MindsDB API Reference

POST/chat/completions

Create a chat

This endpoint creates a model response for the given chat conversation.

Request body

Name
messages
Type
array
Required
Description
A list of messages comprising the conversation so far. Example Python code.
Name
model
Type
string
Required
Description
ID of the model to use. See the model endpoint compatibility table for details on which models work with the Chat API.
Name
stream
Type
number
Description
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.
Name
frequency_penalty
Type
boolean
Description
This setting ranges from -2.0 to 2.0. Positive values make the model less likely to repeat phrases it has already used.
Name
max_tokens
Type
integer
Description
This parameter sets the maximum number of tokens that can be generated in the chat completion. It's limited by the model's total allowable context length, which includes both the input and generated tokens. Here's an example of Python code to count tokens.
Name
temperature
Type
number
Description
This parameter controls the randomness of the output with values ranging from 0 to 2. A higher value, increases randomness in the output, while a lower value, like 0.1, results in more focused and deterministic output.
Name
tools
Type
array
Description
This setting allows you to specify a list of tools that the model can call, currently limited to functions.

Request

POST

/chat/completions

curl https://llm.mdb.ai/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $MINDSDB_API_KEY" \
-d '{
  "model": "gpt-3.5-turbo",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "stream": false
}'

Response

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1702685778,
  "model": "gpt-3.5-turbo-0125",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I assist you today?"
      }
    }
  ]
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 9,
    "total_tokens": 18
  },
  "system_fingerprint": null
}