SkillNext 🚀

SkillNext is a modern AI-powered career assistant built with Streamlit. It compares your resume against a job description, identifies skill gaps, recommends learning resources, and provides a follow-up chat assistant for career guidance.

---

✨ What it does

• Analyzes skill fit between a resume and a target job description
• Scores overall match and highlights strengths vs gaps
• Visualizes missing skills with interactive charts
• Suggests learning paths and course recommendations
• Supports Gemini and OpenAI as LLM backends
• Includes a conversation interface for follow-up career questions

---

🧱 Project structure

SkillNext/
├─ app.py                 # Streamlit app entrypoint
├─ config.py              # Provider config and environment handling
├─ requirements.txt       # Project dependencies
├─ .env.example           # Sample environment configuration
├─ data/                  # Bundled skills + courses knowledge base
│  └─ skills_corpus.json
└─ core/
   ├─ charts.py           # Plotly chart builders
   ├─ chat.py             # RAG chat engine setup
   ├─ embeddings.py       # Embedding model factory
   ├─ gap_analysis.py     # Resume vs JD gap analysis logic
   ├─ index_builder.py    # PDF parsing + vector index creation
   ├─ llm.py              # LLM provider factory
   └─ recommender.py      # Learning and recommendation builder

---

�️ Screenshots

---

�🚀 Quick Start

1. Create a virtual environment

python -m venv venv
venv\Scripts\activate

2. Install dependencies

pip install -r requirements.txt

3. Configure your keys

copy .env.example .env

Edit .env and set either:

• GOOGLE_API_KEY for Gemini
• OPENAI_API_KEY for OpenAI

Then choose your provider with:

LLM_PROVIDER=gemini
# or
LLM_PROVIDER=openai

4. Start the app

venv\Scripts\activate
streamlit run app.py

---

🖥️ Usage

1. Open the Streamlit app in your browser.
2. Choose a provider and enter your API key.
3. Upload a PDF resume or paste resume text.
4. Paste the target job description.
5. Click Analyze Skill Gap.
6. Review the results, charts, and recommendations.

---

📌 Notes

• This app uses LLM-assisted prompts to generate structured JSON analysis and recommendations.
• A bundled knowledge base in data/skills_corpus.json powers the recommendation engine.
• Do not commit .env, venv, or virtual environment folders to GitHub.

---

📦 Dependencies

• Streamlit
• Plotly
• llama-index
• OpenAI / Gemini model adapters
• pypdf
• python-dotenv
• pandas

---

💡 Tip

If you want a cleaner release, add a LICENSE and optionally a .github/workflows CI file for automated testing and deployment.

⚠️ Disclaimer

All analysis and observation provided in this project are generated by a Large Language Model (LLM). While we strive for accuracy, these automated insights may not be 100% correct or exhaustive. We highly recommend verifying any critical information or conclusions independently.