Building enterprise-ready AI requires ensuring users can only augment prompts with data they're authorized to access. Fine-grained authorization in Retrieval-Augmented Generation (RAG) can be achieved with Relationship-based access control (ReBAC). ReBAC enables decisions based on relationships between objects, offering more precise control compared to traditional models like RBAC and ABAC.
This workshop gives you hands-on knowledge on using ReBAC to safeguard sensitive data in RAG pipelines. We'll start with why Authorization is critical for RAG pipelines, and how Google Zanzibar achieves this with ReBAC. Attendees will learn how to pre-filter and post-filter vector database queries with a list of authorized object IDs to improve security and efficiency. The workshop uses Pinecone, Langchain, OpenAI, and SpiceDB.
The list of prerequisites are:
- A Pinecone account and API key
- SpiceDB instance and API key
- An OpenAI account and API key.
- Jupyter Notebook and Python
Key Takeaways:
- Risks facing LLM and GenAI applications in the Enterprise
- Components of a typical RAG pipeline and how to secure it
- Explanation pre- and post-filtering techniques for secure data retrieval.
- Hands-on fine-grained authorization for RAG using Pinecone, Langchain, OpenAI, and SpiceDB.
