5 AI Projects You Can Build This Weekend (with Python)

The best way to develop your AI skills is by building projects. However, figuring out what to build can be difficult if you're just getting started. Here, I share 5 AI projects you can build fast at three levels of sophistication. I'll break down the steps and Python libraries needed to implement each idea.

---

The number one mistake beginners make when thinking of project ideas is starting with the question, "How can I use this new tech?" While this can be a fine way to learn a new tool, there is a better way.

Good project ideas start with the question, "What problem can I solve?" This not only makes for a nice story when sharing with potential employers but solving problems is how you translate technical skills into value.

The following projects all take this problem-first approach. You can take these ideas and implement them directly or (even better) use them as inspiration for solving a problem that you are personally facing.

1) Resume Optimization (Beginner)

An effective yet time-consuming part of applying for jobs is adapting your resume to different job descriptions. While automating this task would have been an advanced project a few years ago, with today's large language models, it is as simple as an API call.

Here's a step-by-step breakdown of how to implement such an automation.

1. Create a markdown version of your resume (Note: ChatGPT can do this for you).
2. Experiment with different prompt templates that take your markdown resume and a job description and output a new resume in markdown.
3. Use OpenAI's Python API to prompt GPT-4o-mini to rewrite your resume dynamically.
4. Convert the markdown file to HTML and then to PDF with the markdown and pdfkit libraries, respectively.

Libraries: openai, markdown, pdfkit

While we could readily use ChatGPT for this, the upside of implementing this with Python is that we can easily scale up the process. Here's some starter code for Step 3.

import openai
openai.api_key = "your_sk"

# prompt (assuming md_resume and job_desciption have been defined)
prompt = f"""
I have a resume formatted in Markdown and a job description. 
Please adapt my resume to better align with the job requirements while 
maintaining a professional tone. Tailor my skills, experiences, and 
achievements to highlight the most relevant points for the position. 
Ensure that my resume still reflects my unique qualifications and strengths 
but emphasizes the skills and experiences that match the job description.

### Here is my resume in Markdown:
{md_resume}

### Here is the job description:
{job_desciption}

Please modify the resume to:
- Use keywords and phrases from the job description.
- Adjust the bullet points under each role to emphasize relevant skills and achievements.
- Make sure my experiences are presented in a way that matches the required qualifications.
- Maintain clarity, conciseness, and professionalism throughout.

Return the updated resume in Markdown format.

"""

# make api call
response = openai.chat.completions.create(
    model="gpt-4o-mini",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ], 
    temperature = 0.25
)

# extract response
resume = response.choices[0].message.content

Note: ChatGPT is super helpful for writing short code snippets (and prompts) like this. If you get stuck, try it for Step 4.

2) YouTube Lecture Summarizer (Beginner)

Although I love adding technical talks to my YouTube "watch later" playlist, it might be a while before I watch them (if I ever get around to it

Tags: AI Data Science Llm Machine Learning Python

Comment