Create object extractor

import requests

url = "https://eu.app.clarifeye.ai/api/v1/projects/{project_id}/object-extractors/"

payload = {
    "name": "Contract clauses",
    "brief": "Extract obligations and effective dates from contracts.",
    "llm_model": "gpt-4o",
    "extractable_pydantic_class": "from pydantic import BaseModel
from typing import Optional

class ContractClause(BaseModel):
    clause_type: str
    text: str
    effective_date: Optional[str] = None
",
    "extraction_prompt": "Extract every distinct contractual obligation as a separate ContractClause object.",
    "document_ids": [],
    "add_anchoring_object": True,
    "extract_single_object": False,
    "compute_alerts": False,
    "extraction_mode": "standard"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    name: 'Contract clauses',
    brief: 'Extract obligations and effective dates from contracts.',
    llm_model: 'gpt-4o',
    extractable_pydantic_class: '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: 'Extract every distinct contractual obligation as a separate ContractClause object.',
    document_ids: [],
    add_anchoring_object: true,
    extract_single_object: false,
    compute_alerts: false,
    extraction_mode: 'standard'
  })
};

fetch('https://eu.app.clarifeye.ai/api/v1/projects/{project_id}/object-extractors/', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

curl --request POST \
  --url https://eu.app.clarifeye.ai/api/v1/projects/{project_id}/object-extractors/ \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "Contract clauses",
  "brief": "Extract obligations and effective dates from contracts.",
  "llm_model": "gpt-4o",
  "extractable_pydantic_class": "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": "Extract every distinct contractual obligation as a separate ContractClause object.",
  "document_ids": [],
  "add_anchoring_object": true,
  "extract_single_object": false,
  "compute_alerts": false,
  "extraction_mode": "standard"
}
'

{
  "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "name": "Contract clauses",
  "brief": "Extract obligations and effective dates from contracts.",
  "llm_model": "gpt-4o",
  "extractable_object": "ContractClause",
  "extractable_pydantic_class": "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": "Extract every distinct contractual obligation as a separate ContractClause object.",
  "document_ids": [
    "b3c1d2e4-5f6a-4b7c-8d9e-0a1b2c3d4e5f"
  ],
  "document_ranges": {},
  "compute_alerts": false,
  "add_anchoring_object": true,
  "filtered_on_block_types": true,
  "block_types": [
    "text",
    "table"
  ],
  "extract_single_object": false,
  "block_grouping_config": {},
  "pre_execution_filter": {},
  "alerts_additional_instructions": "<string>",
  "alerts_llm_model": "<string>",
  "extraction_mode": "standard",
  "agentic_config": {},
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "prompt_generation_status": "<string>",
  "deployed_extractable_pydantic_class": "<string>",
  "deployed_extraction_prompt": "<string>",
  "deployed_llm_model": "<string>",
  "extracted_objects_table": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "alerts_table": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "object_name": "<string>",
  "blocks_table_version_info": {},
  "chunks_table_version_info": {},
  "table_version_updates": {},
  "versions": [
    {
      "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
      "name": "<string>",
      "created_at": "2023-11-07T05:31:56Z",
      "updated_at": "2023-11-07T05:31:56Z",
      "is_default": true,
      "extractable_pydantic_class": "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": "Extract every distinct contractual obligation as a separate ContractClause object.",
      "llm_model": "gpt-4o",
      "add_anchoring_object": true,
      "filtered_on_block_types": true,
      "block_types": [
        "text",
        "table"
      ],
      "extract_single_object": false,
      "block_grouping_config": {},
      "alerts_additional_instructions": "<string>",
      "extraction_mode": "standard",
      "agentic_config": {}
    }
  ],
  "default_version": {
    "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "name": "<string>",
    "created_at": "2023-11-07T05:31:56Z",
    "updated_at": "2023-11-07T05:31:56Z",
    "is_default": true,
    "extractable_pydantic_class": "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": "Extract every distinct contractual obligation as a separate ContractClause object.",
    "llm_model": "gpt-4o",
    "add_anchoring_object": true,
    "filtered_on_block_types": true,
    "block_types": [
      "text",
      "table"
    ],
    "extract_single_object": false,
    "block_grouping_config": {},
    "alerts_additional_instructions": "<string>",
    "extraction_mode": "standard",
    "agentic_config": {}
  },
  "latest_version": {
    "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "name": "<string>",
    "created_at": "2023-11-07T05:31:56Z",
    "updated_at": "2023-11-07T05:31:56Z",
    "is_default": true,
    "extractable_pydantic_class": "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": "Extract every distinct contractual obligation as a separate ContractClause object.",
    "llm_model": "gpt-4o",
    "add_anchoring_object": true,
    "filtered_on_block_types": true,
    "block_types": [
      "text",
      "table"
    ],
    "extract_single_object": false,
    "block_grouping_config": {},
    "alerts_additional_instructions": "<string>",
    "extraction_mode": "standard",
    "agentic_config": {}
  }
}

{
  "error": "User not found"
}

{
  "error": "Authentication credentials were not provided."
}

{
  "error": "You do not have permission to perform this action."
}

POST

projects

{project_id}

object-extractors

Create object extractor

import requests

url = "https://eu.app.clarifeye.ai/api/v1/projects/{project_id}/object-extractors/"

payload = {
    "name": "Contract clauses",
    "brief": "Extract obligations and effective dates from contracts.",
    "llm_model": "gpt-4o",
    "extractable_pydantic_class": "from pydantic import BaseModel
from typing import Optional

class ContractClause(BaseModel):
    clause_type: str
    text: str
    effective_date: Optional[str] = None
",
    "extraction_prompt": "Extract every distinct contractual obligation as a separate ContractClause object.",
    "document_ids": [],
    "add_anchoring_object": True,
    "extract_single_object": False,
    "compute_alerts": False,
    "extraction_mode": "standard"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    name: 'Contract clauses',
    brief: 'Extract obligations and effective dates from contracts.',
    llm_model: 'gpt-4o',
    extractable_pydantic_class: '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: 'Extract every distinct contractual obligation as a separate ContractClause object.',
    document_ids: [],
    add_anchoring_object: true,
    extract_single_object: false,
    compute_alerts: false,
    extraction_mode: 'standard'
  })
};

fetch('https://eu.app.clarifeye.ai/api/v1/projects/{project_id}/object-extractors/', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

curl --request POST \
  --url https://eu.app.clarifeye.ai/api/v1/projects/{project_id}/object-extractors/ \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "Contract clauses",
  "brief": "Extract obligations and effective dates from contracts.",
  "llm_model": "gpt-4o",
  "extractable_pydantic_class": "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": "Extract every distinct contractual obligation as a separate ContractClause object.",
  "document_ids": [],
  "add_anchoring_object": true,
  "extract_single_object": false,
  "compute_alerts": false,
  "extraction_mode": "standard"
}
'

{
  "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "name": "Contract clauses",
  "brief": "Extract obligations and effective dates from contracts.",
  "llm_model": "gpt-4o",
  "extractable_object": "ContractClause",
  "extractable_pydantic_class": "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": "Extract every distinct contractual obligation as a separate ContractClause object.",
  "document_ids": [
    "b3c1d2e4-5f6a-4b7c-8d9e-0a1b2c3d4e5f"
  ],
  "document_ranges": {},
  "compute_alerts": false,
  "add_anchoring_object": true,
  "filtered_on_block_types": true,
  "block_types": [
    "text",
    "table"
  ],
  "extract_single_object": false,
  "block_grouping_config": {},
  "pre_execution_filter": {},
  "alerts_additional_instructions": "<string>",
  "alerts_llm_model": "<string>",
  "extraction_mode": "standard",
  "agentic_config": {},
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "prompt_generation_status": "<string>",
  "deployed_extractable_pydantic_class": "<string>",
  "deployed_extraction_prompt": "<string>",
  "deployed_llm_model": "<string>",
  "extracted_objects_table": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "alerts_table": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "object_name": "<string>",
  "blocks_table_version_info": {},
  "chunks_table_version_info": {},
  "table_version_updates": {},
  "versions": [
    {
      "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
      "name": "<string>",
      "created_at": "2023-11-07T05:31:56Z",
      "updated_at": "2023-11-07T05:31:56Z",
      "is_default": true,
      "extractable_pydantic_class": "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": "Extract every distinct contractual obligation as a separate ContractClause object.",
      "llm_model": "gpt-4o",
      "add_anchoring_object": true,
      "filtered_on_block_types": true,
      "block_types": [
        "text",
        "table"
      ],
      "extract_single_object": false,
      "block_grouping_config": {},
      "alerts_additional_instructions": "<string>",
      "extraction_mode": "standard",
      "agentic_config": {}
    }
  ],
  "default_version": {
    "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "name": "<string>",
    "created_at": "2023-11-07T05:31:56Z",
    "updated_at": "2023-11-07T05:31:56Z",
    "is_default": true,
    "extractable_pydantic_class": "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": "Extract every distinct contractual obligation as a separate ContractClause object.",
    "llm_model": "gpt-4o",
    "add_anchoring_object": true,
    "filtered_on_block_types": true,
    "block_types": [
      "text",
      "table"
    ],
    "extract_single_object": false,
    "block_grouping_config": {},
    "alerts_additional_instructions": "<string>",
    "extraction_mode": "standard",
    "agentic_config": {}
  },
  "latest_version": {
    "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "name": "<string>",
    "created_at": "2023-11-07T05:31:56Z",
    "updated_at": "2023-11-07T05:31:56Z",
    "is_default": true,
    "extractable_pydantic_class": "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": "Extract every distinct contractual obligation as a separate ContractClause object.",
    "llm_model": "gpt-4o",
    "add_anchoring_object": true,
    "filtered_on_block_types": true,
    "block_types": [
      "text",
      "table"
    ],
    "extract_single_object": false,
    "block_grouping_config": {},
    "alerts_additional_instructions": "<string>",
    "extraction_mode": "standard",
    "agentic_config": {}
  }
}

{
  "error": "User not found"
}

{
  "error": "Authentication credentials were not provided."
}

{
  "error": "You do not have permission to perform this action."
}

Authorizations

Authorization

string

header

required

Use Authorization: Bearer

Path Parameters

project_id

string<uuid>

required

UUID of the project

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:

["b3c1d2e4-5f6a-4b7c-8d9e-0a1b2c3d4e5f"]

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:

["text", "table"]

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.

Response

Created

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

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:

["b3c1d2e4-5f6a-4b7c-8d9e-0a1b2c3d4e5f"]

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:

["text", "table"]

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

Show child attributes

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.

Show child attributes

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.

Show child attributes

Concepts

Endpoints

Create object extractor

Authorizations

Path Parameters

Body

Response