openai_converter.py

import os
import requests
import openai
from pathlib import Path
import xml.etree.ElementTree as ET

# Set your OpenAI and DocsGPT API keys
OPENAI_API_KEY = 'YOUR_OPENAI_API_KEY'
DOCSGPT_API_URL = 'https://gptcloud.arc53.com/api/answer' #Will differ for local deployment
DOCSGPT_API_KEY = 'YOUR_DOCSGPT_API_KEY'

# Input path to the summary plan .txt
input_path = 'sum.txt'

# Capture the name of the file (without extension) to create folders
file_name = Path(input_path).stem
text_folder = Path(f'{file_name}_text')
audio_folder = Path(f'{file_name}_audio')

# Create the folders
text_folder.mkdir(parents=True, exist_ok=True)
audio_folder.mkdir(parents=True, exist_ok=True)

# Read the content of the input file
with open(input_path, 'r', encoding='utf-8') as file:
    plan_content = file.read()

# Parse the XML content
root = ET.fromstring(plan_content)

# Initialize the OpenAI client
openai.api_key = OPENAI_API_KEY

# Function to request DocsGPT API
def request_docsgpt(question):
    headers = {'Content-Type': 'application/json; charset=utf-8'}
    data = {
        "question": question,
        "api_key": DOCSGPT_API_KEY,
    }
    response = requests.post(DOCSGPT_API_URL, json=data, headers=headers)
    response_json = response.json()
    return response_json['answer']

# Process each part in the plan
for part in root.findall('part'):
    number = part.get('number')
    title = part.find('title').text
    content = part.find('content').text.strip()
    
    # Create the question for DocsGPT API
    question = f"{title} {content}"
    
    # Request DocsGPT API
    answer = request_docsgpt(question)
    
    # Write the answer to a text file
    text_file_path = text_folder / f'{number}.{title.replace(" ", "_")}.txt'
    with open(text_file_path, 'w', encoding='utf-8') as text_file:
        text_file.write(answer)
    
    print(f"Generated text: {text_file_path}")

    audio_file_path = audio_folder / f'{number}.{title.replace(" ", "_")}.mp3'
    
    # Initialize the OpenAI client
    client = openai.Client(api_key=OPENAI_API_KEY)
    
    # Request text-to-speech conversion
    response = client.audio.speech.create(
        model="tts-1",
        voice="alloy",
        input=answer
    )
    
    # Stream the response to the output file
    response.stream_to_file(audio_file_path)

    print(f"Generated audio: {audio_file_path}")

print("Processing completed.")