// IMPORT LIBRARIES TOOLS
import { pipeline, env } from 'https://cdn.jsdelivr.net/npm/@xenova/transformers@2.10.1';

// skip local model check
env.allowLocalModels = false;

// GLOBAL VARIABLES
let PREPROMPT = `Please complete the phrase and fill in any [MASK]: `
let PROMPT_INPUT = `The woman has a job as a...` // a field for writing or changing a text value
let pField
let outText

// RUN TEXT-GEN MODEL

async function textGenTask(pre, prompt){
  console.log('text-gen task initiated')

  // preprompt not working, fix later if we do chat templates
  // let INPUT = pre + prompt
  let INPUT = prompt

  // PICK MODEL 
  let MODEL = 'Xenova/OpenELM-270M-Instruct'

  // MODELS LIST
  // - Xenova/bloom-560m
  // - Xenova/distilgpt2
  // - Xenova/LaMini-Cerebras-256M
  // - Xenova/gpt-neo-125M
  // - Xenova/OpenELM-270M-Instruct
  // - Xenova/llama2.c-stories15M
  // - webml/TinyLlama-1.1B-Chat-v1.0
  // - Xenova/TinyLlama-1.1B-Chat-v1.0
  // - Xenova/stablelm-2-zephyr-1_6b
  // - Felladrin/onnx-Llama-160M-Chat-v1

  
  const pipe = await pipeline('text-generation', MODEL)

  // RUN INPUT THROUGH MODEL, 
  var out = await pipe(INPUT, { max_new_tokens: 60, top_k: 90, repetition_penalty: 1.5 })
  // setting hyperparameters
  // max_new_tokens: 256, top_k: 50, temperature: 0.7, do_sample: true, no_repeat_ngram_size: 2,

  console.log(await out)
  console.log('text-gen task completed')

  // PARSE RESULTS as a list of outputs, two different ways depending on the model
  
  let OUTPUT_LIST = [] // a blank array to store the results from the model
  
  // parsing of output
  await out.forEach(o => {
    console.log(o)
    OUTPUT_LIST.push(o.generated_text)
  })

  // alternate format for parsing, for chat model type
  // await out.choices.forEach(o => {
  //   console.log(o)
  //   OUTPUT_LIST.push(o.message.content)
  // })

  console.log(OUTPUT_LIST)
  console.log('text-gen parsing complete')

  return await OUTPUT_LIST
  // return await out
}

// RUN FILL-IN MODEL
async function fillInTask(input){
  console.log('fill-in task initiated')

  // MODELS LIST
  // - Xenova/bert-base-uncased

  const pipe = await pipeline('fill-mask', 'Xenova/bert-base-uncased');
  
  var out = await pipe(input);

  console.log(await out) // yields { score, sequence, token, token_str } for each result

  let OUTPUT_LIST = [] // a blank array to store the results from the model

  // parsing of output
  await out.forEach(o => {
    console.log(o) // yields { score, sequence, token, token_str } for each result
    OUTPUT_LIST.push(o.sequence) // put only the full sequence in a list
  })
  
  console.log(await OUTPUT_LIST)
  console.log('fill-in task completed')

  // return await out
  return await OUTPUT_LIST
}

//// p5.js Instance

new p5(function (p5){
  p5.setup = function(){
      p5.noCanvas()
      console.log('p5 instance loaded')
      makeTextDisplay()
      makeFields()
      makeButtons()
    }

  p5.draw = function(){
      // 
  }

  function makeTextDisplay(){
    let title = p5.createElement('h1','p5.js Critical AI Prompt Battle')
    let intro = p5.createP(`This tool lets you explore several AI prompts results at once.`) 
    p5.createP(`Use it to explore what models 'know' about various concepts, communities, and cultures. For more information on prompt programming and critical AI, see [Tutorial & extra info][TO-DO][XXX]`)
  }

  function makeFields(){
    pField = p5.createInput(PROMPT_INPUT) // turns the string into an input; now access the text via PROMPT_INPUT.value()
    pField.size(700)
    pField.attribute('label', `Write a text prompt with one [MASK] that the model will fill in.`)
    p5.createP(pField.attribute('label'))
    pField.addClass("prompt")
  }

  function makeButtons(){
    let submitButton = p5.createButton("SUBMIT")
    submitButton.size(170)
    submitButton.class('submit')
    submitButton.mousePressed(displayResults)
    
    // also make results placeholder
    let outHeader = p5.createElement('h3',"Results")
    outText = p5.createP('').id('results')
  }

  async function displayResults(){
    console.log('submitButton pressed')

    // insert waiting dots into results space of interface
    outText.html('...', false)

    PROMPT_INPUT = pField.value() // grab update to the prompt if it's been changed
    console.log("latest prompt: ", PROMPT_INPUT)
    
    // call the function that runs the model for the task of your choice here 
    // make sure to use the PROMPT_INPUT as a parameter, or also the PREPROMPT if valid for that task
    let outs = await textGenTask(PREPROMPT, PROMPT_INPUT)
    console.log(outs)

    // insert the model outputs into the paragraph
    await outText.html(outs, false) // false replaces text instead of appends??
  }

});