snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2025-10-18 09:36:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

add unit test

Browse Source
This commit is contained in:
Louis Dureuil
2025-10-15 21:36:26 +02:00
parent 76d7f20c87
commit 59316e8d5a
1 changed files with 331 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

331
crates/milli/src/search/new/tests/cutoff.rs
View File

@@ -3,12 +3,17 @@
//! 2. A test that ensure the filters are affectively applied even with a cutoff of 0 //! 2. A test that ensure the filters are affectively applied even with a cutoff of 0
//! 3. A test that ensure the cutoff works well with the ranking scores //! 3. A test that ensure the cutoff works well with the ranking scores
use std::collections::BTreeMap;
use std::sync::Arc;
use std::time::Duration; use std::time::Duration;
use meili_snap::snapshot; use meili_snap::snapshot;
use crate::index::tests::TempIndex; use crate::index::tests::TempIndex;
use crate::score_details::{ScoreDetails, ScoringStrategy}; use crate::score_details::{ScoreDetails, ScoringStrategy};
use crate::update::Setting;
use crate::vector::settings::EmbeddingSettings;
use crate::vector::{Embedder, EmbedderOptions};
use crate::{Criterion, Filter, FilterableAttributesRule, Search, TimeBudget}; use crate::{Criterion, Filter, FilterableAttributesRule, Search, TimeBudget};
fn create_index() -> TempIndex { fn create_index() -> TempIndex {
@@ -493,3 +498,329 @@ fn degraded_search_and_score_details() {
] ]
"###); "###);
} }
#[test]
fn degraded_search_and_score_details_vector() {
let index = create_index();
index
.add_documents(documents!([
{
"id": 4,
"text": "hella puppo kefir",
"_vectors": {
"default": [0.1, 0.1]
}
},
{
"id": 3,
"text": "hella puppy kefir",
"_vectors": {
"default": [-0.1, 0.1]
}
},
{
"id": 2,
"text": "hello",
"_vectors": {
"default": [0.1, -0.1]
}
},
{
"id": 1,
"text": "hello puppy",
"_vectors": {
"default": [-0.1, -0.1]
}
},
{
"id": 0,
"text": "hello puppy kefir",
"_vectors": {
"default": null
}
},
]))
.unwrap();
index
.update_settings(|settings| {
let mut embedders = BTreeMap::new();
embedders.insert(
"default".into(),
Setting::Set(EmbeddingSettings {
source: Setting::Set(crate::vector::settings::EmbedderSource::UserProvided),
dimensions: Setting::Set(2),
..Default::default()
}),
);
settings.set_embedder_settings(embedders);
settings.set_vector_store(crate::vector::VectorStoreBackend::Hannoy);
})
.unwrap();
let rtxn = index.read_txn().unwrap();
let mut search = Search::new(&rtxn, &index);
let embedder = Arc::new(
Embedder::new(
EmbedderOptions::UserProvided(crate::vector::embedder::manual::EmbedderOptions {
dimensions: 2,
distribution: None,
}),
0,
)
.unwrap(),
);
search.semantic("default".into(), embedder, false, Some(vec![1., -1.]), None);
search.limit(4);
search.scoring_strategy(ScoringStrategy::Detailed);
search.time_budget(TimeBudget::max());
let result = search.execute().unwrap();
snapshot!(format!("IDs: {:?}\nScores: {}\nScore Details:\n{:#?}", result.documents_ids, result.document_scores.iter().map(|scores| format!("{:.4} ", ScoreDetails::global_score(scores.iter()))).collect::<String>(), result.document_scores), @r###"
IDs: [2, 0, 3, 1]
Scores: 1.0000 0.5000 0.5000 0.0000
Score Details:
[
[
Vector(
Vector {
similarity: Some(
1.0,
),
},
),
],
[
Vector(
Vector {
similarity: Some(
0.5,
),
},
),
],
[
Vector(
Vector {
similarity: Some(
0.5,
),
},
),
],
[
Vector(
Vector {
similarity: Some(
0.0,
),
},
),
],
]
"###);
// Do ONE loop iteration. Not much can be deduced, almost everyone matched the words first bucket.
search.time_budget(TimeBudget::max().with_stop_after(1));
let result = search.execute().unwrap();
snapshot!(format!("IDs: {:?}\nScores: {}\nScore Details:\n{:#?}", result.documents_ids, result.document_scores.iter().map(|scores| format!("{:.4} ", ScoreDetails::global_score(scores.iter()))).collect::<String>(), result.document_scores), @r###"
IDs: [0, 1, 2, 3]
Scores: 0.5000 0.0000 0.0000 0.0000
Score Details:
[
[
Vector(
Vector {
similarity: Some(
0.5,
),
},
),
],
[
Skipped,
],
[
Skipped,
],
[
Skipped,
],
]
"###);
search.time_budget(TimeBudget::max().with_stop_after(2));
let result = search.execute().unwrap();
snapshot!(format!("IDs: {:?}\nScores: {}\nScore Details:\n{:#?}", result.documents_ids, result.document_scores.iter().map(|scores| format!("{:.4} ", ScoreDetails::global_score(scores.iter()))).collect::<String>(), result.document_scores), @r###"
IDs: [0, 1, 2, 3]
Scores: 0.5000 0.0000 0.0000 0.0000
Score Details:
[
[
Vector(
Vector {
similarity: Some(
0.5,
),
},
),
],
[
Vector(
Vector {
similarity: Some(
0.0,
),
},
),
],
[
Skipped,
],
[
Skipped,
],
]
"###);
search.time_budget(TimeBudget::max().with_stop_after(3));
let result = search.execute().unwrap();
snapshot!(format!("IDs: {:?}\nScores: {}\nScore Details:\n{:#?}", result.documents_ids, result.document_scores.iter().map(|scores| format!("{:.4} ", ScoreDetails::global_score(scores.iter()))).collect::<String>(), result.document_scores), @r###"
IDs: [2, 0, 1, 3]
Scores: 1.0000 0.5000 0.0000 0.0000
Score Details:
[
[
Vector(
Vector {
similarity: Some(
1.0,
),
},
),
],
[
Vector(
Vector {
similarity: Some(
0.5,
),
},
),
],
[
Vector(
Vector {
similarity: Some(
0.0,
),
},
),
],
[
Skipped,
],
]
"###);
search.time_budget(TimeBudget::max().with_stop_after(4));
let result = search.execute().unwrap();
snapshot!(format!("IDs: {:?}\nScores: {}\nScore Details:\n{:#?}", result.documents_ids, result.document_scores.iter().map(|scores| format!("{:.4} ", ScoreDetails::global_score(scores.iter()))).collect::<String>(), result.document_scores), @r###"
IDs: [2, 0, 3, 1]
Scores: 1.0000 0.5000 0.5000 0.0000
Score Details:
[
[
Vector(
Vector {
similarity: Some(
1.0,
),
},
),
],
[
Vector(
Vector {
similarity: Some(
0.5,
),
},
),
],
[
Vector(
Vector {
similarity: Some(
0.5,
),
},
),
],
[
Vector(
Vector {
similarity: Some(
0.0,
),
},
),
],
]
"###);
search.time_budget(TimeBudget::max().with_stop_after(5));
let result = search.execute().unwrap();
snapshot!(format!("IDs: {:?}\nScores: {}\nScore Details:\n{:#?}", result.documents_ids, result.document_scores.iter().map(|scores| format!("{:.4} ", ScoreDetails::global_score(scores.iter()))).collect::<String>(), result.document_scores), @r###"
IDs: [2, 0, 3, 1]
Scores: 1.0000 0.5000 0.5000 0.0000
Score Details:
[
[
Vector(
Vector {
similarity: Some(
1.0,
),
},
),
],
[
Vector(
Vector {
similarity: Some(
0.5,
),
},
),
],
[
Vector(
Vector {
similarity: Some(
0.5,
),
},
),
],
[
Vector(
Vector {
similarity: Some(
0.0,
),
},
),
],
]
"###);
}