Suddenly, OpenAI node stopped working after weeks of correct working

[pitazzo]

Describe the problem/error/question

Suddenly, the OpenAI node stopped working. It has been working for weeks without issue. When we execute the “Message an assistant” node, it produces an internal error. The error began to happen yesterday, with our any modification not in the server nor in the flow.

• The same error happens in all flows using the OpenAI node.
• Sandbox flows created today with only such node fail in the same manner.
• No logs messages are produced after checking with docker logs <container

What is the error message (if any)?

{
  "errorMessage": "Internal error",
  "errorDetails": {},
  "n8nDetails": {
    "nodeName": "Formatter",
    "nodeType": "@n8n/n8n-nodes-langchain.openAi",
    "nodeVersion": 1.3,
    "resource": "assistant",
    "operation": "message",
    "itemIndex": 0,
    "time": "23/7/2024, 19:23:29",
    "n8nVersion": "1.50.2 (Self Hosted)",
    "binaryDataMode": "filesystem",
    "stackTrace": [
      "NodeOperationError: Internal error",
      "    at Object.router (/usr/local/lib/node_modules/n8n/node_modules/@n8n/n8n-nodes-langchain/dist/nodes/vendors/OpenAi/actions/router.js:78:19)",
      "    at processTicksAndRejections (node:internal/process/task_queues:95:5)",
      "    at Object.execute (/usr/local/lib/node_modules/n8n/node_modules/@n8n/n8n-nodes-langchain/dist/nodes/vendors/OpenAi/OpenAi.node.js:16:16)",
      "    at Workflow.runNode (/usr/local/lib/node_modules/n8n/node_modules/n8n-workflow/dist/Workflow.js:725:19)",
      "    at /usr/local/lib/node_modules/n8n/node_modules/n8n-core/dist/WorkflowExecute.js:673:51",
      "    at /usr/local/lib/node_modules/n8n/node_modules/n8n-core/dist/WorkflowExecute.js:1085:20"
    ]
  }
}

Please share your workflow

Information on your n8n setup

• n8n version: 1.50.2
• Database (default: SQLite): SQLite
• Running n8n via (Docker, npm, n8n cloud, desktop app): Docker Compose
• Operating system: Ubuntu Server

services:
 mxa-n8n:
    container_name: mxa-n8n
    image: docker.n8n.io/n8nio/n8n
    restart: always
    ports:
      - "5678:5678"
    environment:
      - N8N_HOST=${SUBDOMAIN}.${DOMAIN_NAME}
      - N8N_PORT=5678
      - N8N_PROTOCOL=http
      - NODE_ENV=production
      - WEBHOOK_URL=https://${SUBDOMAIN}.${DOMAIN_NAME}/
      - GENERIC_TIMEZONE=${GENERIC_TIMEZONE}
      - NODE_FUNCTION_ALLOW_EXTERNAL=uuid
      - N8N_DEFAULT_BINARY_DATA_MODE=filesystem
    volumes:
      - /mnt/raid/platform/n8n/data/:/home/node/.n8n
      - /mnt/raid/platform/n8n/files/:/files

    networks:
      - backend

networks:
  backend:
    name: backend-network
    external: true```

[Jon]

Hey @pitazzo

If it stopped working and nothing was changed it could be a change on the OpenAI side. Can you update to at least 1.51.0 and see if the error message is a bit clearer?

[pitazzo]

hey @Jon , just updated to 1.51.1 and the problem persists with exactly the same error

[Jon]

Hey @pitazzo,

I have just given the node a quick test and it oddly appears to be working for me, I take it there are no issues with your OpenAI account and you have not hit any limits or are running on a trial account?

[djjace]

Same issue here. running 1.52.2

[Jon]

Hey @djjace,

Have you checked the OpenAI console for any issues? This error typically appears when OpenAI is returning an error of some kind normally around limits.