Skip to content

A script to circumvent the context limit of language models.

Notifications You must be signed in to change notification settings

yccheok/RecursiveGPT

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

19 Commits
 
 
 
 
 
 

Repository files navigation

RecursiveGPT

Process large text files and documents with ChatGPT (more APIs coming soon*). Requires Python 3 and an OpenAI API key.

Use:

Currently command-line only.

git clone https://github.com/jckpn/RecursiveGPT.git
cd RecursiveGPT
pip install -r requirements.txt
python RecursiveGPT.py

Then just follow the prompts as given in the termimal.

How it works

This script works by splitting the file into chunks within the context window of ChatGPT (currently limited to 4096 tokens). You simply specify a prompt, and it'll get prepended to the start of each chunk. The ChatGPT outputs are recursively added to an output text file.

Examples

Your prompts could be anything like:

  • "Summarise the following lecture notes."
  • "Proofread the following, providing your response in the form [original text -> revised text]."
  • "Rewrite the following in the style of a pirate."
  • "Convert the following scientific paper into a child-friendly overview."
  • "Task: For each mention of a dog breed, state the breed and describe where in the text it occurs."

The prompt below was "Convert these lecture captions to concise revision notes." Screenshot 2023-05-20 at 16 09 06

I made this to help me with tasks like proofreading and lecture summaries, but it works well for a range of tasks.

*I have very little free time at the moment due to my MSc and other jobs – pull requests would be appreciated!

(Privacy note: No data is sent anywhere except for interacting with the ChatGPT API.)

About

A script to circumvent the context limit of language models.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%