Connect Pinecone and Box to ship vector search and RAG: embed, index, and query at scale with managed infrastructure.
Connect a Box account to a Pinecone vector database.This integration allows embeddings generation based on content stored in a particular account and folder in Box. By default, the Pinecone Inference API is used, as well as OpenAI for the LLM. The integration can be used within a larger AI agent or workflow.