Created
February 20, 2024 23:55
-
-
Save bigsnarfdude/aa3115bf2e6c1053b2361e62d4477ce0 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import os | |
from openai import OpenAI | |
import prompt | |
def truncate_words(input_string, max_words): | |
words = input_string.split() | |
truncated_words = words[:max_words] | |
return ' '.join(truncated_words) | |
def process_file(file_path, client, prompt, max_tokens): | |
with open(file_path, 'r') as file: | |
content = file.read() | |
input_string = truncate_words(prompt + content, max_tokens) | |
try: | |
completion = client.chat.completions.create( | |
model='gpt-4-0125-preview', #gpt-3.5-turbo-0125', | |
messages=[ | |
{"role": "system", "content": "You are a helpful assistant, skilled in summarizing lectures."}, | |
{"role": "user", "content": input_string} | |
] | |
) | |
return completion.choices[0].message.content | |
except Exception as e: | |
print(f"Error with OpenAI API for file {os.path.basename(file_path)}: {e}") | |
return None | |
def save_summary(file_path, summary): | |
if summary: | |
try: | |
with open(file_path, "w") as file: | |
file.write(summary) | |
except Exception as e: | |
print(f"Error with writing summary file {file_path}: {e}") | |
return None | |
def summarize_files(directory_path, processed_directory, prompt, max_tokens, finished_files): | |
client = OpenAI() | |
client.api_key = 'sk-8tBg' | |
for filename in os.listdir(directory_path): | |
if filename.endswith(".txt") and filename not in finished_files: | |
file_path = os.path.join(directory_path, filename) | |
output_path = os.path.join(processed_directory, filename) | |
summary = process_file(file_path, client, prompt, max_tokens) | |
if summary: | |
save_summary(output_path, summary) | |
if __name__ == "__main__": | |
PROMPT = prompt.PromptText().summary_text | |
MODEL_MAX_TOKENS = 128000 | |
target_directory = '/Users/vincent/Desktop/unprocessed/' | |
processed_directory = '/Users/vincent/Desktop/processed/' | |
finished_files = set() # here you can add a list of files already processed | |
# python3 summary.py | |
summarize_files(target_directory, processed_directory, PROMPT, MODEL_MAX_TOKENS, finished_files) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment