requirements.txt

# --- Phase 1: data + EDA ---
datasets>=2.18
pandas>=2.0
pyarrow>=14.0
matplotlib>=3.7
seaborn>=0.13
pyyaml>=6.0

# --- Phase 2: evaluation ---
numpy>=1.24
codebleu>=0.7
tree-sitter>=0.21
tree-sitter-python>=0.21

# --- Phase 3: retrieval ---
sentence-transformers>=2.7
faiss-cpu>=1.8

# --- Phase 4-6: generation, fine-tuning, agent ---
transformers>=4.40
torch>=2.2
accelerate>=0.30
peft>=0.10

# --- Deployment ---
fastapi>=0.110
uvicorn>=0.29
pydantic>=2.0
gradio>=4.0
streamlit>=1.33