Skip to main content

Search and semantic search

What this page is — the two ways the repository finds documents: keyword search over structured data, and semantic search over the meaning of indexed text — and the index that decides what semantic search can see.

What it is for — so a document can be found by what it is about, not only by what somebody happened to call it.

The problem it solves — a badly named document is a lost document, however relevant its content.

Route: /org/papers/repository · Permissions: View this project's documents. for keyword search; Use AI drafting/extraction/Q&A for documents. for the Semantic toggle.


1. What it is​

The two searches read different data, which is the thing to understand first:

KeywordSemantic
ReadsTitle, document number, field valuesPassages of the rendered document, from the index
Documents coveredEvery document in scope, including draftsOnly indexed documents
MatchingPostgres full-text, English word stems — "payments" finds "payment"Meaning, combined with a full-text leg
RunsAs you typeOn Enter
ResultDocument rows, filterable and selectablePassage cards — the same document can appear several times
Filters and bulk barAvailableHidden while the toggle is on

Keyword search does not read the document's wording. A phrase that appears only in a template clause — not in a field — is invisible to it. Neither search reads attachments.

What is indexed. A document is indexed automatically when it is finalized, and on demand with Reindex. Drafts are not indexed, so a young project may have only a fraction of its documents searchable by meaning.


2. Why you would use it​

  • The title is the author's word, not yours. Semantic search for termination for convenience also finds "either party may end this agreement on thirty days' notice".
  • Keyword search is exact and immediate for numbers, party names and field values.
  • Passages, not files. A semantic result shows the section and page where the idea lives, so you land on the paragraph.
  • Both respect access. Two colleagues can run the same search and get different results — correctly.

3. How the index works​

StepDetail
TriggerFinalize, or Reindex on the row
SourceThe rendered document
ChunkingSplit at section headings, then into passages of about 700 characters with overlap; each passage keeps its full section as context
RetrievalA dense (meaning) search and a sparse (full-text) search, fused
Stored per passageSection heading, page, text

Editing a finalized document's content without re-finalizing leaves the index on the old wording until someone presses Reindex.


4. Step by step​

Keyword — type in the search box; results update after a short pause, best match first.

Semantic

  1. Turn on Semantic.
  2. Describe what you are looking for in plain language.
  3. Press Enter.
  4. Click a result card to open the document.

Turning the toggle off restores the keyword list exactly as it was.


5. Field reference​

Semantic result card​

ElementMeans
Document titleWhere the passage comes from
Section headingThe section it sits in
Page badgeThe page
% matchSimilarity — higher is closer
PassageThe matched text

States and messages​

MessageMeans
Semantic search start cardNothing searched yet — describe, then Enter
No matchesNothing close enough — rephrase as a description, not keywords or operators
Red errorCredits, permission or a server problem. Keyword search still works
Failed to search documentsThe keyword request failed; the list keeps its previous rows

Keyword filters​

State, Family, Tag and the selected folder combine with the search (AND). Changing any of them returns to page 1 and clears the selection.


6. Worked example​

A commercial lead needs every agreement in which the company promised service credits for downtime.

Keyword service credit returns 2 documents — both have a field named Service credits. The MSA template at Contoso phrases it "the Supplier shall reduce the monthly fee by 5% for each hour of unavailability", in a clause, not a field. Keyword search cannot see it.

Semantic with "agreements where we owe the customer money when the service is down" → Enter. Seven cards, including MSA — Contoso Ltd · Service Levels · Page 12 · 84% match with the fee-reduction sentence quoted, and a second card from the same MSA's schedule.

One MSA the lead knows about is missing. It is still a draft — never finalized, so never indexed. They finalize it later that week; it appears on the next search.


7. The admin contract​

Must be trueWhereWhat breaks without it
The role holds Use AI drafting/extraction/Q&A for documents.Role editorNo Semantic toggle
A platform embedding model is configuredOrbit AI FlowSemantic search falls back to its full-text leg only
Documents are finalized, or reindexedLifecycle, RepositoryThey are invisible to semantic search
Important terms are captured as fieldsFieldsKeyword search cannot find them

8. Downstream​

When…Then
A document is finalizedIt becomes semantically searchable
You press ReindexIts passages are rebuilt from the current content
A field value changesKeyword search sees it at once; the index does not until reindexed

9. Don't confuse this with…​

Ask the repositoryAnswers a question from the same index
Documents list searchTitle and number, newest 500 only
Knowledge graphEntities, not passages
Portfolio InsightsReads captured fields and obligations

10. Troubleshooting​

SymptomCause
A phrase you can see in the document is not found by keywordIt is template wording, not a field value — use semantic
A document is missing from semantic resultsIt is a draft, or was changed after indexing — Reindex
Filters disappearedThe Semantic toggle is on
The same document appears several timesSeveral passages matched
Semantic returns nothing usefulThe wording is too far from anything indexed, or few documents are indexed