@pxt.query def search_documents(query_text: str, user_id: str): sim = chunks.text.similarity(query_text) return ( chunks.where( (chunks.user_id == user_id) # Metadata filtering & (sim > 0.5) # Filter by similarity threshold & (pxt_str.len(chunks.text) > 30) # Additional filter/transformation ) .order_by(sim, asc=False) .select( chunks.text, source_doc=chunks.document, # Ref to the original document sim=sim, title=chunks.title, heading=chunks.heading, page_number=chunks.page ) .limit(20) )

For instance in https://github.com/pixeltable/pixeltable