Skip to content

Rubix982/InsightForge

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

InsightForge

A CLI tool to auto-generate deep company profiles using AI.

Generate rich, structured company metadata using AI.

InsightForge takes a list of company names (optionally with websites) and uses OpenAI's GPT-4 to produce detailed profiles, including:

  • 📄 Company Description
  • 👨‍💼 Founders and Backgrounds
  • 👥 Company Size
  • 📬 Contact Methods
  • 💼 Job Application Processes
  • 🌟 Notable People to Reach Out To

✨ Features

  • Clean CLI interface
  • Multiple prompt rounds per company for detailed, structured output
  • JSON output for easy further processing
  • OpenAI GPT-4 powered queries
  • Configurable sleep interval to avoid rate limits

🚀 Quickstart

1. Clone the repo

git clone https://github.com/yourusername/insightforge.git
cd insightforge

2. Install with Poetry (recommended)

If you don't have Poetry, install it:

curl -sSL https://install.python-poetry.org | python3 -

Then set Poetry to use .venv inside your project:

poetry config virtualenvs.in-project true

Install dependencies:

poetry install

3. Set your OpenAI API key

export OPENAI_API_KEY="sk-..."

You can also add it to a .env file and load it via python-dotenv if desired.


📄 Poetry Commands

Command Purpose
poetry install Install all project dependencies
poetry run python ... Run script using Poetry’s venv
poetry shell Open shell inside the venv
poetry add <package> Add a new package to pyproject
poetry update Update all dependencies
poetry run make run Run project via Makefile inside venv

🧾 Input File Format

Create a file like:

companies.txt

Endor Labs, https://www.endorlabs.com
Statsig, https://www.statsig.com
Moonvalley, https://www.moonvalley.com

🔁 Run the Tool

poetry run python generate_company_metadata.py --input companies.txt --output companies.json

Or use the Makefile (see below):

make run

🛠 Script Arguments

Argument Description
--input Path to input text file with companies
--output Path to output JSON file
--sleep Delay between requests (default: 5 sec)

📂 Output Structure

[
  {
    "company_name": "Endor Labs",
    "website": "https://www.endorlabs.com",
    "description": "...",
    "founders": "...",
    "company_size": "...",
    "contact": "...",
    "how_to_apply": "...",
    "notable_people": "..."
  },
  ...
]

🧠 Example Use Cases

  • Build a personal CRM of companies you’re interested in
  • Enrich datasets for business development or research
  • Auto-generate scouting reports for job search or investing

✅ TODO

  • Add CSV export
  • Support Claude, Perplexity, or Serper.dev
  • Integrate GitHub scraping for open-source companies
  • Add retry mechanism for failed API calls

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors