requirements.txt

# Data Engineering Knowledge Assistant — Pinned Dependencies
# All versions tested to work together on HF Spaces free tier (Python 3.11)

# ── Web framework ─────────────────────────────────────────────────────────────
fastapi==0.111.0
uvicorn[standard]==0.30.1
python-multipart==0.0.9

# ── LLM (Groq — free tier, ultra-low latency) ────────────────────────────────
groq==0.9.0

# ── LangChain (split-package era >= 0.2) ──────────────────────────────────────
langchain==0.2.16
langchain-core==0.2.38
langchain-community==0.2.16
langchain-text-splitters==0.2.4

# ── PDF parsing ───────────────────────────────────────────────────────────────
pypdf==4.3.1

# ── Vector store ──────────────────────────────────────────────────────────────
chromadb==0.5.5

# ── Embeddings (free, runs on CPU) ───────────────────────────────────────────
sentence-transformers==3.0.1
torch==2.3.1
transformers==4.44.2

# ── MLflow (Databricks compatibility) ────────────────────────────────────────
mlflow==2.16.0

# ── Utilities ─────────────────────────────────────────────────────────────────
python-dotenv==1.0.1
pydantic==2.8.2
httpx==0.27.0