EmpathRAG / requirements.txt
Mukul Rayana
Day 1: data pipeline, session tracker, query router, adversarial probes, Colab training notebooks
bc3ba9e
Raw
History Blame
741 Bytes
ο»Ώ# ── PyTorch (must install separately with CUDA index β€” see below) ──
# torch==2.1.2+cu121 <- installed via separate command, NOT from this file
# ── HuggingFace stack ──
transformers==4.38.2
peft==0.10.0
datasets==2.18.0
accelerate==0.27.2
evaluate==0.4.1
huggingface_hub>=0.20.0
# ── Retrieval ──
faiss-cpu==1.7.4
sentence-transformers==2.5.1
# ── Generator ──
# llama-cpp-python installed separately with CUDA wheel β€” see below
# ── Explainability ──
captum==0.7.0
# ── Evaluation ──
ragas==0.1.21
bert-score==0.3.13
# ── Demo ──
gradio==4.21.0
# ── Data / Utilities ──
pandas==2.2.1
numpy==1.26.4
tqdm==4.66.2
kaggle==1.6.3
scipy==1.12.0
scikit-learn==1.4.1