Merge #4846

4846: Add OpenAI tests r=dureuill a=dureuill

# Pull Request

## Related issue
Part of fixing #4757 

## What does this PR do?
- OpenAI embedder: don't pass apiKey when it is empty (slightly improves error messages)
- rest embedder and rest-based embedders: specialize the authorization denied error message depending on the configuration source
- fix existing tests
- Adds assets containing prerecorded texts to embed and the embeddings obtained from OpenAI
- Adds an asset containing a tokenized long document and the embedding obtained from OpenAI for this token
- Uses the wiremock crate to mock the OpenAI API: parse the openai request, lookup the response in assets, craft an openai response


Co-authored-by: Louis Dureuil <louis@meilisearch.com>

meilisearch/tests/common/mod.rs

@@ -81,6 +81,7 @@ impl Display for Value {
             f,
             "{}",
             json_string!(self, {
+                ".uid" => "[uid]",
                 ".enqueuedAt" => "[date]",
                 ".startedAt" => "[date]",
                 ".finishedAt" => "[date]",

meilisearch/tests/documents/add_documents.rs

@@ -1110,7 +1110,7 @@ async fn document_addition_with_huge_int_primary_key() {
     snapshot!(response,
         @r###"
     {
-      "uid": 0,
+      "uid": "[uid]",
       "indexUid": "test",
       "status": "succeeded",
       "type": "documentAdditionOrUpdate",
@@ -1402,7 +1402,7 @@ async fn error_document_field_limit_reached_over_multiple_documents() {
     snapshot!(response,
         @r###"
     {
-      "uid": 1,
+      "uid": "[uid]",
       "indexUid": "test",
       "status": "succeeded",
       "type": "documentAdditionOrUpdate",
@@ -1436,7 +1436,7 @@ async fn error_document_field_limit_reached_over_multiple_documents() {
     snapshot!(response,
         @r###"
     {
-      "uid": 2,
+      "uid": "[uid]",
       "indexUid": "test",
       "status": "failed",
       "type": "documentAdditionOrUpdate",
@@ -1485,7 +1485,7 @@ async fn error_document_field_limit_reached_in_one_nested_document() {
     snapshot!(response,
         @r###"
     {
-      "uid": 1,
+      "uid": "[uid]",
       "indexUid": "test",
       "status": "succeeded",
       "type": "documentAdditionOrUpdate",
@@ -1528,7 +1528,7 @@ async fn error_document_field_limit_reached_over_multiple_documents_with_nested_
     snapshot!(response,
         @r###"
     {
-      "uid": 1,
+      "uid": "[uid]",
       "indexUid": "test",
       "status": "succeeded",
       "type": "documentAdditionOrUpdate",
@@ -1563,7 +1563,7 @@ async fn error_document_field_limit_reached_over_multiple_documents_with_nested_
     snapshot!(response,
         @r###"
     {
-      "uid": 2,
+      "uid": "[uid]",
       "indexUid": "test",
       "status": "succeeded",
       "type": "documentAdditionOrUpdate",
@@ -2209,7 +2209,7 @@ async fn add_invalid_geo_and_then_settings() {
     let ret = index.wait_task(ret.uid()).await;
     snapshot!(ret, @r###"
     {
-      "uid": 1,
+      "uid": "[uid]",
       "indexUid": "test",
       "status": "succeeded",
       "type": "documentAdditionOrUpdate",
@@ -2231,7 +2231,7 @@ async fn add_invalid_geo_and_then_settings() {
     let ret = index.wait_task(ret.uid()).await;
     snapshot!(ret, @r###"
     {
-      "uid": 2,
+      "uid": "[uid]",
       "indexUid": "test",
       "status": "failed",
       "type": "settingsUpdate",

meilisearch/tests/dumps/snapshots/mod.rs/generate_and_import_dump_containing_vectors/1.snap

@@ -2,7 +2,7 @@
 source: meilisearch/tests/dumps/mod.rs
 ---
 {
-  "uid": 0,
+  "uid": "[uid]",
   "indexUid": "pets",
   "status": "succeeded",
   "type": "settingsUpdate",

meilisearch/tests/dumps/snapshots/mod.rs/generate_and_import_dump_containing_vectors/2.snap

@@ -2,7 +2,7 @@
 source: meilisearch/tests/dumps/mod.rs
 ---
 {
-  "uid": 1,
+  "uid": "[uid]",
   "indexUid": "pets",
   "status": "succeeded",
   "type": "documentAdditionOrUpdate",

meilisearch/tests/search/snapshots/distinct.rs/distinct_at_search_time/succeed.snap

@@ -2,7 +2,7 @@
 source: meilisearch/tests/search/distinct.rs
 ---
 {
-  "uid": 1,
+  "uid": "[uid]",
   "indexUid": "tamo",
   "status": "succeeded",
   "type": "settingsUpdate",

meilisearch/tests/search/snapshots/errors.rs/distinct_at_search_time/task-succeed.snap

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

meilisearch/tests/tasks/mod.rs

@@ -744,7 +744,7 @@ async fn test_summarized_index_deletion() {
     snapshot!(task,
         @r###"
     {
-      "uid": 0,
+      "uid": "[uid]",
       "indexUid": "test",
       "status": "failed",
       "type": "indexDeletion",
@@ -774,7 +774,7 @@ async fn test_summarized_index_deletion() {
     snapshot!(task,
         @r###"
     {
-      "uid": 1,
+      "uid": "[uid]",
       "indexUid": "test",
       "status": "succeeded",
       "type": "documentAdditionOrUpdate",
@@ -796,7 +796,7 @@ async fn test_summarized_index_deletion() {
     snapshot!(task,
         @r###"
     {
-      "uid": 2,
+      "uid": "[uid]",
       "indexUid": "test",
       "status": "succeeded",
       "type": "indexDeletion",
@@ -818,7 +818,7 @@ async fn test_summarized_index_deletion() {
     snapshot!(task,
         @r###"
     {
-      "uid": 3,
+      "uid": "[uid]",
       "indexUid": "test",
       "status": "failed",
       "type": "indexDeletion",

meilisearch/tests/vector/mod.rs

@@ -1,3 +1,4 @@
+mod openai;
 mod rest;
 mod settings;
 
@@ -7,6 +8,22 @@ use crate::common::index::Index;
 use crate::common::{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;
@@ -218,7 +235,7 @@ async fn user_provided_embeddings_error() {
     let task = index.wait_task(value.uid()).await;
     snapshot!(task, @r###"
     {
-      "uid": 2,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "failed",
       "type": "documentAdditionOrUpdate",
@@ -247,7 +264,7 @@ async fn user_provided_embeddings_error() {
     let task = index.wait_task(value.uid()).await;
     snapshot!(task, @r###"
     {
-      "uid": 3,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "failed",
       "type": "documentAdditionOrUpdate",
@@ -277,7 +294,7 @@ async fn user_provided_embeddings_error() {
     let task = index.wait_task(value.uid()).await;
     snapshot!(task, @r###"
     {
-      "uid": 4,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "failed",
       "type": "documentAdditionOrUpdate",
@@ -306,7 +323,7 @@ async fn user_provided_embeddings_error() {
     let task = index.wait_task(value.uid()).await;
     snapshot!(task, @r###"
     {
-      "uid": 5,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "failed",
       "type": "documentAdditionOrUpdate",
@@ -335,7 +352,7 @@ async fn user_provided_embeddings_error() {
     let task = index.wait_task(value.uid()).await;
     snapshot!(task, @r###"
     {
-      "uid": 6,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "failed",
       "type": "documentAdditionOrUpdate",
@@ -364,7 +381,7 @@ async fn user_provided_embeddings_error() {
     let task = index.wait_task(value.uid()).await;
     snapshot!(task, @r###"
     {
-      "uid": 7,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "failed",
       "type": "documentAdditionOrUpdate",
@@ -405,7 +422,7 @@ async fn user_provided_embeddings_error() {
     let task = index.wait_task(value.uid()).await;
     snapshot!(task, @r###"
     {
-      "uid": 10,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "failed",
       "type": "documentAdditionOrUpdate",
@@ -433,7 +450,7 @@ async fn user_provided_embeddings_error() {
     let task = index.wait_task(value.uid()).await;
     snapshot!(task, @r###"
     {
-      "uid": 11,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "failed",
       "type": "documentAdditionOrUpdate",
@@ -461,7 +478,7 @@ async fn user_provided_embeddings_error() {
     let task = index.wait_task(value.uid()).await;
     snapshot!(task, @r###"
     {
-      "uid": 12,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "failed",
       "type": "documentAdditionOrUpdate",
@@ -497,7 +514,7 @@ async fn user_provided_vectors_error() {
     let task = index.wait_task(value.uid()).await;
     snapshot!(task, @r###"
     {
-      "uid": 2,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "failed",
       "type": "documentAdditionOrUpdate",
@@ -526,7 +543,7 @@ async fn user_provided_vectors_error() {
     let task = index.wait_task(value.uid()).await;
     snapshot!(task, @r###"
     {
-      "uid": 3,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "failed",
       "type": "documentAdditionOrUpdate",
@@ -555,7 +572,7 @@ async fn user_provided_vectors_error() {
     let task = index.wait_task(value.uid()).await;
     snapshot!(task, @r###"
     {
-      "uid": 4,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "failed",
       "type": "documentAdditionOrUpdate",

meilisearch/tests/vector/rest.rs

@@ -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;
@@ -896,7 +880,7 @@ async fn bad_settings() {
     let task = server.wait_task(response.uid()).await;
     snapshot!(task, @r###"
     {
-      "uid": 0,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "failed",
       "type": "settingsUpdate",
@@ -941,7 +925,7 @@ async fn bad_settings() {
     let task = server.wait_task(response.uid()).await;
     snapshot!(task, @r###"
     {
-      "uid": 2,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "failed",
       "type": "documentAdditionOrUpdate",
@@ -990,7 +974,7 @@ async fn add_vector_and_user_provided() {
     let task = index.wait_task(value.uid()).await;
     snapshot!(task, @r###"
     {
-      "uid": 1,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "succeeded",
       "type": "documentAdditionOrUpdate",
@@ -1086,7 +1070,7 @@ async fn server_returns_bad_request() {
     let task = server.wait_task(response.uid()).await;
     snapshot!(task, @r###"
     {
-      "uid": 0,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "failed",
       "type": "settingsUpdate",
@@ -1125,7 +1109,7 @@ async fn server_returns_bad_request() {
     let task = server.wait_task(response.uid()).await;
     snapshot!(task, @r###"
     {
-      "uid": 1,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "succeeded",
       "type": "settingsUpdate",
@@ -1154,7 +1138,7 @@ async fn server_returns_bad_request() {
     let task = server.wait_task(response.uid()).await;
     snapshot!(task, @r###"
     {
-      "uid": 2,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "failed",
       "type": "documentAdditionOrUpdate",
@@ -1198,7 +1182,7 @@ async fn server_returns_bad_response() {
     let task = server.wait_task(response.uid()).await;
     snapshot!(task, @r###"
     {
-      "uid": 0,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "failed",
       "type": "settingsUpdate",
@@ -1251,7 +1235,7 @@ async fn server_returns_bad_response() {
     let task = server.wait_task(response.uid()).await;
     snapshot!(task, @r###"
     {
-      "uid": 1,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "failed",
       "type": "settingsUpdate",
@@ -1306,7 +1290,7 @@ async fn server_returns_bad_response() {
     let task = server.wait_task(response.uid()).await;
     snapshot!(task, @r###"
     {
-      "uid": 2,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "failed",
       "type": "settingsUpdate",
@@ -1361,7 +1345,7 @@ async fn server_returns_bad_response() {
     let task = server.wait_task(response.uid()).await;
     snapshot!(task, @r###"
     {
-      "uid": 3,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "failed",
       "type": "settingsUpdate",
@@ -1426,7 +1410,7 @@ async fn server_returns_bad_response() {
     let task = server.wait_task(response.uid()).await;
     snapshot!(task, @r###"
     {
-      "uid": 4,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "failed",
       "type": "settingsUpdate",
@@ -1493,7 +1477,7 @@ async fn server_returns_multiple() {
     let task = index.wait_task(value.uid()).await;
     snapshot!(task, @r###"
     {
-      "uid": 1,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "succeeded",
       "type": "documentAdditionOrUpdate",
@@ -1598,7 +1582,7 @@ async fn server_single_input_returns_in_array() {
     let task = index.wait_task(value.uid()).await;
     snapshot!(task, @r###"
     {
-      "uid": 1,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "succeeded",
       "type": "documentAdditionOrUpdate",
@@ -1703,7 +1687,7 @@ async fn server_raw() {
     let task = index.wait_task(value.uid()).await;
     snapshot!(task, @r###"
     {
-      "uid": 1,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "succeeded",
       "type": "documentAdditionOrUpdate",
@@ -1800,7 +1784,7 @@ async fn server_custom_header() {
     let task = server.wait_task(response.uid()).await;
     snapshot!(task, @r###"
     {
-      "uid": 0,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "failed",
       "type": "settingsUpdate",
@@ -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"
@@ -1839,7 +1823,7 @@ async fn server_custom_header() {
     let task = server.wait_task(response.uid()).await;
     snapshot!(task, @r###"
     {
-      "uid": 1,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "failed",
       "type": "settingsUpdate",
@@ -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"
@@ -1881,7 +1865,7 @@ async fn server_custom_header() {
     let task = server.wait_task(response.uid()).await;
     snapshot!(task, @r###"
     {
-      "uid": 2,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "succeeded",
       "type": "settingsUpdate",

meilisearch/tests/vector/settings.rs

@@ -43,7 +43,7 @@ async fn update_embedder() {
     let ret = server.wait_task(response.uid()).await;
     snapshot!(ret, @r###"
     {
-      "uid": 1,
+      "uid": "[uid]",
       "indexUid": "doggo",
       "status": "succeeded",
       "type": "settingsUpdate",

meilisearch/tests/vector/snapshots/mod.rs/add_remove_one_vector_4588/document-added.snap

@@ -2,7 +2,7 @@
 source: meilisearch/tests/vector/mod.rs
 ---
 {
-  "uid": 1,
+  "uid": "[uid]",
   "indexUid": "doggo",
   "status": "succeeded",
   "type": "documentAdditionOrUpdate",

meilisearch/tests/vector/snapshots/mod.rs/add_remove_one_vector_4588/document-deleted.snap

@@ -2,7 +2,7 @@
 source: meilisearch/tests/vector/mod.rs
 ---
 {
-  "uid": 2,
+  "uid": "[uid]",
   "indexUid": "doggo",
   "status": "succeeded",
   "type": "documentAdditionOrUpdate",

meilisearch/tests/vector/snapshots/mod.rs/add_remove_one_vector_4588/settings-processed.snap

@@ -2,7 +2,7 @@
 source: meilisearch/tests/vector/mod.rs
 ---
 {
-  "uid": 0,
+  "uid": "[uid]",
   "indexUid": "doggo",
   "status": "succeeded",
   "type": "settingsUpdate",

milli/src/vector/error.rs

@@ -62,8 +62,18 @@ pub enum EmbedErrorKind {
     RestResponseDeserialization(std::io::Error),
     #[error("expected a response containing {0} embeddings, got only {1}")]
     RestResponseEmbeddingCount(usize, usize),
-    #[error("could not authenticate against embedding server{}", option_info(.0.as_deref(), "server replied with "))]
-    RestUnauthorized(Option<String>),
+    #[error("could not authenticate against {embedding} server{server_reply}{hint}", embedding=match *.1 {
+        ConfigurationSource::User => "embedding",
+        ConfigurationSource::OpenAi => "OpenAI",
+        ConfigurationSource::Ollama => "ollama"
+    },
+    server_reply=option_info(.0.as_deref(), "server replied with "),
+    hint=match *.1 {
+        ConfigurationSource::User => "\n  - Hint: Check the `apiKey` parameter in the embedder configuration",
+        ConfigurationSource::OpenAi => "\n  - Hint: Check the `apiKey` parameter in the embedder configuration, and the `MEILI_OPENAI_API_KEY` and `OPENAI_API_KEY` environment variables",
+        ConfigurationSource::Ollama => "\n  - Hint: Check the `apiKey` parameter in the embedder configuration"
+    })]
+    RestUnauthorized(Option<String>, ConfigurationSource),
     #[error("sent too many requests to embedding server{}", option_info(.0.as_deref(), "server replied with "))]
     RestTooManyRequests(Option<String>),
     #[error("sent a bad request to embedding server{}{}",
@@ -136,8 +146,14 @@ impl EmbedError {
         }
     }
 
-    pub(crate) fn rest_unauthorized(error_response: Option<String>) -> EmbedError {
-        Self { kind: EmbedErrorKind::RestUnauthorized(error_response), fault: FaultSource::User }
+    pub(crate) fn rest_unauthorized(
+        error_response: Option<String>,
+        configuration_source: ConfigurationSource,
+    ) -> EmbedError {
+        Self {
+            kind: EmbedErrorKind::RestUnauthorized(error_response, configuration_source),
+            fault: FaultSource::User,
+        }
     }
 
     pub(crate) fn rest_too_many_requests(error_response: Option<String>) -> EmbedError {

milli/src/vector/openai.rs

@@ -183,7 +183,7 @@ impl Embedder {
 
         let rest_embedder = RestEmbedder::new(
             RestEmbedderOptions {
-                api_key: Some(api_key.clone()),
+                api_key: (!api_key.is_empty()).then(|| api_key.clone()),
                 distribution: None,
                 dimensions: Some(options.dimensions()),
                 url,

milli/src/vector/rest.rs

@@ -275,7 +275,10 @@ fn check_response(
         Err(ureq::Error::Status(code, response)) => {
             let error_response: Option<String> = response.into_string().ok();
             Err(match code {
-                401 => Retry::give_up(EmbedError::rest_unauthorized(error_response)),
+                401 => Retry::give_up(EmbedError::rest_unauthorized(
+                    error_response,
+                    configuration_source,
+                )),
                 429 => Retry::rate_limited(EmbedError::rest_too_many_requests(error_response)),
                 400 => Retry::give_up(EmbedError::rest_bad_request(
                     error_response,