Pipeline
import requests
url = "https://platform.reducto.ai/pipeline"
payload = {
"input": "<string>",
"pipeline_id": "<string>",
"settings": {}
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text){
"job_id": "<string>",
"usage": {
"num_pages": 123,
"credits": 123,
"credit_breakdown": {},
"page_billing_breakdown": {},
"non_empty_cell_count": 123
},
"result": {
"parse": {
"job_id": "<string>",
"duration": 123,
"usage": {
"num_pages": 123,
"credits": 123,
"credit_breakdown": {},
"page_billing_breakdown": {},
"non_empty_cell_count": 123
},
"result": {
"type": "<string>",
"chunks": [
{
"content": "<string>",
"embed": "<string>",
"enriched": "<string>",
"blocks": [
{
"bbox": {
"left": 123,
"top": 123,
"width": 123,
"height": 123,
"page": 123,
"original_page": 123
},
"content": "<string>",
"image_url": "<string>",
"chart_data": [
"<string>"
],
"confidence": "low",
"granular_confidence": {
"extract_confidence": 123,
"parse_confidence": 123
},
"extra": {}
}
],
"enrichment_success": false
}
],
"ocr": {
"words": [
{
"text": "<string>",
"bbox": {
"left": 123,
"top": 123,
"width": 123,
"height": 123,
"page": 123,
"original_page": 123
},
"confidence": 123,
"chunk_index": 123,
"rotation": 123
}
],
"lines": [
{
"text": "<string>",
"bbox": {
"left": 123,
"top": 123,
"width": 123,
"height": 123,
"page": 123,
"original_page": 123
},
"confidence": 123,
"chunk_index": 123,
"rotation": 123
}
]
},
"custom": null
},
"response_type": "parse",
"pdf_url": "<string>",
"studio_link": "<string>"
},
"extract": [
{
"split_name": "<string>",
"page_range": [
123
],
"result": {},
"partition": "<string>"
}
],
"split": {
"usage": {
"num_pages": 123,
"credits": 123,
"credit_breakdown": {},
"page_billing_breakdown": {},
"non_empty_cell_count": 123
},
"result": {
"section_mapping": {},
"splits": [
{
"name": "<string>",
"pages": [
123
],
"conf": "low",
"partitions": [
{
"name": "<string>",
"pages": [
123
],
"conf": "low"
}
]
}
]
},
"response_type": "split"
},
"edit": {
"document_url": "<string>",
"response_type": "edit",
"form_schema": [
{
"bbox": {
"left": 123,
"top": 123,
"width": 123,
"height": 123,
"page": 123,
"original_page": 123
},
"description": "<string>",
"fill": true,
"value": "<string>",
"font_size": 36.5
}
],
"usage": {
"num_pages": 123,
"credits": 123,
"credit_breakdown": {},
"page_billing_breakdown": {},
"non_empty_cell_count": 123
}
}
},
"response_type": "pipeline"
}Document Processing
Pipeline
POST
/
pipeline
Pipeline
import requests
url = "https://platform.reducto.ai/pipeline"
payload = {
"input": "<string>",
"pipeline_id": "<string>",
"settings": {}
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text){
"job_id": "<string>",
"usage": {
"num_pages": 123,
"credits": 123,
"credit_breakdown": {},
"page_billing_breakdown": {},
"non_empty_cell_count": 123
},
"result": {
"parse": {
"job_id": "<string>",
"duration": 123,
"usage": {
"num_pages": 123,
"credits": 123,
"credit_breakdown": {},
"page_billing_breakdown": {},
"non_empty_cell_count": 123
},
"result": {
"type": "<string>",
"chunks": [
{
"content": "<string>",
"embed": "<string>",
"enriched": "<string>",
"blocks": [
{
"bbox": {
"left": 123,
"top": 123,
"width": 123,
"height": 123,
"page": 123,
"original_page": 123
},
"content": "<string>",
"image_url": "<string>",
"chart_data": [
"<string>"
],
"confidence": "low",
"granular_confidence": {
"extract_confidence": 123,
"parse_confidence": 123
},
"extra": {}
}
],
"enrichment_success": false
}
],
"ocr": {
"words": [
{
"text": "<string>",
"bbox": {
"left": 123,
"top": 123,
"width": 123,
"height": 123,
"page": 123,
"original_page": 123
},
"confidence": 123,
"chunk_index": 123,
"rotation": 123
}
],
"lines": [
{
"text": "<string>",
"bbox": {
"left": 123,
"top": 123,
"width": 123,
"height": 123,
"page": 123,
"original_page": 123
},
"confidence": 123,
"chunk_index": 123,
"rotation": 123
}
]
},
"custom": null
},
"response_type": "parse",
"pdf_url": "<string>",
"studio_link": "<string>"
},
"extract": [
{
"split_name": "<string>",
"page_range": [
123
],
"result": {},
"partition": "<string>"
}
],
"split": {
"usage": {
"num_pages": 123,
"credits": 123,
"credit_breakdown": {},
"page_billing_breakdown": {},
"non_empty_cell_count": 123
},
"result": {
"section_mapping": {},
"splits": [
{
"name": "<string>",
"pages": [
123
],
"conf": "low",
"partitions": [
{
"name": "<string>",
"pages": [
123
],
"conf": "low"
}
]
}
]
},
"response_type": "split"
},
"edit": {
"document_url": "<string>",
"response_type": "edit",
"form_schema": [
{
"bbox": {
"left": 123,
"top": 123,
"width": 123,
"height": 123,
"page": 123,
"original_page": 123
},
"description": "<string>",
"fill": true,
"value": "<string>",
"font_size": 36.5
}
],
"usage": {
"num_pages": 123,
"credits": 123,
"credit_breakdown": {},
"page_billing_breakdown": {},
"non_empty_cell_count": 123
}
}
},
"response_type": "pipeline"
}Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
application/json
For parse/split/extract pipelines, the URL of the document to be processed. You can provide one of the following: 1. A publicly available URL 2. A presigned S3 URL 3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document 4. A jobid:// prefixed URL obtained from a previous /parse invocation 5. A list of URLs (for multi-document pipelines, V3 API only)
For edit pipelines, this should be a string containing the edit instructionsThe ID of the pipeline to use for the document.
Settings for pipeline execution that override pipeline defaults.
Show child attributes
Show child attributes
Was this page helpful?
⌘I