Resume Matcher

𝙹𝚘𝚒𝚗 𝙳𝚒𝚜𝚌𝚘𝚛𝚍 ✦ 𝚆𝚎𝚋𝚜𝚒𝚝𝚎 ✦ 𝙳𝚎𝚖𝚘 ✦ 𝙷𝚘𝚠 𝚝𝚘 𝙸𝚗𝚜𝚝𝚊𝚕𝚕 ✦ 𝙲𝚘𝚗𝚝𝚛𝚒𝚋𝚞𝚝𝚎 ✦ 𝙳𝚘𝚗𝚊𝚝𝚎 ✦ 𝚃𝚠𝚒𝚝𝚝𝚎𝚛

Resume Matcher is an AI Based Free & Open Source Tool. To tailor your resume to a job description. Find the matching keywords, improve the readability and gain deep insights into your resume.

Don't let your resume be a roadblock from getting your next job. Use Resume Matcher!

How does it work?

The Resume Matcher takes your resume and job descriptions as input, parses them using Python, and mimics the functionalities of an ATS, providing you with insights and suggestions to make your resume ATS-friendly.

The process is as follows:

Parsing: The system uses Python to parse both your resume and the provided job description, just like an ATS would.
Keyword Extraction: The tool uses advanced machine learning algorithms to extract the most relevant keywords from the job description. These keywords represent the skills, qualifications, and experiences the employer seeks.
Key Terms Extraction: Beyond keyword extraction, the tool uses textacy to identify the main key terms or themes in the job description. This step helps in understanding the broader context of what the resume is about.
Vector Similarity Using FastEmbedd: The tool uses FastEmbedd, a highly efficient embedding system, to measure how closely your resume matches the job description. The more similar they are, the higher the likelihood that your resume will pass the ATS screening.

How to install

Follow these steps to set up the environment and run the application.

Fork the repository here.

Clone the forked repository.

git clone https://github.com/<YOUR-USERNAME>/Resume-Matcher.git
cd Resume-Matcher

Create a Python Virtual Environment:
- Using virtualenv:
  
  Note: Check how to install virtualenv on your system here link.
```
virtualenv env
```
OR
- Create a Python Virtual Environment:
```
python -m venv env
```

Activate the Virtual Environment.

On Windows.
```
env\Scripts\activate
```
On macOS and Linux.
```
source env/bin/activate
```

OPTIONAL (For pyenv users)

Run the application with pyenv (Refer this article)

Build dependencies (on ubuntu)

sudo apt-get install -y make build-essential libssl-dev zlib1g-dev libbz2-dev libreadline-dev libsqlite3-dev wget curl llvm libncurses5-dev libncursesw5-dev xz-utils tk-dev libffi-dev liblzma-dev python openssl


sudo apt-get install build-essential zlib1g-dev libffi-dev libssl-dev libbz2-dev libreadline-dev libsqlite3-dev liblzma-dev libncurses-dev

sudo apt-get install python-tk python3-tk tk-dev

sudo apt-get install build-essential zlib1g-dev libffi-dev libssl-dev libbz2-dev libreadline-dev libsqlite3-dev liblzma-dev

pyenv installer
```
   curl https://pyenv.run | bash
```
Install desired python version
```
  pyenv install -v 3.11.0
```
pyenv with virtual enviroment
```
   pyenv virtualenv 3.11.0 venv
```
Activate virtualenv with pyenv
```
   pyenv activate venv
```

Install Dependencies:
```
pip install -r requirements.txt
```
Prepare Data:
- Resumes: Place your resumes in PDF format in the Data/Resumes folder. Remove any existing contents in this folder.
- Job Descriptions: Place your job descriptions in PDF format in the Data/JobDescription folder. Remove any existing contents in this folder.
Parse Resumes to JSON:
```
python run_first.py
```
Run the Application:
```
streamlit run streamlit_app.py
```

Note: For local versions, you do not need to run "streamlit_second.py" as it is specifically for deploying to Streamlit servers.

Additional Note: The Vector Similarity part is precomputed to optimize performance due to the resource-intensive nature of sentence encoders that require significant GPU and RAM resources. If you are interested in leveraging this feature in a Google Colab environment for free, refer to the upcoming blog (link to be provided) for further guidance.

Docker

Build the image and start application
```
    docker-compose up
```
Open localhost:80 on your browser

Running the Web Application

The full stack Next.js (React and FastAPI) web application allows users to interact with the Resume Matcher tool interactively via a web browser.

Warning

The results returned from through the web app are currently entirely mocked / faked. This means that the results returned are not real and are just for demonstration purposes. This will be implemented with real data results in a future release.

To run the full stack web application (frontend client and backend api servers), follow the instructions over on the webapp README file.

Google Colab

Create an account in ngrok and get you token
Go to archive/resume_matcher_colab.ipynb and run the notebook.
Enter your ngrok token and run the notebook.
Copy the url and open it in your browser.

Cohere and Qdrant

Visit Cohere website registration and create an account.
Go to API keys and copy your cohere api key.
Visit Qdrant website and create an account.
Get your api key and cluster url.
Go to open dashboard in qdrant and enter your api key for only the first time

1. Now create a yaml file named config.yml in Scripts/Similarity/ folder. 2. The format for the conifg file should be as below: ```yaml cohere: api_key: cohere_key qdrant: api_key: qdrant_api_key url: qdrant_cluster_url ``` 3. Please replace your values without any quotes.

Note: Please make sure that Qdrant_client's version is higher than v1.1

Note: This part needs updating w.r.t to the new FastEmbed changes.

Code Formatting

This project uses Black for code formatting. We believe this helps to keep the code base consistent and reduces the cognitive load when reading code.

Before submitting your pull request, please make sure your changes are in accordance with the Black style guide. You can format your code by running the following command in your terminal:

black .

Pre-commit Hooks

We also use pre-commit to automatically check for common issues before commits are submitted. This includes checks for code formatting with Black.

If you haven't already, please install the pre-commit hooks by running the following command in your terminal:

pip install pre-commit
pre-commit install

Now, the pre-commit hooks will automatically run every time you commit your changes. If any of the hooks fail, the commit will be aborted.

Join Us, Contribute!

Pull Requests & Issues are not just welcomed, they're celebrated! Let's create together.

🎉 Join our lively Discord community and discuss away!

💡 Spot a problem? Create an issue!

👩‍💻 Dive in and help resolve existing issues.

🔔 Share your thoughts in our Discussions & Announcements.

🚀 Explore and improve our Landing Page. PRs always welcome!

📚 Contribute to the Resume Matcher Docs and help people get started with using the software.

Tech Stack

Please support the development by donating.

Heads Up! 📝

Your support means the world to us 💙. We're nurturing this project with an open-source community spirit, and we have an ambitious roadmap ahead! Here are some ways you could contribute and make a significant impact:

✨ Transform our Streamlit dashboard into something more robust.

💡 Improve our parsing algorithm, making data more accessible.

🖋 Share your insights and experiences in a blog post to help others.

Take the leap, contribute, and let's grow together! 🚀

pc-purna/Resume-Matcher