Skip to content

Latest commit

 

History

History
89 lines (54 loc) · 3.27 KB

README.md

File metadata and controls

89 lines (54 loc) · 3.27 KB
Raw

reDocs.ai

Introduction

The lack of an automated solution for converting codebases into documentation poses challenges in terms of time, accuracy, and code comprehension. Documentation is often ignored by developers, especially in fast-building teams. However, this leads to severe technical debt. Since technical documentation is hard and existing tools are limited or expensive, there is a need for comprehensive automatic documentation generation.

Description

Full Codebase to Developer Docs in One Step

Our prototype offers a seamless solution to transform a full codebase into comprehensive developer documentation in just one step. By uploading a zip file containing the codebase, you can let the magic happen. The resulting documentation includes function explanations, API specs, table schemas, and dependencies, all in Markdown format.

Harnessing GPT-3.5 Capabilities

To power our documentation generation, we leverage the capabilities of GPT-3.5. This advanced language model enables us to produce accurate and contextually relevant documentation for the given codebase.

A Step-by-Step Approach

  1. Codebase Traversal

  2. Code Embeddings

  3. Handling Large Code Files

  4. Maintaining Context with Agglomerating Clustering

  5. Efficient Documentation Generation

Code Refactoring Ability

We harness the power of the LLM to perform code refactoring, with our complex prompt to change the given code block to a neater, efficient and structurally sound code output. We focus on the cleanliness in the prompting along with considering various code analytics to get the best output.

Adding Tests to Code

We also provide a solution to add testing for a specific code block. This forms an integral component in the developer experience, and eliminates the need to devote much time to think about the testing. We again leverage well thought of prompts to give optimal and exhaustive tests.

Tech Stack

List of technologies used to build the prototype:

  • Frontend: Next.js
  • Backend: FastAPI

Setup Guide

  1. Check out the Server Setup guide here.

  2. Client Frontend Setup:

    • Install Node.js dependencies:

      npm install

    • Run the development server for the frontend:

      npm run dev

Example Documentations Generated by reDocs.ai -

  1. Documentation of ComicifyAI:
  • Input repo : https://github.com/ayush4345/Comicify.ai
  • Output Docs :
  1. Documentation_1
  2. Documentation_2
  3. Documentation_3
  4. Documentation_4
  5. Documentation_5
  6. Documentation_6
  1. Documentation of Cluboard:
  • Input repo : https://github.com/mittal-parth/Cluboard/
  • Output Docs :
  1. Documentation_1
  2. Documentation_2

Architecture Diagram

redocs_arch

Start Contributing

  • Read our Contribution Guidelines to get started here

License

MIT License