Linkedin to Portfolio Site Generator

This project is a Python script that scrapes your Linkedin PDF and generates a customized portfolio site using OpenAI's GPT-4 model.

We interact with the GPT-4 model using LangChain.

Embed the Linkedin PDF
Store the embeddings into a Chroma vector database
Query that database to get relevant information
Generate text with OpenAI's GPT-4
With the generated text we use the Next JS portfolio site, powered by Nextra, to create the main portfolio file
Build and deploy site on Vercel

Demo

For this demo, I used LangChain's Co-founder and CEO Harrison Chase's LinkedIn.

You can find his deployed site here: https://harrison-six.vercel.app/

Before you begin, ensure you have met the following requirements:

Installed a recent version of Python (3.7 or newer) installed and a way to create virtual environments (virtualenv or conda)
Created a Vercel account and have downloaded/login into Vercel CLI locally
Created OpenAI API account and obtain an OpenAI API key

Clone the repo

git clone https://github.com/waseemhnyc/LinkedIn-to-Portfolio-Site-Generator

Create a virutalenv and source the environment

python3 -m venv myenv
source venv/bin/activate

Install the necessary libraries

pip install -r requirements.txt

Create a .env file and input your OpenAI API Key in the file

cp .env.example .env

To run the program, run the following command in the terminal:

python main.py

This project is licensed under the MIT License - see the LICENSE file for details.