🏟️ FC Barcelona HR RAG - Local Files, No Database

A lightweight Retrieval-Augmented Generation system using Markdown files as knowledge base.

Welcome to the FC Barcelona HR RAG System - a simple, self-contained Retrieval-Augmented Generation (RAG) project that loads Markdown-based HR/player records directly from the filesystem into memory.

No database. No vector DB. No embeddings. Just pure local markdown → dictionary → context injection → LLM.

Perfect for small projects, demo apps, or experimenting with RAG fundamentals.

---

🚀 Features

✔ Local File-Based Knowledge Store

• HR/player records stored as .md files
• Loaded automatically into a Python dict
• Easy to modify, easy to version-control

✔ Context-Injection RAG

• User query analyzed for keyword matches
• Relevant markdown snippets injected into system prompt
• LLM answers with higher accuracy using only local data

✔ OpenAI API Integration

• Uses gpt-4.1-nano for fast + cheap responses
• System prompt built specifically around FC Barcelona employees

✔ Simple Gradio Chat UI

• Full chat interface
• Local browser launch
• Debug logs enabled

✔ Fully Offline Knowledge

• No vectors
• No external DB
• No third-party storage
• Everything lives inside data/employees/*.md

---

📁 Project Structure

/
├── data/
│ └── employees/
│ ├── <employee1>.md
│ ├── <employee2>.md
│ └── ...
│
├── src/
│ ├── main.py
│
├── tests/
│ ├── test_context.py
│
├── synthetic_data_generator.py
├── requirements.txt
└── README.md

---

🧠 How It Works

1️⃣ Load all .md files into memory

knowledge = load_markdown_files()

Each employee record becomes a key-value entry:

{name: markdown_content}

2️⃣ Detect keywords in user query

get_relevant_context(message)

If words from the question match employee names → relevant markdown is returned.

3️⃣ Inject context into system prompt

system_message = SYSTEM_PREFIX + additional_context(message)

4️⃣ Chat model replies with improved accuracy

openai.chat.completions.create(...)

5️⃣ All wrapped in a clean Gradio UI

gr.ChatInterface(...).launch(inbrowser=True)

---

▶️ Running the Project

1. Install dependencies

pip install -r requirements.txt

2. Add your OpenAI API key

Create a .env file:

OPENAI_API_KEY=your_key_here

3. Put employee/player files into

data/employees/*.md

4. Run the app

python main.py

This opens the Gradio chat UI in your browser.

---

✍️ Example Query

"What is the salary of Pedri?" "How did João Félix perform in 2022?" "Tell me about the injuries of Ansu Fati."

The system will automatically: ✔ extract keywords ✔ search local markdown files ✔ inject only relevant context ✔ respond like an FC Barcelona HR expert

---

🛠 Tech Stack

• Python 3.10+
• OpenAI API
• Gradio
• dotenv
• Local markdown RAG (no vector DB)