ChatGPT is a powerful language model developed by OpenAI that can understand and generate human-like language. We can already see a lot of things that ChatGPT can do: from generating music lyrics to passing law exam. GPT 3 (3.5 to be correct) is the underlying model of ChatGPT and it is available via OpenAI API. I want to give the underlying model a try to see how it works.
I pick the resume use case to try mainly because I remembered how much time I spent updating my resume whenever I change jobs. The resume use case is also a good fit for the text summary and text completion task of the model. And maybe this will help me when I need to update my resume when the time comes!
The GPT 3.5 API is very intuitive and easy to use, it is just a single method call to get the result. You give a text input, maximum token, and some other parameters, and the model will generate the text completion for you. In such a way, the GPT 3 gives you a single-turn conversation with the bot. You can give the API a quick try using the OpenAI Playground. There is a $18 for free credit at this moment.
In fact, it was so easy that I made this quick prototype with streamlid. To run it, you will need a OpenAI API key, then follow below script
pip3 install -r requirements.txt
streamlit run resume_generator.py
You provide a job title, and a brief intro about your work, choose the style and the bot takes it from there. Below is a screenshot.
For the above input, it will generate the below description
• Developed an e-commerce system for Dream Company with over 10,000 daily visitors.
• Optimized the system for scalability and performance to ensure a smooth user experience.
• Created a secure payment system to process customer transactions.
• Developed a comprehensive user interface to provide an intuitive and user-friendly experience.
• Collaborated with other developers to ensure the system was properly tested and debugged.
• Monitored system performance and implemented updates to improve…