app.py

import os
import gradio as gr
from dotenv import load_dotenv
import openai

# from utils import serialize
from utils import compress

from description import DESCRIPTION

load_dotenv()

# configuring openai package
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
openai.api_key = OPENAI_API_KEY


def load_prompt(path):
    with open(path) as f:
        lines = f.readlines()
        return "".join(lines)


def chat(passage, max_tokens=256, temprature=0, debug=False):

    if debug:
        passage = """
        A car or automobile is a motor vehicle with wheels. Most definitions of cars say that they run primarily on roads, seat one to eight people, have four wheels, and mainly transport people (rather than goods).
        """

    prompt = load_prompt("summary_prompt.txt").replace("<<SUMMARY>>", passage)

    summary = openai.ChatCompletion.create(
        model="gpt-3.5-turbo",
        messages=[{"role": "user", "content": prompt}],
    )

    return summary["choices"][0]["message"]["content"].strip()


# def chat(message, history):
#     """
#     Sends a request to the OpenAi api based on the user input and the history
#     """
#     messages = serialize(history)
#     messages.append({"role": "user", "content": message})

#     completion = openai.ChatCompletion.create(
#         model="gpt-3.5-turbo",
#         messages=messages,
#     )

#     return completion["choices"][0]["message"]["content"].strip()


def transcribe(audio_file):
    audio_file = open(audio_file, "rb")
    transcription = openai.Audio.transcribe("whisper-1", audio_file, language="en")
    transcription = transcription["text"]
    return transcription


def predict(input, history=[]):
    compress(input)
    transcription = transcribe(input)

    answer = chat(transcription)
    history.append((transcription, answer))
    response = history
    return response, history


with gr.Blocks() as demo:
    gr.Markdown(DESCRIPTION)
    chatbot = gr.Chatbot()
    state = gr.State([])

    with gr.Row():
        audio_file = gr.Audio(label="Audio", source="microphone", type="filepath")

    audio_file.change(predict, [audio_file, state], [chatbot, state])

demo.launch()