Error: Failed to receive response

Questions
,
1

I have this problem when trying to run this workflow. I have the ollama chat model configured with llama3 on a pretty decent machine, it lists all my models for me, so the connection is fine. I even tried with qwen2.5:0.5B and it generated the same error

image
image1101×356 27.2 KB

Share the output returned by the last node

I have it in docker with podman

2

Hi @tomy687

You need to explicitly tell n8n what its “public-facing” address is so it can tell your browser where to send the data. You can do this by setting environment variables in your Podman container configuration.

  1. Identify your Host IP: Find the IP address of the machine running Podman (e.g., 192.168.1.50).
  2. Update your Podman Run/Compose command: Add the following environment variables:
    • WEBHOOK_URL: Set this to the full URL you use to access n8n in your browser (e.g., http://192.168.1.50:5678/). Crucial: Include the trailing slash.
    • N8N_HOST: Set this to the same IP or hostname (e.g., 192.168.1.50).
    • N8N_PROTOCOL: Set this to http (or https if you are using a reverse proxy with SSL).

If you want to be 100% sure this is the cause before restarting:

  1. Open your browser’s Developer Tools (F12 or Right-click > Inspect).
  2. Go to the Network tab.
  3. Try to send a message in the n8n chat.
  4. Look for a red request in the list (it will likely be a POST or GET to a /webhook/... endpoint).
  5. Check the URL of that failed request. If it says localhost or an internal IP like 172.x.x.x, that confirms the configuration error.
3

Thanks for letting us know about this, We have created CV-14 as the internal dev ticket to look into it.