requirements.txt

# Core dependencies
neo4j==5.15.0
pandas
numpy==1.24.3
python-dotenv==1.0.0
redis==5.0.1
openpyxl>=3.1.0

# Demo UI
streamlit>=1.34.0

# FastAPI and web framework
fastapi==0.104.1
uvicorn[standard]==0.24.0
pydantic==2.5.0

# Vector search (ChromaDB - modern vector database)
chromadb==0.4.15

# STT and Audio Processing
openai>=1.0.0                    # For OpenAI Whisper API (optional)
openai-whisper>=20240930         # Local Whisper (no API key needed)
transformers>=4.21.0             # For PhoWhisper (Vietnamese optimized)
pydub>=0.25.1
librosa>=0.10.0
soundfile>=0.12.1
python-multipart>=0.0.6
aiofiles>=23.0.0
torch>=2.0.0
ffmpeg-python

# For NER model training and evaluation
evaluate>=0.4.0
seqeval>=1.2.2
scikit-learn>=1.0
accelerate>=0.21.0
underthesea>=1.3.4

# NLP and ML (traditional approach - disabled due to conflicts)
sentence-transformers>=2.2.2
# spacy==3.7.2
# transformers==4.35.2
# huggingface_hub==0.16.4

# Vector search (traditional approach - disabled)
# faiss-cpu==1.7.4