Sign in

v52

latestOpenAPI 3.0.3raw.githubusercontent.com2026-08-0393116227.2 KB
extract

Data extraction

Performs data extraction using LLM based on the specified data source, filter conditions, and JSON schema. Retrieves chunked data and uses the schema to extract and return the result as JSON via LLM.

Required roles: All, App

post/extract

Request body

tagsstring[]
tag_idsstring[]
tag_filter_logic'AND' | 'OR'

Logical operator for combining filter conditions

source_typesSourceType[]
file_typesFileType[]
date_frominteger

Start date for content search (Unix timestamp in seconds)

date_tointeger

End date for content search (Unix timestamp in seconds)

domainsstring[]
use_postfilterboolean

Whether to bypass LanceDB prefilter and apply WHERE after the vector search (IVF_PQ) returns top-K. Significantly faster for broad filters that cover most of the table, but may return fewer than limit results when the hit rate is low.

limitinteger
offsetinteger
authz_policystring

(reserved for future use) Name of the registered authz policy to evaluate when retrieving content. Defaults to the reserved "default" policy when omitted. Ignored when authz is disabled.

principal_idstring

Identifier of the end-user (principal) on whose behalf this request is made. Used to look up the principal's authz subject attributes for policy evaluation. When omitted, subject attributes are empty (most restrictive). Ignored when authz is disabled.

schemaobject required

JSON Schema for the data to be extracted.

promptstring

Additional prompt for the LLM (optional, if not specified, a default prompt in Japanese will be used).

use_relatedboolean

Whether to search for and use related content

Response

Successful extraction

createdinteger required

抽出実行時刻（Unix timestamp）

resultExtractResult required

Extraction result as a JSON object conforming to the provided schema.