Git Product home page Git Product logo

investorsgpt's Introduction

InvestorsGPT

Automatize writing the tedious monthly investor update using the ChatGPT API and the GitHub API.

Requirements

In order to use InvestorsGPT you need a valid GitHub personal access token and a valid OpenAI API Key.

Usage

In order to use the script, first create a .env file in the root of the repository and place your GITHUB_PA_TOKEN and your OPENAI_API_KEY there. The file should look something like:

GITHUB_PA_TOKEN = "your_github_token"
OPENAI_API_KEY = "your_openai_key"

Once you have created and added your credentials to the .env file, make sure to modify the config.ini file with the Organization and Repositories you want to target for your update.

Now that you have everything setup, proceed to install the required dependencies:

pip install -r requirements.txt

Finally, run the script to get the update from InvestorsGPT:

python main.py

Example output:

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "Exein Platform\n- Enhancements to loading and graphics with live histograms and data tables for a more user-friendly experience\n- Improved functionality for monitoring ESP32 devices including better parsing and tooltips\n- Refined design for better visual appeal including clearer display of event and threat counters\n\nPulsar\n- Improvements for compatibility with different Linux security modules and higher kernel versions\n- New tools to improve cross-compiling and SSH target functionality\n- Enhancements to streaming monitoring, including ergonomic filtering and string representation of event_type field\n\nPulsar-Enterprise\n- Additional API endpoints and features for greater flexibility and customization of event and threat monitoring,\n    including pagination and limits\n- Improved agent and threat centre details for a clearer picture of system activity and security risks\n- Implementation of file system monitoring and optimized API endpoints for enhanced data handling and performance.",
        "role": "assistant"
      }
    }
  ],
  "created": 1679320542,
  "id": "chatcmpl-6wAH83dUzCRY4UIrhTgImfKHiLkII",
  "model": "gpt-3.5-turbo-0301",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 170,
    "prompt_tokens": 1987,
    "total_tokens": 2157
  }
}

investorsgpt's People

Contributors

giovannialberto avatar

Watchers

 avatar

investorsgpt's Issues

add support for open issues - backlog

I also want to automatize the writing of what we are going to work on over the next month.

A good (but certainly not exact) proxy for this would be the issues opened recently and still not closed. I bet that should be accurate enough to be valuable for the investors.

parse also the issue body

There is lots of valuable content in each issue body. However, parsing also bodies adds lots of tokens, often exceeding the max number of token (4096) that the ChatGPT API supports.

To address this issue I could:

  • get rid of the repository key in each issue
  • split the single query into multiple queries (one for each repo)
  • (optional) if nothing else works, find a way to recursively split the input prompt into smaller chunks

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.