To protect private information stored in text embeddings, it’s essential to de-identify the text before embedding and storing it in a vector database. In this article, we’ll demonstrate how to de-identify and chunk text using Tonic Textual, and then easily embed these chunks and store the data in a Pinecone vector database to use for semantic search in RAG or other LLM applications.
The post How to create de-identified embeddings with Tonic Textual & Pinecone appeared first on Security Boulevard.