Crate openai_flows

OpenAI integration for Flows.network

Quick Start

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

use openai_flows::{chat_completion, ChatModel, ChatOptions, FlowsAccount};
use lambda_flows::{request_received, send_response};
use serde_json::Value;
use std::collections::HashMap;

#[no_mangle]
#[tokio::main(flavor = "current_thread")]
pub async fn run() {
    request_received(handler).await;
}

async fn handler(_qry: HashMap<String, Value>, body: Vec<u8>) {
    let co = ChatOptions {
        model: ChatModel::GPT35Turbo,
        restart: false,
        system_prompt: None,
        retry_times: 2,
    };
    let r = match chat_completion(
        FlowsAccount::Default,
        "any_conversation_id",
        String::from_utf8_lossy(&body).into_owned().as_str(),
        &co,
    )
    .await
    {
        Ok(c) => c.choice,
        Err(e) => e,
    };
     
    send_response(
        200,
        vec![(
            String::from("content-type"),
            String::from("text/plain; charset=UTF-8"),
        )],
        r.as_bytes().to_vec(),
    );
}

When the Lambda request is received, chat using chat_completion then send the response.

Structs

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

Enums

• ChatModel
  Models for Chat
• EmbeddingsInput
  The input type for the embeddings.
• FlowsAccount
  The account name you provide to Flows.network platform, which is tied to your OpenAI API key.
• 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.
• create_completion
  Create completion for the provided prompt and parameters.
• create_embeddings
  Create embeddings from the provided input.
• create_image
  Create image for the provided prompt and parameters.