Retrieve chunks extractor
import requests
url = "https://eu.app.clarifeye.ai/api/v1/projects/{project_id}/chunks-extractors/{extractor_id}/"
headers = {"Authorization": "Bearer <token>"}
response = requests.get(url, headers=headers)
print(response.text)const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
fetch('https://eu.app.clarifeye.ai/api/v1/projects/{project_id}/chunks-extractors/{extractor_id}/', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));curl --request GET \
--url https://eu.app.clarifeye.ai/api/v1/projects/{project_id}/chunks-extractors/{extractor_id}/ \
--header 'Authorization: Bearer <token>'{
"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": "Authentication credentials were not provided."
}{
"error": "You do not have permission to perform this action."
}{
"error": "Not found."
}Chunks Extractors
Retrieve chunks extractor
GET
/
projects
/
{project_id}
/
chunks-extractors
/
{extractor_id}
/
Retrieve chunks extractor
import requests
url = "https://eu.app.clarifeye.ai/api/v1/projects/{project_id}/chunks-extractors/{extractor_id}/"
headers = {"Authorization": "Bearer <token>"}
response = requests.get(url, headers=headers)
print(response.text)const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
fetch('https://eu.app.clarifeye.ai/api/v1/projects/{project_id}/chunks-extractors/{extractor_id}/', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));curl --request GET \
--url https://eu.app.clarifeye.ai/api/v1/projects/{project_id}/chunks-extractors/{extractor_id}/ \
--header 'Authorization: Bearer <token>'{
"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": "Authentication credentials were not provided."
}{
"error": "You do not have permission to perform this action."
}{
"error": "Not found."
}Authorizations
BearerAuthTokenAuth
Use Authorization: Bearer
Path Parameters
UUID of the project
UUID of the extractor
Response
Successful response
Segments parsed documents into chunks for downstream processing.
Example:
"Default chunker"
Example:
"Smart chunker with h1/h2 separators."
Example:
[]
Example:
1500
Example:
200
Example:
true
Example:
"h1_h2"
Example:
["page_header", "page_footer"]
Example:
"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