@pageindex/sdk

TypeScript SDK for PageIndex — upload documents, retrieve tree structures, and chat with your PDFs.

Get your API Key at dash.pageindex.ai. Full docs at docs.pageindex.ai/js-sdk.

Installation

npm install @pageindex/sdk

Quick Start

import { PageIndexClient } from '@pageindex/sdk';
import { readFileSync } from 'fs';

const client = new PageIndexClient({ apiKey: 'YOUR_API_KEY' });

// Upload a document
const file = readFileSync('./report.pdf');
const { doc_id } = await client.api.submitDocument(file, 'report.pdf');

// Get tree structure
const tree = await client.api.getTree(doc_id);

// Chat with the document
const response = await client.api.chatCompletions({
  messages: [{ role: 'user', content: 'What are the key findings?' }],
  doc_id,
});
console.log(response.choices[0].message.content);

// Stream a response
const stream = await client.api.chatCompletions({
  messages: [{ role: 'user', content: 'Summarize this document' }],
  doc_id,
  stream: true,
});
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? '');
}

Configuration

const client = new PageIndexClient({
  apiKey: 'YOUR_API_KEY', // Required
  apiUrl: 'https://...', // Default: https://api.pageindex.ai
  folderScope: 'folder-id', // Restrict all operations to a folder
});

REST API (client.api)

| Method | Description | | ------------------------------------------ | ----------------------------------------------- | | submitDocument(file, fileName, options?) | Upload a document | | getTree(docId, options?) | Get tree structure and processing status | | getDocument(docId) | Get document metadata | | listDocuments(options?) | List documents (paginated) | | deleteDocument(docId) | Delete a document | | createFolder(options) | Create a folder | | listFolders(options?) | List folders | | chatCompletions(params) | Chat with documents (streaming & non-streaming) |

Chat API

Supports non-streaming, streaming, multi-document, metadata streaming, and citations. See Chat API docs for full reference.

// Multi-document chat
await client.api.chatCompletions({
  messages: [{ role: 'user', content: 'Compare these' }],
  doc_id: ['doc-1', 'doc-2'],
});

// Streaming with tool call metadata
const stream = await client.api.chatCompletions({
  messages,
  doc_id,
  stream: true,
  stream_metadata: true,
});
for await (const chunk of stream) {
  if (chunk.block_metadata?.type === 'mcp_tool_use_start') {
    console.log(`[Using: ${chunk.block_metadata.tool_name}]`);
  }
  process.stdout.write(chunk.choices[0]?.delta?.content ?? '');
}

MCP Tools (client.tools)

Typed wrappers for PageIndex MCP — for building custom AI agent integrations. See MCP Tools docs.

| Method | Description | | -------------------------------- | ---------------------------- | | recentDocuments(params?) | List recent uploads | | findRelevantDocuments(params?) | Search documents | | getDocument(params) | Get document details by name | | getDocumentStructure(params) | Extract document outline | | getPageContent(params) | Read page content | | getDocumentImage(params) | Retrieve embedded image | | removeDocument(params) | Delete documents (batch) | | listFolders(params?) | List folders |

Error Handling

import { PageIndexError } from '@pageindex/sdk';

try {
  await client.api.getDocument('invalid-id');
} catch (error) {
  if (error instanceof PageIndexError) {
    console.log(error.code); // "NOT_FOUND" | "UNAUTHORIZED" | "PLAN_REQUIRED" | ...
    console.log(error.message);
  }
}

Examples

• examples/chat-with-tools — Next.js + AI SDK with MCP tools
• examples/chat-completions — Direct Chat Completions API usage

Links

• JS SDK Docs · Python SDK · MCP · REST API
• Discord · GitHub

License

MIT