Merge #4818

4818: Custom headers and QoL improvements r=ManyTheFish a=dureuill

# Pull Request

## Related issue
Fixes #4734 
Depends on #4815 

## What does this PR do?
- Adds custom headers for rest embedders ([public usage](https://meilisearch.notion.site/v1-10-AI-search-changes-737c9d7d010d4dd685582bf5dab579e2#41354652885242c899def07e36a66d49))
- Quality of life: allow specifying `dimensions` for `ollama` embedders ([public usage](https://meilisearch.notion.site/v1-10-AI-search-changes-737c9d7d010d4dd685582bf5dab579e2#37218531431343dab3d2d3a9a1937e9d)). As for `rest` embedders, specifying `dimensions` disables the "test" embedding when the embedder is spawned.
- Improve error message again when indexing documents that don't have a vector for a user-provided vector
  1. Remove the contents of the document
  2. Display the docid of the first document that triggered the error
  3. Indicate how many documents in that chunk suffered from the same issue for that embedder


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

index-scheduler/src/snapshots/index_scheduler__tests__import_vectors-5.snap

@@ -9,6 +9,7 @@ expression: fakerest_config.embedder_options
     "dimensions": 384,
     "url": "http://localhost:7777",
     "request": "{{text}}",
-    "response": "{{embedding}}"
+    "response": "{{embedding}}",
+    "headers": {}
   }
 }

index-scheduler/src/snapshots/index_scheduler__tests__settings_update-5.snap

@@ -9,6 +9,7 @@ expression: config.embedder_options
     "dimensions": 4,
     "url": "http://localhost:7777",
     "request": "{{text}}",
-    "response": "{{embedding}}"
+    "response": "{{embedding}}",
+    "headers": {}
   }
 }

index-scheduler/src/snapshots/lib.rs/import_vectors/Intel to kefir succeeds.snap

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 1 {uid: 1, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
 2 {uid: 2, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: None, method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
 ----------------------------------------------------------------------

index-scheduler/src/snapshots/lib.rs/import_vectors/Intel to kefir.snap

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 1 {uid: 1, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
 2 {uid: 2, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: None, method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000001, documents_count: 1, allow_index_creation: true }}
 ----------------------------------------------------------------------

index-scheduler/src/snapshots/lib.rs/import_vectors/adding Intel succeeds.snap

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 1 {uid: 1, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:

index-scheduler/src/snapshots/lib.rs/import_vectors/after adding Intel.snap

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 1 {uid: 1, status: enqueued, details: { received_documents: 1, indexed_documents: None }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: UpdateDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:

index-scheduler/src/snapshots/lib.rs/import_vectors/after_registering_settings_task_vectors.snap

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, status: enqueued, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, status: enqueued, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued [0,]

index-scheduler/src/snapshots/lib.rs/import_vectors/settings_update_processed_vectors.snap

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"A_fakerest": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(384), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet }), "B_small_hf": Set(EmbeddingSettings { source: Set(HuggingFace), model: Set("sentence-transformers/all-MiniLM-L6-v2"), revision: Set("e4ce9877abf3edfe10b0d82785e83bdcb973e22e"), api_key: NotSet, dimensions: NotSet, document_template: Set("{{doc.doggo}} the {{doc.breed}} best doggo"), url: NotSet, request: NotSet, response: NotSet, headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued []

index-scheduler/src/snapshots/lib.rs/test_settings_update/after_registering_settings_task.snap

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, status: enqueued, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, status: enqueued, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued [0,]

index-scheduler/src/snapshots/lib.rs/test_settings_update/settings_update_processed.snap

@@ -6,7 +6,7 @@ source: index-scheduler/src/lib.rs
 []
 ----------------------------------------------------------------------
 ### All Tasks:
-0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
+0 {uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: NotSet, sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: Set({"default": Set(EmbeddingSettings { source: Set(Rest), model: NotSet, revision: NotSet, api_key: Set("My super secret"), dimensions: Set(4), document_template: NotSet, url: Set("http://localhost:7777"), request: Set(String("{{text}}")), response: Set(String("{{embedding}}")), headers: NotSet, distribution: NotSet })}), search_cutoff_ms: NotSet, localized_attributes: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 ----------------------------------------------------------------------
 ### Status:
 enqueued []

meilisearch/tests/common/server.rs

@@ -1,6 +1,7 @@
 #![allow(dead_code)]
 
 use std::path::Path;
+use std::str::FromStr as _;
 use std::time::Duration;
 
 use actix_http::body::MessageBody;
@@ -8,7 +9,7 @@ use actix_web::dev::ServiceResponse;
 use actix_web::http::StatusCode;
 use byte_unit::{Byte, Unit};
 use clap::Parser;
-use meilisearch::option::{IndexerOpts, MaxMemory, Opt};
+use meilisearch::option::{IndexerOpts, MaxMemory, MaxThreads, Opt};
 use meilisearch::{analytics, create_app, setup_meilisearch, SubscriberForSecondLayer};
 use once_cell::sync::Lazy;
 use tempfile::TempDir;
@@ -239,7 +240,7 @@ pub fn default_settings(dir: impl AsRef<Path>) -> Opt {
             // memory has to be unlimited because several meilisearch are running in test context.
             max_indexing_memory: MaxMemory::unlimited(),
             skip_index_budget: true,
-            ..Parser::parse_from(None as Option<&str>)
+            max_indexing_threads: MaxThreads::from_str("1").unwrap(),
         },
         experimental_enable_metrics: false,
         ..Parser::parse_from(None as Option<&str>)

meilisearch/tests/settings/get_settings.rs

@@ -192,7 +192,8 @@ async fn secrets_are_hidden_in_settings() {
           "documentTemplate": "{% for field in fields %} {{ field.name }}: {{ field.value }}\n{% endfor %}",
           "url": "https://localhost:7777",
           "request": "{{text}}",
-          "response": "{{embedding}}"
+          "response": "{{embedding}}",
+          "headers": {}
         }
       },
       "searchCutoffMs": null,

meilisearch/tests/vector/mod.rs

@@ -487,10 +487,11 @@ async fn user_provided_embeddings_error() {
 #[actix_rt::test]
 async fn user_provided_vectors_error() {
     let server = Server::new().await;
+
     let index = generate_default_user_provided_documents(&server).await;
 
     // First case, we forget to specify `_vectors`
-    let documents = json!({"id": 42, "name": "kefir"});
+    let documents = json!([{"id": 40, "name": "kefir"}, {"id": 41, "name": "intel"}, {"id": 42, "name": "max"}, {"id": 43, "name": "venus"}, {"id": 44, "name": "eva"}]);
     let (value, code) = index.add_documents(documents, None).await;
     snapshot!(code, @"202 Accepted");
     let task = index.wait_task(value.uid()).await;
@@ -502,11 +503,11 @@ async fn user_provided_vectors_error() {
       "type": "documentAdditionOrUpdate",
       "canceledBy": null,
       "details": {
-        "receivedDocuments": 1,
+        "receivedDocuments": 5,
         "indexedDocuments": 0
       },
       "error": {
-        "message": "While embedding documents for embedder `manual`: user error: attempt to embed the following text in a configuration where embeddings must be user provided:\n  - ` id: 42\n name: kefir\n _vectors: \n _vectors.manual: \n _vectors.manual.regenerate: \n _vectors.manual.embeddings: \n`\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: opt-out for a document with `_vectors.manual: null`",
+        "message": "While embedding documents for embedder `manual`: no vectors provided for document \"40\" and at least 4 other document(s)\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: opt-out for a document with `_vectors.manual: null`",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -535,7 +536,7 @@ async fn user_provided_vectors_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "While embedding documents for embedder `manual`: user error: attempt to embed the following text in a configuration where embeddings must be user provided:\n  - ` id: 42\n name: kefir\n _vectors: \n _vectors.manual: \n _vectors.manual.regenerate: \n _vectors.manual.embeddings: \n _vector: manaul000\n _vector.manaul: \n`\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: try replacing `_vector` by `_vectors` in 1 document(s).",
+        "message": "While embedding documents for embedder `manual`: no vectors provided for document \"42\"\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: try replacing `_vector` by `_vectors` in 1 document(s).",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -564,7 +565,7 @@ async fn user_provided_vectors_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "While embedding documents for embedder `manual`: user error: attempt to embed the following text in a configuration where embeddings must be user provided:\n  - ` id: 42\n name: kefir\n _vectors: manaul000\n _vectors.manual: \n _vectors.manual.regenerate: \n _vectors.manual.embeddings: \n _vectors.manaul: \n`\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: try replacing `_vectors.manaul` by `_vectors.manual` in 1 document(s).",
+        "message": "While embedding documents for embedder `manual`: no vectors provided for document \"42\"\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: try replacing `_vectors.manaul` by `_vectors.manual` in 1 document(s).",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"

meilisearch/tests/vector/rest.rs

@@ -161,6 +161,55 @@ async fn create_mock_single_response_in_array() -> (MockServer, Value) {
     (mock_server, embedder_settings)
 }
 
+async fn create_mock_raw_with_custom_header() -> (MockServer, Value) {
+    let mock_server = MockServer::start().await;
+
+    let counter = AtomicUsize::new(0);
+
+    Mock::given(method("POST"))
+        .and(path("/"))
+        .respond_with(move |req: &Request| {
+            match req.headers.get("my-nonstandard-auth") {
+                Some(x) if x == "bearer of the ring" => {}
+                Some(x) => {
+                    return ResponseTemplate::new(401).set_body_json(
+                        json!({"error": format!("thou shall not pass, {}", x.to_str().unwrap())}),
+                    )
+                }
+                None => {
+                    return ResponseTemplate::new(401)
+                        .set_body_json(json!({"error": "missing header 'my-nonstandard-auth'"}))
+                }
+            }
+
+            let _req: String = match req.body_json() {
+                Ok(req) => req,
+                Err(error) => {
+                    return ResponseTemplate::new(400).set_body_json(json!({
+                      "error": format!("Invalid request: {error}")
+                    }));
+                }
+            };
+
+            let output = vec![counter.fetch_add(1, Ordering::Relaxed) as f32; 3];
+
+            ResponseTemplate::new(200).set_body_json(output)
+        })
+        .mount(&mock_server)
+        .await;
+    let url = mock_server.uri();
+
+    let embedder_settings = json!({
+        "source": "rest",
+        "url": url,
+        "request": "{{text}}",
+        "response": "{{embedding}}",
+        "headers": {"my-nonstandard-auth": "bearer of the ring"}
+    });
+
+    (mock_server, embedder_settings)
+}
+
 async fn create_mock_raw() -> (MockServer, Value) {
     let mock_server = MockServer::start().await;
 
@@ -1732,3 +1781,129 @@ async fn server_raw() {
     }
     "###);
 }
+
+#[actix_rt::test]
+async fn server_custom_header() {
+    let (mock, setting) = create_mock_raw_with_custom_header().await;
+
+    let server = get_server_vector().await;
+    let index = server.index("doggo");
+
+    let (response, code) = index
+  .update_settings(json!({
+    "embedders": {
+        "rest": json!({ "source": "rest", "url": mock.uri(), "request": "{{text}}", "response": "{{embedding}}" }),
+    },
+  }))
+  .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]",
+            "request": "{{text}}",
+            "response": "{{embedding}}"
+          }
+        }
+      },
+      "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'\"}`",
+        "code": "vector_embedding_error",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
+      },
+      "duration": "[duration]",
+      "enqueuedAt": "[date]",
+      "startedAt": "[date]",
+      "finishedAt": "[date]"
+    }
+    "###);
+
+    let (response, code) = index
+.update_settings(json!({
+  "embedders": {
+      "rest": json!({ "source": "rest", "url": mock.uri(), "request": "{{text}}", "response": "{{embedding}}", "headers": {"my-nonstandard-auth": "Balrog"} }),
+  },
+}))
+.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]",
+            "request": "{{text}}",
+            "response": "{{embedding}}",
+            "headers": {
+              "my-nonstandard-auth": "Balrog"
+            }
+          }
+        }
+      },
+      "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\"}`",
+        "code": "vector_embedding_error",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
+      },
+      "duration": "[duration]",
+      "enqueuedAt": "[date]",
+      "startedAt": "[date]",
+      "finishedAt": "[date]"
+    }
+    "###);
+
+    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, @r###"
+    {
+      "uid": 2,
+      "indexUid": "doggo",
+      "status": "succeeded",
+      "type": "settingsUpdate",
+      "canceledBy": null,
+      "details": {
+        "embedders": {
+          "rest": {
+            "source": "rest",
+            "url": "[url]",
+            "request": "{{text}}",
+            "response": "{{embedding}}",
+            "headers": {
+              "my-nonstandard-auth": "bearer of the ring"
+            }
+          }
+        }
+      },
+      "error": null,
+      "duration": "[duration]",
+      "enqueuedAt": "[date]",
+      "startedAt": "[date]",
+      "finishedAt": "[date]"
+    }
+    "###);
+}

milli/src/update/index_documents/extract/extract_vector_points.rs

@@ -95,6 +95,84 @@ enum ExtractionAction {
     DocumentOperation(DocumentOperation),
 }
 
+struct ManualEmbedderErrors {
+    embedder_name: String,
+    docid: String,
+    other_docids: usize,
+}
+
+impl ManualEmbedderErrors {
+    pub fn push_error(
+        errors: &mut Option<ManualEmbedderErrors>,
+        embedder_name: &str,
+        document_id: impl Fn() -> Value,
+    ) {
+        match errors {
+            Some(errors) => {
+                if errors.embedder_name == embedder_name {
+                    errors.other_docids = errors.other_docids.saturating_add(1)
+                }
+            }
+            None => {
+                *errors = Some(Self {
+                    embedder_name: embedder_name.to_owned(),
+                    docid: document_id().to_string(),
+                    other_docids: 0,
+                });
+            }
+        }
+    }
+
+    pub fn to_result(
+        errors: Option<ManualEmbedderErrors>,
+        possible_embedding_mistakes: &PossibleEmbeddingMistakes,
+        unused_vectors_distribution: &UnusedVectorsDistribution,
+    ) -> Result<()> {
+        match errors {
+            Some(errors) => {
+                let embedder_name = &errors.embedder_name;
+                let mut msg = format!(
+                    r"While embedding documents for embedder `{embedder_name}`: no vectors provided for document {}{}",
+                    errors.docid,
+                    if errors.other_docids != 0 {
+                        format!(" and at least {} other document(s)", errors.other_docids)
+                    } else {
+                        "".to_string()
+                    }
+                );
+
+                msg += &format!("\n- Note: `{embedder_name}` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.{embedder_name}`.");
+
+                let mut hint_count = 0;
+
+                for (vector_misspelling, count) in
+                    possible_embedding_mistakes.vector_mistakes().take(2)
+                {
+                    msg += &format!("\n- Hint: try replacing `{vector_misspelling}` by `_vectors` in {count} document(s).");
+                    hint_count += 1;
+                }
+
+                for (embedder_misspelling, count) in possible_embedding_mistakes
+                    .embedder_mistakes(embedder_name, unused_vectors_distribution)
+                    .take(2)
+                {
+                    msg += &format!("\n- Hint: try replacing `_vectors.{embedder_misspelling}` by `_vectors.{embedder_name}` in {count} document(s).");
+                    hint_count += 1;
+                }
+
+                if hint_count == 0 {
+                    msg += &format!(
+                        "\n- Hint: opt-out for a document with `_vectors.{embedder_name}: null`"
+                    );
+                }
+
+                Err(crate::Error::UserError(crate::UserError::DocumentEmbeddingError(msg)))
+            }
+            None => Ok(()),
+        }
+    }
+}
+
 /// Extracts the embedding vector contained in each document under the `_vectors` field.
 ///
 /// Returns the generated grenad reader containing the docid as key associated to the Vec<f32>
@@ -104,8 +182,10 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
     indexer: GrenadParameters,
     embedders_configs: &[IndexEmbeddingConfig],
     settings_diff: &InnerIndexSettingsDiff,
+    possible_embedding_mistakes: &PossibleEmbeddingMistakes,
 ) -> Result<(Vec<ExtractedVectorPoints>, UnusedVectorsDistribution)> {
     let mut unused_vectors_distribution = UnusedVectorsDistribution::new();
+    let mut manual_errors = None;
     let reindex_vectors = settings_diff.reindex_vectors();
 
     let old_fields_ids_map = &settings_diff.old.fields_ids_map;
@@ -246,7 +326,7 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
 
         for EmbedderVectorExtractor {
             embedder_name,
-            embedder: _,
+            embedder,
             prompt,
             prompts_writer,
             remove_vectors_writer,
@@ -255,6 +335,8 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
             action,
         } in extractors.iter_mut()
         {
+            let embedder_is_manual = matches!(**embedder, Embedder::UserProvided(_));
+
             let (old, new) = parsed_vectors.remove(embedder_name);
             let delta = match action {
                 ExtractionAction::SettingsFullReindex => match old {
@@ -285,11 +367,29 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
                     // this happens only when an existing embedder changed. We cannot regenerate userProvided vectors
                     VectorState::Manual => VectorStateDelta::NoChange,
                     // generated vectors must be regenerated
-                    VectorState::Generated => regenerate_prompt(obkv, prompt, new_fields_ids_map)?,
+                    VectorState::Generated => {
+                        if embedder_is_manual {
+                            ManualEmbedderErrors::push_error(
+                                &mut manual_errors,
+                                embedder_name.as_str(),
+                                document_id,
+                            );
+                            continue;
+                        }
+                        regenerate_prompt(obkv, prompt, new_fields_ids_map)?
+                    }
                 },
                 // prompt regeneration is only triggered for existing embedders
                 ExtractionAction::SettingsRegeneratePrompts { old_prompt } => {
                     if old.must_regenerate() {
+                        if embedder_is_manual {
+                            ManualEmbedderErrors::push_error(
+                                &mut manual_errors,
+                                embedder_name.as_str(),
+                                document_id,
+                            );
+                            continue;
+                        }
                         regenerate_if_prompt_changed(
                             obkv,
                             (old_prompt, prompt),
@@ -311,6 +411,9 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
                     (old, new),
                     (old_fields_ids_map, new_fields_ids_map),
                     document_id,
+                    embedder_name,
+                    embedder_is_manual,
+                    &mut manual_errors,
                 )?,
             };
             // and we finally push the unique vectors into the writer
@@ -326,6 +429,12 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
         unused_vectors_distribution.append(parsed_vectors);
     }
 
+    ManualEmbedderErrors::to_result(
+        manual_errors,
+        possible_embedding_mistakes,
+        &unused_vectors_distribution,
+    )?;
+
     let mut results = Vec::new();
 
     for EmbedderVectorExtractor {
@@ -363,6 +472,7 @@ pub fn extract_vector_points<R: io::Read + io::Seek>(
     Ok((results, unused_vectors_distribution))
 }
 
+#[allow(clippy::too_many_arguments)] // feel free to find efficient way to factor arguments
 fn extract_vector_document_diff(
     docid: DocumentId,
     obkv: obkv::KvReader<'_, FieldId>,
@@ -371,6 +481,9 @@ fn extract_vector_document_diff(
     (old, new): (VectorState, VectorState),
     (old_fields_ids_map, new_fields_ids_map): (&FieldsIdsMap, &FieldsIdsMap),
     document_id: impl Fn() -> Value,
+    embedder_name: &str,
+    embedder_is_manual: bool,
+    manual_errors: &mut Option<ManualEmbedderErrors>,
 ) -> Result<VectorStateDelta> {
     match (old.must_regenerate(), new.must_regenerate()) {
         (true, true) | (false, false) => {}
@@ -408,6 +521,10 @@ fn extract_vector_document_diff(
                 .any(|deladd| deladd.get(DelAdd::Addition).is_some());
 
             if document_is_kept {
+                if embedder_is_manual {
+                    ManualEmbedderErrors::push_error(manual_errors, embedder_name, document_id);
+                    return Ok(VectorStateDelta::NoChange);
+                }
                 // Don't give up if the old prompt was failing
                 let old_prompt = Some(&prompt).map(|p| {
                     p.render(obkv, DelAdd::Deletion, old_fields_ids_map).unwrap_or_default()
@@ -439,6 +556,10 @@ fn extract_vector_document_diff(
                 .map(|(_, deladd)| KvReaderDelAdd::new(deladd))
                 .any(|deladd| deladd.get(DelAdd::Addition).is_some());
             if document_is_kept {
+                if embedder_is_manual {
+                    ManualEmbedderErrors::push_error(manual_errors, embedder_name, document_id);
+                    return Ok(VectorStateDelta::NoChange);
+                }
                 // becomes autogenerated
                 VectorStateDelta::NowGenerated(prompt.render(
                     obkv,

milli/src/update/index_documents/extract/mod.rs

@@ -251,6 +251,7 @@ fn send_original_documents_data(
                 indexer,
                 &embedders_configs,
                 &settings_diff,
+                &possible_embedding_mistakes,
             ) {
                 Ok((extracted_vectors, unused_vectors_distribution)) => {
                     for ExtractedVectorPoints {

milli/src/update/index_documents/mod.rs

@@ -2744,6 +2744,7 @@ mod tests {
                         request: Setting::NotSet,
                         response: Setting::NotSet,
                         distribution: Setting::NotSet,
+                        headers: Setting::NotSet,
                     }),
                 );
                 settings.set_embedder_settings(embedders);

milli/src/update/settings.rs

@@ -67,6 +67,13 @@ impl<T> Setting<T> {
         }
     }
 
+    pub fn some_or_not_set(option: Option<T>) -> Self {
+        match option {
+            Some(value) => Setting::Set(value),
+            None => Setting::NotSet,
+        }
+    }
+
     pub const fn as_ref(&self) -> Setting<&T> {
         match *self {
             Self::Set(ref value) => Setting::Set(value),
@@ -1544,6 +1551,7 @@ fn validate_prompt(
             request,
             response,
             distribution,
+            headers,
         }) => {
             // validate
             let template = crate::prompt::Prompt::new(template)
@@ -1561,6 +1569,7 @@ fn validate_prompt(
                 request,
                 response,
                 distribution,
+                headers,
             }))
         }
         new => Ok(new),
@@ -1584,6 +1593,7 @@ pub fn validate_embedding_settings(
         request,
         response,
         distribution,
+        headers,
     } = settings;
 
     if let Some(0) = dimensions.set() {
@@ -1622,6 +1632,7 @@ pub fn validate_embedding_settings(
             request,
             response,
             distribution,
+            headers,
         }));
     };
     match inferred_source {
@@ -1630,6 +1641,7 @@ pub fn validate_embedding_settings(
 
             check_unset(&request, EmbeddingSettings::REQUEST, inferred_source, name)?;
             check_unset(&response, EmbeddingSettings::RESPONSE, inferred_source, name)?;
+            check_unset(&headers, EmbeddingSettings::HEADERS, inferred_source, name)?;
 
             if let Setting::Set(model) = &model {
                 let model = crate::vector::openai::EmbeddingModel::from_name(model.as_str())
@@ -1662,13 +1674,12 @@ pub fn validate_embedding_settings(
             }
         }
         EmbedderSource::Ollama => {
-            // Dimensions get inferred, only model name is required
-            check_unset(&dimensions, EmbeddingSettings::DIMENSIONS, inferred_source, name)?;
             check_set(&model, EmbeddingSettings::MODEL, inferred_source, name)?;
             check_unset(&revision, EmbeddingSettings::REVISION, inferred_source, name)?;
 
             check_unset(&request, EmbeddingSettings::REQUEST, inferred_source, name)?;
             check_unset(&response, EmbeddingSettings::RESPONSE, inferred_source, name)?;
+            check_unset(&headers, EmbeddingSettings::HEADERS, inferred_source, name)?;
         }
         EmbedderSource::HuggingFace => {
             check_unset(&api_key, EmbeddingSettings::API_KEY, inferred_source, name)?;
@@ -1677,6 +1688,7 @@ pub fn validate_embedding_settings(
             check_unset(&url, EmbeddingSettings::URL, inferred_source, name)?;
             check_unset(&request, EmbeddingSettings::REQUEST, inferred_source, name)?;
             check_unset(&response, EmbeddingSettings::RESPONSE, inferred_source, name)?;
+            check_unset(&headers, EmbeddingSettings::HEADERS, inferred_source, name)?;
         }
         EmbedderSource::UserProvided => {
             check_unset(&model, EmbeddingSettings::MODEL, inferred_source, name)?;
@@ -1693,6 +1705,7 @@ pub fn validate_embedding_settings(
             check_unset(&url, EmbeddingSettings::URL, inferred_source, name)?;
             check_unset(&request, EmbeddingSettings::REQUEST, inferred_source, name)?;
             check_unset(&response, EmbeddingSettings::RESPONSE, inferred_source, name)?;
+            check_unset(&headers, EmbeddingSettings::HEADERS, inferred_source, name)?;
         }
         EmbedderSource::Rest => {
             check_unset(&model, EmbeddingSettings::MODEL, inferred_source, name)?;
@@ -1713,6 +1726,7 @@ pub fn validate_embedding_settings(
         request,
         response,
         distribution,
+        headers,
     }))
 }
 

milli/src/vector/mod.rs

@@ -202,22 +202,6 @@ impl Default for EmbedderOptions {
     }
 }
 
-impl EmbedderOptions {
-    /// Default options for the Hugging Face embedder
-    pub fn huggingface() -> Self {
-        Self::HuggingFace(hf::EmbedderOptions::new())
-    }
-
-    /// Default options for the OpenAI embedder
-    pub fn openai(api_key: Option<String>) -> Self {
-        Self::OpenAi(openai::EmbedderOptions::with_default_model(api_key))
-    }
-
-    pub fn ollama(api_key: Option<String>, url: Option<String>) -> Self {
-        Self::Ollama(ollama::EmbedderOptions::with_default_model(api_key, url))
-    }
-}
-
 impl Embedder {
     /// Spawns a new embedder built from its options.
     pub fn new(options: EmbedderOptions) -> std::result::Result<Self, NewEmbedderError> {

milli/src/vector/ollama.rs

@@ -17,11 +17,22 @@ pub struct EmbedderOptions {
     pub url: Option<String>,
     pub api_key: Option<String>,
     pub distribution: Option<DistributionShift>,
+    pub dimensions: Option<usize>,
 }
 
 impl EmbedderOptions {
-    pub fn with_default_model(api_key: Option<String>, url: Option<String>) -> Self {
-        Self { embedding_model: "nomic-embed-text".into(), api_key, url, distribution: None }
+    pub fn with_default_model(
+        api_key: Option<String>,
+        url: Option<String>,
+        dimensions: Option<usize>,
+    ) -> Self {
+        Self {
+            embedding_model: "nomic-embed-text".into(),
+            api_key,
+            url,
+            distribution: None,
+            dimensions,
+        }
     }
 }
 
@@ -31,7 +42,7 @@ impl Embedder {
         let rest_embedder = match RestEmbedder::new(
             RestEmbedderOptions {
                 api_key: options.api_key,
-                dimensions: None,
+                dimensions: options.dimensions,
                 distribution: options.distribution,
                 url: options.url.unwrap_or_else(get_ollama_path),
                 request: serde_json::json!({
@@ -41,6 +52,7 @@ impl Embedder {
                 response: serde_json::json!({
                     "embedding": super::rest::RESPONSE_PLACEHOLDER,
                 }),
+                headers: Default::default(),
             },
             super::rest::ConfigurationSource::Ollama,
         ) {

milli/src/vector/openai.rs

@@ -195,6 +195,7 @@ impl Embedder {
                     super::rest::REPEAT_PLACEHOLDER
                     ]
                 }),
+                headers: Default::default(),
             },
             super::rest::ConfigurationSource::OpenAi,
         )?;

milli/src/vector/rest.rs

@@ -1,3 +1,5 @@
+use std::collections::BTreeMap;
+
 use deserr::Deserr;
 use rand::Rng;
 use rayon::iter::{IntoParallelIterator as _, ParallelIterator as _};
@@ -80,6 +82,7 @@ pub struct Embedder {
 struct EmbedderData {
     client: ureq::Agent,
     bearer: Option<String>,
+    headers: BTreeMap<String, String>,
     url: String,
     request: Request,
     response: Response,
@@ -94,6 +97,7 @@ pub struct EmbedderOptions {
     pub url: String,
     pub request: serde_json::Value,
     pub response: serde_json::Value,
+    pub headers: BTreeMap<String, String>,
 }
 
 impl std::hash::Hash for EmbedderOptions {
@@ -138,6 +142,7 @@ impl Embedder {
             request,
             response,
             configuration_source,
+            headers: options.headers,
         };
 
         let dimensions = if let Some(dimensions) = options.dimensions {
@@ -223,7 +228,10 @@ where
     } else {
         request
     };
-    let request = request.set("Content-Type", "application/json");
+    let mut request = request.set("Content-Type", "application/json");
+    for (header, value) in &data.headers {
+        request = request.set(header.as_str(), value.as_str());
+    }
 
     let body = data.request.inject_texts(inputs);
 

milli/src/vector/settings.rs

@@ -1,3 +1,5 @@
+use std::collections::BTreeMap;
+
 use deserr::Deserr;
 use roaring::RoaringBitmap;
 use serde::{Deserialize, Serialize};
@@ -41,6 +43,9 @@ pub struct EmbeddingSettings {
     pub response: Setting<serde_json::Value>,
     #[serde(default, skip_serializing_if = "Setting::is_not_set")]
     #[deserr(default)]
+    pub headers: Setting<BTreeMap<String, String>>,
+    #[serde(default, skip_serializing_if = "Setting::is_not_set")]
+    #[deserr(default)]
     pub distribution: Setting<DistributionShift>,
 }
 
@@ -105,6 +110,7 @@ impl SettingsDiff {
                     mut request,
                     mut response,
                     mut distribution,
+                    mut headers,
                 } = old;
 
                 let EmbeddingSettings {
@@ -118,6 +124,7 @@ impl SettingsDiff {
                     request: new_request,
                     response: new_response,
                     distribution: new_distribution,
+                    headers: new_headers,
                 } = new;
 
                 let mut reindex_action = None;
@@ -135,6 +142,7 @@ impl SettingsDiff {
                         &mut request,
                         &mut response,
                         &mut document_template,
+                        &mut headers,
                     )
                 }
                 if model.apply(new_model) {
@@ -144,7 +152,18 @@ impl SettingsDiff {
                     ReindexAction::push_action(&mut reindex_action, ReindexAction::FullReindex);
                 }
                 if dimensions.apply(new_dimensions) {
-                    ReindexAction::push_action(&mut reindex_action, ReindexAction::FullReindex);
+                    match source {
+                        // regenerate on dimensions change in OpenAI since truncation is supported
+                        Setting::Set(EmbedderSource::OpenAi) | Setting::Reset => {
+                            ReindexAction::push_action(
+                                &mut reindex_action,
+                                ReindexAction::FullReindex,
+                            );
+                        }
+                        // for all other embedders, the parameter is a hint that should not be able to change the result
+                        // and so won't cause a reindex by itself.
+                        _ => {}
+                    }
                 }
                 if url.apply(new_url) {
                     match source {
@@ -173,6 +192,7 @@ impl SettingsDiff {
 
                 distribution.apply(new_distribution);
                 api_key.apply(new_api_key);
+                headers.apply(new_headers);
 
                 let updated_settings = EmbeddingSettings {
                     source,
@@ -185,6 +205,7 @@ impl SettingsDiff {
                     request,
                     response,
                     distribution,
+                    headers,
                 };
 
                 match reindex_action {
@@ -218,6 +239,7 @@ fn apply_default_for_source(
     request: &mut Setting<serde_json::Value>,
     response: &mut Setting<serde_json::Value>,
     document_template: &mut Setting<String>,
+    headers: &mut Setting<BTreeMap<String, String>>,
 ) {
     match source {
         Setting::Set(EmbedderSource::HuggingFace) => {
@@ -227,6 +249,7 @@ fn apply_default_for_source(
             *url = Setting::NotSet;
             *request = Setting::NotSet;
             *response = Setting::NotSet;
+            *headers = Setting::NotSet;
         }
         Setting::Set(EmbedderSource::Ollama) => {
             *model = Setting::Reset;
@@ -235,6 +258,7 @@ fn apply_default_for_source(
             *url = Setting::NotSet;
             *request = Setting::NotSet;
             *response = Setting::NotSet;
+            *headers = Setting::NotSet;
         }
         Setting::Set(EmbedderSource::OpenAi) | Setting::Reset => {
             *model = Setting::Reset;
@@ -243,6 +267,7 @@ fn apply_default_for_source(
             *url = Setting::Reset;
             *request = Setting::NotSet;
             *response = Setting::NotSet;
+            *headers = Setting::NotSet;
         }
         Setting::Set(EmbedderSource::Rest) => {
             *model = Setting::NotSet;
@@ -251,6 +276,7 @@ fn apply_default_for_source(
             *url = Setting::Reset;
             *request = Setting::Reset;
             *response = Setting::Reset;
+            *headers = Setting::Reset;
         }
         Setting::Set(EmbedderSource::UserProvided) => {
             *model = Setting::NotSet;
@@ -260,6 +286,7 @@ fn apply_default_for_source(
             *request = Setting::NotSet;
             *response = Setting::NotSet;
             *document_template = Setting::NotSet;
+            *headers = Setting::NotSet;
         }
         Setting::NotSet => {}
     }
@@ -293,6 +320,7 @@ impl EmbeddingSettings {
     pub const URL: &'static str = "url";
     pub const REQUEST: &'static str = "request";
     pub const RESPONSE: &'static str = "response";
+    pub const HEADERS: &'static str = "headers";
 
     pub const DISTRIBUTION: &'static str = "distribution";
 
@@ -312,9 +340,12 @@ impl EmbeddingSettings {
             Self::API_KEY => {
                 &[EmbedderSource::OpenAi, EmbedderSource::Ollama, EmbedderSource::Rest]
             }
-            Self::DIMENSIONS => {
-                &[EmbedderSource::OpenAi, EmbedderSource::UserProvided, EmbedderSource::Rest]
-            }
+            Self::DIMENSIONS => &[
+                EmbedderSource::OpenAi,
+                EmbedderSource::UserProvided,
+                EmbedderSource::Ollama,
+                EmbedderSource::Rest,
+            ],
             Self::DOCUMENT_TEMPLATE => &[
                 EmbedderSource::HuggingFace,
                 EmbedderSource::OpenAi,
@@ -324,6 +355,7 @@ impl EmbeddingSettings {
             Self::URL => &[EmbedderSource::Ollama, EmbedderSource::Rest, EmbedderSource::OpenAi],
             Self::REQUEST => &[EmbedderSource::Rest],
             Self::RESPONSE => &[EmbedderSource::Rest],
+            Self::HEADERS => &[EmbedderSource::Rest],
             Self::DISTRIBUTION => &[
                 EmbedderSource::HuggingFace,
                 EmbedderSource::Ollama,
@@ -359,6 +391,7 @@ impl EmbeddingSettings {
                 Self::DOCUMENT_TEMPLATE,
                 Self::URL,
                 Self::API_KEY,
+                Self::DIMENSIONS,
                 Self::DISTRIBUTION,
             ],
             EmbedderSource::UserProvided => &[Self::SOURCE, Self::DIMENSIONS, Self::DISTRIBUTION],
@@ -370,6 +403,7 @@ impl EmbeddingSettings {
                 Self::URL,
                 Self::REQUEST,
                 Self::RESPONSE,
+                Self::HEADERS,
                 Self::DISTRIBUTION,
             ],
         }
@@ -433,14 +467,15 @@ impl From<EmbeddingConfig> for EmbeddingSettings {
             }) => Self {
                 source: Setting::Set(EmbedderSource::HuggingFace),
                 model: Setting::Set(model),
-                revision: revision.map(Setting::Set).unwrap_or_default(),
+                revision: Setting::some_or_not_set(revision),
                 api_key: Setting::NotSet,
                 dimensions: Setting::NotSet,
                 document_template: Setting::Set(prompt.template),
                 url: Setting::NotSet,
                 request: Setting::NotSet,
                 response: Setting::NotSet,
-                distribution: distribution.map(Setting::Set).unwrap_or_default(),
+                headers: Setting::NotSet,
+                distribution: Setting::some_or_not_set(distribution),
             },
             super::EmbedderOptions::OpenAi(super::openai::EmbedderOptions {
                 url,
@@ -452,30 +487,33 @@ impl From<EmbeddingConfig> for EmbeddingSettings {
                 source: Setting::Set(EmbedderSource::OpenAi),
                 model: Setting::Set(embedding_model.name().to_owned()),
                 revision: Setting::NotSet,
-                api_key: api_key.map(Setting::Set).unwrap_or_default(),
-                dimensions: dimensions.map(Setting::Set).unwrap_or_default(),
+                api_key: Setting::some_or_not_set(api_key),
+                dimensions: Setting::some_or_not_set(dimensions),
                 document_template: Setting::Set(prompt.template),
-                url: url.map(Setting::Set).unwrap_or_default(),
+                url: Setting::some_or_not_set(url),
                 request: Setting::NotSet,
                 response: Setting::NotSet,
-                distribution: distribution.map(Setting::Set).unwrap_or_default(),
+                headers: Setting::NotSet,
+                distribution: Setting::some_or_not_set(distribution),
             },
             super::EmbedderOptions::Ollama(super::ollama::EmbedderOptions {
                 embedding_model,
                 url,
                 api_key,
                 distribution,
+                dimensions,
             }) => Self {
                 source: Setting::Set(EmbedderSource::Ollama),
                 model: Setting::Set(embedding_model),
                 revision: Setting::NotSet,
-                api_key: api_key.map(Setting::Set).unwrap_or_default(),
-                dimensions: Setting::NotSet,
+                api_key: Setting::some_or_not_set(api_key),
+                dimensions: Setting::some_or_not_set(dimensions),
                 document_template: Setting::Set(prompt.template),
-                url: url.map(Setting::Set).unwrap_or_default(),
+                url: Setting::some_or_not_set(url),
                 request: Setting::NotSet,
                 response: Setting::NotSet,
-                distribution: distribution.map(Setting::Set).unwrap_or_default(),
+                headers: Setting::NotSet,
+                distribution: Setting::some_or_not_set(distribution),
             },
             super::EmbedderOptions::UserProvided(super::manual::EmbedderOptions {
                 dimensions,
@@ -490,7 +528,8 @@ impl From<EmbeddingConfig> for EmbeddingSettings {
                 url: Setting::NotSet,
                 request: Setting::NotSet,
                 response: Setting::NotSet,
-                distribution: distribution.map(Setting::Set).unwrap_or_default(),
+                headers: Setting::NotSet,
+                distribution: Setting::some_or_not_set(distribution),
             },
             super::EmbedderOptions::Rest(super::rest::EmbedderOptions {
                 api_key,
@@ -499,17 +538,19 @@ impl From<EmbeddingConfig> for EmbeddingSettings {
                 request,
                 response,
                 distribution,
+                headers,
             }) => Self {
                 source: Setting::Set(EmbedderSource::Rest),
                 model: Setting::NotSet,
                 revision: Setting::NotSet,
-                api_key: api_key.map(Setting::Set).unwrap_or_default(),
-                dimensions: dimensions.map(Setting::Set).unwrap_or_default(),
+                api_key: Setting::some_or_not_set(api_key),
+                dimensions: Setting::some_or_not_set(dimensions),
                 document_template: Setting::Set(prompt.template),
                 url: Setting::Set(url),
                 request: Setting::Set(request),
                 response: Setting::Set(response),
-                distribution: distribution.map(Setting::Set).unwrap_or_default(),
+                distribution: Setting::some_or_not_set(distribution),
+                headers: Setting::Set(headers),
             },
         }
     }
@@ -529,6 +570,7 @@ impl From<EmbeddingSettings> for EmbeddingConfig {
             request,
             response,
             distribution,
+            headers,
         } = value;
 
         if let Some(source) = source.set() {
@@ -557,6 +599,7 @@ impl From<EmbeddingSettings> for EmbeddingConfig {
                         super::ollama::EmbedderOptions::with_default_model(
                             api_key.set(),
                             url.set(),
+                            dimensions.set(),
                         );
                     if let Some(model) = model.set() {
                         options.embedding_model = model;
@@ -598,6 +641,7 @@ impl From<EmbeddingSettings> for EmbeddingConfig {
                             request: request.set().unwrap(),
                             response: response.set().unwrap(),
                             distribution: distribution.set(),
+                            headers: headers.set().unwrap_or_default(),
                         })
                 }
             }