ai-agents-knowledge-base-creat-need-to-combine-semantic-search-over-unstructured--87f38cde

THEN Create a `KNOWLEDGE_BASE` object specifying a vector storage, content columns for embedding, and metadata columns for filtering. Then run queries that mix semantic search and structured criteria.

CREATE KNOWLEDGE_BASE customers_issues USING storage = my_vector.db, content_columns = ['ticket_description'], metadata_columns = ['customer_name', 'segment', 'revenue', 'is_pending_renewal']; SELECT * FROM customers_issues WHERE content = 'data security' AND is_pending_renewal = 'true' AND revenue > 1000000;