feat(langchain-community): Add Polaris AI DataInsight Document Loader

[ai-solution-dev]

Description

This PR integrates the Polaris AI DataInsight Document Loader into LangChain.js.
The integration enables the use of Polaris AI's advanced document extraction capabilities to process various document formats and extract text, images, tables, charts, and mathematical equations.

---

Key Features

• Added Polaris AI DataInsight Document Loader support in LangChain.js

  • Load documents either from the file system or buffer data
  • Extract text, images, tables, charts, and equations from various document formats
  • Process documents through Polaris AI's DataInsight API service

• Flexible document loading modes

  • element: Load each element in the pages as a separate Document object
  • page: Load each page in the document as a separate Document object
  • single: Load the entire document as a single Document object

• Comprehensive document element support

  • Text content extraction
  • Table processing with HTML output
  • Chart data with CSV format and metadata
  • Image handling with file path references

• Source: Located under libs/langchain-community

• Includes comprehensive testing and examples for the integration

---

Example Usage

import { PolarisAIDataInsightLoader } from "@langchain/community/document_loaders/web/polaris_ai_datainsight";
import fs from "fs";



const loaderFromPath = new PolarisAIDataInsightLoader({
  filePath: "path/to/file.docx",
  apiKey: process.env.POLARIS_AI_DATA_INSIGHT_API_KEY,
  resourcesDir: "path/to/save/resources/",
  mode: "single",
});
const docsFromPath = await loaderFromPath.load();



const docsFromBuffer = await loaderFromBuffer.load();

[changeset-bot]

🦋 Changeset detected

Latest commit: 59d6409

The changes in this PR will be included in the next version bump.

This PR includes changesets to release 5 packages

Name	Type
@langchain/redis	Patch
@langchain/openai	Patch
@langchain/anthropic	Patch
@langchain/mongodb	Minor
langchain	Patch

Not sure what this means? Click here to learn what changesets are.

Click here if you're a maintainer who wants to add another changeset to this PR

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

1 Skipped Deployment

Project	Deployment	Preview	Updated (UTC)
langchainjs-docs	Ignored		Oct 13, 2025 5:56am