NEURA Knowledge icon

NEURA Knowledge

Search and interact with NEURA enterprise knowledge base

Actions4

RAG Search → Search With Context

AI-generated

Summary

Searches the NEURA knowledge base and returns formatted context with citations for use in a downstream LLM or workflow step. The operation sends the query and retrieval settings to the search-with-tool endpoint, using the configured Nextcloud login as the user email.

Inputs

  • Query (required) — Search query for the knowledge base.
  • Top K — Maximum number of results requested; defaults to 20.
  • Options: Chat ID — Chat ID passed for Redis memory management and refinement.
  • Options: Conversation History — JSON array of previous queries to provide as context; defaults to an empty array. Invalid JSON is ignored.
  • Options: Enable Multi-Query — Enables multi-query decomposition; defaults to true.
  • Options: Max Sub Queries — Maximum generated sub-queries when multi-query is enabled; defaults to 3.
  • Options: BM25 Weight — Hybrid retrieval BM25 weight from 0 to 1; defaults to 0.4.
  • Options: Uploaded File IDs — JSON array of OpenWebUI uploaded file IDs to include; defaults to an empty array. Invalid JSON is ignored.

Output shape

A single item containing a JSON object with context, citations, status_message, and metadata.

The operation returns these fields from the search-with-tool endpoint. Although Doc Type Filter and Include Hierarchy appear in the shared properties, this operation does not send them in its request.

Links

Discussion