> ## Documentation Index > Fetch the complete documentation index at: https://meilisearch-6b28dec2-add-render-template-route.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Request a chat completion ## OpenAPI ````yaml /assets/open-api/meilisearch-openapi-mintlify.json post /chats/{workspace_uid}/chat/completions 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: 1.48.1 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: Search rules description: The `/dynamic-search-rules` route allows you to configure search rules. - name: Render templates description: The /render-template route allows rendering templates used by Meilisearch. externalDocs: url: https://www.meilisearch.com/docs/reference/api/render-template description: Render template API reference paths: /chats/{workspace_uid}/chat/completions: post: tags: - Chats summary: Request a chat completion operationId: chat parameters: - name: workspace_uid in: path description: The unique identifier of the chat workspace. required: true schema: type: string example: my-workspace requestBody: content: application/json: schema: $ref: '#/components/schemas/CreateChatCompletionRequest' required: true responses: '200': description: Start a conversation. content: application/json: schema: $ref: '#/components/schemas/CreateChatCompletionResponse' example: id: chatcmpl-abc123 choices: - index: 0 message: content: >- After searching the Steam database, here are some game recommendations related to your query: 1. **Game Dev Tycoon**: This game might interest you, as it involves developing games, which could resonate with your work as a developer working on selling a search engine. It is a casual, strategy, and simulation game where you simulate a game development studio. 2. **Mad Games Tycoon**: Another game that could be relevant is Mad Games Tycoon. In this game, you build up your own games, similar to the process of creating and selling software, which could provide insights and inspiration for your work. 3. **Airline Tycoon 2**: While not directly related to search engines, Airline Tycoon 2 involves strategic decision-making and business management, which could offer valuable lessons for selling a product like a search engine. These games provide a mix of strategic thinking, simulation, and development aspects that might appeal to you as a developer working on selling a search engine. refusal: null tool_calls: null role: assistant function_call: null audio: null finish_reason: stop logprobs: null created: 1747922647 model: gpt-3.5-turbo-0125 service_tier: default system_fingerprint: null object: chat.completion usage: prompt_tokens: 1515 completion_tokens: 197 total_tokens: 1712 prompt_tokens_details: audio_tokens: 0 cached_tokens: 0 completion_tokens_details: accepted_prediction_tokens: 0 audio_tokens: 0 reasoning_tokens: 0 rejected_prediction_tokens: 0 '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: Chat not found. content: application/json: schema: $ref: '#/components/schemas/ResponseError' example: message: Chat :workspaceUid not found. code: chat_not_found type: invalid_request link: https://docs.meilisearch.com/errors#chat_not_found security: - Bearer: - chatsCompletions - '*' x-codeSamples: - lang: cURL source: |- curl -N \ -X POST 'MEILISEARCH_URL/chats/WORKSPACE_NAME/chat/completions' \ -H 'Authorization: Bearer MEILISEARCH_KEY' \ -H 'Content-Type: application/json' \ --data-binary '{ "model": "PROVIDER_MODEL_UID", "messages": [ { "role": "user", "content": "USER_PROMPT" } ], "tools": [ { "type": "function", "function": { "name": "_meiliSearchProgress", "description": "Reports real-time search progress to the user" } }, { "type": "function", "function": { "name": "_meiliSearchSources", "description": "Provides sources and references for the information" } } ] }' components: schemas: CreateChatCompletionRequest: type: object description: A chat completion request compatible with the OpenAI API. required: - messages - model properties: messages: type: array items: $ref: '#/components/schemas/ChatCompletionRequestMessage' description: >- A list of messages comprising the conversation so far. Depending on the [model](https://platform.openai.com/docs/models) you use, different message types (modalities) are supported, like [text](https://platform.openai.com/docs/guides/text-generation), [images](https://platform.openai.com/docs/guides/vision), and [audio](https://platform.openai.com/docs/guides/audio). model: type: string description: >- ID of the model to use. See the [model endpoint compatibility](https://platform.openai.com/docs/models#model-endpoint-compatibility) table for details on which models work with the Chat API. store: type: - boolean - 'null' description: >- Whether or not to store the output of this chat completion request for use in our [model distillation](https://platform.openai.com/docs/guides/distillation) or [evals](https://platform.openai.com/docs/guides/evals) products. reasoning_effort: oneOf: - type: 'null' - $ref: '#/components/schemas/ReasoningEffort' description: >- **o1 models only** Constrains effort on reasoning for [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently supported values are `low`, `medium`, and `high`. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. metadata: description: >- Developer-defined tags and values used for filtering completions in the [dashboard](https://platform.openai.com/chat-completions). frequency_penalty: type: - number - 'null' format: float description: >- Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. logit_bias: type: - object - 'null' description: >- Modify the likelihood of specified tokens appearing in the completion. Accepts a json object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. additionalProperties: {} propertyNames: type: string logprobs: type: - boolean - 'null' description: >- Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the `content` of `message`. top_logprobs: type: - integer - 'null' format: u-int8 description: >- An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. `logprobs` must be set to `true` if this parameter is used. minimum: 0 max_tokens: type: - integer - 'null' format: u-int32 description: >- The maximum number of [tokens](https://platform.openai.com/tokenizer) that can be generated in the chat completion. This value can be used to control [costs](https://openai.com/api/pricing/) for text generated via API. This value is now deprecated in favor of `max_completion_tokens`, and is not compatible with [o1 series models](https://platform.openai.com/docs/guides/reasoning). deprecated: true minimum: 0 max_completion_tokens: type: - integer - 'null' format: u-int32 description: >- An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and [reasoning tokens](https://platform.openai.com/docs/guides/reasoning). minimum: 0 'n': type: - integer - 'null' format: u-int8 description: >- How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep `n` as `1` to minimize costs. minimum: 0 modalities: type: - array - 'null' items: $ref: '#/components/schemas/ChatCompletionModalities' description: >- Output types that you would like the model to generate for this request. Most models are capable of generating text, which is the default: `["text"]`. prediction: oneOf: - type: 'null' - $ref: '#/components/schemas/PredictionContent' description: >- Configuration for a [Predicted Output](https://platform.openai.com/docs/guides/predicted-outputs),which can greatly improve response times when large parts of the model response are known ahead of time. This is most common when you are regenerating a file with only minor changes to most of the content. audio: oneOf: - type: 'null' - $ref: '#/components/schemas/ChatCompletionAudio' description: >- Parameters for audio output. Required when audio output is requested with `modalities: ["audio"]`. [Learn more](https://platform.openai.com/docs/guides/audio). presence_penalty: type: - number - 'null' format: float description: >- Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. response_format: oneOf: - type: 'null' - $ref: '#/components/schemas/ResponseFormat' description: >- An object specifying the format that the model must output. Compatible with [GPT-4o](https://platform.openai.com/docs/models/gpt-4o), [GPT-4o mini](https://platform.openai.com/docs/models/gpt-4o-mini), [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo) and all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`. Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured Outputs which guarantees the model will match your supplied JSON schema. Learn more in the [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs). Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the message the model generates is valid JSON. **Important:** when using JSON mode, you **must** also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if `finish_reason="length"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length. seed: type: - integer - 'null' format: int64 description: >2- This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result. Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend. service_tier: oneOf: - type: 'null' - $ref: '#/components/schemas/ServiceTier' description: >- Specifies the latency tier to use for processing the request. This parameter is relevant for customers subscribed to the scale tier service: - If set to 'auto', the system will utilize scale tier credits until they are exhausted. - If set to 'default', the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee. - When not set, the default behavior is 'auto'. When this parameter is set, the response body will include the `service_tier` utilized. stop: oneOf: - type: 'null' - $ref: '#/components/schemas/Stop' description: >- Up to 4 sequences where the API will stop generating further tokens. stream: type: - boolean - 'null' description: >- If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]` message. [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions). stream_options: oneOf: - type: 'null' - $ref: '#/components/schemas/ChatCompletionStreamOptions' description: >- Options for streaming response. Only set this when you set `stream: true`. temperature: type: - number - 'null' format: float description: >- What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. top_p: type: - number - 'null' format: float description: >- An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both. tools: type: - array - 'null' items: $ref: '#/components/schemas/ChatCompletionTool' description: >- A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported. tool_choice: oneOf: - type: 'null' - $ref: '#/components/schemas/ChatCompletionToolChoiceOption' description: >- Controls which (if any) tool is called by the model. `none` means the model will not call any tool and instead generates a message. `auto` means the model can pick between generating a message or calling one or more tools. `required` means the model must call one or more tools. `none` is the default when no tools are present. `auto` is the default if tools are present. parallel_tool_calls: type: - boolean - 'null' description: >- Whether to enable [parallel function calling](https://platform.openai.com/docs/guides/function-calling/parallel-function-calling) during tool use. user: type: - string - 'null' description: >- A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids). function_call: oneOf: - type: 'null' - $ref: '#/components/schemas/ChatCompletionFunctionCall' description: >- Deprecated in favor of `tool_choice`. Controls which (if any) function is called by the model. `none` means the model will not call a function and instead generates a message. `auto` means the model can pick between generating a message or calling a function. Specifying a particular function via `{"name": "my_function"}` forces the model to call that function. `none` is the default when no functions are present. `auto` is the default if functions are present. functions: type: - array - 'null' items: $ref: '#/components/schemas/ChatCompletionFunctions' description: |- Deprecated in favor of `tools`. A list of functions the model may generate JSON inputs for. deprecated: true CreateChatCompletionResponse: type: object description: >- Represents a chat completion response returned by model, based on the provided input. required: - id - choices - created - model - object properties: id: type: string description: A unique identifier for the chat completion. choices: type: array items: $ref: '#/components/schemas/ChatChoice' description: >- A list of chat completion choices. Can be more than one if `n` is greater than 1. created: type: integer format: u-int32 description: >- The Unix timestamp (in seconds) of when the chat completion was created. minimum: 0 model: type: string description: The model used for the chat completion. service_tier: oneOf: - type: 'null' - $ref: '#/components/schemas/ServiceTierResponse' description: >- The service tier used for processing the request. This field is only included if the `service_tier` parameter is specified in the request. system_fingerprint: type: - string - 'null' description: >- This fingerprint represents the backend configuration that the model runs with. Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism. object: type: string description: The object type, which is always `chat.completion`. usage: oneOf: - type: 'null' - $ref: '#/components/schemas/CompletionUsage' description: Usage statistics for the completion request. 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. ChatCompletionRequestMessage: oneOf: - allOf: - $ref: '#/components/schemas/ChatCompletionRequestDeveloperMessage' - type: object required: - role properties: role: type: string enum: - developer - allOf: - $ref: '#/components/schemas/ChatCompletionRequestSystemMessage' - type: object required: - role properties: role: type: string enum: - system - allOf: - $ref: '#/components/schemas/ChatCompletionRequestUserMessage' - type: object required: - role properties: role: type: string enum: - user - allOf: - $ref: '#/components/schemas/ChatCompletionRequestAssistantMessage' - type: object required: - role properties: role: type: string enum: - assistant - allOf: - $ref: '#/components/schemas/ChatCompletionRequestToolMessage' - type: object required: - role properties: role: type: string enum: - tool - allOf: - $ref: '#/components/schemas/ChatCompletionRequestFunctionMessage' - type: object required: - role properties: role: type: string enum: - function description: >- A message in the chat completion conversation. Tagged by `role` (system, user, assistant, tool, developer, or function). ReasoningEffort: type: string description: >- Constrains effort on reasoning for reasoning models. Supported values are `low`, `medium`, and `high`. enum: - low - medium - high ChatCompletionModalities: type: string description: >- Output types that you would like the model to generate for this request. Most models are capable of generating text, which is the default: `["text"]` The `gpt-4o-audio-preview` model can also be used to [generate audio](https://platform.openai.com/docs/guides/audio). To request that this model generate both text and audio responses, you can use: `["text", "audio"]` enum: - text - audio PredictionContent: oneOf: - type: object description: |- The type of the predicted content you want to provide. This type is currently always `content`. required: - content - type properties: content: $ref: '#/components/schemas/PredictionContentContent' description: >- The type of the predicted content you want to provide. This type is currently always `content`. type: type: string enum: - content description: >- Static predicted output content, such as the content of a text file that is being regenerated. ChatCompletionAudio: type: object description: >- Parameters for audio output. Required when audio output is requested with `modalities: ["audio"]`. required: - voice - format properties: voice: $ref: '#/components/schemas/ChatCompletionAudioVoice' description: >- The voice the model uses to respond. Supported voices are `ash`, `ballad`, `coral`, `sage`, and `verse` (also supported but not recommended are `alloy`, `echo`, and `shimmer`; these voices are less expressive). format: $ref: '#/components/schemas/ChatCompletionAudioFormat' description: >- Specifies the output audio format. Must be one of `wav`, `mp3`, `flac`, `opus`, or `pcm16`. ResponseFormat: oneOf: - type: object description: 'The type of response format being defined: `text`' required: - type properties: type: type: string enum: - text - type: object description: 'The type of response format being defined: `json_object`' required: - type properties: type: type: string enum: - json_object - type: object description: 'The type of response format being defined: `json_schema`' required: - json_schema - type properties: json_schema: $ref: '#/components/schemas/ResponseFormatJsonSchema' type: type: string enum: - json_schema description: >- An object specifying the format that the model must output (text, JSON object, or JSON schema). ServiceTier: type: string description: Specifies the latency tier to use for processing the request. enum: - auto - default Stop: oneOf: - type: string - type: array items: type: string description: Up to 4 sequences where the API will stop generating further tokens. ChatCompletionStreamOptions: type: object description: >- Options for streaming response. Only set this when you set `stream: true`. required: - include_usage properties: include_usage: type: boolean description: >- If set, an additional chunk will be streamed before the `data: [DONE]` message. The `usage` field on this chunk shows the token usage statistics for the entire request, and the `choices` field will always be an empty array. All other chunks will also include a `usage` field, but with a null value. ChatCompletionTool: type: object description: >- A tool the model may call. Currently, only functions are supported as a tool. required: - type - function properties: type: $ref: '#/components/schemas/ChatCompletionToolType' function: $ref: '#/components/schemas/FunctionObject' ChatCompletionToolChoiceOption: oneOf: - type: string enum: - none - type: string enum: - auto - type: string enum: - required - type: object required: - named properties: named: $ref: '#/components/schemas/ChatCompletionNamedToolChoice' description: >- Controls which (if any) tool is called by the model. `none` means the model will not call any tool and instead generates a message. `auto` means the model can pick between generating a message or calling one or more tools. `required` means the model must call one or more tools. Specifying a particular tool via `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that tool. `none` is the default when no tools are present. `auto` is the default if tools are present.present. ChatCompletionFunctionCall: oneOf: - type: string description: The model does not call a function, and responds to the end-user. enum: - none - type: string description: The model can pick between an end-user or calling a function. enum: - auto - type: object description: Forces the model to call the specified function. required: - Function properties: Function: type: object description: Forces the model to call the specified function. required: - name properties: name: type: string description: >- Deprecated in favor of `tool_choice`. Controls which (if any) function is called by the model. ChatCompletionFunctions: type: object description: >- Deprecated: A function the model may generate JSON inputs for. Use `ChatCompletionTool` instead. required: - name - parameters properties: name: type: string description: >- The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. description: type: - string - 'null' description: >- A description of what the function does, used by the model to choose when and how to call the function. parameters: description: >- The parameters the functions accepts, described as a JSON Schema object. See the [guide](https://platform.openai.com/docs/guides/text-generation/function-calling) for examples, and the [JSON Schema reference](https://json-schema.org/understanding-json-schema/) for documentation about the format. Omitting `parameters` defines a function with an empty parameter list. deprecated: true ChatChoice: type: object description: A chat completion choice generated by the model. required: - index - message properties: index: type: integer format: u-int32 description: The index of the choice in the list of choices. minimum: 0 message: $ref: '#/components/schemas/ChatCompletionResponseMessage' finish_reason: oneOf: - type: 'null' - $ref: '#/components/schemas/FinishReason' description: >- The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, `length` if the maximum number of tokens specified in the request was reached, `content_filter` if content was omitted due to a flag from our content filters, `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function. logprobs: oneOf: - type: 'null' - $ref: '#/components/schemas/ChatChoiceLogprobs' description: Log probability information for the choice. ServiceTierResponse: type: string description: >- The service tier used for processing the request, as returned in the response. enum: - scale - default - auto CompletionUsage: type: object description: Usage statistics for the completion request. required: - prompt_tokens - completion_tokens - total_tokens properties: prompt_tokens: type: integer format: u-int32 description: Number of tokens in the prompt. minimum: 0 completion_tokens: type: integer format: u-int32 description: Number of tokens in the generated completion. minimum: 0 total_tokens: type: integer format: u-int32 description: Total number of tokens used in the request (prompt + completion). minimum: 0 prompt_tokens_details: oneOf: - type: 'null' - $ref: '#/components/schemas/PromptTokensDetails' description: Breakdown of tokens used in the prompt. completion_tokens_details: oneOf: - type: 'null' - $ref: '#/components/schemas/CompletionTokensDetails' description: Breakdown of tokens used in a completion. 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_stats_show_internal_database_sizes - invalid_stats_size_format - 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 - unknown_remote - 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_render_template - invalid_render_input - render_document_not_found - template_parsing_error - template_rendering_error - 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 ChatCompletionRequestDeveloperMessage: type: object description: A developer message in the conversation. required: - content properties: content: $ref: '#/components/schemas/ChatCompletionRequestDeveloperMessageContent' description: The contents of the developer message. name: type: - string - 'null' description: >- An optional name for the participant. Provides the model information to differentiate between participants of the same role. ChatCompletionRequestSystemMessage: type: object description: A system message setting the behavior of the assistant. required: - content properties: content: $ref: '#/components/schemas/ChatCompletionRequestSystemMessageContent' description: The contents of the system message. name: type: - string - 'null' description: >- An optional name for the participant. Provides the model information to differentiate between participants of the same role. ChatCompletionRequestUserMessage: type: object description: A user message in the conversation. required: - content properties: content: $ref: '#/components/schemas/ChatCompletionRequestUserMessageContent' description: The contents of the user message. name: type: - string - 'null' description: >- An optional name for the participant. Provides the model information to differentiate between participants of the same role. ChatCompletionRequestAssistantMessage: type: object description: An assistant message in the conversation, possibly including tool calls. properties: content: oneOf: - type: 'null' - $ref: >- #/components/schemas/ChatCompletionRequestAssistantMessageContent description: >- The contents of the assistant message. Required unless `tool_calls` or `function_call` is specified. refusal: type: - string - 'null' description: The refusal message by the assistant. name: type: - string - 'null' description: >- An optional name for the participant. Provides the model information to differentiate between participants of the same role. audio: oneOf: - type: 'null' - $ref: '#/components/schemas/ChatCompletionRequestAssistantMessageAudio' description: |- Data about a previous audio response from the model. [Learn more](https://platform.openai.com/docs/guides/audio). tool_calls: type: - array - 'null' items: $ref: '#/components/schemas/ChatCompletionMessageToolCall' function_call: oneOf: - type: 'null' - $ref: '#/components/schemas/FunctionCall' description: >- Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model. ChatCompletionRequestToolMessage: type: object description: Tool message required: - content - tool_call_id properties: content: $ref: '#/components/schemas/ChatCompletionRequestToolMessageContent' description: The contents of the tool message. tool_call_id: type: string ChatCompletionRequestFunctionMessage: type: object description: 'Deprecated: A function response message. Use tool messages instead.' required: - name properties: content: type: - string - 'null' description: The return value from the function call, to return to the model. name: type: string description: The name of the function to call. PredictionContentContent: oneOf: - type: string description: >- The content used for a Predicted Output. This is often the text of a file you are regenerating with minor changes. - type: array items: $ref: '#/components/schemas/ChatCompletionRequestMessageContentPartText' description: >- An array of content parts with a defined type. Supported options differ based on the [model](https://platform.openai.com/docs/models) being used to generate the response. Can contain text inputs. description: >- The content that should be matched when generating a model response. If generated tokens would match this content, the entire model response can be returned much more quickly. ChatCompletionAudioVoice: type: string description: The voice the model uses to respond in audio output. enum: - alloy - ash - ballad - coral - echo - sage - shimmer - verse ChatCompletionAudioFormat: type: string description: >- Specifies the output audio format. Must be one of `wav`, `mp3`, `flac`, `opus`, or `pcm16`. enum: - wav - mp3 - flac - opus - pcm16 ResponseFormatJsonSchema: type: object description: >- A JSON Schema-based response format specification for Structured Outputs. required: - name properties: description: type: - string - 'null' description: >- A description of what the response format is for, used by the model to determine how to respond in the format. name: type: string description: >- The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. schema: description: >- The schema for the response format, described as a JSON Schema object. strict: type: - boolean - 'null' description: >- Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the `schema` field. Only a subset of JSON Schema is supported when `strict` is `true`. To learn more, read the [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs). ChatCompletionToolType: type: string description: The type of a tool. Currently, only `function` is supported. enum: - function FunctionObject: type: object description: A function definition for tool use, described as a JSON Schema object. required: - name properties: name: type: string description: >- The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. description: type: - string - 'null' description: >- A description of what the function does, used by the model to choose when and how to call the function. parameters: description: >- The parameters the functions accepts, described as a JSON Schema object. See the [guide](https://platform.openai.com/docs/guides/text-generation/function-calling) for examples, and the [JSON Schema reference](https://json-schema.org/understanding-json-schema/) for documentation about the format. Omitting `parameters` defines a function with an empty parameter list. strict: type: - boolean - 'null' description: >- Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the `parameters` field. Only a subset of JSON Schema is supported when `strict` is `true`. Learn more about Structured Outputs in the [function calling guide](https://platform.openai.com/docs/guides/function-calling). ChatCompletionNamedToolChoice: type: object description: >- Specifies a tool the model should use. Use to force the model to call a specific function. required: - type - function properties: type: $ref: '#/components/schemas/ChatCompletionToolType' description: The type of the tool. Currently, only `function` is supported. function: $ref: '#/components/schemas/FunctionName' ChatCompletionResponseMessage: type: object description: A chat completion message generated by the model. required: - role properties: content: type: - string - 'null' description: The contents of the message. refusal: type: - string - 'null' description: The refusal message generated by the model. tool_calls: type: - array - 'null' items: $ref: '#/components/schemas/ChatCompletionMessageToolCall' description: The tool calls generated by the model, such as function calls. role: $ref: '#/components/schemas/Role' description: The role of the author of this message. function_call: oneOf: - type: 'null' - $ref: '#/components/schemas/FunctionCall' description: >- Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model. audio: oneOf: - type: 'null' - $ref: '#/components/schemas/ChatCompletionResponseMessageAudio' description: >- If the audio output modality is requested, this object contains data about the audio response from the model. [Learn more](https://platform.openai.com/docs/guides/audio). FinishReason: type: string description: The reason the model stopped generating tokens. enum: - stop - length - tool_calls - content_filter - function_call ChatChoiceLogprobs: type: object description: Log probability information for a chat completion choice. properties: content: type: - array - 'null' items: $ref: '#/components/schemas/ChatCompletionTokenLogprob' description: A list of message content tokens with log probability information. refusal: type: - array - 'null' items: $ref: '#/components/schemas/ChatCompletionTokenLogprob' PromptTokensDetails: type: object description: Breakdown of tokens used in a completion. properties: audio_tokens: type: - integer - 'null' format: u-int32 description: Audio input tokens present in the prompt. minimum: 0 cached_tokens: type: - integer - 'null' format: u-int32 description: Cached tokens present in the prompt. minimum: 0 CompletionTokensDetails: type: object description: Breakdown of tokens used in a completion. properties: accepted_prediction_tokens: type: - integer - 'null' format: u-int32 minimum: 0 audio_tokens: type: - integer - 'null' format: u-int32 description: Audio input tokens generated by the model. minimum: 0 reasoning_tokens: type: - integer - 'null' format: u-int32 description: Tokens generated by the model for reasoning. minimum: 0 rejected_prediction_tokens: type: - integer - 'null' format: u-int32 description: |2- When using Predicted Outputs, the number of tokens in the prediction that did not appear in the completion. However, like reasoning tokens, these tokens are still counted in the total completion tokens for purposes of billing, output, and context window limits. minimum: 0 ChatCompletionRequestDeveloperMessageContent: oneOf: - type: string - type: array items: $ref: '#/components/schemas/ChatCompletionRequestMessageContentPartText' description: >- The contents of a developer message: either a text string or an array of text content parts. ChatCompletionRequestSystemMessageContent: oneOf: - type: string description: The text contents of the system message. - type: array items: $ref: '#/components/schemas/ChatCompletionRequestSystemMessageContentPart' description: >- An array of content parts with a defined type. For system messages, only type `text` is supported. description: >- The contents of a system message: either a text string or an array of text content parts. ChatCompletionRequestUserMessageContent: oneOf: - type: string description: The text contents of the message. - type: array items: $ref: '#/components/schemas/ChatCompletionRequestUserMessageContentPart' description: >- An array of content parts with a defined type. Supported options differ based on the [model](https://platform.openai.com/docs/models) being used to generate the response. Can contain text, image, or audio inputs. description: >- The contents of a user message: either a text string or an array of content parts (text, image, or audio). ChatCompletionRequestAssistantMessageContent: oneOf: - type: string description: The text contents of the message. - type: array items: $ref: >- #/components/schemas/ChatCompletionRequestAssistantMessageContentPart description: >- An array of content parts with a defined type. Can be one or more of type `text`, or exactly one of type `refusal`. description: >- The contents of an assistant message: either a text string or an array of content parts (text or refusal). ChatCompletionRequestAssistantMessageAudio: type: object description: >- Data about a previous audio response from the model, used in multi-turn conversations. required: - id properties: id: type: string description: Unique identifier for a previous audio response from the model. ChatCompletionMessageToolCall: type: object description: A tool call generated by the model. required: - id - function properties: id: type: string description: The ID of the tool call. type: oneOf: - type: 'null' - $ref: '#/components/schemas/ChatCompletionToolType' description: The type of the tool. Currently, only `function` is supported. function: $ref: '#/components/schemas/FunctionCall' description: The function that the model called. FunctionCall: type: object description: >- The name and arguments of a function that should be called, as generated by the model. required: - name - arguments properties: name: type: string description: The name of the function to call. arguments: type: string description: >- The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. ChatCompletionRequestToolMessageContent: oneOf: - type: string description: The text contents of the tool message. - type: array items: $ref: '#/components/schemas/ChatCompletionRequestToolMessageContentPart' description: >- An array of content parts with a defined type. For tool messages, only type `text` is supported. description: >- The contents of a tool message: either a text string or an array of text content parts. ChatCompletionRequestMessageContentPartText: type: object description: A text content part of a message. required: - text properties: text: type: string FunctionName: type: object description: A wrapper for a function name reference. required: - name properties: name: type: string description: The name of the function to call. Role: type: string description: The role of the author of a message. enum: - system - user - assistant - tool - function ChatCompletionResponseMessageAudio: type: object description: Audio data in a chat completion response message. required: - id - expires_at - data - transcript properties: id: type: string description: Unique identifier for this audio response. expires_at: type: integer format: u-int32 description: >- The Unix timestamp (in seconds) for when this audio response will no longer be accessible on the server for use in multi-turn conversations. minimum: 0 data: type: string description: >- Base64 encoded audio bytes generated by the model, in the format specified in the request. transcript: type: string description: Transcript of the audio generated by the model. ChatCompletionTokenLogprob: type: object description: Log probability information for an output token. required: - token - logprob - top_logprobs properties: token: type: string description: The token. logprob: type: number format: float description: >- The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value `-9999.0` is used to signify that the token is very unlikely. bytes: type: - array - 'null' items: type: integer format: u-int8 minimum: 0 description: >- A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be `null` if there is no bytes representation for the token. top_logprobs: type: array items: $ref: '#/components/schemas/TopLogprobs' description: >- List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested `top_logprobs` returned. ChatCompletionRequestSystemMessageContentPart: oneOf: - allOf: - $ref: '#/components/schemas/ChatCompletionRequestMessageContentPartText' - type: object required: - type properties: type: type: string enum: - text description: A content part in a system message (text only). ChatCompletionRequestUserMessageContentPart: oneOf: - allOf: - $ref: '#/components/schemas/ChatCompletionRequestMessageContentPartText' - type: object required: - type properties: type: type: string enum: - text - allOf: - $ref: >- #/components/schemas/ChatCompletionRequestMessageContentPartImage - type: object required: - type properties: type: type: string enum: - image_url - allOf: - $ref: >- #/components/schemas/ChatCompletionRequestMessageContentPartAudio - type: object required: - type properties: type: type: string enum: - input_audio description: A content part in a user message (text, image, or audio). ChatCompletionRequestAssistantMessageContentPart: oneOf: - allOf: - $ref: '#/components/schemas/ChatCompletionRequestMessageContentPartText' - type: object required: - type properties: type: type: string enum: - text - allOf: - $ref: >- #/components/schemas/ChatCompletionRequestMessageContentPartRefusal - type: object required: - type properties: type: type: string enum: - refusal description: A content part in an assistant message (text or refusal). ChatCompletionRequestToolMessageContentPart: oneOf: - allOf: - $ref: '#/components/schemas/ChatCompletionRequestMessageContentPartText' - type: object required: - type properties: type: type: string enum: - text description: A content part in a tool message (text only). TopLogprobs: type: object description: A most likely token and its log probability at a given position. required: - token - logprob properties: token: type: string description: The token. logprob: type: number format: float description: The log probability of this token. bytes: type: - array - 'null' items: type: integer format: u-int8 minimum: 0 description: >- A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be `null` if there is no bytes representation for the token. ChatCompletionRequestMessageContentPartImage: type: object description: An image content part of a message. required: - image_url properties: image_url: $ref: '#/components/schemas/ImageUrl' ChatCompletionRequestMessageContentPartAudio: type: object description: >- Learn about [audio inputs](https://platform.openai.com/docs/guides/audio). required: - input_audio properties: input_audio: $ref: '#/components/schemas/InputAudio' ChatCompletionRequestMessageContentPartRefusal: type: object description: A refusal content part of a message. required: - refusal properties: refusal: type: string description: The refusal message generated by the model. ImageUrl: type: object description: An image URL with optional detail level. required: - url properties: url: type: string description: Either a URL of the image or the base64 encoded image data. detail: oneOf: - type: 'null' - $ref: '#/components/schemas/ImageDetail' description: >- Specifies the detail level of the image. Learn more in the [Vision guide](https://platform.openai.com/docs/guides/vision/low-or-high-fidelity-image-understanding). InputAudio: type: object description: Input audio data for an audio content part. required: - data - format properties: data: type: string description: Base64 encoded audio data. format: $ref: '#/components/schemas/InputAudioFormat' description: >- The format of the encoded audio data. Currently supports "wav" and "mp3". ImageDetail: type: string description: Specifies the detail level of the image. enum: - auto - low - high InputAudioFormat: type: string description: The format of the encoded audio data. enum: - wav - mp3 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' }); ``` ````