Connect Langflow to OpenLLM Buddy

Connect Langflow to OpenLLM Buddy by setting a custom OpenAI API base on the OpenAI model component in your flows.

No-code, automation & home · Integration guide

What is Langflow?

Langflow is a visual framework for building and deploying agents and RAG flows, with components you wire together and export as an API. Visit Langflow.

Why connect OpenLLM Buddy?

Langflow's OpenAI model component can override the API base, so a flow runs on OpenLLM Buddy and can still be exposed as its own API or MCP server.

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

Add the OpenAI component

Create a flow and drag an OpenAI model component onto the canvas.

2

Override the base and model

Open the component's fields. Show Advanced options if the base URL field is hidden.

  • OpenAI API Base: https://openllmbuddy-proxy.botbuddytech.workers.dev/v1
  • OpenAI API Key: your OpenLLM Buddy key (store it as a Langflow global variable).
  • Model Name: gemma4:26b

Wire the component's output into an Agent or Prompt chain, then use the Playground to test.

3

Test the endpoint with curl

Confirm the key, URL, and model id work before debugging Langflow. 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

  • Model dropdown limits the choice — type the model id directly when the field accepts free text, or use an advanced option that allows a custom name.
  • Key rejected — confirm the global variable holds the key without quotes or extra whitespace.
  • 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 Langflow 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