import requests
url = "https://eu.app.clarifeye.ai/api/v1/projects/{project_id}/chunks-extractors/"
payload = {
"name": "Default chunker",
"brief": "Smart chunker with h1/h2 separators, 200–1500 char chunks.",
"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": True,
"document_ids": []
}
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: 'Default chunker',
brief: 'Smart chunker with h1/h2 separators, 200–1500 char chunks.',
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: true,
document_ids: []
})
};
fetch('https://eu.app.clarifeye.ai/api/v1/projects/{project_id}/chunks-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}/chunks-extractors/ \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"name": "Default chunker",
"brief": "Smart chunker with h1/h2 separators, 200–1500 char chunks.",
"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": true,
"document_ids": []
}
'{
"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."
}Create chunks extractor
Create a ChunksExtractor. A first ChunksExtractorVersion is created
automatically and marked as default.
import requests
url = "https://eu.app.clarifeye.ai/api/v1/projects/{project_id}/chunks-extractors/"
payload = {
"name": "Default chunker",
"brief": "Smart chunker with h1/h2 separators, 200–1500 char chunks.",
"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": True,
"document_ids": []
}
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: 'Default chunker',
brief: 'Smart chunker with h1/h2 separators, 200–1500 char chunks.',
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: true,
document_ids: []
})
};
fetch('https://eu.app.clarifeye.ai/api/v1/projects/{project_id}/chunks-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}/chunks-extractors/ \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"name": "Default chunker",
"brief": "Smart chunker with h1/h2 separators, 200–1500 char chunks.",
"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": true,
"document_ids": []
}
'{
"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."
}Authorizations
Use Authorization: Bearer <token>. The token is either a user token / OAuth access
token, or a service-account API key (cfk_...). A key is valid on every endpoint and
acts as its service account, an organization member with per-store permissions.
Refused keys answer 403 with Invalid API key., API key revoked.,
API key expired. or API key disabled..
Path Parameters
UUID of the project
Body
Segments parsed documents into chunks for downstream processing.
"Default chunker"
"Smart chunker with h1/h2 separators."
[]
1500
200
true
"h1_h2"
["page_header", "page_footer"]
"smart"
Response
Created
Segments parsed documents into chunks for downstream processing.
"Default chunker"
"Smart chunker with h1/h2 separators."
[]
1500
200
true
"h1_h2"
["page_header", "page_footer"]
"smart"
Show child attributes
Show child attributes
Immutable snapshot of a ChunksExtractor's version-bearing configuration.
Show child attributes
Show child attributes
Immutable snapshot of a ChunksExtractor's version-bearing configuration.
Show child attributes
Show child attributes