import llama3pure from "./llama3pure-js-engine.js"
import fs from "fs"

const readFileAsArrayBuffer = (filePath) => {
  const fd = fs.openSync(filePath, "r")
  const fileSize = fs.fstatSync(fd).size
  const arrayBuffer = new ArrayBuffer(fileSize)
  const fileUint8 = new Uint8Array(arrayBuffer)
  const chunkSize = 256 * 1024 * 1024
  let pos = 0
  while (pos < fileSize) {
    const toRead = Math.min(chunkSize, fileSize - pos)
    fs.readSync(fd, fileUint8, pos, toRead, pos)
    pos = pos + toRead
  }
  fs.closeSync(fd)
  return arrayBuffer
}

llama3pure({
  type: "load",
  model: readFileAsArrayBuffer("/path/to/your-model.gguf"),
  cbRender: (token) => {
    process.stdout.write(token)
  },
  systemPrompt: "You are a helpful assistant.",
  maxTokens: 256,
  contextSize: 2048,
  temperature: 0.9,
  topP: 0.9,
  topK: 40,
})

llama3pure({
  type: "generate",
  chatHistory: [
    { role: "user", content: "Tell me in 1 line what is Microsoft." },
    {
      role: "assistant",
      content:
        "Microsoft is a global technology leader known for its innovative products and services.",
    },
    { role: "user", content: "Tell me in 1 line the names of the founders." },
  ],
})

const reader = new FileReader()

reader.onload = (event) => {
  const arrayBuffer = event.target.result
  worker.postMessage(
    {
      type: "load",
      model: arrayBuffer,
      systemPrompt: "You are a helpful assistant.",
      maxTokens: 256,
      contextSize: 2048,
      temperature: 0.9,
      topP: 0.9,
      topK: 40,
    },
    [arrayBuffer]
  )
}

reader.readAsArrayBuffer(file)

worker.postMessage({
  type: "generate",
  chatHistory: [
    { role: "user", content: "Tell me in 1 line what is Microsoft." },
    {
      role: "assistant",
      content:
        "Microsoft is a global technology leader known for its innovative products and services.",
    },
    { role: "user", content: "Tell me in 1 line the names of the founders." },
  ],
})

worker.onmessage = function (e) {
  var data = e.data
  switch (data.type) {
    case "progress":
      // Fired during model loading
      break

    case "loaded":
      // Fired once the model is fully loaded and ready
      break

    case "token":
      // Fired for each generated token during inference
      console.log(data.token)
      break

    case "complete":
      // Fired when generation is finished
      console.log(data.output)
      break
  }
}