4888: bring back v1.10.0 into main r=Kerollmops a=ManyTheFish



Co-authored-by: Louis Dureuil <louis@meilisearch.com>
Co-authored-by: meili-bors[bot] <89034592+meili-bors[bot]@users.noreply.github.com>
Co-authored-by: Tamo <tamo@meilisearch.com>
Co-authored-by: ManyTheFish <many@meilisearch.com>
This commit is contained in:
meili-bors[bot] 2024-08-27 14:02:08 +00:00 committed by GitHub
commit 9a756cf2c5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
27 changed files with 2618 additions and 99 deletions

View file

@ -72,6 +72,19 @@ fn on_panic(info: &std::panic::PanicInfo) {
#[actix_web::main]
async fn main() -> anyhow::Result<()> {
try_main().await.inspect_err(|error| {
tracing::error!(%error);
let mut current = error.source();
let mut depth = 0;
while let Some(source) = current {
tracing::info!(%source, depth, "Error caused by");
current = source.source();
depth += 1;
}
})
}
async fn try_main() -> anyhow::Result<()> {
let (opt, config_read_from) = Opt::try_build()?;
std::panic::set_hook(Box::new(on_panic));

View file

@ -682,6 +682,7 @@ generate_configure!(
filterable_attributes,
sortable_attributes,
displayed_attributes,
localized_attributes,
searchable_attributes,
distinct_attribute,
proximity_precision,

View file

@ -1369,12 +1369,18 @@ pub fn perform_facet_search(
None => TimeBudget::default(),
};
// In the faceted search context, we want to use the intersection between the locales provided by the user
// and the locales of the facet string.
// If the facet string is not localized, we **ignore** the locales provided by the user because the facet data has no locale.
// If the user does not provide locales, we use the locales of the facet string.
let localized_attributes = index.localized_attributes_rules(&rtxn)?.unwrap_or_default();
let locales = locales.or_else(|| {
localized_attributes
let localized_attributes_locales =
localized_attributes.into_iter().find(|attr| attr.match_str(&facet_name));
let locales = localized_attributes_locales.map(|attr| {
attr.locales
.into_iter()
.find(|attr| attr.match_str(&facet_name))
.map(|attr| attr.locales)
.filter(|locale| locales.as_ref().map_or(true, |locales| locales.contains(locale)))
.collect()
});
let (search, _, _, _) =

View file

@ -386,12 +386,39 @@ async fn force_locales() {
|response, code| {
snapshot!(response, @r###"
{
"hits": [],
"hits": [
{
"name_zh": "进击的巨人",
"author_zh": "諫山創",
"description_zh": "进击的巨人是日本的漫画系列,由諫山 創作画。",
"id": 853,
"_vectors": {
"manual": [
1.0,
2.0,
3.0
]
},
"_formatted": {
"name_zh": "<em>进</em><em>击</em><em>的</em><em>巨人</em>",
"author_zh": "諫山創",
"description_zh": "<em>进</em><em>击</em><em>的</em><em>巨人</em>是日本的漫画系列,由諫山 創作画。",
"id": "853",
"_vectors": {
"manual": [
"1.0",
"2.0",
"3.0"
]
}
}
}
],
"query": "\"进击的巨人\"",
"processingTimeMs": "[duration]",
"limit": 20,
"offset": 0,
"estimatedTotalHits": 0
"estimatedTotalHits": 1
}
"###);
snapshot!(code, @"200 OK");
@ -483,12 +510,39 @@ async fn force_locales_with_pattern() {
|response, code| {
snapshot!(response, @r###"
{
"hits": [],
"hits": [
{
"name_zh": "进击的巨人",
"author_zh": "諫山創",
"description_zh": "进击的巨人是日本的漫画系列,由諫山 創作画。",
"id": 853,
"_vectors": {
"manual": [
1.0,
2.0,
3.0
]
},
"_formatted": {
"name_zh": "<em>进</em><em>击</em><em>的</em><em>巨人</em>",
"author_zh": "諫山創",
"description_zh": "<em>进</em><em>击</em><em>的</em><em>巨人</em>是日本的漫画系列,由諫山 創作画。",
"id": "853",
"_vectors": {
"manual": [
"1.0",
"2.0",
"3.0"
]
}
}
}
],
"query": "\"进击的巨人\"",
"processingTimeMs": "[duration]",
"limit": 20,
"offset": 0,
"estimatedTotalHits": 0
"estimatedTotalHits": 1
}
"###);
snapshot!(code, @"200 OK");
@ -761,6 +815,275 @@ async fn force_different_locales_with_pattern() {
.await;
}
#[actix_rt::test]
async fn auto_infer_locales_at_search_with_attributes_to_search_on() {
let server = Server::new().await;
let index = server.index("test");
let documents = DOCUMENTS.clone();
let (response, _) = index
.update_settings(
json!({
"searchableAttributes": ["name_en", "name_ja", "name_zh", "author_en", "author_ja", "author_zh", "description_en", "description_ja", "description_zh"],
"localizedAttributes": [
// force japanese
{"attributePatterns": ["*_zh"], "locales": ["jpn"]},
// force chinese
{"attributePatterns": ["*_ja"], "locales": ["cmn"]},
// any language
{"attributePatterns": ["*_en"], "locales": []}
]
}),
)
.await;
snapshot!(response, @r###"
{
"taskUid": 0,
"indexUid": "test",
"status": "enqueued",
"type": "settingsUpdate",
"enqueuedAt": "[date]"
}
"###);
index.add_documents(documents, None).await;
index.wait_task(1).await;
// auto infer any language
index
.search(
json!({"q": "\"进击的巨人\"", "attributesToHighlight": ["*"]}),
|response, code| {
snapshot!(response, @r###"
{
"hits": [],
"query": "\"进击的巨人\"",
"processingTimeMs": "[duration]",
"limit": 20,
"offset": 0,
"estimatedTotalHits": 0
}
"###);
snapshot!(code, @"200 OK");
},
)
.await;
// should infer chinese
index
.search(
json!({"q": "\"进击的巨人\"", "attributesToHighlight": ["*"], "attributesToSearchOn": ["name_zh", "description_zh"]}),
|response, code| {
snapshot!(response, @r###"
{
"hits": [
{
"name_zh": "进击的巨人",
"author_zh": "諫山創",
"description_zh": "进击的巨人是日本的漫画系列,由諫山 創作画。",
"id": 853,
"_vectors": {
"manual": [
1.0,
2.0,
3.0
]
},
"_formatted": {
"name_zh": "<em>进</em><em>击</em><em>的</em><em>巨人</em>",
"author_zh": "諫山創",
"description_zh": "<em>进</em><em>击</em><em>的</em><em>巨人</em>是日本的漫画系列,由諫山 創作画。",
"id": "853",
"_vectors": {
"manual": [
"1.0",
"2.0",
"3.0"
]
}
}
}
],
"query": "\"进击的巨人\"",
"processingTimeMs": "[duration]",
"limit": 20,
"offset": 0,
"estimatedTotalHits": 1
}
"###);
snapshot!(code, @"200 OK");
},
)
.await;
}
#[actix_rt::test]
async fn auto_infer_locales_at_search() {
let server = Server::new().await;
let index = server.index("test");
let documents = DOCUMENTS.clone();
let (response, _) = index
.update_settings(
json!({
"searchableAttributes": ["name_en", "name_ja", "name_zh", "author_en", "author_ja", "author_zh", "description_en", "description_ja", "description_zh"],
"localizedAttributes": [
// force japanese
{"attributePatterns": ["*"], "locales": ["jpn"]},
]
}),
)
.await;
snapshot!(response, @r###"
{
"taskUid": 0,
"indexUid": "test",
"status": "enqueued",
"type": "settingsUpdate",
"enqueuedAt": "[date]"
}
"###);
index.add_documents(documents, None).await;
index.wait_task(1).await;
index
.search(
json!({"q": "\"进击的巨人\"", "attributesToHighlight": ["*"]}),
|response, code| {
snapshot!(response, @r###"
{
"hits": [
{
"name_zh": "进击的巨人",
"author_zh": "諫山創",
"description_zh": "进击的巨人是日本的漫画系列,由諫山 創作画。",
"id": 853,
"_vectors": {
"manual": [
1.0,
2.0,
3.0
]
},
"_formatted": {
"name_zh": "<em>进</em><em>击</em><em>的</em><em>巨人</em>",
"author_zh": "諫山創",
"description_zh": "<em>进</em><em>击</em><em>的</em><em>巨人</em>是日本的漫画系列,由諫山 創作画。",
"id": "853",
"_vectors": {
"manual": [
"1.0",
"2.0",
"3.0"
]
}
}
}
],
"query": "\"进击的巨人\"",
"processingTimeMs": "[duration]",
"limit": 20,
"offset": 0,
"estimatedTotalHits": 1
}
"###);
snapshot!(code, @"200 OK");
},
)
.await;
index
.search(
json!({"q": "\"进击的巨人\"", "attributesToHighlight": ["*"]}),
|response, code| {
snapshot!(response, @r###"
{
"hits": [
{
"name_zh": "进击的巨人",
"author_zh": "諫山創",
"description_zh": "进击的巨人是日本的漫画系列,由諫山 創作画。",
"id": 853,
"_vectors": {
"manual": [
1.0,
2.0,
3.0
]
},
"_formatted": {
"name_zh": "<em>进</em><em>击</em><em>的</em><em>巨人</em>",
"author_zh": "諫山創",
"description_zh": "<em>进</em><em>击</em><em>的</em><em>巨人</em>是日本的漫画系列,由諫山 創作画。",
"id": "853",
"_vectors": {
"manual": [
"1.0",
"2.0",
"3.0"
]
}
}
}
],
"query": "\"进击的巨人\"",
"processingTimeMs": "[duration]",
"limit": 20,
"offset": 0,
"estimatedTotalHits": 1
}
"###);
snapshot!(code, @"200 OK");
},
)
.await;
index
.search(
json!({"q": "\"进击的巨人\"", "attributesToHighlight": ["*"]}),
|response, code| {
snapshot!(response, @r###"
{
"hits": [
{
"name_zh": "进击的巨人",
"author_zh": "諫山創",
"description_zh": "进击的巨人是日本的漫画系列,由諫山 創作画。",
"id": 853,
"_vectors": {
"manual": [
1.0,
2.0,
3.0
]
},
"_formatted": {
"name_zh": "<em>进</em><em>击</em><em>的</em><em>巨人</em>",
"author_zh": "諫山創",
"description_zh": "<em>进</em><em>击</em><em>的</em><em>巨人</em>是日本的漫画系列,由諫山 創作画。",
"id": "853",
"_vectors": {
"manual": [
"1.0",
"2.0",
"3.0"
]
}
}
}
],
"query": "\"进击的巨人\"",
"processingTimeMs": "[duration]",
"limit": 20,
"offset": 0,
"estimatedTotalHits": 1
}
"###);
snapshot!(code, @"200 OK");
},
)
.await;
}
#[actix_rt::test]
async fn force_different_locales_with_pattern_nested() {
let server = Server::new().await;

View file

@ -7,6 +7,7 @@ mod facet_search;
mod formatted;
mod geo;
mod hybrid;
#[cfg(not(feature = "chinese-pinyin"))]
mod locales;
mod matching_strategy;
mod multi;
@ -169,6 +170,7 @@ async fn negative_special_cases_search() {
}
#[cfg(feature = "default")]
#[cfg(not(feature = "chinese-pinyin"))]
#[actix_rt::test]
async fn test_kanji_language_detection() {
let server = Server::new().await;

View file

@ -2,7 +2,7 @@
source: meilisearch/tests/search/errors.rs
---
{
"uid": 0,
"uid": "[uid]",
"indexUid": "tamo",
"status": "succeeded",
"type": "indexCreation",

View file

@ -9,6 +9,7 @@ static DEFAULT_SETTINGS_VALUES: Lazy<HashMap<&'static str, Value>> = Lazy::new(|
let mut map = HashMap::new();
map.insert("displayed_attributes", json!(["*"]));
map.insert("searchable_attributes", json!(["*"]));
map.insert("localized_attributes", json!(null));
map.insert("filterable_attributes", json!([]));
map.insert("distinct_attribute", json!(null));
map.insert(
@ -409,6 +410,7 @@ macro_rules! test_setting_routes {
test_setting_routes!(
filterable_attributes put,
displayed_attributes put,
localized_attributes put,
searchable_attributes put,
distinct_attribute put,
stop_words put,

Binary file not shown.

View file

@ -1,3 +1,4 @@
mod openai;
mod rest;
mod settings;
@ -10,6 +11,22 @@ use crate::common::index::Index;
use crate::common::{default_settings, GetAllDocumentsOptions, Server};
use crate::json;
async fn get_server_vector() -> Server {
let server = Server::new().await;
let (value, code) = server.set_features(json!({"vectorStore": true})).await;
snapshot!(code, @"200 OK");
snapshot!(value, @r###"
{
"vectorStore": true,
"metrics": false,
"logsRoute": false,
"editDocumentsByFunction": false,
"containsFilter": false
}
"###);
server
}
#[actix_rt::test]
async fn add_remove_user_provided() {
let server = Server::new().await;

File diff suppressed because it is too large Load diff

Binary file not shown.

View file

@ -5,9 +5,9 @@ use reqwest::IntoUrl;
use wiremock::matchers::{method, path};
use wiremock::{Mock, MockServer, Request, ResponseTemplate};
use crate::common::{Server, Value};
use crate::common::Value;
use crate::json;
use crate::vector::GetAllDocumentsOptions;
use crate::vector::{get_server_vector, GetAllDocumentsOptions};
async fn create_mock() -> (MockServer, Value) {
let mock_server = MockServer::start().await;
@ -265,22 +265,6 @@ async fn dummy_testing_the_mock() {
snapshot!(body, @r###"{"data":[4,4,4]}"###);
}
async fn get_server_vector() -> Server {
let server = Server::new().await;
let (value, code) = server.set_features(json!({"vectorStore": true})).await;
snapshot!(code, @"200 OK");
snapshot!(value, @r###"
{
"vectorStore": true,
"metrics": false,
"logsRoute": false,
"editDocumentsByFunction": false,
"containsFilter": false
}
"###);
server
}
#[actix_rt::test]
async fn bad_request() {
let (mock, _setting) = create_mock().await;
@ -1816,7 +1800,7 @@ async fn server_custom_header() {
}
},
"error": {
"message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n - test embedding failed with user error: could not authenticate against embedding server\n - server replied with `{\"error\":\"missing header 'my-nonstandard-auth'\"}`",
"message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n - test embedding failed with user error: could not authenticate against embedding server\n - server replied with `{\"error\":\"missing header 'my-nonstandard-auth'\"}`\n - Hint: Check the `apiKey` parameter in the embedder configuration",
"code": "vector_embedding_error",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@ -1858,7 +1842,7 @@ async fn server_custom_header() {
}
},
"error": {
"message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n - test embedding failed with user error: could not authenticate against embedding server\n - server replied with `{\"error\":\"thou shall not pass, Balrog\"}`",
"message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n - test embedding failed with user error: could not authenticate against embedding server\n - server replied with `{\"error\":\"thou shall not pass, Balrog\"}`\n - Hint: Check the `apiKey` parameter in the embedder configuration",
"code": "vector_embedding_error",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#vector_embedding_error"