API Reference
Extract
API Reference
Extract
POST
/
extract
import requests
url = "https://platform.reducto.ai/extract"
payload = {
"options": {
"ocr_mode": "standard",
"extraction_mode": "ocr",
"chunking": {"chunk_mode": "variable"},
"table_summary": {"enabled": False},
"figure_summary": {
"enabled": False,
"override": False
},
"filter_blocks": ["Page Number", "Header", "Footer", "Comment"],
"force_url_result": False
},
"advanced_options": {
"ocr_system": "highres",
"table_output_format": "html",
"merge_tables": False,
"continue_hierarchy": True,
"keep_line_breaks": False,
"page_range": {},
"large_table_chunking": {
"enabled": True,
"size": 50
},
"spreadsheet_table_clustering": "default",
"add_page_markers": False,
"remove_text_formatting": False,
"return_ocr_data": False,
"filter_line_numbers": False,
"read_comments": False
},
"experimental_options": {
"enrich": {
"enabled": False,
"mode": "standard"
},
"native_office_conversion": False,
"enable_checkboxes": False,
"enable_equations": False,
"rotate_pages": True,
"enable_scripts": False,
"return_figure_images": False,
"return_table_images": False,
"layout_model": "default",
"danger_filter_wide_boxes": False
},
"document_url": "<string>",
"schema": "<any>",
"system_prompt": "Be precise and thorough.",
"generate_citations": False,
"array_extract": {
"enabled": False,
"mode": "legacy",
"pages_per_segment": 10,
"streaming_extract_item_density": 50
},
"use_chunking": False,
"priority": True
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.request("POST", url, json=payload, headers=headers)
print(response.text)
{
"usage": {
"num_pages": 123,
"num_fields": 123
},
"result": [
"<any>"
],
"citations": [
"<any>"
]
}
Authorizations
Bearer authentication header of the form Bearer <token>
, where <token>
is your auth token.
Body
application/json
Response
200
application/json
Successful Response
The response is of type object
.
Was this page helpful?
import requests
url = "https://platform.reducto.ai/extract"
payload = {
"options": {
"ocr_mode": "standard",
"extraction_mode": "ocr",
"chunking": {"chunk_mode": "variable"},
"table_summary": {"enabled": False},
"figure_summary": {
"enabled": False,
"override": False
},
"filter_blocks": ["Page Number", "Header", "Footer", "Comment"],
"force_url_result": False
},
"advanced_options": {
"ocr_system": "highres",
"table_output_format": "html",
"merge_tables": False,
"continue_hierarchy": True,
"keep_line_breaks": False,
"page_range": {},
"large_table_chunking": {
"enabled": True,
"size": 50
},
"spreadsheet_table_clustering": "default",
"add_page_markers": False,
"remove_text_formatting": False,
"return_ocr_data": False,
"filter_line_numbers": False,
"read_comments": False
},
"experimental_options": {
"enrich": {
"enabled": False,
"mode": "standard"
},
"native_office_conversion": False,
"enable_checkboxes": False,
"enable_equations": False,
"rotate_pages": True,
"enable_scripts": False,
"return_figure_images": False,
"return_table_images": False,
"layout_model": "default",
"danger_filter_wide_boxes": False
},
"document_url": "<string>",
"schema": "<any>",
"system_prompt": "Be precise and thorough.",
"generate_citations": False,
"array_extract": {
"enabled": False,
"mode": "legacy",
"pages_per_segment": 10,
"streaming_extract_item_density": 50
},
"use_chunking": False,
"priority": True
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.request("POST", url, json=payload, headers=headers)
print(response.text)
{
"usage": {
"num_pages": 123,
"num_fields": 123
},
"result": [
"<any>"
],
"citations": [
"<any>"
]
}