Chat node response with JSON

[Adam_Hajdu]

Hi
I was looking for solutions and I can see that there are some similar questions but they are not solving my issue.
I was running in in ubuntu localy and now hosting it on n8n and having the same issue.

Describe the problem/error/question

I have a chat node, going into a Question and answer chain. I have the OpenAI Chat node set up to respond in text, in the test chat window I get a plain text answer but if I use the public chat app (hosted) the answers are always seems to be in JSON incited of plain text. How can I change it?

What is the error message (if any)?

Please share your workflow

(Select the nodes on your canvas and use the keyboard shortcuts CMD+C/CTRL+C and CMD+V/CTRL+V to copy and paste the workflow.)

Share the output returned by the last node

Information on your n8n setup

• n8n version:
• **Database (default: SQLite):pincone
• n8n EXECUTIONS_PROCESS setting (default: own, main):
• **Running n8n via (Docker, npm, n8n cloud, desktop app):tried local UBUNTU and hosted
• **Operating system:n/a

[n8n]

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:

[aya]

Hi @Adam_Hajdu,

Welcome to the community

Tip for sharing your workflow in the forum

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>
```

Make sure that you’ve removed any sensitive information from your workflow and include dummy data or pinned data as much as you can!

---

This looks similar to the issue here:

Chat embed returns JSON

Hi @holgerkurtz92 Thanks for posting here and welcome to the community! What does the end of your workflow look like? If you use a Set Node for example you can specify a key value with the name of either text or output and set it to the AI response. The Agent will then pick that up and return only the response text. Here’s an example of what I mean:

Have you tried out the above solution?

[aditya_gaur]

@Adam_Hajdu
I addition to what @aya just mentioned, you need to add a code node which will parse your json since it is string then use ‘Split Out’ node and drag your ‘text’ field.

Something like this: