100 дней искусственного интеллекта. День 5: Транскрипция и извлечение информации из подкастов с помощью OpenAI

import os
import sys
import openai

from dotenv import load_dotenv, find_dotenv
_ = load_dotenv(find_dotenv()) # read local .env file
openai.api_key  = os.environ['OPENAI_API_KEY']


## youtube video's audio loader - langchain 
from langchain_community.document_loaders.blob_loaders.youtube_audio import YoutubeAudioLoader
from langchain_community.document_loaders.generic import GenericLoader
from langchain_community.document_loaders.parsers import OpenAIWhisperParser #, OpenAIWhisperParserLocal

url="https://www.youtube.com/watch?v=DcWqzZ3I2cY&ab_channel=LexFridman"
save_dir="outputs/youtube/"
loader = GenericLoader(
     YoutubeAudioLoader([url],save_dir),
     OpenAIWhisperParser()
 )
docs = loader.load()
print(docs[0].page_content[0:500])

# Specify the file path where you want to save the text
file_path = "audio-transcript.txt"
try:
    with open(file_path, 'a', encoding='utf-8') as file:
        for doc in docs:
            file.write(doc.page_content)
    print(f'Large text saved to {file_path}')
except FileNotFoundError:
    print(f"Error: Input file '{file_path}' not found.")
except Exception as e:
    print(f"An error occurred: {e}")

import os
import sys
import openai
import shutil
from pprint import pprint

from dotenv import load_dotenv, find_dotenv
_ = load_dotenv(find_dotenv()) # read local .env file
openai.api_key  = os.environ['OPENAI_API_KEY']

client = openai.OpenAI()

file_path = "audio-transcript-copy.txt"
try:
    with open(file_path, 'r', encoding='utf-8') as file:
        long_text = file.read()
    print(f'{file_path} is rad')
except FileNotFoundError:
    print(f"Error: Input file '{file_path}' not found.")
except Exception as e:
    print(f"An error occurred: {e}")

prompt2 = f"""
You will be provided with text deilimited by triple quotes.
The given text is a podcast transcript.

Provide the host and guest name.
Summarize the transcript in to 10 points.

If there are any people referred in the transcript. Extract the people mentioned and list them along with some info about them in the following format
1. Person 1's Name: Person 1's profession or what he or she is known for or the context in which he or she was referred to.
2. Person 2's Name: Person 2's profession or what he or she is known for or the context in which he or she was referred to.
...
2. Person N's Name: Person N's profession or what he or she is known for or the context in which he or she was referred to.
If the transcript doesnt contain refereces to any people then simply write "No people referred to in the conversation."

Extract the books mentioned and list them in the following format.
1. Book 1's Title: Context in which the book was referred to.
2. Book 2's Title: Context in which the book was referred to.
...
N. Book N's Title: Context in which the book was referred to.
If the transcript doesnt contain refereces to any books then simply write "No books referred to in the conversation."

IF you find any inspiration quotoes complie them in to a list.

"""{long_text}"""
"""

response = client.chat.completions.create(
  model="gpt-4",
  messages=[
    {
      "role": "user",
      "content": prompt2
    }
  ],
  temperature=0.7,
  #max_tokens=64,
  #top_p=1
)

print(response.choices[0].message.content)