Workspaces

Locate information

Other errors (500, 502, 503, 504) are on Errors.

POST
/v1/workspaces/{id}/tools/locate

Other errors (500, 502, 503, 504) are on Errors.

Authorization

bearerAuth
AuthorizationBearer <token>

Your API key, sent as Authorization: Bearer nace_sk_...

  • Where: the dashboard's API Keys page. It is shown once, when you create it.
  • Format: nace_sk_ followed by 43 URL-safe characters (A-Z, a-z, 0-9, _ and -).
  • Limit: an account can hold at most 3 active keys.
  • Wrong or missing key: returns 401 authentication_error.

In: header

Path Parameters

idstringrequired

The workspace's workspace_id.

Header Parameters

Idempotency-Keystring

Up to 200 characters, unique per account. A call that timed out keeps running: send it again with the same key and body to get its answer instead of running it twice.

Lengthlength <= 200

Request Body

application/json

needstringrequired

What is still needed, in a few words: a year, an entity, a line item, a definition.

Length1 <= length <= 400
questionstring

The whole question the need is part of; every decision weighs the need within it. Leave it out and the need is the whole question.

Length1 <= length <= 4096
kinteger

How many pieces to name.

Range1 <= value <= 24
Default12
everyboolean

The need names a kind of file and every one is wanted (each invoice, every statement): the model rates each file of that kind and lists the members in population.

Defaultfalse
path_prefixstring

Only files under this folder; paths adds files. Leave both out for the whole workspace.

pathsarray<string>

Only these files (with path_prefix, its folder's files too). An unknown path, or one the key can't read, is refused.

Items1 <= items
excludearray<Offered piece>

Pieces earlier locates offered, left out of this answer.

Itemsitems <= 1000
Show child attributes
already_readarray<Read done>

Reads already done: their pieces are left out, and the model is told they did not settle the need.

Itemsitems <= 1000
Show child attributes
pointerboolean

Name every page in text by its opening lines only. Leave it out and the best pages come in full, as a task's first locate wants them; a task's later locates send it, so page text does not pile up in an agent's context.

Defaultfalse

Response Body

application/json

application/json

application/json

application/json

application/json

application/json

curl -X POST "https://example.com/v1/workspaces/string/tools/locate" \  -H "Content-Type: application/json" \  -d '{    "need": "total liabilities at year end 2024",    "question": "How did total liabilities change from 2023 to 2024?"  }'
{  "text": "string",  "pages": [    {      "path": "string",      "component": "string",      "paged": true,      "number": 0,      "line_start": 0,      "line_end": 0,      "score": 0,      "head": "string"    }  ],  "tables": [    {      "sql_table": "string",      "path": "string",      "tab": "string",      "score": 0,      "columns": [        "string"      ],      "relevant_columns": [        "string"      ]    }  ],  "population": [    {      "path": "string",      "score": 0    }  ],  "population_unrated": 0,  "job_id": "string"}