Markdown Output Options

Markdown output options allow you to configure how the parsed content is formatted when output as Markdown.

Available Options

Annotate Links

Add annotations to links in the markdown output, providing additional context about the link destinations.

{
  "output_options": {
    "markdown": {
      "annotate_links": true
    }
  }
}

Inline image

Inline images in the markdown output as a image tag \[description\]\(path\) instead of transcribing them,

{
  "output_options": {
    "markdown": {
      "inline_images": true
    }
  }
}

Page Options

Configure page-level formatting for markdown output:

Table Options

Configure how tables are formatted in markdown output:

Compact Markdown Tables

Use compact formatting for markdown tables, reducing whitespace and creating more condensed table layouts.

{
  "output_options": {
    "markdown": {
      "tables": {
        "compact_markdown_tables": true
      }
    }
  }
}

Output Tables as Markdown

Control whether tables are output in markdown format or as HTML. Set to false to output tables as HTML instead of markdown.

{
  "output_options": {
    "markdown": {
      "tables": {
        "output_tables_as_markdown": false
      }
    }
  }
}

Multiline Separator

Specify a separator for multiline content within markdown table cells.

{
  "output_options": {
    "markdown": {
      "tables": {
        "markdown_table_multiline_separator": " | "
      }
    }
  }
}

Combined Configuration

You can combine multiple markdown options:

{
  "output_options": {
    "markdown": {
      "annotate_links": true,
      "tables": {
        "compact_markdown_tables": true,
        "output_tables_as_markdown": 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_plus",
    "version": "latest",
    "output_options": {
      "markdown": {
        "annotate_links": true,
        "tables": {
          "compact_markdown_tables": 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_plus",
    version="latest",
    output_options={
        "markdown": {
            "annotate_links": True,
            "tables": {
                "compact_markdown_tables": True
            }
        }
    }
)

print(result.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_plus",
  version: "latest",
  output_options: {
    markdown: {
      annotate_links: true,
      tables: {
        compact_markdown_tables: true
      }
    }
  }
});

console.log(result.markdown);