Update chunks extractor (auto-creates new version)

import requests

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

payload = { "name": "Default chunker (rebranded)" }
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

{
  "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "name": "Default chunker",
  "brief": "Smart chunker with h1/h2 separators.",
  "document_ids": [],
  "maximum_chunk_size": 1500,
  "minimum_chunk_size": 200,
  "page_as_separator": true,
  "title_section_separator_mode": "h1_h2",
  "excluded_block_types": [
    "page_header",
    "page_footer"
  ],
  "chunking_mode": "smart",
  "is_project_default": false,
  "pre_execution_filter": {},
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "extracted_chunks_table": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "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,
      "maximum_chunk_size": 1500,
      "minimum_chunk_size": 200,
      "page_as_separator": true,
      "title_section_separator_mode": "h1_h2",
      "excluded_block_types": [
        "page_header",
        "page_footer"
      ],
      "chunking_mode": "smart"
    }
  ],
  "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,
    "maximum_chunk_size": 1500,
    "minimum_chunk_size": 200,
    "page_as_separator": true,
    "title_section_separator_mode": "h1_h2",
    "excluded_block_types": [
      "page_header",
      "page_footer"
    ],
    "chunking_mode": "smart"
  },
  "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,
    "maximum_chunk_size": 1500,
    "minimum_chunk_size": 200,
    "page_as_separator": true,
    "title_section_separator_mode": "h1_h2",
    "excluded_block_types": [
      "page_header",
      "page_footer"
    ],
    "chunking_mode": "smart"
  }
}

{
  "error": "User not found"
}

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

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

{
  "error": "Not found."
}

PATCH

projects

{project_id}

chunks-extractors

{extractor_id}

import requests

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

payload = { "name": "Default chunker (rebranded)" }
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

{
  "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "name": "Default chunker",
  "brief": "Smart chunker with h1/h2 separators.",
  "document_ids": [],
  "maximum_chunk_size": 1500,
  "minimum_chunk_size": 200,
  "page_as_separator": true,
  "title_section_separator_mode": "h1_h2",
  "excluded_block_types": [
    "page_header",
    "page_footer"
  ],
  "chunking_mode": "smart",
  "is_project_default": false,
  "pre_execution_filter": {},
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "extracted_chunks_table": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "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,
      "maximum_chunk_size": 1500,
      "minimum_chunk_size": 200,
      "page_as_separator": true,
      "title_section_separator_mode": "h1_h2",
      "excluded_block_types": [
        "page_header",
        "page_footer"
      ],
      "chunking_mode": "smart"
    }
  ],
  "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,
    "maximum_chunk_size": 1500,
    "minimum_chunk_size": 200,
    "page_as_separator": true,
    "title_section_separator_mode": "h1_h2",
    "excluded_block_types": [
      "page_header",
      "page_footer"
    ],
    "chunking_mode": "smart"
  },
  "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,
    "maximum_chunk_size": 1500,
    "minimum_chunk_size": 200,
    "page_as_separator": true,
    "title_section_separator_mode": "h1_h2",
    "excluded_block_types": [
      "page_header",
      "page_footer"
    ],
    "chunking_mode": "smart"
  }
}

{
  "error": "User not found"
}

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

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

{
  "error": "Not found."
}

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

Segments parsed documents into chunks for downstream processing.

name

string

Example:

"Default chunker"

brief

string

Example:

"Smart chunker with h1/h2 separators."

document_ids

string<uuid>[]

Example:

[]

maximum_chunk_size

integer

Example:

1500

minimum_chunk_size

integer

Example:

200

page_as_separator

boolean

Example:

true

title_section_separator_mode

string

Example:

"h1_h2"

excluded_block_types

string[]

Example:

["page_header", "page_footer"]

chunking_mode

string

Example:

"smart"

is_project_default

boolean

default:false

pre_execution_filter

object | null

import_mode

boolean

default:false

write-only

set_latest_as_default

boolean

write-only

Response

Updated

Segments parsed documents into chunks for downstream processing.

string<uuid>

read-only

name

string

Example:

"Default chunker"

brief

string

Example:

"Smart chunker with h1/h2 separators."

document_ids

string<uuid>[]

Example:

[]

maximum_chunk_size

integer

Example:

1500

minimum_chunk_size

integer

Example:

200

page_as_separator

boolean

Example:

true

title_section_separator_mode

string

Example:

"h1_h2"

excluded_block_types

string[]

Example:

["page_header", "page_footer"]

chunking_mode

string

Example:

"smart"

is_project_default

boolean

default:false

pre_execution_filter

object | null

created_at

string<date-time>

read-only

updated_at

string<date-time>

read-only

extracted_chunks_table

string<uuid> | null

read-only

versions

object[]

read-only

Show child attributes

default_version

object | null

Immutable snapshot of a ChunksExtractor's version-bearing configuration.

Show child attributes

latest_version

object | null

Immutable snapshot of a ChunksExtractor's version-bearing configuration.

Show child attributes

Concepts

Endpoints

Update chunks extractor (auto-creates new version)

Authorizations

Path Parameters

Body

Response