
index.wait_task(response.uid()).await.succeeded();
let (stats, _code) = index.stats().await;
snapshot!(json_string!(stats), @r###"
snapshot!(json_string!(stats, {
".rawDocumentDbSize" => "[size]",
".avgDocumentSize" => "[size]",
}), @r###"
{
"numberOfDocuments": 2,
"rawDocumentDbSize": 27,
"avgDocumentSize": 13,
"rawDocumentDbSize": "[size]",
"avgDocumentSize": "[size]",
"isIndexing": false,
"numberOfEmbeddings": 5,
"numberOfEmbeddedDocuments": 2,
@ -257,11 +272,14 @@ async fn add_remove_embedded_documents() {
index.wait_task(response.uid()).await.succeeded();
let (stats, _code) = index.stats().await;
snapshot!(json_string!(stats), @r###"
snapshot!(json_string!(stats, {
".rawDocumentDbSize" => "[size]",
".avgDocumentSize" => "[size]",
}), @r###"
{
"numberOfDocuments": 1,
"rawDocumentDbSize": 13,
"avgDocumentSize": 13,
"rawDocumentDbSize": "[size]",
"avgDocumentSize": "[size]",
"isIndexing": false,
"numberOfEmbeddings": 3,
"numberOfEmbeddedDocuments": 1,
@ -290,11 +308,14 @@ async fn update_embedder_settings() {
index.wait_task(response.uid()).await.succeeded();
let (stats, _code) = index.stats().await;
snapshot!(json_string!(stats), @r###"
snapshot!(json_string!(stats, {
".rawDocumentDbSize" => "[size]",
".avgDocumentSize" => "[size]",
}), @r###"
{
"numberOfDocuments": 2,
"rawDocumentDbSize": 108,
"avgDocumentSize": 54,
"rawDocumentDbSize": "[size]",
"avgDocumentSize": "[size]",
"isIndexing": false,
"numberOfEmbeddings": 0,
"numberOfEmbeddedDocuments": 0,
@ -326,11 +347,14 @@ async fn update_embedder_settings() {
server.wait_task(response.uid()).await.succeeded();
let (stats, _code) = index.stats().await;
snapshot!(json_string!(stats), @r###"
snapshot!(json_string!(stats, {
".rawDocumentDbSize" => "[size]",
".avgDocumentSize" => "[size]",
}), @r###"
{
"numberOfDocuments": 2,
"rawDocumentDbSize": 108,
"avgDocumentSize": 54,
"rawDocumentDbSize": "[size]",
"avgDocumentSize": "[size]",
"isIndexing": false,
"numberOfEmbeddings": 3,
"numberOfEmbeddedDocuments": 2,

45
crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
View file

@ -133,7 +133,9 @@ async fn check_the_index_scheduler(server: &Server) {
let (stats, _) = server.stats().await;
assert_json_snapshot!(stats, {
".databaseSize" => "[bytes]",
".usedDatabaseSize" => "[bytes]"
".usedDatabaseSize" => "[bytes]",
".indexes.kefir.rawDocumentDbSize" => "[bytes]",
".indexes.kefir.avgDocumentSize" => "[bytes]",
},
@r###"
{
@ -143,8 +145,8 @@ async fn check_the_index_scheduler(server: &Server) {
"indexes": {
"kefir": {
"numberOfDocuments": 1,
"rawDocumentDbSize": 109,
"avgDocumentSize": 109,
"rawDocumentDbSize": "[bytes]",
"avgDocumentSize": "[bytes]",
"isIndexing": false,
"numberOfEmbeddings": 0,
"numberOfEmbeddedDocuments": 0,
@ -193,31 +195,33 @@ async fn check_the_index_scheduler(server: &Server) {
// Tests all the batches query parameters
let (batches, _) = server.batches_filter("uids=10").await;
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_uids_equal_10");
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_uids_equal_10");
let (batches, _) = server.batches_filter("batchUids=10").await;
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_batchUids_equal_10");
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_batchUids_equal_10");
let (batches, _) = server.batches_filter("statuses=canceled").await;
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_statuses_equal_canceled");
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_statuses_equal_canceled");
// types has already been tested above to retrieve the upgrade database
let (batches, _) = server.batches_filter("canceledBy=19").await;
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_canceledBy_equal_19");
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_canceledBy_equal_19");
let (batches, _) = server.batches_filter("beforeEnqueuedAt=2025-01-16T16:47:41Z").await;
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_beforeEnqueuedAt_equal_2025-01-16T16_47_41");
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_beforeEnqueuedAt_equal_2025-01-16T16_47_41");
let (batches, _) = server.batches_filter("afterEnqueuedAt=2025-01-16T16:47:41Z").await;
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_afterEnqueuedAt_equal_2025-01-16T16_47_41");
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_afterEnqueuedAt_equal_2025-01-16T16_47_41");
let (batches, _) = server.batches_filter("beforeStartedAt=2025-01-16T16:47:41Z").await;
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_beforeStartedAt_equal_2025-01-16T16_47_41");
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_beforeStartedAt_equal_2025-01-16T16_47_41");
let (batches, _) = server.batches_filter("afterStartedAt=2025-01-16T16:47:41Z").await;
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_afterStartedAt_equal_2025-01-16T16_47_41");
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_afterStartedAt_equal_2025-01-16T16_47_41");
let (batches, _) = server.batches_filter("beforeFinishedAt=2025-01-16T16:47:41Z").await;
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_beforeFinishedAt_equal_2025-01-16T16_47_41");
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_beforeFinishedAt_equal_2025-01-16T16_47_41");
let (batches, _) = server.batches_filter("afterFinishedAt=2025-01-16T16:47:41Z").await;
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_afterFinishedAt_equal_2025-01-16T16_47_41");
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_afterFinishedAt_equal_2025-01-16T16_47_41");
let (stats, _) = server.stats().await;
assert_json_snapshot!(stats, {
".databaseSize" => "[bytes]",
".usedDatabaseSize" => "[bytes]"
".usedDatabaseSize" => "[bytes]",
".indexes.kefir.rawDocumentDbSize" => "[bytes]",
".indexes.kefir.avgDocumentSize" => "[bytes]",
},
@r###"
{
@ -227,8 +231,8 @@ async fn check_the_index_scheduler(server: &Server) {
"indexes": {
"kefir": {
"numberOfDocuments": 1,
"rawDocumentDbSize": 109,
"avgDocumentSize": 109,
"rawDocumentDbSize": "[bytes]",
"avgDocumentSize": "[bytes]",
"isIndexing": false,
"numberOfEmbeddings": 0,
"numberOfEmbeddedDocuments": 0,
@ -245,11 +249,14 @@ async fn check_the_index_scheduler(server: &Server) {
"###);
let index = server.index("kefir");
let (stats, _) = index.stats().await;
snapshot!(stats, @r###"
snapshot!(json_string!(stats, {
".rawDocumentDbSize" => "[bytes]",
".avgDocumentSize" => "[bytes]",
}), @r###"
{
"numberOfDocuments": 1,
"rawDocumentDbSize": 109,
"avgDocumentSize": 109,
"rawDocumentDbSize": "[bytes]",
"avgDocumentSize": "[bytes]",
"isIndexing": false,
"numberOfEmbeddings": 0,
"numberOfEmbeddedDocuments": 0,

60
crates/meilisearch/tests/vector/mod.rs
View file

@ -188,7 +188,7 @@ async fn user_provide_mismatched_embedding_dimension() {
let (value, code) = index.add_documents(documents, None).await;
snapshot!(code, @"202 Accepted");
let task = index.wait_task(value.uid()).await;
snapshot!(task, @r#"
snapshot!(task, @r###"
{
"uid": "[uid]",
"batchUid": "[batch_uid]",
@ -201,7 +201,7 @@ async fn user_provide_mismatched_embedding_dimension() {
"indexedDocuments": 0
},
"error": {
"message": "Index `doggo`: Invalid vector dimensions: expected: `3`, found: `2`.",
"message": "Index `doggo`: Invalid vector dimensions in document with id `0` in `._vectors.manual`.\n - note: embedding #0 has dimensions 2\n - note: embedder `manual` requires 3",
"code": "invalid_vector_dimensions",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#invalid_vector_dimensions"
@ -211,46 +211,36 @@ async fn user_provide_mismatched_embedding_dimension() {
"startedAt": "[date]",
"finishedAt": "[date]"
}
"#);
"###);
// FIXME: /!\ Case where number of embeddings is divisor of `dimensions` would still pass
let new_document = json!([
{"id": 0, "name": "kefir", "_vectors": { "manual": [[0, 0], [1, 1], [2, 2]] }},
]);
let (response, code) = index.add_documents(new_document, None).await;
snapshot!(code, @"202 Accepted");
index.wait_task(response.uid()).await.succeeded();
let (documents, _code) = index
.get_all_documents(GetAllDocumentsOptions { retrieve_vectors: true, ..Default::default() })
.await;
snapshot!(json_string!(documents), @r###"
let task = index.wait_task(response.uid()).await;
snapshot!(task, @r###"
{
"results": [
{
"id": 0,
"name": "kefir",
"_vectors": {
"manual": {
"embeddings": [
[
0.0,
0.0,
1.0
],
[
1.0,
2.0,
2.0
]
],
"regenerate": false
}
}
}
],
"offset": 0,
"limit": 20,
"total": 1
"uid": "[uid]",
"batchUid": "[batch_uid]",
"indexUid": "doggo",
"status": "failed",
"type": "documentAdditionOrUpdate",
"canceledBy": null,
"details": {
"receivedDocuments": 1,
"indexedDocuments": 0
},
"error": {
"message": "Index `doggo`: Invalid vector dimensions in document with id `0` in `._vectors.manual`.\n - note: embedding #0 has dimensions 2\n - note: embedder `manual` requires 3",
"code": "invalid_vector_dimensions",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#invalid_vector_dimensions"
},
"duration": "[duration]",
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]"
}
"###);
}