Request a chat completion

POST /chats/{workspace_uid}/chat/completions

cURL

cURL

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"
        }
      }
    ]
  }'

200

{
  "id": "chatcmpl-abc123",
  "choices": [
    {
      "index": 0,
      "message": {
        "content": "After searching the Steam database, here are some game recommendations related to your query:\n\n1. **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.\n\n2. **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.\n\n3. **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.\n\nThese 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
    }
  }
}

Authorizations

Authorization · string · header · required

An API key is a token that you provide when making API calls. Read more about how to secure your project.

Include the API key to the Authorization header, for instance:

-H 'Authorization: Bearer 6436fc5237b0d6e0d64253fbaac21d135012ecf1'

If you use a SDK, ensure you instantiate the client with the API key, for instance with JS SDK:

const client = new MeiliSearch({
  host: 'MEILISEARCH_URL',
  apiKey: '6436fc5237b0d6e0d64253fbaac21d135012ecf1'
});

Path Parameters

workspace_uid · string · required

The unique identifier of the chat workspace.

Body

application/json

A chat completion request compatible with the OpenAI API.

messages · object[] · required

A list of messages comprising the conversation so far. Depending on the model you use, different message types (modalities) are supported, like text, images, and audio.

A message in the chat completion conversation. Tagged by role (system, user, assistant, tool, developer, or function).

Option 1

Option 2

Option 3

Option 4

Option 5

Option 6

Show child attributes

model · string · required

ID of the model to use. See the model endpoint compatibility table for details on which models work with the Chat API.

store · boolean | null

Whether or not to store the output of this chat completion request

for use in our model distillation or evals products.

reasoning_effort · null | enum<string>

o1 models only

Constrains effort on reasoning for reasoning models.

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.

Available options: low, medium, high

metadata · any

Developer-defined tags and values used for filtering completions in the dashboard.

frequency_penalty · number<float> | null

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 · object

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.

Show child attributes

logprobs · boolean | null

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 · integer<u-int8> | null

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.

Required range: x >= 0

max_tokens · integer<u-int32> | null · deprecated

The maximum number of tokens that can be generated in the chat completion.

This value can be used to control costs for text generated via API. This value is now deprecated in favor of max_completion_tokens, and is not compatible with o1 series models.

Required range: x >= 0

max_completion_tokens · integer<u-int32> | null

An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.

Required range: x >= 0

n · integer<u-int8> | null

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.

Required range: x >= 0

modalities · enum<string>[] | null

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"].

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. To request that this model generate both text and audio responses, you can use: ["text", "audio"]

Available options: text, audio

prediction · object

Configuration for a Predicted Output,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.

Show child attributes

audio · object

Parameters for audio output. Required when audio output is requested with modalities: ["audio"]. Learn more.

Show child attributes

presence_penalty · number<float> | null

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 · object

An object specifying the format that the model must output. Compatible with GPT-4o, GPT-4o mini, 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.

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.

Option 1

Option 2

Option 3

Show child attributes

seed · integer<int64> | null

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 · null | enum<string>

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.

Available options: auto, default

stop · string string[]

Up to 4 sequences where the API will stop generating further tokens.

stream · boolean | null

If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. Example Python code.

stream_options · object

Options for streaming response. Only set this when you set stream: true.

Show child attributes

temperature · number<float> | null

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 · number<float> | null

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 · object[] | null

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.

Show child attributes

tool_choice · Option 1 · enum<string> Option 2 · enum<string> Option 3 · enum<string> Option 4 · object

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.

Available options: none

parallel_tool_calls · boolean | null

Whether to enable parallel function calling during tool use.

user · string | null

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.

function_call · Option 1 · enum<string> Option 2 · enum<string> Option 3 · object

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.

Available options: none

functions · object[] | null · deprecated

Deprecated in favor of tools.

A list of functions the model may generate JSON inputs for.

Show child attributes

Response

200

application/json

Start a conversation.

Represents a chat completion response returned by model, based on the provided input.

id · string · required

A unique identifier for the chat completion.

choices · object[] · required

A list of chat completion choices. Can be more than one if n is greater than 1.

Show child attributes

created · integer<u-int32> · required

The Unix timestamp (in seconds) of when the chat completion was created.

Required range: x >= 0

model · string · required

The model used for the chat completion.

object · string · required

The object type, which is always chat.completion.

service_tier · null | enum<string>

The service tier used for processing the request. This field is only included if the service_tier parameter is specified in the request.

Available options: scale, default, auto

system_fingerprint · string | null

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.

usage · object

Usage statistics for the completion request.

Show child attributes