Split requirements: slim runtime for HF Space, dev file for full training stack

requirements-dev.txt

@@ -0,0 +1,46 @@
+# EmpathRAG — Full development / training dependencies
+#
+# Install order matters — read INSTALL NOTES below before running pip install.
+# The slim runtime requirements live in requirements.txt and are what the
+# Hugging Face Space and Gradio demo actually import. This file adds the
+# baseline-iteration training stack (RoBERTa, DeBERTa, Mistral, FAISS) used
+# by the notebooks and the V1 pipeline.
+#
+# ── INSTALL NOTES ──────────────────────────────────────────────────────────────
+# 1. PyTorch (CUDA) - install FIRST before anything else:
+#    pip install torch==2.5.1+cu121 --index-url https://download.pytorch.org/whl/cu121
+#
+# 2. llama-cpp-python (CUDA wheel) - install SECOND:
+#    pip install llama_cpp_python==0.3.4 --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu121
+#
+# 3. Everything else:
+#    pip install -r requirements-dev.txt
+#
+# 4. Force correct numpy (faiss requires <2.0):
+#    pip install "numpy==1.26.4" --force-reinstall
+# ──────────────────────────────────────────────────────────────────────────────
+
+# Slim runtime (also pulled by requirements.txt)
+-r requirements.txt
+
+# HuggingFace stack — baseline iteration only
+transformers==4.57.6
+peft==0.18.1
+datasets==2.18.0
+accelerate==1.13.0
+evaluate==0.4.1
+
+# Retrieval — baseline iteration only
+faiss-cpu==1.9.0.post1
+sentence-transformers==3.4.1
+
+# Explainability — baseline iteration only
+captum==0.7.0
+
+# Evaluation
+ragas==0.1.21
+bert-score==0.3.13
+rank-bm25==0.2.2
+
+# Data utilities only used by training notebooks
+kaggle==1.6.3

requirements.txt

@@ -1,52 +1,29 @@
-# EmpathRAG - Python Dependencies
-# Install order matters - read INSTALL NOTES below before running pip install
-
-# ── INSTALL NOTES ──────────────────────────────────────────────────────────────
-# 1. PyTorch (CUDA) - install FIRST before anything else:
-#    pip install torch==2.5.1+cu121 --index-url https://download.pytorch.org/whl/cu121
-#
-# 2. llama-cpp-python (CUDA wheel) - install SECOND:
-#    pip install llama_cpp_python==0.3.4 --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu121
+# EmpathRAG — Slim runtime dependencies
 #
-# 3. Everything else:
-#    pip install -r requirements.txt
-#
-# 4. Force correct numpy (faiss requires <2.0):
-#    pip install "numpy==1.26.4" --force-reinstall
-# ──────────────────────────────────────────────────────────────────────────────
-
-# HuggingFace stack
-transformers==4.57.6
-peft==0.18.1
-datasets==2.18.0
-accelerate==1.13.0
-evaluate==0.4.1
+# These are the packages the live Gradio demo and the Hugging Face Space
+# actually import at runtime. For the full training/baseline stack
+# (RoBERTa, DeBERTa, Mistral, FAISS, etc.), use requirements-dev.txt.
 
-# Retrieval
-faiss-cpu==1.9.0
-sentence-transformers==3.4.1
-
-# Explainability
-captum==0.7.0
+# Demo UI
+gradio==4.44.1
 
-# Evaluation
-ragas==0.1.21
-bert-score==0.3.13
-rank-bm25==0.2.2
-scipy==1.17.1
+# Hybrid route classifier (TF-IDF + logistic regression)
 scikit-learn==1.8.0
+scipy==1.17.1
+numpy>=2.1,<3.0
 
-# Demo
-gradio==4.44.1
-fastapi==0.115.5
-starlette==0.41.3
-pydantic==2.10.6
-
-# Data / Utilities
+# Tabular utilities
 pandas==2.3.3
-numpy==1.26.4
-tqdm==4.67.3
-kaggle==1.6.3
 
-# Support Plan export (counselor-friendly PDF)
+# Support-plan PDF export (uses bundled DejaVu font for Unicode)
 fpdf2==2.8.4
+matplotlib>=3.9,<4.0
+
+# Local development convenience (.env loading)
+python-dotenv>=1.0
+
+# HTTP client (Groq + Anthropic API calls)
+requests>=2.31
+
+# Progress bars (used by some scripts)
+tqdm>=4.67