Describe the problem/error/question
I am making an API call to our ERP system to retrieve a specific order. The URL and header configuration work perfectly when using a standard HTTP Request node in callin.io.
However, when I try to execute the same call through an AI Agent using the HTTP Request Tool, I encounter an error.
What is the error message (if any)?
json
{
"response": "There was an error: "Binary data is not supported""
}
Please share your workflow
{
"nodes": [
{
"parameters": {
"inputSource": "passthrough"
},
"type": "n8n-nodes-base.executeWorkflowTrigger",
"typeVersion": 1.1,
"position": [
0,
0
],
"id": "d81bda9d-ccb7-4b8c-9ece-02eb70b2f33d",
"name": "Workflow Input Trigger"
},
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 1.7,
"position": [
220,
0
],
"id": "bd252bd6-e6a5-4548-8816-dc23f35d681a",
"name": "AI Agent"
},
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1.1,
"position": [
160,
220
],
"id": "36ecb496-2a00-420b-82ec-228d012b0978",
"name": "OpenAI Chat Model",
"credentials": {
"openAiApi": {
"id": "4ZJQfA4xhF8qp1NL",
"name": "OpenAi account"
}
}
},
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"typeVersion": 1.1,
"position": [
0,
-160
],
"id": "3ab5aa8a-0551-4e43-bff4-804d5d027fdf",
"name": "When chat message received",
"webhookId": "1cdfb364-b97d-428c-83a2-0f46bd710e9d"
},
{
"parameters": {
"toolDescription": "Rufe ein den Auftrag 63144 auf.",
"url": "https://637a04a74b2c1.xentral.biz/api/salesOrders/63144",
"sendHeaders": true,
"specifyHeaders": "json",
"jsonHeaders": "=n",
"optimizeResponse": true,
"responseType": "text"
},
"type": "@n8n/n8n-nodes-langchain.toolHttpRequest",
"typeVersion": 1.1,
"position": [
480,
220
],
"id": "6833f987-4b88-4ebf-b847-00fe2fe294bd",
"name": "Auftrag 63144 abrufen"
}
],
"connections": {
"Workflow Input Trigger": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"Auftrag 63144 abrufen": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
}
},
"pinData": {},
"meta": {
"templateCredsSetupCompleted": true,
"instanceId": "1f00b6613e292a556a49f87a1c03b4a67c47ce091865b8f2a517bb3b16ece7b9"
}
}
Share the output returned by the last node
Information on your callin.io setup
- callin.io version:
- Database (default: SQLite):
- callin.io EXECUTIONS_PROCESS setting (default: own, main):
- Running callin.io via (Docker, npm, callin.io cloud, desktop app):
- Operating system:
It appears your topic is missing some crucial details. Could you please provide the following information, if relevant?
- callin.io version:
- Database (default: SQLite):
- callin.io EXECUTIONS_PROCESS setting (default: own, main):
- Running callin.io via (Docker, npm, callin.io cloud, desktop app):
- Operating system:
Please provide the requested information.
Hi,
I'm encountering the same issue.
The standard HTTP Request node, configured with the same parameters, functions correctly. However, the AI Agent Tool's HTTP Request node, using identical settings, returns:
json
{
“response”: “There was an error: “Binary data is not supported””
}
I've attempted to have the agent populate the values, manually set them, and use expressions to supply the names and values as strings, all resulting in the same error message.
My suspicion is that this might be due to the response content-type not being advertised or returned as application/json
, but rather a custom type application/custom+json;version=2.1
. Nevertheless, it's still plain and valid JSON and should be handled appropriately, just as the regular HTTP Request node does.
Yes, the reason for this is
This approach treats anything other than expected content types as binary, which is incorrect. Downgrading to version 1.63.4 resolves this issue with custom JSON content declarations. I believe this is a bug, and I've raised an issue on GitHub:
This thread was automatically closed 90 days following the last response. New replies are no longer permitted.