LM Studio Simple Message
AI-generatedSummary
Send a user message to a specified LM Studio model and receive a generated response, optionally enforcing output structure with a JSON schema.
Inputs
- Model Name or ID (required) — Select or specify the identifier of the model to use, fetched dynamically from your LM Studio server.
- Message (required) — The text message to send as user input to the selected model.
- JSON Schema — Optional JSON schema to enforce a structured output format from the model. Use an empty object '{}' for no schema.
- Temperature — Number between 0 and 2 controlling output randomness; lower values produce more deterministic responses.
- Max Tokens — Maximum tokens the model can generate. Leave blank to use the model's default limit.
- Timeout (Seconds) — Maximum time to wait for the model's response, in seconds. Set 0 for no timeout.
Output shape
A list of items each containing a JSON object with the model's response under 'response' and metadata about the request under '_metadata'.
If a JSON schema is provided, the response is parsed and validated against it; otherwise, the response is raw text. Errors produce node execution failure unless 'Continue On Fail' is enabled, in which case an error message is returned for that item.