Completions Recommendations Chat

POST

Returns a response for the chat conversation.

Request

This endpoint expects an object.
messageslist of objectsRequired

A list of messages comprising the conversation so far.

max_tokensintegerOptional

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

stop_sequenceslist of stringsOptional

Sequences where the API will stop generating further tokens. Maximum of 4 sequences are supported. Defaults to none.

streambooleanOptional

If set, partial message deltas will be sent. Defaults to false.

temperaturedoubleOptional

What sampling temperature to use. Value can be between 0 and 2 and defaults to 1.0. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

top_pdoubleOptional

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. For openai: Between 0 and

  1. Defaults to 1.0.

Response

The response for the generated chat completion.

text_responsestringOptional

Text response generated for the chat.

Built with