snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2024-11-26 03:55:07 +08:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

add tests on the rest embedder

Browse Source
This commit is contained in:
Tamo 2024-06-12 18:27:03 +02:00
parent f6a00f4a90
commit 2141cb3b69
5 changed files with 483 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

141
Cargo.lock generated
View File

@ -55,7 +55,7 @@ dependencies = [
"encoding_rs", "encoding_rs",
"flate2", "flate2",
"futures-core", "futures-core",
"h2", "h2 0.3.26",
"http 0.2.11", "http 0.2.11",
"httparse", "httparse",
"httpdate", "httpdate",
@ -456,6 +456,12 @@ dependencies = [
"critical-section", "critical-section",
] ]
[[package]]
name = "atomic-waker"
version = "1.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1505bd5d3d116872e7271a6d4e16d81d0c8570876c8de68093a09ac269d8aac0"
[[package]] [[package]]
name = "autocfg" name = "autocfg"
version = "1.2.0" version = "1.2.0"
@ -1338,6 +1344,24 @@ dependencies = [
"syn 2.0.60", "syn 2.0.60",
] ]
[[package]]
name = "deadpool"
version = "0.10.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fb84100978c1c7b37f09ed3ce3e5f843af02c2a2c431bae5b19230dad2c1b490"
dependencies = [
"async-trait",
"deadpool-runtime",
"num_cpus",
"tokio",
]
[[package]]
name = "deadpool-runtime"
version = "0.1.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "092966b41edc516079bdf31ec78a2e0588d1d0c08f78b91d8307215928642b2b"
[[package]] [[package]]
name = "debugid" name = "debugid"
version = "0.8.0" version = "0.8.0"
@ -2213,6 +2237,25 @@ dependencies = [
"tracing", "tracing",
] ]
[[package]]
name = "h2"
version = "0.4.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fa82e28a107a8cc405f0839610bdc9b15f1e25ec7d696aa5cf173edbcb1486ab"
dependencies = [
"atomic-waker",
"bytes",
"fnv",
"futures-core",
"futures-sink",
"http 1.0.0",
"indexmap",
"slab",
"tokio",
"tokio-util",
"tracing",
]
[[package]] [[package]]
name = "half" name = "half"
version = "1.8.2" version = "1.8.2"
@ -2378,6 +2421,29 @@ dependencies = [
"pin-project-lite", "pin-project-lite",
] ]
[[package]]
name = "http-body"
version = "1.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1cac85db508abc24a2e48553ba12a996e87244a0395ce011e62b37158745d643"
dependencies = [
"bytes",
"http 1.0.0",
]
[[package]]
name = "http-body-util"
version = "0.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "793429d76616a256bcb62c2a2ec2bed781c8307e797e2598c50010f2bee2544f"
dependencies = [
"bytes",
"futures-util",
"http 1.0.0",
"http-body 1.0.0",
"pin-project-lite",
]
[[package]] [[package]]
name = "httparse" name = "httparse"
version = "1.8.0" version = "1.8.0"
@ -2400,9 +2466,9 @@ dependencies = [
"futures-channel", "futures-channel",
"futures-core", "futures-core",
"futures-util", "futures-util",
"h2", "h2 0.3.26",
"http 0.2.11", "http 0.2.11",
"http-body", "http-body 0.4.5",
"httparse", "httparse",
"httpdate", "httpdate",
"itoa", "itoa",
@ -2414,6 +2480,27 @@ dependencies = [
"want", "want",
] ]
[[package]]
name = "hyper"
version = "1.3.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fe575dd17d0862a9a33781c8c4696a55c320909004a67a00fb286ba8b1bc496d"
dependencies = [
"bytes",
"futures-channel",
"futures-util",
"h2 0.4.5",
"http 1.0.0",
"http-body 1.0.0",
"httparse",
"httpdate",
"itoa",
"pin-project-lite",
"smallvec",
"tokio",
"want",
]
[[package]] [[package]]
name = "hyper-rustls" name = "hyper-rustls"
version = "0.24.1" version = "0.24.1"
@ -2422,12 +2509,27 @@ checksum = "8d78e1e73ec14cf7375674f74d7dde185c8206fd9dea6fb6295e8a98098aaa97"
dependencies = [ dependencies = [
"futures-util", "futures-util",
"http 0.2.11", "http 0.2.11",
"hyper", "hyper 0.14.27",
"rustls 0.21.12", "rustls 0.21.12",
"tokio", "tokio",
"tokio-rustls", "tokio-rustls",
] ]
[[package]]
name = "hyper-util"
version = "0.1.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7b875924a60b96e5d7b9ae7b066540b1dd1cbd90d1828f54c92e02a283351c56"
dependencies = [
"bytes",
"futures-util",
"http 1.0.0",
"http-body 1.0.0",
"hyper 1.3.1",
"pin-project-lite",
"tokio",
]
[[package]] [[package]]
name = "ident_case" name = "ident_case"
version = "1.0.1" version = "1.0.1"
@ -3352,6 +3454,7 @@ dependencies = [
"urlencoding", "urlencoding",
"uuid", "uuid",
"walkdir", "walkdir",
"wiremock",
"yaup", "yaup",
"zip", "zip",
] ]
@ -4348,10 +4451,10 @@ dependencies = [
"encoding_rs", "encoding_rs",
"futures-core", "futures-core",
"futures-util", "futures-util",
"h2", "h2 0.3.26",
"http 0.2.11", "http 0.2.11",
"http-body", "http-body 0.4.5",
"hyper", "hyper 0.14.27",
"hyper-rustls", "hyper-rustls",
"ipnet", "ipnet",
"js-sys", "js-sys",
@ -6031,6 +6134,30 @@ dependencies = [
"windows-sys 0.48.0", "windows-sys 0.48.0",
] ]
[[package]]
name = "wiremock"
version = "0.6.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ec874e1eef0df2dcac546057fe5e29186f09c378181cd7b635b4b7bcc98e9d81"
dependencies = [
"assert-json-diff",
"async-trait",
"base64 0.21.7",
"deadpool",
"futures",
"http 1.0.0",
"http-body-util",
"hyper 1.3.1",
"hyper-util",
"log",
"once_cell",
"regex",
"serde",
"serde_json",
"tokio",
"url",
]
[[package]] [[package]]
name = "xattr" name = "xattr"
version = "1.0.1" version = "1.0.1"

1
meilisearch/Cargo.toml
View File

@ -118,6 +118,7 @@ maplit = "1.0.2"
meili-snap = { path = "../meili-snap" } meili-snap = { path = "../meili-snap" }
temp-env = "0.3.6" temp-env = "0.3.6"
urlencoding = "2.1.3" urlencoding = "2.1.3"
wiremock = "0.6.0"
yaup = "0.2.1" yaup = "0.2.1"
[build-dependencies] [build-dependencies]

9
meilisearch/tests/common/mod.rs
View File

@ -65,7 +65,14 @@ impl Display for Value {
write!( write!(
f, f,
"{}", "{}",
json_string!(self, { ".enqueuedAt" => "[date]", ".startedAt" => "[date]", ".finishedAt" => "[date]", ".duration" => "[duration]", ".processingTimeMs" => "[duration]" }) json_string!(self, {
".enqueuedAt" => "[date]",
".startedAt" => "[date]",
".finishedAt" => "[date]",
".duration" => "[duration]",
".processingTimeMs" => "[duration]",
".details.embedders.*.url" => "[url]"
})
) )
} }
} }

1
meilisearch/tests/vector/mod.rs
View File

@ -1,3 +1,4 @@
mod rest;
mod settings; mod settings;
use meili_snap::{json_string, snapshot}; use meili_snap::{json_string, snapshot};

339
meilisearch/tests/vector/rest.rs Normal file
View File

@ -0,0 +1,339 @@
use crate::vector::GetAllDocumentsOptions;
use meili_snap::{json_string, snapshot};
use std::sync::atomic::{AtomicUsize, Ordering};
use wiremock::matchers::{method, path};
use wiremock::{Mock, MockServer, Request, ResponseTemplate};
use crate::common::{Server, Value};
use crate::json;
static COUNTER: AtomicUsize = AtomicUsize::new(0);
async fn create_mock() -> (MockServer, Value) {
let mock_server = MockServer::start().await;
Mock::given(method("POST"))
.and(path("/"))
.respond_with(|_req: &Request| {
let cpt = COUNTER.fetch_add(1, Ordering::Relaxed);
ResponseTemplate::new(200).set_body_json(json!({ "data": vec![cpt; 3] }))
})
.mount(&mock_server)
.await;
let url = mock_server.uri();
let embedder_settings = json!({
"source": "rest",
"url": url,
"dimensions": 3,
"query": {},
});
(mock_server, embedder_settings)
}
#[actix_rt::test]
async fn dummy_testing_the_mock() {
let (mock, _setting) = create_mock().await;
let body = reqwest::get(&mock.uri()).await.unwrap().text().await.unwrap();
snapshot!(body, @"[0,0,0]");
let body = reqwest::get(&mock.uri()).await.unwrap().text().await.unwrap();
snapshot!(body, @"[1,1,1]");
let body = reqwest::get(&mock.uri()).await.unwrap().text().await.unwrap();
snapshot!(body, @"[2,2,2]");
let body = reqwest::get(&mock.uri()).await.unwrap().text().await.unwrap();
snapshot!(body, @"[3,3,3]");
let body = reqwest::get(&mock.uri()).await.unwrap().text().await.unwrap();
snapshot!(body, @"[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
}
"###);
server
}
#[actix_rt::test]
async fn bad_settings() {
let (mock, _setting) = create_mock().await;
let server = get_server_vector().await;
let index = server.index("doggo");
let (response, code) = index
.update_settings(json!({
"embedders": {
"rest": json!({ "source": "rest" }),
},
}))
.await;
snapshot!(code, @"400 Bad Request");
snapshot!(response, @r###"
{
"message": "`.embedders.rest`: Missing field `url` (note: this field is mandatory for source rest)",
"code": "invalid_settings_embedders",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#invalid_settings_embedders"
}
"###);
let (response, code) = index
.update_settings(json!({
"embedders": {
"rest": json!({ "source": "rest", "url": "kefir" }),
},
}))
.await;
snapshot!(code, @"400 Bad Request");
snapshot!(response, @r###"
{
"message": "`.embedders.rest.url`: could not parse `kefir`: relative URL without a base",
"code": "invalid_settings_embedders",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#invalid_settings_embedders"
}
"###);
let (response, code) = index
.update_settings(json!({
"embedders": {
"rest": json!({ "source": "rest", "url": mock.uri() }),
},
}))
.await;
snapshot!(code, @"202 Accepted");
let task = server.wait_task(response.uid()).await;
snapshot!(task, @r###"
{
"uid": 0,
"indexUid": "doggo",
"status": "failed",
"type": "settingsUpdate",
"canceledBy": null,
"details": {
"embedders": {
"rest": {
"source": "rest",
"url": "[url]"
}
}
},
"error": {
"message": "internal: Error while generating embeddings: runtime error: could not determine model dimensions: test embedding failed with user error: was expected 'input' to be an object in query 'null'.",
"code": "internal",
"type": "internal",
"link": "https://docs.meilisearch.com/errors#internal"
},
"duration": "[duration]",
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]"
}
"###);
let (response, code) = index
.update_settings(json!({
"embedders": {
"rest": json!({ "source": "rest", "url": mock.uri(), "query": {} }),
},
}))
.await;
snapshot!(code, @"202 Accepted");
let task = server.wait_task(response.uid()).await;
snapshot!(task, @r###"
{
"uid": 1,
"indexUid": "doggo",
"status": "failed",
"type": "settingsUpdate",
"canceledBy": null,
"details": {
"embedders": {
"rest": {
"source": "rest",
"url": "[url]",
"query": {}
}
}
},
"error": {
"message": "internal: Error while generating embeddings: runtime error: could not determine model dimensions: test embedding failed with error: component `embedding` not found in path `embedding` in response: `{\n \"data\": [\n 0,\n 0,\n 0\n ]\n}`.",
"code": "internal",
"type": "internal",
"link": "https://docs.meilisearch.com/errors#internal"
},
"duration": "[duration]",
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]"
}
"###);
let (response, code) = index
.update_settings(json!({
"embedders": {
"rest": json!({ "source": "rest", "url": mock.uri(), "query": {}, "pathToEmbeddings": ["data"] }),
},
}))
.await;
snapshot!(code, @"202 Accepted");
let task = server.wait_task(response.uid()).await;
snapshot!(task, @r###"
{
"uid": 2,
"indexUid": "doggo",
"status": "failed",
"type": "settingsUpdate",
"canceledBy": null,
"details": {
"embedders": {
"rest": {
"source": "rest",
"url": "[url]",
"query": {},
"pathToEmbeddings": [
"data"
]
}
}
},
"error": {
"message": "internal: Error while generating embeddings: runtime error: could not determine model dimensions: test embedding failed with error: component `embedding` not found in path `embedding` in response: `{\n \"data\": [\n 1,\n 1,\n 1\n ]\n}`.",
"code": "internal",
"type": "internal",
"link": "https://docs.meilisearch.com/errors#internal"
},
"duration": "[duration]",
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]"
}
"###);
let (response, code) = index
.update_settings(json!({
"embedders": {
"rest": json!({ "source": "rest", "url": mock.uri(), "query": {}, "embeddingObject": ["data"] }),
},
}))
.await;
snapshot!(code, @"202 Accepted");
let task = server.wait_task(response.uid()).await;
snapshot!(task, @r###"
{
"uid": 3,
"indexUid": "doggo",
"status": "failed",
"type": "settingsUpdate",
"canceledBy": null,
"details": {
"embedders": {
"rest": {
"source": "rest",
"url": "[url]",
"query": {},
"embeddingObject": [
"data"
]
}
}
},
"error": {
"message": "internal: Error while generating embeddings: runtime error: could not determine model dimensions: test embedding failed with error: component `data` not found in path `data` in response: `{\n \"data\": [\n 2,\n 2,\n 2\n ]\n}`.",
"code": "internal",
"type": "internal",
"link": "https://docs.meilisearch.com/errors#internal"
},
"duration": "[duration]",
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]"
}
"###);
// Validate an embedder with a bad dimension of 2 instead of 3
let (response, code) = index
.update_settings(json!({
"embedders": {
"rest": json!({ "source": "rest", "url": mock.uri(), "query": {}, "pathToEmbeddings": [], "embeddingObject": ["data"], "dimensions": 2 }),
},
}))
.await;
snapshot!(code, @"202 Accepted");
let task = server.wait_task(response.uid()).await;
snapshot!(task["status"], @r###""succeeded""###);
let (response, code) = index.add_documents(json!( { "id": 1, "name": "kefir" }), None).await;
snapshot!(code, @"202 Accepted");
let task = server.wait_task(response.uid()).await;
snapshot!(task, @r###"
{
"uid": 5,
"indexUid": "doggo",
"status": "failed",
"type": "documentAdditionOrUpdate",
"canceledBy": null,
"details": {
"receivedDocuments": 1,
"indexedDocuments": 0
},
"error": {
"message": "An unexpected crash occurred when processing the task.",
"code": "internal",
"type": "internal",
"link": "https://docs.meilisearch.com/errors#internal"
},
"duration": "[duration]",
"enqueuedAt": "[date]",
"startedAt": "[date]",
"finishedAt": "[date]"
}
"###);
}
#[actix_rt::test]
async fn add_vector_and_user_provided() {
let (_mock, setting) = create_mock().await;
let server = get_server_vector().await;
let index = server.index("doggo");
let (response, code) = index
.update_settings(json!({
"embedders": {
"rest": setting,
},
}))
.await;
snapshot!(code, @"202 Accepted");
let task = server.wait_task(response.uid()).await;
snapshot!(task["status"], @r###""succeeded""###);
let documents = json!([
{"id": 0, "name": "kefir"},
{"id": 1, "name": "echo", "_vectors": { "rest": [1, 1, 1] }},
{"id": 2, "name": "intel"},
]);
let (value, code) = index.add_documents(documents, None).await;
snapshot!(code, @"202 Accepted");
let task = index.wait_task(value.uid()).await;
snapshot!(task, @"");
let (documents, _code) = index
.get_all_documents(GetAllDocumentsOptions { retrieve_vectors: true, ..Default::default() })
.await;
snapshot!(json_string!(documents), @r###"
{
"results": [],
"offset": 0,
"limit": 20,
"total": 0
}
"###);
}