Skip to content

Commit

Permalink
📝 Update documentation for CodeInterpreterAPI
Browse files Browse the repository at this point in the history
  • Loading branch information
shroominic authored and nobu007 committed Apr 23, 2024
1 parent a04079b commit 6258635
Showing 1 changed file with 22 additions and 7 deletions.
29 changes: 22 additions & 7 deletions docs/index.md
Original file line number Diff line number Diff line change
@@ -1,10 +1,25 @@
# Welcome
# 👾 Code Interpreter API

This project provides a LangChain implementation of the ChatGPT Code Interpreter. It allows you to have a back and forth chat with the AI assistant to get it to help with programming tasks, data analysis, and more. You can run everything local except the LLM using your own OpenAI API Key.
[![Version](https://badge.fury.io/py/codeinterpreterapi.svg)](https://badge.fury.io/py/codeinterpreterapi)
[![code-check](https://github.com/shroominic/codeinterpreter-api/actions/workflows/code-check.yml/badge.svg)](https://github.com/shroominic/codeinterpreter-api/actions/workflows/code-check.yml)
![Downloads](https://img.shields.io/pypi/dm/codeinterpreterapi)
![License](https://img.shields.io/pypi/l/codeinterpreterapi)
![PyVersion](https://img.shields.io/pypi/pyversions/codeinterpreterapi)

Some key features:
CodeInterpreterAPI allows you to easily build apps like the "Advanced Data Analysis" you may know from ChatGPT. Build on top of [LangChain](https://github.com/langchain-ai/langchain) and [CodeBox](https://github.com/shroominic/codebox-api), it provides a simple API for chatting with an AI that can run Python code to do anything you want.

- Sandboxed execution of Python code snippets provided by the AI assistant using CodeBox. CodeBox is the simplest cloud infrastructure for your LLM Apps.
- Automatic handling of file uploads/downloads
- Support for stateful conversations with chat history
- Extensible architecture to add custom tools and logic
## Key features

- Dataset Analysis, Stock Charting, Image Manipulation, ....
- Internet access and auto Python package installation
- Input `text + files` -> Receive `text + files`
- Conversation Memory: respond based on previous inputs
- Run everything local except the OpenAI API (OpenOrca or others maybe soon)
- Use CodeBox API for easy scaling in production

## Resources

- [Blog Post](https://blog.langchain.dev/code-interpreter-api/)
- [Github Repo](https://github.com/shroominic/codeinterpreter-api/)
- [Documentation](https://shroominic.github.io/codeinterpreter-api/)
- [Join the Discord](https://discord.gg/Vaq25XJvvW)

0 comments on commit 6258635

Please sign in to comment.