nangelov/ai-career-coach

Career Coach Agent

An AI-powered career coaching assistant that helps users create personalized development plans and provides career guidance.

Project Structure

career-coach-agent/
├── app.py              # Main FastAPI application with agent setup
├── main.py            # Application entry point
├── prompts.yaml       # System prompts and templates
├── output_parser.py   # Response parsing and validation
├── frontend/          # React frontend application
│   ├── src/
│   │   ├── components/    # React components
│   │   ├── types/        # TypeScript type definitions
│   │   └── App.tsx       # Main application component
├── tools/             # Tool implementations
│   ├── visit_webpage.py    # Web page content fetcher
│   ├── wikipedia_tool.py   # Wikipedia search tool
│   ├── python_repl.py      # Python code execution tool
│   ├── internet_search.py  # Internet search tool
│   ├── google_jobs_search.py # Google Jobs search tool
│   └── date_and_time.py    # Date and time utilities
├── helpers/           # Helper functions
│   ├── helper.py         # General helper functions
│   └── feedback_handler.py # Feedback processing
└── README.md          # This file

Requirements

Backend

• —Python 3.12+
• —FastAPI
• —LangChain
• —Hugging Face Hub API token
• —Additional dependencies:
• —requests
• —markdownify
• —wikipedia
• —duckduckgo-search
• —pytz
• —python-multipart
• —uvicorn

Frontend

• —Node.js 16+
• —React
• —TypeScript
• —Additional dependencies:
• —styled-components
• —axios
• —@types/react
• —@types/styled-components

Environment Variables

Required environment variables:

HUGGINGFACEHUB_API_TOKEN=your_huggingface_token

Installation

1. 1.Clone the repository:

git clone <repository-url>
cd career-coach-agent

1. 1.Install backend dependencies:

pip install -r requirements.txt

1. 1.Install frontend dependencies:

cd frontend
npm install

1. 1.Set up your Hugging Face API token as an environment variable.

Running the Application

Development Mode

1. 1.Start the backend:

uvicorn main:app --reload

1. 1.Start the frontend development server:

cd frontend
npm start

Production Mode

1. 1.Build the frontend:

cd frontend
npm run build

1. 1.Start the application:

uvicorn main:app

The application will be available at:

• —Web Interface: http://localhost:8000
• —API Documentation: http://localhost:8000/docs

API Endpoints

/agent/query (POST)

Submit queries to the AI assistant.

Request body:

{
    "query": "string",
    "thread_id": "string (optional)",
    "context": {} (optional)
}

/agent/feedback (POST)

Submit user feedback.

Request body:

{
    "contact": "string",
    "feedback": "string"
}

/pdp-generator (POST)

Generate a Personal Development Plan.

Request body:

{
    "file": "PDF file",
    "career_goal": "string",
    "additional_context": "string (optional)",
    "target_date": "string"
}

Available Tools

The AI assistant has access to the following tools:

1. 1.Wikipedia Search
2. 2.Searches Wikipedia for information about topics, people, or concepts
3. 3.Returns relevant summaries and information

1. 1.Web Page Visitor
2. 2.Fetches and processes content from web pages
3. 3.Converts HTML to markdown for better readability
4. 4.Handles timeouts and errors gracefully

1. 1.Python Code Execution
2. 2.Executes Python code in a safe environment
3. 3.Returns execution results
4. 4.Handles syntax errors and runtime exceptions

1. 1.Internet Search
2. 2.Performs web searches using DuckDuckGo
3. 3.Returns relevant search results
4. 4.Useful for finding current information

1. 1.Google Jobs Search
2. 2.Searches for job listings on Google Jobs
3. 3.Returns relevant job opportunities
4. 4.Helps with career research

1. 1.Date and Time
2. 2.Provides current date and time information
3. 3.Supports multiple timezones
4. 4.Useful for scheduling and planning

Features

Frontend

• —Modern, responsive UI built with React and TypeScript
• —Real-time chat interface with message history
• —Personal Development Plan (PDP) generation
• —PDF upload and processing
• —User feedback system
• —Mobile-friendly design

Backend

• —FastAPI-based REST API
• —LangChain-powered AI agent
• —Conversation memory and context management
• —Error handling and graceful degradation
• —CORS support
• —Interactive API documentation
• —Tool execution with proper error handling
• —Markdown formatting for better readability

Architecture

• —Frontend:
• —React with TypeScript
• —Styled Components for styling
• —Axios for API communication
• —Responsive design for all devices

• —Backend:
• —FastAPI: Handles HTTP requests and API endpoints
• —LangChain: Manages the AI agent and tools
• —Llama-3.3-70B-Instruct: Powers the AI responses
• —YAML Configuration: Manages system prompts and templates
• —Tools Integration: Wikipedia, Web, Python, Search, and more

Contributing

1. 1.Fork the repository
2. 2.Create a feature branch
3. 3.Commit your changes
4. 4.Push to the branch
5. 5.Create a Pull Request

License

[Add your license here]