LinerInstall

Summary

Generate a grounded AI-powered answer using Liner's deeper search coverage by providing either a single user question or a full conversation history in JSON format. Optionally specify language, model, search mode (general or scholar), and whether to include raw streaming events.

Inputs

• Language — Optional language code (e.g., 'en', 'ko', 'ja') to localize the AI search.
• Input (required) — Choose between providing a single user question or a full Liner messages array as conversation history.
• Question (required) — The user question to send if 'Input' is set to 'Question' mode.
• Messages JSON (required) — A JSON array of message objects with 'role' and 'content', representing the conversation history; the last message must have role 'user'. Used if 'Input' is set to 'Messages JSON' mode.
• Model — Optional AI model identifier; leave empty to use Liner's default model.
• Search Mode (required) — Select between 'General' web search or 'Scholar' search to influence the AI search scope.
• Include Raw Events — Boolean flag to include raw server-sent event envelopes in the output for streaming responses.
• Request ID — Optional client-supplied identifier echoed by Liner for request tracking.

Output shape

a single JSON object

Returns a JSON object representing the AI-generated answer with source-backed information. If 'Include Raw Events' is enabled, the response also includes the raw server-sent events received. In case of errors during streaming, an error is thrown. Pagination is not applicable.

Links

• n8n community nodes installation guide