banyaroo/cambridge-as-a-level-biology-vector-db

Cambridge AS and A Level Biology Vector Database

This repository contains a serialized vector database (knowledge index) built from the Cambridge International AS and A Level Biology Coursebook (Fourth Edition) by Mary Jones, Richard Fosbery, Jennifer Gregory, and Dennis Taylor.

It is specifically designed for Retrieval-Augmented Generation (RAG) pipelines, educational AI assistants, and semantic search applications targeting advanced biology concepts.

Dataset Specifications

• Source Material: Cambridge International AS and A Level Biology Coursebook (Fourth Edition)
• Authors: Mary Jones, Richard Fosbery, Jennifer Gregory, Dennis Taylor
• Embedding Model Used: google/embeddinggemma-300m

Configuration & Chunking Strategy

• Chunking Technique: Docling's HybridChunker
• Chunk Size: 256 tokens
• Database Format: FAISS

License & Fair Use Notice

This vector database contains mathematical transformations (embeddings) of copyrighted text from the Cambridge International AS and A Level Biology Coursebook.

• This asset is shared strictly for non-commercial educational research purposes under Fair Use guidelines.
• If you are the copyright holder of the source text and wish to request removal, please open an issue in this repository.