> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/vectifyai/pageindex/llms.txt
> Use this file to discover all available pages before exploring further.

# Quick Start

> Generate a PageIndex tree structure from a PDF document in under 5 minutes

## Overview

This guide will walk you through generating your first PageIndex tree structure from a PDF document. You'll transform a lengthy PDF into a hierarchical, semantic tree index optimized for LLM-powered retrieval.

<Note>
  PageIndex is ideal for financial reports, regulatory filings, academic textbooks, legal or technical manuals, and any document that exceeds LLM context limits.
</Note>

<Steps>
  <Step title="Install Dependencies">
    Install the required Python packages using pip:

    ```bash theme={null}
    pip3 install --upgrade -r requirements.txt
    ```

    This will install:

    * `openai==1.101.0` - OpenAI API client
    * `pymupdf==1.26.4` - PDF parsing
    * `PyPDF2==3.0.1` - Additional PDF utilities
    * `python-dotenv==1.1.0` - Environment variable management
    * `tiktoken==0.11.0` - Token counting
    * `pyyaml==6.0.2` - Configuration file support
  </Step>

  <Step title="Configure Your OpenAI API Key">
    Create a `.env` file in the root directory and add your OpenAI API key:

    ```bash theme={null}
    CHATGPT_API_KEY=your_openai_key_here
    ```

    <Warning>
      PageIndex uses GPT-4o by default for high-quality tree generation. Make sure your API key has access to the required models.
    </Warning>
  </Step>

  <Step title="Run PageIndex on Your PDF">
    Process your PDF document to generate the tree structure:

    ```bash theme={null}
    python3 run_pageindex.py --pdf_path /path/to/your/document.pdf
    ```

    PageIndex will:

    1. Parse your PDF and extract text content
    2. Detect the table of contents (if present)
    3. Generate a hierarchical tree structure with summaries
    4. Save the output as a JSON file in `./results/`

    You should see output like:

    ```
    Parsing done, saving to file...
    Tree structure saved to: ./results/document_structure.json
    ```
  </Step>

  <Step title="Explore the Generated Tree">
    Open the generated JSON file to explore your document's tree structure:

    ```json theme={null}
    {
      "title": "Financial Stability",
      "node_id": "0006",
      "start_index": 21,
      "end_index": 22,
      "summary": "The Federal Reserve ...",
      "nodes": [
        {
          "title": "Monitoring Financial Vulnerabilities",
          "node_id": "0007",
          "start_index": 22,
          "end_index": 28,
          "summary": "The Federal Reserve's monitoring ..."
        },
        {
          "title": "Domestic and International Cooperation",
          "node_id": "0008",
          "start_index": 28,
          "end_index": 31,
          "summary": "In 2023, the Federal Reserve collaborated ..."
        }
      ]
    }
    ```

    Each node contains:

    * `title` - Section heading
    * `node_id` - Unique identifier
    * `start_index` / `end_index` - Page range
    * `summary` - AI-generated section summary
    * `nodes` - Nested subsections (if any)
  </Step>
</Steps>

## Customization Options

PageIndex supports various optional parameters to customize tree generation:

<CodeGroup>
  ```bash Model Selection theme={null}
  python3 run_pageindex.py \
    --pdf_path document.pdf \
    --model gpt-4o-2024-11-20
  ```

  ```bash Page Limits theme={null}
  python3 run_pageindex.py \
    --pdf_path document.pdf \
    --max-pages-per-node 10 \
    --max-tokens-per-node 20000
  ```

  ```bash TOC Detection theme={null}
  python3 run_pageindex.py \
    --pdf_path document.pdf \
    --toc-check-pages 20
  ```

  ```bash Output Options theme={null}
  python3 run_pageindex.py \
    --pdf_path document.pdf \
    --if-add-node-id yes \
    --if-add-node-summary yes \
    --if-add-doc-description yes
  ```
</CodeGroup>

### Available Parameters

| Parameter                  | Default             | Description                                    |
| -------------------------- | ------------------- | ---------------------------------------------- |
| `--model`                  | `gpt-4o-2024-11-20` | OpenAI model to use for tree generation        |
| `--toc-check-pages`        | `20`                | Number of pages to check for table of contents |
| `--max-pages-per-node`     | `10`                | Maximum pages per tree node                    |
| `--max-tokens-per-node`    | `20000`             | Maximum tokens per tree node                   |
| `--if-add-node-id`         | `yes`               | Add unique node IDs                            |
| `--if-add-node-summary`    | `yes`               | Generate AI summaries for each node            |
| `--if-add-doc-description` | `no`                | Add document-level description                 |

## Markdown Support

PageIndex also supports markdown files. Use the `--md_path` flag instead:

```bash theme={null}
python3 run_pageindex.py --md_path /path/to/your/document.md
```

<Note>
  PageIndex uses `#` markers to determine node hierarchy. Ensure your markdown file has proper heading structure (`##` for level 2, `###` for level 3, etc.).
</Note>

<Warning>
  If your markdown was converted from PDF or HTML, most tools don't preserve hierarchy correctly. Consider using [PageIndex OCR](https://pageindex.ai/blog/ocr) for better conversion quality.
</Warning>

## Next Steps

<CardGroup cols={2}>
  <Card title="Vectorless RAG Cookbook" icon="flask" href="/cookbook/vectorless-rag-pageindex">
    Build a complete reasoning-based RAG system with PageIndex
  </Card>

  <Card title="API Reference" icon="code" href="/api/page-index">
    Explore the full Python API and configuration options
  </Card>

  <Card title="Tree Search Tutorial" icon="magnifying-glass" href="/tutorials/tree-search">
    Learn how to perform reasoning-based retrieval over the tree
  </Card>

  <Card title="Example Documents" icon="file-pdf" href="https://github.com/VectifyAI/PageIndex/tree/main/tests/pdfs">
    See sample PDFs and their generated tree structures
  </Card>
</CardGroup>