{"componentChunkName":"component---src-templates-simple-markdown-js","path":"/docs/ai/document-ai/semantic-search/","matchPath":"","result":{"data":{"markdownRemark":{"html":"

Search

\n

Document AI search finds processed content by meaning, exact terms, identifiers, and common spelling variations.

\n

Search returns page-level matches so users can open the most relevant location in a document.

\n

Prerequisite

\n

A document must be processed with embed: true before its content is available to semantic search.

\n

If a document does not appear:

\n
    \n
  1. \nConfirm its latest applicable run completed.\n
    2. \n
  2. \nConfirm the selected processing configuration enabled embeddings.\n
    3. \n
  3. \nCreate a new run with embeddings enabled if needed.\n
    4. \n
\n

Search in Shipwell

\n
    \n
  1. \nOpen \nDocument AI\n.\n
    2. \n
  2. \nEnter a phrase, identifier, party name, or document concept in search.\n
    3. \n
  3. \nApply filters if needed.\n
    4. \n
  4. \nOpen a result to review the matched page.\n
    5. \n
\n\n

Useful searches include:

\n\n

Search through the API

\n

Use one or more q parameters:

\n\n
\n
\n curlpython\n
\n
\n
\n
" \\\\\n --data-urlencode "q=proof of delivery for SW-1001" \\\\\n --data-urlencode "page=1" \\\\\n --data-urlencode "page_size=25"`, `71336983350040550000`)\"\n >\n
Copy
\n
Copied
\n
\n 
curl --get \\\n  "https://sandbox-api.shipwell.com/document-store/documents:search" \\\n  -H "Authorization: Token <user-token>" \\\n  --data-urlencode "q=proof of delivery for SW-1001" \\\n  --data-urlencode "page=1" \\\n  --data-urlencode "page_size=25"
\n
\n
"},\n params={\n "q": "proof of delivery for SW-1001",\n "page": 1,\n "page_size": 25,\n },\n timeout=30,\n)\nresponse.raise_for_status()\nresults = response.json()`, `79063400136142010000`)\"\n >\n
Copy
\n
Copied
\n
\n 
import requests\n\nresponse = requests.get(\n    \"https://sandbox-api.shipwell.com/document-store/documents:search\",\n    headers={\"Authorization\": \"Token <user-token>\"},\n    params={\n        \"q\": \"proof of delivery for SW-1001\",\n        \"page\": 1,\n        \"page_size\": 25,\n    },\n    timeout=30,\n)\nresponse.raise_for_status()\nresults = response.json()
\n
\n
\n \n

The response includes:

\n\n

A hit includes:

\n\n

Use document_id, result_id, and page_number to open or inspect the matching source page.

\n

Filter results

\n

Available filters include:

\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
ParameterUse
document_idSearch within one document.
content_typeRestrict results to a MIME type.
entity_typeRestrict results by association type. Repeat to include multiple values.
entity_idRestrict results by association identifier. Repeat to include multiple values.
statusRestrict results by document status. Repeat to include multiple values.
document_typeRestrict results by detected document type. Repeat to include multiple values.
\n

For example, use entity_type=shipment and entity_id=SW-1001 to search documents associated with one shipment.

\n

Multiple query variants

\n

Repeat q to submit up to eight alternative descriptions:

\n
\n
\n
Copy
\n
Copied
\n
\n 
?q=proof+of+delivery&q=delivery+receipt&q=signed+POD
\n
\n

Variants are useful when your application knows domain-specific alternatives. Put the user's original query first.

\n

Relevance controls

\n\n

Start with the defaults. Tune thresholds only after evaluating representative searches; high thresholds can remove useful results.

\n

Pagination

\n\n

Search safety

\n

Search results are evidence, not a final business decision. Before automating a high-impact action:

\n
    \n
  1. \nRetrieve the matching document and page.\n
    2. \n
  2. \nVerify the relevant extracted value or source text.\n
    3. \n
  3. \nApply your workflow's validation and authorization rules.\n
    4. \n
","headings":[{"value":"Search","depth":1},{"value":"Prerequisite","depth":2},{"value":"Search in Shipwell","depth":2},{"value":"Search through the API","depth":2},{"value":"Filter results","depth":2},{"value":"Multiple query variants","depth":2},{"value":"Relevance controls","depth":2},{"value":"Pagination","depth":2},{"value":"Search safety","depth":2}]},"contentItem":{"data":{"lastModified":"2026-07-17T16:00:10.000Z","enableToc":null,"disableLastModified":null,"tocMaxDepth":null,"requestLogin":false}},"siteConfig":{"enableToc":true,"disableLastModified":false,"tocMaxDepth":4}},"pageContext":{"matchPath":"","id":"2f23a3ac-4c3a-5779-8ab5-2284b8845ef0__redocly content/docs/ai/document-ai/semantic-search/","seo":{"title":"Search","description":null,"image":"","keywords":null,"jsonLd":null,"lang":null,"siteUrl":null},"pageId":"docs/ai/document-ai/semantic-search.md","pageBaseUrl":"/docs/ai/document-ai/semantic-search","type":"markdown","toc":{"enable":true,"maxDepth":4,"headings":[{"depth":1,"value":"Search","id":"search"},{"depth":2,"value":"Prerequisite","id":"prerequisite"},{"depth":2,"value":"Search in Shipwell","id":"search-in-shipwell"},{"depth":2,"value":"Search through the API","id":"search-through-the-api"},{"depth":2,"value":"Filter results","id":"filter-results"},{"depth":2,"value":"Multiple query variants","id":"multiple-query-variants"},{"depth":2,"value":"Relevance controls","id":"relevance-controls"},{"depth":2,"value":"Pagination","id":"pagination"},{"depth":2,"value":"Search safety","id":"search-safety"}]},"data":{"title":"Search"},"catalogInfo":null,"link":"/docs/ai/document-ai/semantic-search/","sidebarName":"developerPortal","isLanding":false,"showPrevButton":null,"showNextButton":null,"apiVersions":null,"apiVersionId":null,"isDefaultApiVersion":null}},"staticQueryHashes":["1123603147","1302185487","1344209882","1398840060","1520077861","1975142765","2667623876","2950305614","3240152602","3743992808","561138138"]}