This project uses Pinecone as a vector database for storing embeddings of user data (documents, emails, notes, etc.) in an agentic application. The goal is fast, scalable semantic search for RAG pipelines and direct querying.
This project uses Pinecone as a vector database for storing embeddings of user data (documents, emails, notes, etc.) in an agentic application. The goal is fast, scalable semantic search for RAG pipelines and direct querying.