Skip to main content
POST
/
parse_async
Async Parse
import requests

url = "https://platform.reducto.ai/parse_async"

payload = {
    "input": "<string>",
    "async": { "priority": False },
    "enhance": {
        "agentic": [],
        "summarize_figures": True,
        "intelligent_ordering": False
    },
    "retrieval": {
        "chunking": {
            "chunk_mode": "disabled",
            "chunk_overlap": 0
        },
        "filter_blocks": [],
        "embedding_optimized": False
    },
    "formatting": {
        "add_page_markers": False,
        "table_output_format": "dynamic",
        "merge_tables": False,
        "include": []
    },
    "spreadsheet": {
        "split_large_tables": {
            "enabled": True,
            "size": 50
        },
        "include": [],
        "clustering": "accurate",
        "exclude": []
    },
    "settings": {
        "ocr_system": "standard",
        "extraction_mode": "hybrid",
        "force_url_result": False,
        "return_ocr_data": False,
        "return_images": [],
        "embed_pdf_metadata": False,
        "embed_pdf_metadata_dpi": 100,
        "persist_results": False,
        "hybrid_vpc": {}
    },
    "queue_priority": "auto"
}
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({
input: '<string>',
async: {priority: false},
enhance: {agentic: [], summarize_figures: true, intelligent_ordering: false},
retrieval: {
chunking: {chunk_mode: 'disabled', chunk_overlap: 0},
filter_blocks: [],
embedding_optimized: false
},
formatting: {
add_page_markers: false,
table_output_format: 'dynamic',
merge_tables: false,
include: []
},
spreadsheet: {
split_large_tables: {enabled: true, size: 50},
include: [],
clustering: 'accurate',
exclude: []
},
settings: {
ocr_system: 'standard',
extraction_mode: 'hybrid',
force_url_result: false,
return_ocr_data: false,
return_images: [],
embed_pdf_metadata: false,
embed_pdf_metadata_dpi: 100,
persist_results: false,
hybrid_vpc: {}
},
queue_priority: 'auto'
})
};

fetch('https://platform.reducto.ai/parse_async', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));
package main

import (
"fmt"
"strings"
"net/http"
"io"
)

func main() {

url := "https://platform.reducto.ai/parse_async"

payload := strings.NewReader("{\n \"input\": \"<string>\",\n \"async\": {\n \"priority\": false\n },\n \"enhance\": {\n \"agentic\": [],\n \"summarize_figures\": true,\n \"intelligent_ordering\": false\n },\n \"retrieval\": {\n \"chunking\": {\n \"chunk_mode\": \"disabled\",\n \"chunk_overlap\": 0\n },\n \"filter_blocks\": [],\n \"embedding_optimized\": false\n },\n \"formatting\": {\n \"add_page_markers\": false,\n \"table_output_format\": \"dynamic\",\n \"merge_tables\": false,\n \"include\": []\n },\n \"spreadsheet\": {\n \"split_large_tables\": {\n \"enabled\": true,\n \"size\": 50\n },\n \"include\": [],\n \"clustering\": \"accurate\",\n \"exclude\": []\n },\n \"settings\": {\n \"ocr_system\": \"standard\",\n \"extraction_mode\": \"hybrid\",\n \"force_url_result\": false,\n \"return_ocr_data\": false,\n \"return_images\": [],\n \"embed_pdf_metadata\": false,\n \"embed_pdf_metadata_dpi\": 100,\n \"persist_results\": false,\n \"hybrid_vpc\": {}\n },\n \"queue_priority\": \"auto\"\n}")

req, _ := http.NewRequest("POST", url, payload)

req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")

res, _ := http.DefaultClient.Do(req)

defer res.Body.Close()
body, _ := io.ReadAll(res.Body)

fmt.Println(string(body))

}
{
  "job_id": "<string>"
}
{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>",
"input": "<unknown>",
"ctx": {}
}
]
}

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
input
required

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 instructions
async
AsyncConfig · object

The configuration options for asynchronous processing (default synchronous).

enhance
Enhance · object
retrieval
Retrieval · object
formatting
Formatting · object
spreadsheet
Spreadsheet · object
settings
Settings · object
queue_priority
enum<string>
default:auto

Queue priority. 'batch' for non-urgent work that processes when spare GPU capacity is available. 'auto' (alias: 'standard') uses the default queue.

Available options:
auto,
standard,
batch

Response

Successful Response

job_id
string
required