Skip to main content
PATCH

Authorizations

Authorization
string
header
required

Use Authorization: Bearer

Path Parameters

project_id
string<uuid>
required

UUID of the project

extractor_id
string<uuid>
required

UUID of the extractor

Body

application/json

Extracts structured data (instances of a Pydantic model) from chunks or blocks of documents.

name
string

Human-readable name.

Example:

"Contract clauses"

brief
string

Short description shown in the UI.

Example:

"Extract obligations and effective dates from contracts."

llm_model
string
Example:

"gpt-4o"

extractable_object
string | null

Display name of the object class (auto-derived from extractable_pydantic_class if omitted).

Example:

"ContractClause"

extractable_pydantic_class
string

Python source of the Pydantic model used as the extraction schema.

Example:

"from pydantic import BaseModel\nfrom typing import Optional\n\nclass ContractClause(BaseModel):\n clause_type: str\n text: str\n effective_date: Optional[str] = None\n"

extraction_prompt
string
Example:

"Extract every distinct contractual obligation as a separate ContractClause object."

document_ids
string<uuid>[]

Documents to extract from. Empty array means "all documents in the project".

Example:
document_ranges
object | null

Optional per-document page-range filter ({document_id: [start_page, end_page]}).

compute_alerts
boolean
default:false
Example:

false

add_anchoring_object
boolean
default:false
Example:

true

filtered_on_block_types
boolean | null
block_types
string[] | null
Example:
extract_single_object
boolean
default:false
block_grouping_config
object | null
pre_execution_filter
object | null

Filter applied to the source chunks/blocks before extraction runs.

alerts_additional_instructions
string | null
alerts_llm_model
string | null
extraction_mode
enum<string>
default:standard
Available options:
standard,
agentic
agentic_config
object | null

Configuration for agentic extraction mode.

import_mode
boolean
default:false
write-only

Bulk-import flag. When true, the create endpoint skips auto-version creation.

set_latest_as_default
boolean
write-only

When true and a new version is created by this update, mark it as the default version.

Response

Updated. A new version may have been created — inspect versions[] to confirm.

Extracts structured data (instances of a Pydantic model) from chunks or blocks of documents.

id
string<uuid>
read-only
name
string

Human-readable name.

Example:

"Contract clauses"

brief
string

Short description shown in the UI.

Example:

"Extract obligations and effective dates from contracts."

llm_model
string
Example:

"gpt-4o"

extractable_object
string | null

Display name of the object class (auto-derived from extractable_pydantic_class if omitted).

Example:

"ContractClause"

extractable_pydantic_class
string

Python source of the Pydantic model used as the extraction schema.

Example:

"from pydantic import BaseModel\nfrom typing import Optional\n\nclass ContractClause(BaseModel):\n clause_type: str\n text: str\n effective_date: Optional[str] = None\n"

extraction_prompt
string
Example:

"Extract every distinct contractual obligation as a separate ContractClause object."

document_ids
string<uuid>[]

Documents to extract from. Empty array means "all documents in the project".

Example:
document_ranges
object | null

Optional per-document page-range filter ({document_id: [start_page, end_page]}).

compute_alerts
boolean
default:false
Example:

false

add_anchoring_object
boolean
default:false
Example:

true

filtered_on_block_types
boolean | null
block_types
string[] | null
Example:
extract_single_object
boolean
default:false
block_grouping_config
object | null
pre_execution_filter
object | null

Filter applied to the source chunks/blocks before extraction runs.

alerts_additional_instructions
string | null
alerts_llm_model
string | null
extraction_mode
enum<string>
default:standard
Available options:
standard,
agentic
agentic_config
object | null

Configuration for agentic extraction mode.

created_at
string<date-time>
read-only
updated_at
string<date-time>
read-only
prompt_generation_status
string | null
read-only
deployed_extractable_pydantic_class
string | null
read-only
deployed_extraction_prompt
string | null
read-only
deployed_llm_model
string | null
read-only
extracted_objects_table
string<uuid> | null
read-only

ID of the warehouse Table where extracted objects are stored.

alerts_table
string<uuid> | null
read-only
object_name
string
read-only
blocks_table_version_info
object | null
read-only
chunks_table_version_info
object | null
read-only
table_version_updates
object | null
read-only
versions
object[]
read-only
default_version
object | null

Immutable snapshot of an ObjectExtractor's version-bearing configuration. New version rows are created automatically on PATCH when any of these fields differs from the latest version.

latest_version
object | null

Immutable snapshot of an ObjectExtractor's version-bearing configuration. New version rows are created automatically on PATCH when any of these fields differs from the latest version.