Retrieving Exported PDF

A PDF version of each document is generated during parsing.

You can request a presigned url to retrieve the generated PDF after parsing completes.

Complete API Request Example

cURL

Parse the Document

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",
  }'

Retrieving the Exported PDF

After parsing completes, retrieve the exported PDF using the output_pdf_content_metadata expand parameter. This returns a presigned URL for direct download:

curl -X 'GET' \
  'https://api.cloud.llamaindex.ai/api/v2/parse/{job_id}?expand=output_pdf_content_metadata' \
  -H 'Accept: application/json' \
  -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY"

The response includes metadata with a presigned URL:

{
  "job": { ... },
  "result_content_metadata": {
    "outputPDF": {
      "size_bytes": 102400,
      "exists": true,
      "presigned_url": "https://s3.amazonaws.com/..."
    }
  }
}

Use the presigned_url to download the PDF file directly. The URL is temporary and valid for a limited time.

Python

from llama_cloud import LlamaCloud

client = LlamaCloud(api_key="LLAMA_CLOUD_API_KEY")

result = client.parsing.parse(
    upload_file="example_file.docx",
    tier="agentic_plus",
    expand=["output_pdf_content_metadata"],
)

# Returns a presigned URL to download the exported PDF
print(result.result_content_metadata['outputPDF'].presigned_url)

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.docx'),
  tier: "agentic_plus",
  version: "latest",
  expand: ["output_pdf_content_metadata"],
});

// Returns a presigned URL to download the exported PDF
console.log(result.result_content_metadata!.outputPDF!.presigned_url);