Build an AI Resume Scorer App with Python | LLM | FastAPI

Install Anaconda and set up the base environment, then launch JupyterLab from the Anaconda prompt to work with notebooks and Python kernels. Explore cells and .py deployment basics.

Create a conda environment named resume_scora with python 3.12 using the Anaconda prompt. Activate it with conda activate resume_scora to begin the course setup.

Install the cursor ide on Windows, download and accept the terms, then finish installation. Open a folder with cursor to explore a vs code-like interface and its auto chat agent.

Master Python data types from strings and numbers to lists, tuples, dictionaries, sets, and bytes, plus indexing, slicing, range, and bytearray basics.

Explore Python flow control through conditional statements and loops, using if, elif, else, and boolean comparisons. Practice while and for loops, break and continue, range, and nested loops with examples.

Learn how Python functions operate as reusable blocks with inputs and outputs, using def, positional and keyword arguments, star args, and recursive factorial examples.

Explore Python classes and inheritance through practical examples of dogs and animals. Create classes with constructors, attributes, and methods, and use super to extend functionality.

Explore Python modules and modularity through main.py and helper.py, learning to import functions and classes for a reusable package that controls a universal robot via socket and OpenCV brightness project.

Build a python project using OpenCV and MediaPipe to detect hand landmarks via webcam and map the distance between thumb and index finger to screen brightness.

Master python exception handling with try and except, else and finally, to gracefully manage errors, validate input, and raise custom exceptions for scenarios like insufficient funds and negative square roots.

Learn to implement Python logging by importing the logging module, configuring basic level info, and logging messages at debug, info, warning, error, critical levels, including division by zero handling.

Clone the provided https url with git clone, or download and unzip the zip to access the codes.

Show flow of building a UI to paste a resume and job description, scrape the PDF into strings, and run an LLM analysis chain with schemas, displayed as a chart.

Build a modular folder structure for the AI resume scorer app, organizing API, data, sessions, exceptions, logger, models, prompts, and utilities with config, env.

Activate your conda environment, paste the required packages into requirements.txt, and install them with the project’s install command. Optionally build the package with setup.py or configure pyproject.toml.

Develop and implement a custom exception module for the resume scorer project, leveraging system and traceback to generate precise error traces, and prepare for a future custom logger.

Learn how to scrape an uploaded pdf resume and extract its text using fits, a PyMuPDF wrapper, by iterating pages and printing the full content.

Configure the project by filling config.yml with two llms, grok and Google Gemini, and placing their API keys in a dot env file to keep them private.

Create a Pydantic base model in models.py to validate data with typing hints (List, Union) and an Enum, defining overall_score, scores_description, skills_match, experience_match, education_match, and job_compliance for LLM schemas.

Define and configure a custom Python logger with structlog, writing JSON logs to timestamped files and the console, using file and console handlers for visibility.

Learn to build a prompt library for an ai resume scorer app using lang chain, combining resume and job description with a validated schema to rate skills, experience, and fit.

Build a python modelloader.py for an ai resume scorer app, loading .env keys, config files, and LangChain llms (Google Gemini or Grok) with validation, logging, and provider defaults.