Processing Control

Processing control options allow you to configure timeouts and job failure conditions for parsing operations.

Timeouts

Configure how long parsing operations are allowed to run before timing out.

Base Timeout

Set the base timeout for parsing operations in seconds (maximum 30 minutes).

{
  "processing_control": {
    "timeouts": {
      "base_in_seconds": 300
    }
  }
}

Extra Time Per Page

Set additional timeout per page in seconds (maximum 5 minutes per page).

{
  "processing_control": {
    "timeouts": {
      "base_in_seconds": 300,
      "extra_time_per_page_in_seconds": 30
    }
  }
}

Job Failure Conditions

Configure conditions that determine when a parsing job should fail.

Allowed Page Failure Ratio

Set the maximum ratio of pages allowed to fail (0-1). If more pages fail than this ratio, the entire job fails.

{
  "processing_control": {
    "job_failure_conditions": {
      "allowed_page_failure_ratio": 0.1
    }
  }
}

Fail on Image Extraction Error

Fail the job if image extraction encounters errors.

{
  "processing_control": {
    "job_failure_conditions": {
      "fail_on_image_extraction_error": true
    }
  }
}

Fail on Image OCR Error

Fail the job if image OCR encounters errors.

{
  "processing_control": {
    "job_failure_conditions": {
      "fail_on_image_ocr_error": true
    }
  }
}

Fail on Markdown Reconstruction Error

Fail the job if markdown reconstruction encounters errors.

{
  "processing_control": {
    "job_failure_conditions": {
      "fail_on_markdown_reconstruction_error": true
    }
  }
}

Fail on Buggy Font

Fail the job if buggy fonts are detected in the document.

{
  "processing_control": {
    "job_failure_conditions": {
      "fail_on_buggy_font": true
    }
  }
}

Combined Configuration

You can combine timeout and failure condition settings:

{
  "processing_control": {
    "timeouts": {
      "base_in_seconds": 600,
      "extra_time_per_page_in_seconds": 45
    },
    "job_failure_conditions": {
      "allowed_page_failure_ratio": 0.05,
      "fail_on_image_extraction_error": false,
      "fail_on_buggy_font": true
    }
  }
}

Complete API Request Example

curl -X 'POST' \
  'https://api.cloud.llamaindex.ai/api/v2/parse' \
  -H 'Accept: application/json' \
  -H 'Content-Type: application/json' \
  -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY" \
  --data '{
    "file_id": "<file_id>",
    "tier": "agentic_plus",
    "version": "latest",
    "processing_control": {
      "timeouts": {
        "base_in_seconds": 600
      },
      "job_failure_conditions": {
        "allowed_page_failure_ratio": 0.1
      }
    }
  }'

from llama_cloud import LlamaCloud

client = LlamaCloud(api_key="LLAMA_CLOUD_API_KEY")

result = client.parsing.parse(
    upload_file="example_file.pdf",
    tier="agentic_plus",
    version="latest",
    processing_control={
        "timeouts": {"base_in_seconds": 600},
        "job_failure_conditions": {"allowed_page_failure_ratio": 0.1},
    },
    expand=["markdown"],
)

import fs from "fs";
import { LlamaCloud } from "@llamaindex/llama-cloud";

const client = new LlamaCloud({
  apiKey: "LLAMA_CLOUD_API_KEY",
});

const result = await client.parsing.parse({
  upload_file: fs.createReadStream('example_file.pdf'),
  tier: "agentic_plus",
  version: "latest",
  processing_control: {
    timeouts: { base_in_seconds: 600 },
    job_failure_conditions: { allowed_page_failure_ratio: 0.1 },
  },
  expand: ["markdown"],
});