Connect Flowise to OpenLLM Buddy

Connect Flowise to OpenLLM Buddy with the ChatOpenAI Custom node and a custom BasePath for chatflows and agent flows.

No-code, automation & home · Integration guide

What is Flowise?

Flowise is an open-source visual builder for LLM flows, with nodes for models, memory, tools, vector stores, and agents. Visit Flowise.

Why connect OpenLLM Buddy?

The ChatOpenAI Custom node exposes a BasePath field, so any Flowise flow can run on your OpenLLM Buddy model without code.

Before you start, create an API key in the console and deploy a model. If anything fails, run the curl test in Step 3 first: no tool can fix a broken endpoint.

1

Create a credential

Open Credentials → Add New → OpenAI API. Name it OpenLLM Buddy and paste your API key.

2

Add the ChatOpenAI Custom node

In a chatflow canvas, add Chat Models → ChatOpenAI Custom and configure it.

  • Connect Credential: the one you just created.
  • Model Name: gemma4:26b
  • Under Additional Parameters, set BasePath to https://openllmbuddy-proxy.botbuddytech.workers.dev/v1.
  • Set temperature and max tokens to taste.

Connect the node to a Conversation Chain or an agent, save, and test in the chat panel.

3

Test the endpoint with curl

Confirm the key, URL, and model id work before debugging Flowise. A short JSON reply means the endpoint is healthy.

Terminal
bash
curl -sS https://openllmbuddy-proxy.botbuddytech.workers.dev/v1/chat/completions   -H "Authorization: Bearer YOUR_API_KEY"   -H "Content-Type: application/json"   -d '{"model": "gemma4:26b", "messages": [{"role": "user", "content": "Reply with OK"}], "max_tokens": 16}'

Troubleshooting

  • Plain ChatOpenAI ignores the URL — use the Custom variant, which has the BasePath field.
  • Flows built on the Responses API — the endpoint serves chat completions only. Keep nodes on the chat completions path.
  • 401 or 403 — the API key is wrong, revoked, or missing the Bearer prefix. Create a fresh key in the console.
  • 404 on /chat/completions — the base URL must end in /v1, with no trailing /chat/completions and no extra path.
  • Model not found — the model id must match your deployment exactly. Run the curl test and copy the id you used.
  • Timeouts on the first request — a GPU that was idle may still be loading the model. Retry after a minute.
  • Connection refused from Docker or a remote host — use the public HTTPS base URL, never localhost.

Connection details

Use these values wherever Flowise asks for an OpenAI-compatible provider.

Reference
text
Base URL:  https://openllmbuddy-proxy.botbuddytech.workers.dev/v1
Chat URL:  https://openllmbuddy-proxy.botbuddytech.workers.dev/v1/chat/completions
API key:   your key from the console
Model id:  gemma4:26b