Ignore Options

Ignore options allow you to skip specific types of text during parsing. These options are available for all tiers.

Configuration

Use processing_options.ignore to configure these options.

Available Options

Ignore Diagonal Text

Skip text that appears diagonally on the page.

{
  "tier": "agentic",
  "version": "latest",
  "processing_options": {
    "ignore": {
      "ignore_diagonal_text": true
    }
  }
}

Ignore Text in Images

Skip OCR processing of text that appears within images.

{
  "tier": "fast",
  "version": "latest",
  "processing_options": {
    "ignore": {
      "ignore_text_in_image": true
    }
  }
}

Ignore Hidden Text

Skip text that is hidden in the document (such as white text on white background or text marked as hidden).

{
  "tier": "agentic_plus",
  "version": "latest",
  "processing_options": {
    "ignore": {
      "ignore_hidden_text": true
    }
  }
}

Combined Configuration

You can combine multiple ignore options:

{
  "tier": "agentic_plus",
  "version": "latest",
  "processing_options": {
    "ignore": {
      "ignore_diagonal_text": true,
      "ignore_hidden_text": true,
      "ignore_text_in_image": true
    }
  }
}

Complete API Request Example

cURL

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",
    "version": "latest",
    "processing_options": {
      "ignore": {
        "ignore_diagonal_text": true,
        "ignore_hidden_text": true
      }
    }
  }'

Python

from llama_cloud import LlamaCloud

client = LlamaCloud(api_key="LLAMA_CLOUD_API_KEY")

result = client.parsing.parse(
    upload_file="example_file.pdf",
    tier="agentic",
    version="latest",
    processing_options={
        "ignore": {
            "ignore_diagonal_text": True,
            "ignore_hidden_text": True
        }
    },
    expand=["markdown"],
)

TypeScript

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",
  version: "latest",
  processing_options: {
    ignore: {
      ignore_diagonal_text: true,
      ignore_hidden_text: true,
    },
  },
  expand: ["markdown"],
});