# dhanushk-offl/resume-analyzer architecture

> Architecture diagram of the GitHub repository dhanushk-offl/resume-analyzer, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-03-30). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/dhanushk-offl/resume-analyzer
- Repository: https://github.com/dhanushk-offl/resume-analyzer

## Overview

##### Project Type and Purpose
- This is a single-page, full-stack web application focused on analyzing resumes by matching candidate skills with job descriptions.
- It leverages Streamlit for the frontend UI, and it uses LangChain and Groq LLM to perform natural language processing on uploaded PDF resumes to extract and score skills.

##### Key Components
a. User Interface (UI):
- Built with Streamlit.
- Handles resume uploads, skill & job description input, and displays analysis results.
b. Resume Processing Engine:
- Uses LangChain to load and process PDF resumes.
- Preprocesses text using Regular Expressions to prepare data for analysis.
c. Analysis Engine:
- Utilizes Groq LLM to evaluate resumes against the provided job description and required skills.
- Determines matched skills, computes scores, and generates the final evaluation.
d. Application Controller:
- Encapsulated in app.py, it orchestrates the data flow between the UI, resume processing, and analysis modules.
e. Dependencies and Configuration:
- requirements.txt outlines all dependencies.
- LICENSE and README provide project documentation and legal context.

- UI directing user actions (file upload, text inputs) towards the Application Controller.
- Flow from the UI to the Resume Processing Engine where PDF files are parsed.
- Processed data moving from the Resume Processing Engine into the Analysis Engine.
- Link the Analysis Engine back to the Application Controller, which then sends results back to the UI.
- Optionally, note any error-handling or logging components if applicable.

##### Architectural Patterns and Design Principles
- Separation of concerns by clearly distinguishing the roles of LangChain and Groq LLM in the analysis pipeline.

- Create nodes for:
- User Interface (Streamlit frontend)
- File Input Handler (for resume PDFs)
- Text Extraction & Preprocessing (using LangChain and Regex)
- Analysis Module (using Groq LLM for evaluation and scoring)
- Result Renderer (back on the UI)

## Diagram (Mermaid)

```mermaid
flowchart TD
    A["User Interface (Streamlit)"]:::ui
    B["Application Controller (app.py)"]:::control
    C["Resume Processing Engine (LangChain + PDF Parser)"]:::processing
    D["Analysis Engine (Groq LLM + Regex Preprocessing)"]:::analysis
    E["Dependencies and Configuration"]:::doc
    F["Project Documentation (README.md)"]:::doc
    G["Legal Information (LICENSE)"]:::doc

    A -->|"sends_input"| B
    B -->|"triggers_processing"| C
    C -->|"extracts_text"| D
    D -->|"evaluates_resume"| B
    B -->|"returns_result"| A

    B -.->|"uses_config"| E
    B -.->|"refers_doc"| F
    B -.->|"refers_legal"| G

    click A "https://github.com/dhanushk-offl/resume-analyzer/blob/master/app.py"
    click B "https://github.com/dhanushk-offl/resume-analyzer/blob/master/app.py"
    click C "https://github.com/dhanushk-offl/resume-analyzer/blob/master/app.py"
    click D "https://github.com/dhanushk-offl/resume-analyzer/blob/master/app.py"
    click E "https://github.com/dhanushk-offl/resume-analyzer/blob/master/requirements.txt"
    click F "https://github.com/dhanushk-offl/resume-analyzer/blob/master/README.md"
    click G "https://github.com/dhanushk-offl/resume-analyzer/tree/master/LICENSE"

    classDef ui fill:#9de0ff,stroke:#333,stroke-width:2px;
    classDef control fill:#c3e6cb,stroke:#333,stroke-width:2px;
    classDef processing fill:#a1f7a1,stroke:#333,stroke-width:2px;
    classDef analysis fill:#fff3cd,stroke:#333,stroke-width:2px;
    classDef doc fill:#f8d7da,stroke:#333,stroke-width:2px;
```
