Control retrieval breadth using the parameters that GoCux actually accepts.
Practical procedure
- Supply projectId explicitly and express the question as a concise query. Include distinctive names, terms or dates from the corpus when a broad phrase returns unrelated passages.
- Start with limit 10 and expand only when reviewing more evidence will help. Split unrelated questions into separate queries instead of concatenating them into a large prompt.
- Inspect which source each hit belongs to and compare multiple passages before concluding that a term is absent. Use a research source allowlist when evidence scope must be fixed for a plan.
Search the project corpus
Knowledge holds document text and provenance inside a project. Create a source, upload a document into that source, and inspect the extracted text before relying on a search result. Full-text retrieval is available after ingestion; semantic retrieval contributes when the embedding configuration and backfill are available. This operation searches the uploaded corpus, rather than fetching arbitrary web pages.
Contract example
Developer examples below describe routes on an authorized, configured GoCux control-plane base URL. They are request shapes or operation references, not claims that a particular public hostname exposes the API. Use the workspace for the corresponding human workflow; availability and permissions depend on the actual deployment.
POST /knowledge/search — example request body
{
"projectId": "project-id",
"query": "renewal conditions effective date",
"limit": 10
}Inspect the result
The response contains the query and a hits array. Use the returned chunk provenance to trace each hit to its document and source. Compare the actual passage with the question before treating it as evidence. Search ranking helps find material; it does not itself establish that a claim is correct.
What to keep explicit
This endpoint does not accept arbitrary web-search modes, domain filters or fetch parameters. Sending unsupported fields is different from choosing a broader search objective.
Handle incomplete and refused work
projectId must identify an existing project; the query is 1–1,000 characters and limit is 1–50, default 10. An empty hits array is a valid result. A 503 is an unavailable store and must remain visibly different from an empty result. Semantic unavailability must not be described as a complete search outage when full-text search still works.
Continue with related guides
Bring this workflow into your workspace.
Set the scope. Review the evidence. Approve the steps that need it.