> ## Documentation Index > Fetch the complete documentation index at: https://www.meilisearch.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Update embedders > Updates the `embedders` setting for the index. Send the new value in the request body; send null to reset to default. ## OpenAPI ````yaml /assets/open-api/meilisearch-openapi-mintlify.json patch /indexes/{index_uid}/settings/embedders openapi: 3.1.0 info: title: meilisearch description: Meilisearch HTTP server contact: name: Quentin de Quelen email: quentin@dequelen.me license: name: MIT identifier: MIT version: 1.41.0 servers: - url: http://localhost:7700 description: Local server. security: [] tags: - name: Stats description: >- Stats gives extended information and metrics about indexes and the Meilisearch database. - name: Health description: >- The health check endpoint enables you to periodically test the health of your Meilisearch instance. - name: Version description: Returns the version of the running Meilisearch instance. - name: Backups description: >- Meilisearch offers two types of backups: snapshots and dumps. Snapshots are mainly intended as a safeguard, while dumps are useful when migrating Meilisearch. - name: Export description: >- Export documents and settings from this instance to a remote Meilisearch server. - name: Async task management description: >- Routes for listing and managing batches and tasks (asynchronous operations). - name: Chats description: The `/chats` route allows you to manage chat workspaces. - name: Tasks description: >- The tasks route gives information about the progress of the [asynchronous operations](https://docs.meilisearch.com/learn/advanced/asynchronous_operations.html). - name: Batches description: >- Meilisearch groups compatible tasks ([asynchronous operations](https://www.meilisearch.com/docs/learn/async/asynchronous_operations)) into batches for efficient processing. For example, multiple document additions to the same index may be batched together. The /batches routes give information about the progress of these batches and let you monitor batch progress and performance. - name: Indexes description: >- An index is an entity that gathers a set of [documents](https://www.meilisearch.com/docs/learn/getting_started/documents) with its own [settings](https://www.meilisearch.com/docs/reference/api/settings). Learn more about indexes. - name: Documents description: >- Documents are objects composed of fields that can store any type of data. Each field contains an attribute and its associated value. Documents are stored inside [indexes](https://www.meilisearch.com/docs/learn/getting_started/indexes). - name: Facet Search description: >- The `/facet-search` route allows you to search for facet values. Facet search supports prefix search and typo tolerance. The returned hits are sorted lexicographically in ascending order. You can configure how facets are sorted using the sortFacetValuesBy property of the faceting index settings. - name: Similar documents description: >- The /similar route uses AI-powered search to return a number of documents similar to a target document. Meilisearch exposes two routes for retrieving similar documents: POST and GET. In the majority of cases, POST will offer better performance and ease of use. - name: Settings description: >- Configure search and index behavior. Update all settings at once via PATCH /indexes/{indexUid}/settings, or use a sub-route to get, update, or reset a single setting. - name: Search description: >- Meilisearch exposes two routes to perform searches: - A POST route: this is the preferred route when using API authentication, as it allows [preflight request](https://developer.mozilla.org/en-US/docs/Glossary/Preflight_request) caching and better performance. - A GET route: the usage of this route is discouraged, unless you have good reason to do otherwise (specific caching abilities for example) externalDocs: url: https://www.meilisearch.com/docs/reference/api/search description: Search API reference - name: Keys description: >- Manage API `keys` for a Meilisearch instance. Each key has a given set of permissions. You must have the master key or the default admin key to access the keys route. More information about the keys and their rights. Accessing any route under `/keys` without having set a master key will result in an error. - name: Logs description: >- Everything about retrieving or customizing logs. Currently [experimental](https://www.meilisearch.com/docs/learn/experimental/overview). - name: Multi-search description: >- The `/multi-search` route allows you to perform multiple search queries on one or more indexes by bundling them into a single HTTP request. Multi-search is also known as federated search. - name: Experimental features description: >- The `/experimental-features` route allows you to activate or deactivate some of Meilisearch's experimental features. This route is **synchronous**. This means that no task object will be returned, and any activated or deactivated features will be made available or unavailable immediately. - name: Network description: >- The `/network` route allows you to describe the topology of a network of Meilisearch instances. This route is **synchronous**. This means that no task object will be returned, and any change to the network will be made available immediately. - name: Webhooks description: >- The `/webhooks` route allows you to register endpoints to be called once tasks are processed. - name: Dynamic search rules description: >- The `/dynamic-search-rules` route allows you to configure dynamic search rules. paths: /indexes/{index_uid}/settings/embedders: patch: tags: - Settings summary: Update embedders description: >- Updates the `embedders` setting for the index. Send the new value in the request body; send null to reset to default. operationId: patchembedders parameters: - name: index_uid in: path description: Unique identifier of the index. required: true schema: type: string example: movies requestBody: content: application/json: schema: type: object additionalProperties: $ref: '#/components/schemas/SettingEmbeddingSettings' propertyNames: type: string required: true responses: '202': description: Task successfully enqueued. content: application/json: schema: $ref: '#/components/schemas/SummarizedTaskView' example: taskUid: 147 indexUid: movies status: enqueued type: settingsUpdate enqueuedAt: '2024-08-08T17:05:55.791772Z' '401': description: The authorization header is missing. content: application/json: schema: $ref: '#/components/schemas/ResponseError' example: message: >- The Authorization header is missing. It must use the bearer authorization method. code: missing_authorization_header type: auth link: >- https://docs.meilisearch.com/errors#missing_authorization_header '404': description: Index not found. content: application/json: schema: $ref: '#/components/schemas/ResponseError' example: message: Index `movies` not found. code: index_not_found type: invalid_request link: https://docs.meilisearch.com/errors#index_not_found security: - Bearer: - settings.update - settings.* - '*' x-codeSamples: - lang: cURL source: |- curl \ -X PATCH 'MEILISEARCH_URL/indexes/INDEX_NAME/settings/embedders' \ -H 'Content-Type: application/json' \ --data-binary '{ "default": { "source": "openAi", "apiKey": "OPEN_AI_API_KEY", "model": "text-embedding-3-small", "documentTemplate": "A document titled '{{doc.title}}' whose description starts with {{doc.overview|truncatewords: 20}}" } }' - lang: JS source: |- client.index('INDEX_NAME').updateEmbedders({ default: { source: 'openAi', apiKey: 'OPEN_AI_API_KEY', model: 'text-embedding-3-small', documentTemplate: 'A document titled '{{doc.title}}' whose description starts with {{doc.overview|truncatewords: 20}}' } }); - lang: PHP source: |- $client->updateEmbedders([ 'default' => [ 'source' => 'openAi', 'apiKey' => 'OPEN_AI_API_KEY', 'model' => 'text-embedding-3-small', 'documentTemplate' => 'A document titled '{{doc.title}}' whose description starts with {{doc.overview|truncatewords: 20}}' ] ]); - lang: Python source: |- client.index('INDEX_NAME').update_embedders({ "default": { "source": "openAi", "apiKey": "OPEN_AI_API_KEY", "model": "text-embedding-3-small", "documentTemplate": "A document titled '{{doc.title}}' whose description starts with {{doc.overview|truncatewords: 20}}" } }) - lang: Ruby source: |- client.index('INDEX_NAME').update_embedders( default: { source: 'openAi', api_key: 'OPEN_AI_API_KEY', model: 'text-embedding-3-small', document_template: "A document titled '{{doc.title}}' whose description starts with {{doc.overview|truncatewords: 20}}" } ) - lang: Rust source: |- let embedders = HashMap::from([( String::from("default"), Embedder { source: EmbedderSource::OpenAi, api_key: Some(String::from("OPEN_AI_API_KEY")), model: Some(String::from("text-embedding-3-small")), document_template: Some(String::from("A document titled '{{doc.title}}' whose description starts with {{doc.overview|truncatewords: 20}}")), ..Embedder::default() } )]); let task = index .set_embedders(&embedders) .await .unwrap(); components: schemas: SettingEmbeddingSettings: type: object description: >- Configuration for one [embedder](https://www.meilisearch.com/docs/learn/ai_powered_search/getting_started_with_ai_search) used for semantic and hybrid search. Set `source` (`openAi`, `huggingFace`, `ollama`, `rest`, `userProvided`), then the options that apply: `model`, `apiKey`, `documentTemplate`, `dimensions`, `url`, etc. properties: inner: oneOf: - type: 'null' - type: object description: >- Embedder configuration for [AI-powered / hybrid search](https://www.meilisearch.com/docs/learn/ai_powered_search/getting_started_with_ai_search). properties: source: oneOf: - type: 'null' - $ref: '#/components/schemas/EmbedderSource' description: >- Embedding provider. - `openAi`: integration with OpenAI. Use `rest` for OpenAI-like APIs. - `huggingFace`: download a model from [Hugging Face](https://huggingface.co/), then compute embeddings on the local CPU/GPU. - `ollama`: integration with [ollama](https://ollama.com/). - `rest`: configurable integration with a remote embedder via its REST API. - `composite`: combine two embedding providers at indexing and search time. The generated embeddings must be **exactly the same** regardless of the embedding provider. - `userProvided`: manually provide embeddings in documents. - Determines which other fields are required or allowed. - 🏗️ Changing the value of this parameter always regenerates embeddings. default: openAi model: type: - string - 'null' description: >- Model name. - Available for `openAi`, `huggingFace`, `ollama`. - Mandatory for `ollama`. - For `openAi`/`huggingFace` optional with defaults. - 🏗️ Changing the value of this parameter always regenerates embeddings. example: text-embedding-3-small revision: type: - string - 'null' description: >- Model revision (e.g. Hugging Face commit SHA). - Only available for `huggingFace`. - If unset, latest is used. - 🏗️ Changing the value of this parameter always regenerates embeddings pooling: oneOf: - type: 'null' - $ref: '#/components/schemas/OverridePooling' description: >- Pooling method when computing embedding locally. - Only available for `huggingFace`. - `useModel`: automatically determine the pooling method depending on the chosen model (recommended). - `forceMean`: always use mean pooling. - `forceCls`: always use CLS pooling. - 🏗️ Changing the value of this parameter always regenerates embeddings default: useModel apiKey: type: - string - 'null' description: >- API key sent to the embedder. - If not set for source `openAi`, the key is read from the `OPENAI_API_KEY` then `MEILI_OPENAI_API_KEY` environment variables. - If not set for other sources, no bearer token is sent. - This setting is partially hidden when returned by the settings - 🌱 Changing the value of this parameter never regenerates embeddings dimensions: type: - integer - 'null' description: >- Number of dimensions of the embedding vectors. - Available for `userProvided`, `openAi`, `ollama`, `rest`. - Mandatory for `userProvided`. - For `openAi`/`ollama`/`rest` inferred if omitted. - 🏗️ For `openAi`, changing the value of this parameter always regenerates embeddings - 🌱 For other sources, changing the value of this parameter never regenerates embeddings example: 1536 minimum: 0 binaryQuantized: type: - boolean - 'null' description: >- When true, vectors are stored as 1-bit (smaller, faster, less precise). - Available for all sources. - Irreversible once enabled. - 🏗️ When set to true, embeddings are not regenerated, but they are binary quantized, which takes time. default: false documentTemplate: type: - string - 'null' description: >- [Liquid template](https://shopify.github.io/liquid/) to build the text sent to the embedder for each document. - Available for `openAi`, `huggingFace`, `ollama`, `rest`. - 🏗️ When modified, embeddings are regenerated for documents whose rendering through the template produces a different text. example: '{{doc.title}}: {{doc.overview}}' documentTemplateMaxBytes: type: - integer - 'null' description: >- Max size in bytes of the rendered document template. Longer output is truncated. - Available for `openAi`, `huggingFace`, `ollama`, `rest`. - 🏗️ When increased, embeddings are regenerated for documents whose rendering through the template produces a different text. - 🌱 When decreased, embeddings are never regenerated default: 400 example: 400 minimum: 0 url: type: - string - 'null' description: >- URL of the embedder API. - Mandatory for `rest`. Optional for `openAi` and `ollama`. - 🌱 When modified for `openAi``, embeddings are never regenerated - 🏗️ When modified for `ollama` and `rest`, embeddings are always regenerated - If targetting URL resolving to a non-global IP (such as `localhost`), make sure that `--experimental-allowed-ip-networks` allows it. For details on how use this parameter, refer to [this documentation](https://www.meilisearch.com/docs/learn/self_hosted/configure_meilisearch_at_launch#allow-requests-to-private-networks). example: http://localhost:11434/api/embeddings indexingFragments: type: - object - 'null' description: >- Fragments (with [Liquid](https://shopify.github.io/liquid/)) sent to the embedder at indexing time. For `rest` with multimodal; key is fragment name, value the payload. See also [Image search with multimodal embeddings](https://www.meilisearch.com/docs/learn/ai_powered_search/image_search_with_multimodal_embeddings) - 🏗️ When a fragment is deleted by passing `null` to its name, the corresponding embeddings are removed from documents. - 🏗️ When a fragment is modified, the corresponding embeddings are regenerated if their rendered version changes. default: {} additionalProperties: {} propertyNames: type: string searchFragments: type: - object - 'null' description: >- Fragments (with [Liquid](https://shopify.github.io/liquid/)) sent to the embedder at search time. For `rest` with multimodal. See also [Image search with multimodal embeddings](https://www.meilisearch.com/docs/learn/ai_powered_search/image_search_with_multimodal_embeddings) - 🌱 Changing the value of this parameter never regenerates embeddings default: {} additionalProperties: {} propertyNames: type: string request: description: >- Request body template for `rest` embedder. See also [Configure a REST embedder](https://www.meilisearch.com/docs/learn/ai_powered_search/configure_rest_embedder) - Use `"{{text}}"` for the input. - Mandatory for `rest`. - 🏗️ Changing the value of this parameter always regenerates embeddings response: description: >- Response template for `rest` embedder. See also [Configure a REST embedder](https://www.meilisearch.com/docs/learn/ai_powered_search/configure_rest_embedder) - Use `"{{embedding}}"` where the embedding array is. - Mandatory for `rest`. headers: type: - object - 'null' description: >- Extra HTTP headers sent to the embedder. - Available for `rest`. - 🌱 Changing the value of this parameter never regenerates embeddings additionalProperties: type: string propertyNames: type: string searchEmbedder: oneOf: - type: 'null' - $ref: '#/components/schemas/SubEmbeddingSettings' description: >- Embedder used at search time when using a composite embedder. Same sub-parameters as a top-level embedder (`source`, `model`, `url`, etc.); no `documentTemplate`/`documentTemplateMaxBytes`. indexingEmbedder: oneOf: - type: 'null' - $ref: '#/components/schemas/SubEmbeddingSettings' description: >- Embedder used at indexing time when using a composite embedder. Same sub-parameters as a top-level embedder (`source`, `model`, `documentTemplate`, `url`, etc.). distribution: oneOf: - type: 'null' - $ref: '#/components/schemas/DistributionShift' description: >- Affine transform (mean, sigma) applied to the semantic score to make it more comparable with the ranking score. See also [this article](https://www.meilisearch.com/blog/fixing-hybrid-search#making-the-scores-comparable). - Available for all sources. - 🌱 Changing the value of this parameter never regenerates embeddings additionalProperties: false SummarizedTaskView: type: object description: A summarized view of a task, returned when a task is enqueued required: - taskUid - status - type - enqueuedAt properties: taskUid: type: integer format: u-int32 description: Unique sequential identifier of the task. minimum: 0 indexUid: type: - string - 'null' description: Unique identifier of the targeted index. Null for global tasks. status: $ref: '#/components/schemas/Status' description: |- Status of the task. Possible values are `enqueued`, `processing`, `succeeded`, `failed`, and `canceled`. type: $ref: '#/components/schemas/Kind' description: Type of operation performed by the task. enqueuedAt: type: string format: date-time description: Date and time when the task was enqueued. customMetadata: type: - string - 'null' description: >- Custom metadata attached to this task at creation. Use it to associate tasks with external systems or add application-specific information. ResponseError: type: object required: - message - code - type - link properties: message: type: string description: The error message. code: $ref: '#/components/schemas/Code' description: The error code. type: $ref: '#/components/schemas/ErrorType' description: The error type. link: type: string description: A link to the documentation about this specific error. EmbedderSource: type: string enum: - openAi - huggingFace - ollama - userProvided - rest - composite OverridePooling: type: string enum: - useModel - forceCls - forceMean SubEmbeddingSettings: type: object description: >- Sub-embedder config for composite embedders. Used by `indexingEmbedder` (vectorize documents at index time) and `searchEmbedder` (vectorize queries at search time). Same fields as a top-level embedder, except no `binaryQuantized`, `distribution`, `documentTemplate`/`documentTemplateMaxBytes` for searchEmbedder. properties: source: oneOf: - type: 'null' - $ref: '#/components/schemas/EmbedderSource' description: >- Embedding provider. - `openAi`: integration with OpenAI. Use `rest` for OpenAI-like APIs. - `huggingFace`: download a model from [Hugging Face](https://huggingface.co/), then compute embeddings on the local CPU/GPU. - `ollama`: integration with [ollama](https://ollama.com/). - `rest`: configurable integration with a remote embedder via its REST API. - `userProvided`: manually provide embeddings in documents. - Determines which other fields are required or allowed. - 🏗️ Changing the value of this parameter always regenerates embeddings. default: openAi model: type: - string - 'null' description: >- Model name. - Available for `openAi`, `huggingFace`, `ollama`. - Mandatory for `ollama`. - For `openAi`/`huggingFace` optional with defaults. - 🏗️ Changing the value of this parameter always regenerates embeddings. example: text-embedding-3-small revision: type: - string - 'null' description: >- Model revision (e.g. Hugging Face commit SHA). - Only available for `huggingFace`. - If unset, latest is used. - 🏗️ Changing the value of this parameter always regenerates embeddings example: 617ca489d9e86b49b8167676d8220688b99db36e pooling: oneOf: - type: 'null' - $ref: '#/components/schemas/OverridePooling' description: >- Pooling method when computing embedding locally. - Only available for `huggingFace`. - `useModel`: automatically determine the pooling method depending on the chosen model (recommended). - `forceMean`: always use mean pooling. - `forceCls`: always use CLS pooling. - 🏗️ Changing the value of this parameter always regenerates embeddings default: useModel apiKey: type: - string - 'null' description: >- API key sent to the embedder. - If not set for source `openAi`, the key is read from the `OPENAI_API_KEY` then `MEILI_OPENAI_API_KEY` environment variables. - If not set for other sources, no bearer token is sent. - This setting is partially hidden when returned by the settings - 🌱 Changing the value of this parameter never regenerates embeddings example: your-api-key dimensions: type: - integer - 'null' description: >- Number of dimensions of the embedding vectors. - Available for `userProvided`, `openAi`, `ollama`, `rest`. - Mandatory for `userProvided`. - For `openAi`/`ollama`/`rest` inferred if omitted. - 🏗️ For `openAi`, changing the value of this parameter always regenerates embeddings - 🌱 For other sources, changing the value of this parameter never regenerates embeddings example: 1536 minimum: 0 documentTemplate: type: - string - 'null' description: >- [Liquid template](https://shopify.github.io/liquid/) to build the text sent to the embedder for each document. - Only available for `indexingEmbedder`, not `searchEmbedder`. - Available for `openAi`, `huggingFace`, `ollama`, `rest`. - 🏗️ When modified, embeddings are regenerated for documents whose rendering through the template produces a different text. example: '{{doc.title}}: {{doc.overview}}' documentTemplateMaxBytes: type: - integer - 'null' description: >- Max size in bytes of the rendered document template. Longer output is truncated. - Only available for `indexingEmbedder`, not `searchEmbedder`. - Available for `openAi`, `huggingFace`, `ollama`, `rest`. - 🏗️ When increased, embeddings are regenerated for documents whose rendering through the template produces a different text. - 🌱 When decreased, embeddings are never regenerated default: 400 example: 400 minimum: 0 url: type: - string - 'null' description: >- URL of the embedder API. - Mandatory for `rest`. Optional for `openAi` and `ollama`. - 🌱 When modified for `openAi``, embeddings are never regenerated - 🏗️ When modified for `ollama` and `rest`, embeddings are always regenerated - If targetting URL resolving to a non-global IP (such as `localhost`), make sure that `--experimental-allowed-ip-networks` allows it. For details on how use this parameter, refer to [this documentation](https://www.meilisearch.com/docs/learn/self_hosted/configure_meilisearch_at_launch#allow-requests-to-private-networks). example: http://localhost:11434/api/embeddings indexingFragments: type: - object - 'null' description: >- Fragments (with [Liquid](https://shopify.github.io/liquid/)) sent to the embedder at indexing time. For `rest` with multimodal; key is fragment name, value the payload. See also [Image search with multimodal embeddings](https://www.meilisearch.com/docs/learn/ai_powered_search/image_search_with_multimodal_embeddings) - Only available for `indexingEmbedder`, not `searchEmbedder`. - 🏗️ When a fragment is deleted by passing `null` to its name, the corresponding embeddings are removed from documents. - 🏗️ When a fragment is modified, the corresponding embeddings are regenerated if their rendered version changes. default: {} additionalProperties: {} propertyNames: type: string searchFragments: type: - object - 'null' description: >- Fragments (with [Liquid](https://shopify.github.io/liquid/)) sent to the embedder at search time. For `rest` with multimodal. See also [Image search with multimodal embeddings](https://www.meilisearch.com/docs/learn/ai_powered_search/image_search_with_multimodal_embeddings) - 🌱 Changing the value of this parameter never regenerates embeddings default: {} additionalProperties: {} propertyNames: type: string request: description: >- Request body template for `rest` embedder. See also [Configure a REST embedder](https://www.meilisearch.com/docs/learn/ai_powered_search/configure_rest_embedder) - Use `"{{text}}"` for the input. - Mandatory for `rest`. - 🏗️ Changing the value of this parameter always regenerates embeddings response: description: >- Response template for `rest` embedder. See also [Configure a REST embedder](https://www.meilisearch.com/docs/learn/ai_powered_search/configure_rest_embedder) - Use `"{{embedding}}"` where the embedding array is. - Mandatory for `rest`. headers: type: - object - 'null' description: >- Extra HTTP headers sent to the embedder. - Available for `rest`. - 🌱 Changing the value of this parameter never regenerates embeddings additionalProperties: type: string propertyNames: type: string additionalProperties: false DistributionShift: type: object description: >- Describes the mean and sigma of distribution of embedding similarity in the embedding space. The intended use is to make the similarity score more comparable to the regular ranking score. This allows to correct effects where results are too "packed" around a certain value. required: - current_mean - current_sigma properties: current_mean: type: number format: float description: >- Value where the results are "packed". Similarity scores are translated so that they are packed around 0.5 instead current_sigma: type: number format: float description: >- standard deviation of a similarity score. Set below 0.4 to make the results less packed around the mean, and above 0.4 to make them more packed. Status: type: string description: The status of a task. enum: - enqueued - processing - succeeded - failed - canceled example: processing Kind: type: string description: The type of the task. enum: - documentAdditionOrUpdate - documentEdition - documentDeletion - settingsUpdate - indexCreation - indexDeletion - indexUpdate - indexSwap - taskCancelation - taskDeletion - dumpCreation - snapshotCreation - export - upgradeDatabase - indexCompaction - networkTopologyChange example: documentAdditionOrUpdate Code: type: string enum: - api_key_already_exists - api_key_not_found - bad_parameter - bad_request - database_size_limit_reached - document_not_found - dump_already_processing - dump_not_found - dump_process_failed - duplicate_index_found - immutable_api_key_actions - immutable_api_key_created_at - immutable_api_key_expires_at - immutable_api_key_indexes - immutable_api_key_key - immutable_api_key_uid - immutable_api_key_updated_at - immutable_index_created_at - immutable_index_updated_at - import_task_already_received - import_task_unknown_remote - receive_import_finished_unknown_remote - import_task_without_network_task - index_already_exists - index_creation_failed - index_not_found - index_primary_key_already_exists - index_primary_key_multiple_candidates_found - index_primary_key_no_candidate_found - internal - invalid_api_key - invalid_api_key_actions - invalid_api_key_description - invalid_api_key_expires_at - invalid_api_key_indexes - invalid_api_key_limit - invalid_api_key_name - invalid_api_key_offset - invalid_api_key_uid - invalid_content_type - invalid_document_csv_delimiter - invalid_document_fields - invalid_document_retrieve_vectors - missing_document_filter - missing_document_edition_function - inconsistent_document_change_headers - invalid_document_filter - invalid_document_sort - invalid_document_geo_field - invalid_document_geojson_field - invalid_header_value - invalid_vector_dimensions - invalid_vectors_type - invalid_document_id - invalid_document_ids - invalid_document_limit - invalid_document_offset - invalid_search_embedder - invalid_similar_embedder - invalid_search_hybrid_query - invalid_index_limit - invalid_index_offset - invalid_index_primary_key - invalid_index_custom_metadata - invalid_skip_creation - invalid_index_uid - invalid_multi_search_facets - invalid_multi_search_facets_by_index - invalid_multi_search_facet_order - invalid_multi_search_query_personalization - invalid_multi_search_query_show_performance_details - invalid_multi_search_federated - invalid_multi_search_federation_options - invalid_multi_search_max_values_per_facet - invalid_multi_search_merge_facets - invalid_multi_search_query_facets - invalid_multi_search_distinct - invalid_multi_search_query_pagination - invalid_multi_search_query_ranking_rules - invalid_multi_search_query_position - invalid_multi_search_remote - invalid_multi_search_weight - invalid_network_leader - invalid_network_remotes - invalid_network_shards - invalid_network_self - invalid_network_search_api_key - invalid_network_write_api_key - invalid_network_url - invalid_search_attributes_to_search_on - invalid_search_attributes_to_crop - invalid_search_attributes_to_highlight - invalid_similar_attributes_to_retrieve - invalid_similar_retrieve_vectors - invalid_search_attributes_to_retrieve - invalid_search_ranking_score_threshold - invalid_similar_ranking_score_threshold - invalid_search_retrieve_vectors - invalid_search_crop_length - invalid_search_crop_marker - invalid_search_facets - invalid_search_semantic_ratio - invalid_search_locales - invalid_facet_search_exhaustive_facet_count - invalid_facet_search_facet_name - invalid_similar_id - invalid_search_filter - invalid_similar_filter - invalid_search_highlight_post_tag - invalid_search_highlight_pre_tag - invalid_search_hits_per_page - invalid_similar_limit - invalid_search_limit - invalid_search_matching_strategy - invalid_similar_offset - invalid_search_offset - invalid_search_page - invalid_search_q - invalid_facet_search_query - invalid_facet_search_name - facet_search_disabled - invalid_search_vector - invalid_search_media - invalid_search_show_matches_position - invalid_search_show_ranking_score - invalid_similar_show_ranking_score - invalid_search_show_ranking_score_details - invalid_search_show_performance_details - invalid_search_use_network - invalid_similar_show_ranking_score_details - invalid_similar_show_performance_details - invalid_search_sort - invalid_search_distinct - invalid_search_personalize - invalid_search_personalize_user_context - invalid_search_media_and_vector - invalid_settings_displayed_attributes - invalid_settings_distinct_attribute - invalid_settings_proximity_precision - invalid_settings_facet_search - invalid_settings_prefix_search - invalid_settings_faceting - invalid_settings_filterable_attributes - invalid_settings_foreign_keys - invalid_settings_pagination - invalid_settings_search_cutoff_ms - invalid_settings_embedders - invalid_settings_ranking_rules - invalid_settings_searchable_attributes - invalid_settings_sortable_attributes - invalid_settings_stop_words - invalid_settings_non_separator_tokens - invalid_settings_separator_tokens - invalid_settings_dictionary - invalid_settings_synonyms - invalid_settings_typo_tolerance - invalid_settings_localized_attributes - invalid_state - invalid_store_file - invalid_swap_duplicate_index_found - invalid_swap_indexes - invalid_swap_rename - invalid_task_after_enqueued_at - invalid_task_after_finished_at - invalid_task_after_started_at - invalid_task_before_enqueued_at - invalid_task_before_finished_at - invalid_task_before_started_at - invalid_task_canceled_by - invalid_task_from - invalid_task_limit - invalid_task_reverse - invalid_task_statuses - invalid_task_types - invalid_task_uids - invalid_batch_uids - io_error - feature_not_enabled - malformed_payload - max_fields_limit_exceeded - missing_api_key_actions - missing_api_key_expires_at - missing_api_key_indexes - missing_authorization_header - missing_content_type - missing_document_id - missing_facet_search_facet_name - missing_index_uid - missing_master_key - missing_network_url - missing_payload - missing_search_hybrid - missing_swap_indexes - missing_task_filters - network_version_mismatch - no_space_left_on_device - not_leader - payload_too_large - remote_bad_response - remote_bad_request - remote_could_not_send_request - remote_invalid_api_key - remote_remote_error - remote_timeout - too_many_search_requests - task_not_found - task_file_not_found - batch_not_found - too_many_open_files - too_many_vectors - unexpected_network_previous_remotes - network_version_too_old - unprocessed_network_task - unretrievable_document - unretrievable_error_code - unsupported_media_type - invalid_s3_snapshot_request - invalid_s3_snapshot_parameters - s3_snapshot_server_error - vector_embedding_error - not_found_similar_id - invalid_document_edition_context - invalid_document_edition_function_filter - edit_documents_by_function_error - invalid_settings_index_chat - invalid_export_url - invalid_export_api_key - invalid_export_payload_size - invalid_export_indexes_patterns - invalid_export_index_filter - invalid_export_index_override_settings - unimplemented_external_function_calling - unimplemented_non_streaming_chat_completions - unimplemented_multi_choice_chat_completions - chat_not_found - invalid_chat_setting_document_template - invalid_chat_completion_org_id - invalid_chat_completion_project_id - invalid_chat_completion_api_version - invalid_chat_completion_deployment_id - invalid_chat_completion_source - invalid_chat_completion_base_api - invalid_chat_completion_api_key - invalid_chat_completion_prompts - invalid_chat_completion_system_prompt - invalid_chat_completion_search_description_prompt - invalid_chat_completion_search_query_param_prompt - invalid_chat_completion_search_filter_param_prompt - invalid_chat_completion_search_index_uid_param_prompt - invalid_chat_completion_pre_query_prompt - invalid_index_fields_filter - invalid_index_fields_filter_attribute_patterns - invalid_index_fields_filter_displayed - invalid_index_fields_filter_searchable - invalid_index_fields_filter_sortable - invalid_index_fields_filter_distinct - invalid_index_fields_filter_ranking_rule - invalid_index_fields_filter_filterable - requires_enterprise_edition - invalid_webhooks - invalid_webhook_url - invalid_webhook_headers - immutable_webhook - invalid_webhook_uuid - webhook_not_found - immutable_webhook_uuid - immutable_webhook_is_editable - invalid_dynamic_search_rule_offset - invalid_dynamic_search_rule_limit - invalid_dynamic_search_rule_filter - invalid_dynamic_search_rule_description - invalid_dynamic_search_rule_priority - invalid_dynamic_search_rule_active - invalid_dynamic_search_rule_conditions - invalid_dynamic_search_rule_actions - invalid_dynamic_search_rule_filter_attribute_patterns - invalid_dynamic_search_rule_filter_active - dynamic_search_rule_not_found ErrorType: type: string enum: - internal - invalid_request - auth - system securitySchemes: Bearer: type: http scheme: bearer bearerFormat: Uuidv4, string or JWT description: >- An API key is a token that you provide when making API calls. Read more about [how to secure your project](https://www.meilisearch.com/docs/learn/security/basic_security). Include the API key to the `Authorization` header, for instance: ```bash -H 'Authorization: Bearer 6436fc5237b0d6e0d64253fbaac21d135012ecf1' ``` If you use a SDK, ensure you instantiate the client with the API key, for instance with [JS SDK](https://github.com/meilisearch/meilisearch-js): ```js const client = new Meilisearch({ host: 'MEILISEARCH_URL', apiKey: '6436fc5237b0d6e0d64253fbaac21d135012ecf1' }); ``` ````