MeiliSearch/meilisearch/tests/similar/mod.rs

732 lines
23 KiB
Rust
Raw Normal View History

2024-05-27 16:08:28 +02:00
mod errors;
2024-05-27 16:57:50 +02:00
use meili_snap::{json_string, snapshot};
2024-05-27 16:08:28 +02:00
use once_cell::sync::Lazy;
use crate::common::{Server, Value};
use crate::json;
static DOCUMENTS: Lazy<Value> = Lazy::new(|| {
json!([
{
"title": "Shazam!",
2024-05-27 16:57:50 +02:00
"release_year": 2019,
2024-05-27 16:08:28 +02:00
"id": "287947",
2024-05-27 16:57:50 +02:00
// Three semantic properties:
// 1. magic, anything that reminds you of magic
// 2. authority, anything that inspires command
// 3. horror, anything that inspires fear or dread
"_vectors": { "manual": [0.8, 0.4, -0.5]},
2024-05-27 16:08:28 +02:00
},
{
"title": "Captain Marvel",
2024-05-27 16:57:50 +02:00
"release_year": 2019,
2024-05-27 16:08:28 +02:00
"id": "299537",
2024-05-27 16:57:50 +02:00
"_vectors": { "manual": [0.6, 0.8, -0.2] },
2024-05-27 16:08:28 +02:00
},
{
"title": "Escape Room",
2024-05-27 16:57:50 +02:00
"release_year": 2019,
2024-05-27 16:08:28 +02:00
"id": "522681",
2024-05-27 16:57:50 +02:00
"_vectors": { "manual": [0.1, 0.6, 0.8] },
2024-05-27 16:08:28 +02:00
},
{
"title": "How to Train Your Dragon: The Hidden World",
2024-05-27 16:57:50 +02:00
"release_year": 2019,
2024-05-27 16:08:28 +02:00
"id": "166428",
2024-05-27 16:57:50 +02:00
"_vectors": { "manual": [0.7, 0.7, -0.4] },
2024-05-27 16:08:28 +02:00
},
{
2024-05-27 16:57:50 +02:00
"title": "All Quiet on the Western Front",
"release_year": 1930,
"id": "143",
"_vectors": { "manual": [-0.5, 0.3, 0.85] },
2024-05-27 16:08:28 +02:00
}
])
});
2024-05-27 16:57:50 +02:00
#[actix_rt::test]
async fn basic() {
let server = Server::new().await;
let index = server.index("test");
let (value, code) = server.set_features(json!({"vectorStore": true})).await;
snapshot!(code, @"200 OK");
snapshot!(value, @r###"
{
"vectorStore": true,
"metrics": false,
"logsRoute": false
}
"###);
let (response, code) = index
.update_settings(json!({
"embedders": {
"manual": {
"source": "userProvided",
"dimensions": 3,
}
},
"filterableAttributes": ["title"]}))
.await;
snapshot!(code, @"202 Accepted");
server.wait_task(response.uid()).await;
let documents = DOCUMENTS.clone();
let (value, code) = index.add_documents(documents, None).await;
snapshot!(code, @"202 Accepted");
index.wait_task(value.uid()).await;
index
.similar(json!({"id": 143, "retrieveVectors": true}), |response, code| {
2024-05-27 16:57:50 +02:00
snapshot!(code, @"200 OK");
snapshot!(json_string!(response["hits"]), @r###"
[
{
"title": "Escape Room",
"release_year": 2019,
"id": "522681",
"_vectors": {
2024-06-04 17:38:28 +02:00
"manual": {
"embeddings": [
[
0.10000000149011612,
0.6000000238418579,
0.800000011920929
]
],
2024-06-12 18:13:34 +02:00
"regenerate": false
2024-06-04 17:38:28 +02:00
}
2024-05-27 16:57:50 +02:00
}
},
{
"title": "Captain Marvel",
"release_year": 2019,
"id": "299537",
"_vectors": {
2024-06-04 17:38:28 +02:00
"manual": {
"embeddings": [
[
0.6000000238418579,
0.800000011920929,
-0.20000000298023224
]
],
2024-06-12 18:13:34 +02:00
"regenerate": false
2024-06-04 17:38:28 +02:00
}
2024-05-27 16:57:50 +02:00
}
},
{
"title": "How to Train Your Dragon: The Hidden World",
"release_year": 2019,
"id": "166428",
"_vectors": {
2024-06-04 17:38:28 +02:00
"manual": {
"embeddings": [
[
0.699999988079071,
0.699999988079071,
-0.4000000059604645
]
],
2024-06-12 18:13:34 +02:00
"regenerate": false
2024-06-04 17:38:28 +02:00
}
2024-05-27 16:57:50 +02:00
}
},
{
"title": "Shazam!",
"release_year": 2019,
"id": "287947",
"_vectors": {
2024-06-04 17:38:28 +02:00
"manual": {
"embeddings": [
[
0.800000011920929,
0.4000000059604645,
-0.5
]
],
2024-06-12 18:13:34 +02:00
"regenerate": false
2024-06-04 17:38:28 +02:00
}
2024-05-27 16:57:50 +02:00
}
}
]
"###);
})
.await;
index
.similar(json!({"id": "299537", "retrieveVectors": true}), |response, code| {
2024-05-27 16:57:50 +02:00
snapshot!(code, @"200 OK");
snapshot!(json_string!(response["hits"]), @r###"
[
{
"title": "How to Train Your Dragon: The Hidden World",
"release_year": 2019,
"id": "166428",
"_vectors": {
2024-06-04 17:38:28 +02:00
"manual": {
"embeddings": [
[
0.699999988079071,
0.699999988079071,
-0.4000000059604645
]
],
2024-06-12 18:13:34 +02:00
"regenerate": false
2024-06-04 17:38:28 +02:00
}
2024-05-27 16:57:50 +02:00
}
},
{
"title": "Shazam!",
"release_year": 2019,
"id": "287947",
"_vectors": {
2024-06-04 17:38:28 +02:00
"manual": {
"embeddings": [
[
0.800000011920929,
0.4000000059604645,
-0.5
]
],
2024-06-12 18:13:34 +02:00
"regenerate": false
2024-06-04 17:38:28 +02:00
}
2024-05-27 16:57:50 +02:00
}
},
{
"title": "Escape Room",
"release_year": 2019,
"id": "522681",
"_vectors": {
2024-06-04 17:38:28 +02:00
"manual": {
"embeddings": [
[
0.10000000149011612,
0.6000000238418579,
0.800000011920929
]
],
2024-06-12 18:13:34 +02:00
"regenerate": false
2024-06-04 17:38:28 +02:00
}
2024-05-27 16:57:50 +02:00
}
},
{
"title": "All Quiet on the Western Front",
"release_year": 1930,
"id": "143",
"_vectors": {
2024-06-04 17:38:28 +02:00
"manual": {
"embeddings": [
[
-0.5,
0.30000001192092896,
0.8500000238418579
]
],
2024-06-12 18:13:34 +02:00
"regenerate": false
2024-06-04 17:38:28 +02:00
}
2024-05-27 16:57:50 +02:00
}
}
]
"###);
})
.await;
}
2024-05-30 11:22:26 +02:00
#[actix_rt::test]
async fn ranking_score_threshold() {
let server = Server::new().await;
let index = server.index("test");
let (value, code) = server.set_features(json!({"vectorStore": true})).await;
snapshot!(code, @"200 OK");
snapshot!(value, @r###"
{
"vectorStore": true,
"metrics": false,
"logsRoute": false
}
"###);
let (response, code) = index
.update_settings(json!({
"embedders": {
"manual": {
"source": "userProvided",
"dimensions": 3,
}
},
"filterableAttributes": ["title"]}))
.await;
snapshot!(code, @"202 Accepted");
server.wait_task(response.uid()).await;
let documents = DOCUMENTS.clone();
let (value, code) = index.add_documents(documents, None).await;
snapshot!(code, @"202 Accepted");
index.wait_task(value.uid()).await;
index
.similar(
2024-06-05 11:05:19 +02:00
json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0, "retrieveVectors": true}),
2024-05-30 11:22:26 +02:00
|response, code| {
snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @"4");
snapshot!(json_string!(response["hits"]), @r###"
[
{
"title": "Escape Room",
"release_year": 2019,
"id": "522681",
"_vectors": {
2024-06-05 11:05:19 +02:00
"manual": {
"embeddings": [
[
0.10000000149011612,
0.6000000238418579,
0.800000011920929
]
],
2024-06-12 18:13:34 +02:00
"regenerate": false
2024-06-05 11:05:19 +02:00
}
2024-05-30 11:22:26 +02:00
},
"_rankingScore": 0.890957772731781
},
{
"title": "Captain Marvel",
"release_year": 2019,
"id": "299537",
"_vectors": {
2024-06-05 11:05:19 +02:00
"manual": {
"embeddings": [
[
0.6000000238418579,
0.800000011920929,
-0.20000000298023224
]
],
2024-06-12 18:13:34 +02:00
"regenerate": false
2024-06-05 11:05:19 +02:00
}
2024-05-30 11:22:26 +02:00
},
"_rankingScore": 0.39060014486312866
},
{
"title": "How to Train Your Dragon: The Hidden World",
"release_year": 2019,
"id": "166428",
"_vectors": {
2024-06-05 11:05:19 +02:00
"manual": {
"embeddings": [
[
0.699999988079071,
0.699999988079071,
-0.4000000059604645
]
],
2024-06-12 18:13:34 +02:00
"regenerate": false
2024-06-05 11:05:19 +02:00
}
2024-05-30 11:22:26 +02:00
},
"_rankingScore": 0.2819308042526245
},
{
"title": "Shazam!",
"release_year": 2019,
"id": "287947",
"_vectors": {
2024-06-05 11:05:19 +02:00
"manual": {
"embeddings": [
[
0.800000011920929,
0.4000000059604645,
-0.5
]
],
2024-06-12 18:13:34 +02:00
"regenerate": false
2024-06-05 11:05:19 +02:00
}
2024-05-30 11:22:26 +02:00
},
"_rankingScore": 0.1662663221359253
}
]
"###);
},
)
.await;
index
.similar(
2024-06-05 11:05:19 +02:00
json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0.2, "retrieveVectors": true}),
2024-05-30 11:22:26 +02:00
|response, code| {
snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @"3");
snapshot!(json_string!(response["hits"]), @r###"
[
{
"title": "Escape Room",
"release_year": 2019,
"id": "522681",
"_vectors": {
2024-06-05 11:05:19 +02:00
"manual": {
"embeddings": [
[
0.10000000149011612,
0.6000000238418579,
0.800000011920929
]
],
2024-06-12 18:13:34 +02:00
"regenerate": false
2024-06-05 11:05:19 +02:00
}
2024-05-30 11:22:26 +02:00
},
"_rankingScore": 0.890957772731781
},
{
"title": "Captain Marvel",
"release_year": 2019,
"id": "299537",
"_vectors": {
2024-06-05 11:05:19 +02:00
"manual": {
"embeddings": [
[
0.6000000238418579,
0.800000011920929,
-0.20000000298023224
]
],
2024-06-12 18:13:34 +02:00
"regenerate": false
2024-06-05 11:05:19 +02:00
}
2024-05-30 11:22:26 +02:00
},
"_rankingScore": 0.39060014486312866
},
{
"title": "How to Train Your Dragon: The Hidden World",
"release_year": 2019,
"id": "166428",
"_vectors": {
2024-06-05 11:05:19 +02:00
"manual": {
"embeddings": [
[
0.699999988079071,
0.699999988079071,
-0.4000000059604645
]
],
2024-06-12 18:13:34 +02:00
"regenerate": false
2024-06-05 11:05:19 +02:00
}
2024-05-30 11:22:26 +02:00
},
"_rankingScore": 0.2819308042526245
}
]
"###);
},
)
.await;
index
.similar(
2024-06-05 11:05:19 +02:00
json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0.3, "retrieveVectors": true}),
2024-05-30 11:22:26 +02:00
|response, code| {
snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @"2");
snapshot!(json_string!(response["hits"]), @r###"
[
{
"title": "Escape Room",
"release_year": 2019,
"id": "522681",
"_vectors": {
2024-06-05 11:05:19 +02:00
"manual": {
"embeddings": [
[
0.10000000149011612,
0.6000000238418579,
0.800000011920929
]
],
2024-06-12 18:13:34 +02:00
"regenerate": false
2024-06-05 11:05:19 +02:00
}
2024-05-30 11:22:26 +02:00
},
"_rankingScore": 0.890957772731781
},
{
"title": "Captain Marvel",
"release_year": 2019,
"id": "299537",
"_vectors": {
2024-06-05 11:05:19 +02:00
"manual": {
"embeddings": [
[
0.6000000238418579,
0.800000011920929,
-0.20000000298023224
]
],
2024-06-12 18:13:34 +02:00
"regenerate": false
2024-06-05 11:05:19 +02:00
}
2024-05-30 11:22:26 +02:00
},
"_rankingScore": 0.39060014486312866
}
]
"###);
},
)
.await;
index
.similar(
2024-06-05 11:05:19 +02:00
json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0.6, "retrieveVectors": true}),
2024-05-30 11:22:26 +02:00
|response, code| {
snapshot!(code, @"200 OK");
meili_snap::snapshot!(meili_snap::json_string!(response["estimatedTotalHits"]), @"1");
snapshot!(json_string!(response["hits"]), @r###"
[
{
"title": "Escape Room",
"release_year": 2019,
"id": "522681",
"_vectors": {
2024-06-05 11:05:19 +02:00
"manual": {
"embeddings": [
[
0.10000000149011612,
0.6000000238418579,
0.800000011920929
]
],
2024-06-12 18:13:34 +02:00
"regenerate": false
2024-06-05 11:05:19 +02:00
}
2024-05-30 11:22:26 +02:00
},
"_rankingScore": 0.890957772731781
}
]
"###);
},
)
.await;
index
.similar(
2024-06-05 11:05:19 +02:00
json!({"id": 143, "showRankingScore": true, "rankingScoreThreshold": 0.9, "retrieveVectors": true}),
2024-05-30 11:22:26 +02:00
|response, code| {
snapshot!(code, @"200 OK");
snapshot!(json_string!(response["hits"]), @"[]");
},
)
.await;
}
2024-05-27 16:57:50 +02:00
#[actix_rt::test]
async fn filter() {
let server = Server::new().await;
let index = server.index("test");
let (value, code) = server.set_features(json!({"vectorStore": true})).await;
snapshot!(code, @"200 OK");
snapshot!(value, @r###"
{
"vectorStore": true,
"metrics": false,
"logsRoute": false
}
"###);
let (response, code) = index
.update_settings(json!({
"embedders": {
"manual": {
"source": "userProvided",
"dimensions": 3,
}
},
"filterableAttributes": ["title", "release_year"]}))
.await;
snapshot!(code, @"202 Accepted");
server.wait_task(response.uid()).await;
let documents = DOCUMENTS.clone();
let (value, code) = index.add_documents(documents, None).await;
snapshot!(code, @"202 Accepted");
index.wait_task(value.uid()).await;
index
.similar(
json!({"id": 522681, "filter": "release_year = 2019", "retrieveVectors": true}),
|response, code| {
snapshot!(code, @"200 OK");
snapshot!(json_string!(response["hits"]), @r###"
[
{
"title": "Captain Marvel",
"release_year": 2019,
"id": "299537",
"_vectors": {
2024-06-04 17:38:28 +02:00
"manual": {
"embeddings": [
[
0.6000000238418579,
0.800000011920929,
-0.20000000298023224
]
],
2024-06-12 18:13:34 +02:00
"regenerate": false
2024-06-04 17:38:28 +02:00
}
}
},
{
"title": "How to Train Your Dragon: The Hidden World",
"release_year": 2019,
"id": "166428",
"_vectors": {
2024-06-04 17:38:28 +02:00
"manual": {
"embeddings": [
[
0.699999988079071,
0.699999988079071,
-0.4000000059604645
]
],
2024-06-12 18:13:34 +02:00
"regenerate": false
2024-06-04 17:38:28 +02:00
}
}
},
{
"title": "Shazam!",
"release_year": 2019,
"id": "287947",
"_vectors": {
2024-06-04 17:38:28 +02:00
"manual": {
"embeddings": [
[
0.800000011920929,
0.4000000059604645,
-0.5
]
],
2024-06-12 18:13:34 +02:00
"regenerate": false
2024-06-04 17:38:28 +02:00
}
}
}
]
"###);
},
)
2024-05-27 16:57:50 +02:00
.await;
index
.similar(
json!({"id": 522681, "filter": "release_year < 2000", "retrieveVectors": true}),
|response, code| {
snapshot!(code, @"200 OK");
snapshot!(json_string!(response["hits"]), @r###"
[
{
"title": "All Quiet on the Western Front",
"release_year": 1930,
"id": "143",
"_vectors": {
2024-06-04 17:38:28 +02:00
"manual": {
"embeddings": [
[
-0.5,
0.30000001192092896,
0.8500000238418579
]
],
2024-06-12 18:13:34 +02:00
"regenerate": false
2024-06-04 17:38:28 +02:00
}
}
}
]
"###);
},
)
2024-05-27 16:57:50 +02:00
.await;
}
#[actix_rt::test]
async fn limit_and_offset() {
let server = Server::new().await;
let index = server.index("test");
let (value, code) = server.set_features(json!({"vectorStore": true})).await;
snapshot!(code, @"200 OK");
snapshot!(value, @r###"
{
"vectorStore": true,
"metrics": false,
"logsRoute": false
}
"###);
let (response, code) = index
.update_settings(json!({
"embedders": {
"manual": {
"source": "userProvided",
"dimensions": 3,
}
},
"filterableAttributes": ["title"]}))
.await;
snapshot!(code, @"202 Accepted");
server.wait_task(response.uid()).await;
let documents = DOCUMENTS.clone();
let (value, code) = index.add_documents(documents, None).await;
snapshot!(code, @"202 Accepted");
index.wait_task(value.uid()).await;
index
.similar(json!({"id": 143, "limit": 1, "retrieveVectors": true}), |response, code| {
2024-05-27 16:57:50 +02:00
snapshot!(code, @"200 OK");
snapshot!(json_string!(response["hits"]), @r###"
[
{
"title": "Escape Room",
"release_year": 2019,
"id": "522681",
"_vectors": {
2024-06-04 17:38:28 +02:00
"manual": {
"embeddings": [
[
0.10000000149011612,
0.6000000238418579,
0.800000011920929
]
],
2024-06-12 18:13:34 +02:00
"regenerate": false
2024-06-04 17:38:28 +02:00
}
2024-05-27 16:57:50 +02:00
}
}
]
"###);
})
.await;
index
.similar(
json!({"id": 143, "limit": 1, "offset": 1, "retrieveVectors": true}),
|response, code| {
snapshot!(code, @"200 OK");
snapshot!(json_string!(response["hits"]), @r###"
[
{
"title": "Captain Marvel",
"release_year": 2019,
"id": "299537",
"_vectors": {
2024-06-04 17:38:28 +02:00
"manual": {
"embeddings": [
[
0.6000000238418579,
0.800000011920929,
-0.20000000298023224
]
],
2024-06-12 18:13:34 +02:00
"regenerate": false
2024-06-04 17:38:28 +02:00
}
}
}
]
"###);
},
)
2024-05-27 16:57:50 +02:00
.await;
}