Does RAG require agent if not chat?

Hi! I’m trying to create a RAG pipeline to reference a knowledge base for content creation. Since this does not require chat or memory, do I still need to use the agent node, or can I connect the OpenAI message modal to the Retrieve Documents nodal (and then to the vector database, etc)?

Thank you for the help!

It looks like your topic is missing some important information. Could you provide the following if applicable.

  • n8n version:
  • Database (default: SQLite):
  • n8n EXECUTIONS_PROCESS setting (default: own, main):
  • Running n8n via (Docker, npm, n8n cloud, desktop app):
  • Operating system:

Welcome to the community @automationturtle !

Tip for sharing information

Pasting your n8n workflow


Ensure to copy your n8n workflow and paste it in the code block, that is in between the pairs of triple backticks, which also could be achieved by clicking </> (preformatted text) in the editor and pasting in your workflow.

```
<your workflow>
```

That implies to any JSON output you would like to share with us.

Make sure that you have removed any sensitive information from your workflow and include dummy or pinned data with it!


No, you do not have to use the agent. AI agent is a more generic and a versatile app. You could use Question and Answer Chain in its place, for example.

1 Like

thank you ihortom! I guess what is a bit confusing to me is, once I add the tool (retrieve documents) to the OpenAI message node, I’m not sure how exactly to reference it in the OpenAI message node settings (like “look for docs in XYZ”)

This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.