Search the source datasheet of an extraction
datasheetvend_search_documentFind where the source datasheet behind an extraction job says something: every text token containing the term, with its page and its box on the page in PDF points. Use it to check an extracted value against the document, or to find the page to read with datasheetvend_read_document_page. Counts are honest: total_hits with hits_returned, a per-page cap of 20 stated with dropped_hits, and fetch_truncated when the database fetch stopped at its cap. A token is one line of text, so a phrase across lines may not match. Three different refusals: DOCUMENT_MAP_UNAVAILABLE (this job has no document map), DOCUMENT_MAP_EXPIRED (the map passed its retention window: no hits does NOT mean the term is absent) and, for a real answer, zero hits. Deterministic: reads the stored document map, calls no model and extracts nothing. Costs no credits. Needs a DatasheetVend API key; readable jobs are your own, your workspace's TEAM-shared jobs and PUBLIC jobs, as on the REST API.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"job_id": "<job_id>",
"query": "<query>"
},
"name": "datasheetvend_search_document"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | The term to find, 2-128 characters, for example 'VDDIO' or 'Absolute Maximum'. | |
| job_id | Yes | An extraction job in your account (or shared with it). | |
| max_hits | No | Hits to return, in page order. Default 50, at most 300. |