Understand why a query can work before semantic embeddings are available.
Practical procedure
- Use a distinctive phrase from an imported document to establish that full-text retrieval can find the expected content.
- Try a paraphrase of that phrase and inspect the evidence returned. Semantic contributions depend on configured embeddings and backfill, so compare actual results rather than assuming a particular ranking mode.
- Keep both exact-term and paraphrase questions in a small regression set. Reevaluate when corpus contents or retrieval configuration changes.
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
Full-text availability and semantic availability are different observations. Do not label a deployment as incapable of search solely because embedding configuration is absent.
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.