Chatbot (CLI)

We can easily create a chatbot command-line interface (CLI) using neets.ai’s Text-To-Speech (TTS) and Large Language Model (LLM) APIs. This guide is compatible with Windows Terminal, but the steps can be applied to any terminal interface.

Prerequisites

  • Python installation: Ensure you have Python version 3.8 or newer installed.
  • MPV: Install MPV to handle audio playback. If you are on Windows/Linux, visit <https://mpv.io/installation>. If you are on Mac, run: brew install mpv

Setting Up

  1. Open your terminal: Launch your terminal and navigate to your desired directory where you want to setup the project.
  2. Install Python dependencies: You need to install two Python packages. Execute the following commands in your terminal:
pip install requests
pip install openai

Creating Your Chatbot

  1. Code preparation: Open your chosen code editor. Copy and paste the following code from our API documentation below:
import shutil
import subprocess
from typing import Iterator

import requests
from openai import OpenAI

def play_stream(audio_stream: Iterator[bytes]) -> bytes:
  process = subprocess.Popen(
    ["mpv", "--no-cache", "--no-terminal", "--", "fd://0"],
    stdin=subprocess.PIPE,
    stdout=subprocess.DEVNULL,
    stderr=subprocess.DEVNULL,
  )

  audio = b""

  for chunk in audio_stream:
    if chunk is not None:
      process.stdin.write(chunk)
      process.stdin.flush()
      audio += chunk

  if process.stdin:
    process.stdin.close()

  process.wait()

def say(text: str, api_key: str):
  response = requests.request(
    method="POST",
    url="https://api.neets.ai/v1/tts",
    headers={
      "Content-Type": "application/json",
      "X-API-Key": api_key
    },
    json={
      "text": text,
      "voice_id": "us-female-2",
      "params": {
        "model": "style-diff-500"
      }
    }
  )

  audio_stream = response.iter_content(chunk_size=None)
  play_stream(audio_stream)

api_key = input("Neets API Key: ")
messages = []

client = OpenAI(
  api_key=api_key,
  base_url="https://api.neets.ai/v1"
)

while True:
  user_message = input("Type a message: ")
  messages.append({
    "role": "user",
    "content": user_message
  })

  response = client.chat.completions.create(
    model="mistralai/Mixtral-8X7B-Instruct-v0.1",
    messages=messages
  )

  bot_response = response.choices[0].message.content
  messages.append({
    "role": "assistant",
    "content": bot_response
  })

  print("Bot: " + bot_response)
  say(bot_response, api_key)
  1. Save your script: Ensure that you save the file with a clear name. For example: chatbot.py

Running Your Chatbot

  1. Execute your script: In your terminal, run the script using the command python chatbot.py
  2. Enter your API Key: When prompted, enter your NEETS_API_KEY. You can find this key on your API Keys page.

Now you're all set! Follow these steps to build your own Chatbot CLI using neets.ai's easy to use APIs.