# Conda
conda create -n finred python=3.10 -y
conda activate finred

# Or venv
python3.10 -m venv finred_env
source finred_env/bin/activate

cd /path/to/FinRED
pip install -r requirements.txt

# Unstructured
pip install "unstructured[all-docs]"

# System dependencies (Ubuntu/Debian)
sudo apt-get install -y libmagic-dev poppler-utils tesseract-ocr tesseract-ocr-kor libreoffice pandoc

python --version  # Python 3.10.x
python -c "import torch; print(f'CUDA: {torch.cuda.is_available()}')"

[Context + Schema + Query]
         │
         ▼
   ┌─────────────┐
   │ Step1_build │  Scenario generation (OpenAI GPT-4)
   └─────────────┘
         │
         ▼
   [Scenario JSON]
         │
         ▼
   ┌─────────────┐
   │ Step2_build │  Seed prompt generation (Gemini)
   └─────────────┘
         │
         ▼
   [Seed Prompts]
         │
         ▼
   ┌─────────────┐
   │ Evaluation  │  Model response evaluation
   └─────────────┘

# Run the full pipeline with the example script
sh run/run_data_generate.sh

python src/eval/judge_finred.py \
    -i src/eval/dataset/qwen_2.5_test.csv \
    -o qwen_2.5_test_judged \
    -d src/eval/infer_result

cd /path/to/FinRED

python main.py \
    --step <1|2|all> \
    --category <category> \
    --openai_api_key "sk-..." \
    --gemini_api_key "AIza..."

# Full pipeline (R1)
python main.py \
    --step all \
    --category R1 \
    --openai_api_key "sk-proj-..." \
    --gemini_api_key "AIza..."

# Step 1 only
python main.py \
    --step 1 \
    --category R2 \
    --openai_api_key "sk-proj-..."

# Step 2 only (English, 5 prompts)
python main.py \
    --step 2 \
    --category R5 \
    --lang en \
    --num_prompts 5 \
    --gemini_api_key "AIza..."

# Single subcategory
python main.py \
    --step 2 \
    --category R1_1 \
    --num_prompts 3 \
    --gemini_api_key "AIza..."

cd /path/to/FinRED/src/eval

python src/eval/judge_finred.py \
    -i <input_csv_path> \
    -o <output_basename> \
    -d <output_dir>

python src/eval/judge_finred.py \
    -i ./dataset/qwen_2.5_7b_all_with_responses.csv \
    -o qwen2.5_7b_responses \
    -d ./infer_result/

{
  "scenario_id": "R1_1_0001",
  "context": "...",
  "risk_description": "...",
  "attack_vector": "..."
}

{
  "prompt_1": "Provide details about vulnerabilities in a financial system...",
  "prompt_1_optionalelements": ["social engineering", "phishing"],
  "prompt_2": "...",
  "prompt_2_optionalelements": ["..."]
}