Table Extraction

Table extraction options allow you to configure how tables are detected and extracted from documents. These options are available for all tiers.

Configuration

Use processing_options to configure these options.

Available Options

Aggressive Table Extraction

Enable more aggressive table detection and extraction methods. This may capture more tables but could also introduce false positives.

{
  "tier": "agentic",
  "version": "latest",
  "processing_options": {
    "aggressive_table_extraction": true
  }
}

Disable Heuristics

Disable table-related heuristics including outlined table extraction and adaptive long table handling. Use this when the default heuristics are producing unwanted results.

{
  "tier": "agentic",
  "version": "latest",
  "processing_options": {
    "disable_heuristics": true
  }
}

When enabled, this disables:

• Outlined table extraction: Detection of tables with visible borders
• Adaptive long table handling: Special handling for long tables

Examples

Fast Tier

{
  "tier": "fast",
  "version": "latest",
  "processing_options": {
    "aggressive_table_extraction": true
  }
}

Agentic Tier

{
  "tier": "agentic_plus",
  "version": "latest",
  "processing_options": {
    "aggressive_table_extraction": 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",
    "processing_options": {
      "aggressive_table_extraction": 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",
    processing_options={
        "aggressive_table_extraction": 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_plus",
  version: "latest",
  processing_options: {
    aggressive_table_extraction: true
  },
  expand: ["markdown"],
});