pAIring connectors
A connector lets pAIring send chat requests to an engine that runs on a cloud GPU service, instead of a local Ollama or Matricxon. It is useful when you need a large model your own hardware cannot hold.
Admins open Connectors from the sidebar. Each connector is a card. Click it to open its settings.
Set one up
Section titled “Set one up”- Open the connector’s card and fill in its fields.
- Press Save.
- Press Test connection. It must pass before the connector can be used. Run it again after any change.
- Switch the connector on.
- Open Admin settings → External servers and pick it as the active engine.
Secret fields, such as API keys, are stored encrypted and are not shown again.
RunPod Serverless
Section titled “RunPod Serverless”Today there is one connector, for RunPod Serverless. It talks to a RunPod endpoint that runs the vLLM worker, which offers an OpenAI-compatible API. pAIring calls your endpoint directly. Nothing extra runs locally.
| Field | What to enter |
|---|---|
| Endpoint ID | From your endpoint’s URL in the RunPod console |
| API key | A RunPod API key with access to that endpoint |
| Model name | The model your endpoint serves. Used when the model list cannot be read live |
Before you start, deploy the endpoint in RunPod with the vLLM worker template and the model you want.
What works
Section titled “What works”- Streaming chat, with your generation settings. Temperature, Top-P, Top-K, repeat penalty and reply length are passed to vLLM.
- Chat titles and other short internal requests.
What does not
Section titled “What does not”- Embeddings. The knowledge base needs a local engine for them.
- Model management. Models are managed in RunPod, so the Hugging Face browser is hidden while a connector is active.