Crate openai_flows

OpenAI integration for Flows.network

Quick Start

To get started, let’s write a very tiny flow function.

use openai_flows::{CompletionRequest, create_completion};
use slack_flows::{listen_to_channel, send_message_to_channel};

#[no_mangle]
pub fn run() {
    listen_to_channel("myworkspace", "mychannel", |sm| {
        let cr = CompletionRequest {
            prompt: sm.text,
            ..Default::default()
        };
        let r = create_completion("myaccount", cr);
        r.iter().for_each(|c| {
            send_message_to_channel("myworkspace", "mychannel", c.to_string());
        });
    });
}

When the Slack message is received, create completion using create_completion then send the response to Slack.

Structs

• ChatOptions
  struct for setting the chat options.
• ChatResponse
  Response struct for the chat completion.
• CompletionRequest
  Request struct for the completion.
• ImageRequest
  Request struct for the image creation.

Enums

• ChatModel
  Models for Chat
• ImageSize

Functions

• chat_completion
  Create chat completion with the provided sentence. It use OpenAI’s GPT-3.5 model to make a conversation. It will keep the conversation history for 10 minutes for you. That means a new conversation will be created if you haven’t call this method for 10 minutes.
• chat_completion_inner
• create_completion
  Create completion for the provided prompt and parameters.
• create_completion_inner
• create_image
  Create image for the provided prompt and parameters.