Skip to content
GOCUX
Documentation
GOCUX / Documentationsearch

Make document search useful

Improve the evidence quality of a search workflow before increasing retrieval volume.

Improve the evidence quality of a search workflow before increasing retrieval volume.

Practical procedure

  1. Name sources by their purpose and keep document titles recognizable. Preserve dates and version context inside extracted text so a hit can be interpreted without guessing.
  2. Ask one question at a time and compare short lexical queries with a natural-language version. Record passages that appear relevant but do not actually answer the question.
  3. Review source coverage before writing a negative conclusion. Report that the selected documents contain no supporting passage rather than claiming the information does not exist anywhere.

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

A passage can match the query and still refer to the wrong version, entity or effective date. Source relevance and claim support are separate judgments.

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.

Bring this workflow into your workspace.

Set the scope. Review the evidence. Approve the steps that need it.

Open the workspace

Keep exploring