> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agentium.in/llms.txt
> Use this file to discover all available pages before exploring further.

# PageIndex

> Vectorless, reasoning-based RAG — submit PDFs, build tree indexes, and retrieve via LLM reasoning.

# PageIndex

Reasoning-based RAG for complex, long-form documents. Unlike vector search, PageIndex builds a hierarchical tree index and uses LLM reasoning to navigate it — delivering significantly better accuracy on financial reports, legal filings, technical manuals, and research papers.

<Info>
  Uses the PageIndex cloud API — no vector database or embedding pipeline needed.
</Info>

***

## Quick Start

```typescript theme={null}
import { Agent, openai, PageIndexToolkit } from "@agentium/core";

const pageindex = new PageIndexToolkit({
  apiKey: process.env.PAGEINDEX_API_KEY,
});

const agent = new Agent({
  name: "document-analyst",
  model: openai("gpt-4o"),
  instructions: "Analyze uploaded documents. Answer questions accurately with citations.",
  tools: [...pageindex.getTools()],
});

const result = await agent.run(
  "Submit https://example.com/annual-report.pdf and then summarize the revenue breakdown by segment."
);
```

***

## Config

<ParamField body="apiKey" type="string" required>
  PageIndex API key. Falls back to `PAGEINDEX_API_KEY` env var. Get yours at [dash.pageindex.ai](https://dash.pageindex.ai).
</ParamField>

<ParamField body="apiBase" type="string" default="https://api.pageindex.ai">
  API base URL. Override for self-hosted PageIndex deployments.
</ParamField>

<ParamField body="timeout" type="number" default="120000">
  Request timeout in milliseconds. PDF processing can take time — the default is 2 minutes.
</ParamField>

<ParamField body="maxResponseSize" type="number" default="50000">
  Max response characters returned per tool call.
</ParamField>

***

## Tools

| Tool                 | Description                                                                               |
| -------------------- | ----------------------------------------------------------------------------------------- |
| `pageindex_submit`   | Submit a PDF document for tree indexing. Returns a `doc_id` for subsequent operations.    |
| `pageindex_status`   | Check document processing status — returns tree structure when complete.                  |
| `pageindex_tree`     | Get the hierarchical tree structure of a processed document (semantic table of contents). |
| `pageindex_list`     | List all documents with IDs, names, statuses, and page counts.                            |
| `pageindex_chat`     | Ask questions about documents using reasoning-based RAG with optional citations.          |
| `pageindex_retrieve` | Retrieve specific sections from a document using tree-based search.                       |
| `pageindex_delete`   | Delete a document and all associated data.                                                |

***

## How It Works

PageIndex takes a fundamentally different approach from traditional vector RAG:

1. **Tree Indexing** — Documents are parsed into a hierarchical tree of sections, subsections, and paragraphs with summaries at each level
2. **LLM Tree Search** — At query time, an LLM navigates the tree from root to relevant leaves, using reasoning instead of embedding similarity
3. **No Vectors Needed** — No embedding model, no vector database, no chunking strategy to tune

This approach excels on documents where structure matters: financial reports with complex tables, legal contracts with nested clauses, and technical specs with cross-references.

***

## Use Cases

### Document Q\&A

```typescript theme={null}
// After submitting a document
await agent.run("What were the total operating expenses in Q3 2024?");
```

### Multi-Document Analysis

```typescript theme={null}
await agent.run(
  "Compare the risk factors section between the 2023 and 2024 annual reports."
);
```

### Structured Extraction

```typescript theme={null}
const agent = new Agent({
  name: "extractor",
  model: openai("gpt-4o"),
  instructions: "Extract structured data from documents with page citations.",
  tools: [...pageindex.getTools()],
  outputType: z.object({
    items: z.array(z.object({
      field: z.string(),
      value: z.string(),
      page: z.number(),
    })),
  }),
});
```

***

## Environment Variables

| Variable            | Description                                                           |
| ------------------- | --------------------------------------------------------------------- |
| `PAGEINDEX_API_KEY` | PageIndex API key from [dash.pageindex.ai](https://dash.pageindex.ai) |

***

## Combining with Agentium Knowledge

PageIndex works best for complex professional documents. For simpler content or when you need a fully local pipeline, combine it with Agentium's built-in vector knowledge base:

```typescript theme={null}
import { Agent, openai, PageIndexToolkit, InMemoryKnowledge } from "@agentium/core";

const agent = new Agent({
  name: "hybrid-knowledge",
  model: openai("gpt-4o"),
  tools: [...new PageIndexToolkit({ apiKey: "..." }).getTools()],
  knowledge: new InMemoryKnowledge({ /* local vector search for quick lookups */ }),
  instructions: "Use PageIndex for complex document analysis. Use knowledge search for quick factual lookups.",
});
```

<Tip>
  PageIndex is ideal for **complex, structured documents** (100+ pages). For short text snippets and FAQ-style retrieval, the built-in vector knowledge base is faster and cheaper.
</Tip>