Chat Completion

Chat Completion is for generating predicted completions.

Path Parameters
chat_completion_api_id integer — REQUIRED The API ID.

Header Parameters
Authorization string — REQUIRED Bearer Auth Example: Bearer #your_token

Request Body
params object The passed-in fields will partially override the API config. model string Possible values: [gpt-3.5-turbo, vicuna-7B] Name of the model to use. system_prompt string The system prompt. max_tokens integer Possible values: 1 ≤ value The maximum number of tokens to generate in the chat completion.The total length of input tokens and generated tokens is limited by the model's context length. temperature number Possible values: value ≤ 2 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 Possible values: value ≤ 1 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 but not both.
inputs object — REQUIRED Parameters for invoking the API. session_id string Possible values: length ≤ 32 Unique identifier used to maintain user session state. If not provided, a new session_id will be generated and returned in the response. prompt string — REQUIRED The latest user prompt. variables object Format the system prompt with these variables. var1_name string var2_name string ... string

Responses
200 OK Schema — OPTIONAL code integer Error code. 0 when success. msg string Error message. Please use "code" instead of "msg" to determine errors. data object — OPTIONAL Business data. session_id string Unique identifier used to maintain user session state. text string AI generated content.
400 Invalid input
401 Unauthorized
404 Record not found