Skip to main content

Python REPL with LLM integration

Project description

pai: A Python REPL with built in LLM support

Features

  • Supports ChatGPT and LlamaCpp
  • Generate code in the REPL by typing pai: <prompt>
  • REPL history used as context for the LLM prompt
  • Review, edit and confirm all generated code prior to execution.
  • Code executes on your machine.

Installation & Usage

pip install pai-repl
$ export OPENAI_API_KEY=<api key>
$ pai --chat-gpt gpt-4
Inp [0]>

Examples

Access to REPL history as context

Inp [0]> nums = [1,2,3,4,5,6,7,8]
Inp [2]> ai: calc mean, median and mode. assign each to a var
Gen [2]> from statistics import mean, median, mode
    ...>
    ...> mean_val = mean(nums)
    ...> median_val = median(nums)
    ...> try:
    ...>     mode_val = mode(nums)
    ...> except:
    ...>     mode_val = 'No mode'
    ...>
    ...> mean_val, median_val, mode_val
Out [2]> (4.5, 4.5, 1)
Inp [3]> mean_val
Out [3]> 4.5

Local filesystem access

Inp [0]> ai: list markdown files in the current directory
Gen [0]> import os
    ...>
    ...> # List all markdown files in the current directory
    ...> markdown_files = [file for file in os.listdir() if file.endswith('.md')]
    ...>
    ...> markdown_files
Out [0]> ['README.md']

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

pai_repl-0.1.6.tar.gz (9.2 kB view hashes)

Uploaded Source

Built Distribution

pai_repl-0.1.6-py3-none-any.whl (11.5 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page