Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.unsiloed.ai/llms.txt

Use this file to discover all available pages before exploring further.

Instead of configuring ocr_engine, segment_processing, agentic_ocr, and merge_tables individually, you can apply a preset mode that bundles a recommended combination of all four. The parser ships with three:

​
Fast

Optimized for speed. Best for standard documents with clean text and simple tables.

​
Accurate

Balanced accuracy and performance. Best for complex layouts and detailed tables.

​
Agentic

Maximum accuracy with per-segment re-OCR. Best for critical documents requiring the highest fidelity.

​
Mode Parameters

Each mode is shorthand for a specific set of parameters. To use a mode, pass the values from its column in your /parse request.
ParameterFastAccurateAgentic
ocr_engineUnsiloedBetaUnsiloedBetaUnsiloedBeta
segment_processing.Table.htmlVLMVLMVLM
segment_processing.Table.model_idastra_v2astra_v3astra_v3
agentic_ocrnullnulladvanced
merge_tablesfalsetruefalse
Modes are preset configurations. You can override any individual parameter after applying one. See the Parse API reference for the full parameter list.

​
Applying a Mode

The submit-and-poll flow is the same as in the Quickstart; only the request body differs. The snippets below show each mode in Python — translate to JavaScript or cURL by changing the request body shape, not the parameter values. 
import os
import requests

API_KEY = os.environ["UNSILOED_API_KEY"]
BASE_URL = "https://prod.visionapi.unsiloed.ai"

with open("document.pdf", "rb") as f:
    response = requests.post(
        f"{BASE_URL}/parse",
        headers={"api-key": API_KEY},
        files={"file": ("document.pdf", f, "application/pdf")},
        data={
            "ocr_engine": "UnsiloedBeta",
            "merge_tables": "false",
            "agentic_ocr": "",
            "segment_processing": '{"Table": {"html": "VLM", "model_id": "astra_v2"}}',
        },
    )
response.raise_for_status()
job_id = response.json()["job_id"]
print(f"Job submitted: {job_id}")