OCR Options

OCR options allow you to configure optical character recognition settings for processing images within documents. These options are available for all tiers.

Configuration

Use processing_options.ocr_parameters to configure these options.

Available Options

Languages

Specify which languages to use for OCR processing of images. This only affects text extracted from images, not native text in the document.

{
  "tier": "agentic",
  "version": "latest",
  "processing_options": {
    "ocr_parameters": {
      "languages": ["en", "zh", "ja"]
    }
  }
}

Examples

Single Language

{
  "tier": "fast",
  "version": "latest",
  "processing_options": {
    "ocr_parameters": {
      "languages": ["en"]
    }
  }
}

Multiple Languages

{
  "tier": "agentic_plus",
  "version": "latest",
  "processing_options": {
    "ocr_parameters": {
      "languages": ["en", "fr", "de", "es"]
    }
  }
}

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": {
      "ocr_parameters": {
        "languages": ["en", "es"]
      }
    }
  }'

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={
        "ocr_parameters": {
            "languages": ["en", "es"]
        }
    }
)

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: {
    ocr_parameters: {
      languages: ["en", "es"]
    }
  }
});