In this article, we showcase a powerful new query engine ( SQLAutoVectorQueryEngine ) in LlamaIndex that can leverage both a SQL database as well as a vector store to fulfill complex natural language queries over a combination of structured and unstructured data. This query engine can leverage the expressivity of SQL over structured data, and join it with unstructured context from a vector database. We showcase this query engine on a few examples and show that it can handle queries that make use of both structured/unstructured data, or either.

Check out the full guide here: https://gpt-index.readthedocs.io/en/latest/examples/query_engine/SQLAutoVectorQueryEngine.html.

Read More