AI & Workflows
What is a Document Search node?
Updated May 5, 2026
A Document Search node lets your AI answer questions using your own documents.
You upload files (PDF, DOCX, or MD), select them in the node, and the AI uses their content to generate accurate responses.
When to use it
Use Document Search when your information is:
- In documents or text files
- Unstructured (not in tables or databases)
- Meant to answer questions like:
- “What does this document say about X?”
- “What is our policy on Y?”
How it works
- Upload your documents
- Select up to 10 files in the node
- User asks a question
- AI searches those documents and responds using their content
What you configure
Inside the node:
-
Documents to Search
Select the files the AI should use -
AI Response Style (prompt)
Control how the AI responds (tone, format, instructions)
Example:
“Answer clearly and concisely using only the provided documents.”
Important to know
- Works best for text-based knowledge
- Not suited for structured data (like filters, calculations, tables)
- For structured queries, use Data Search instead
Simple rule
Have documents with information? → Use Document Search
Have structured data (tables, filters)? → Use Data Search