Using RAG on XML as a possible BigQuery replacement

A project is considering RAG as a re for BigQuery when working with XML data. The core question is whether a search-and-answer setup can replace a database-style .

No details are given about data size, cost, speed, , or . The real tradeoff depends on how much XML data exists, what questions need answering, and whether the current BigQuery work is search-like or analysis-heavy.

Key points

  • The project target is XML data.
  • The proposed change is to replace BigQuery with RAG.
  • No , , or cost numbers are provided.
  • RAG may reduce token use if only small XML sections need to be sent to the model.
  • BigQuery may still be needed for structured analysis tasks.
Read original