Textbook Vectorization

Objectives

• Extract text from PDF textbooks
• Generate vector embeddings for semantic search
• Enable fast concept lookup across large textbooks
• Support both local (free) and cloud-based embedding models

Key Instructions

1. Choose Embedding Model

Local Model (Free):

from sentence_transformers import SentenceTransformer
model = SentenceTransformer('all-MiniLM-L6-v2')  # ~80MB, runs locally