Skip to content

Fix: Replace Turndown with node-html-markdown for Node.js compatibility #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Mar 11, 2025
Merged

Fix: Replace Turndown with node-html-markdown for Node.js compatibility #1

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9d62714
update packagejson
hideokamoto Mar 11, 2025
bc9f846
fix: Replace Turndown with node-html-markdown for Node.js compatibility
hideokamoto Mar 11, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 17 additions & 3 deletions package.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,10 +13,24 @@
"format": "prettier --write \"**/*.{js,jsx,ts,tsx,json,md}\"",
"format:check": "prettier --check \"**/*.{js,jsx,ts,tsx,json,md}\""
},
"keywords": [],
"keywords": [
"stripe",
"documentation",
"loader",
"langchain",
"sitemap"
],
"author": "hideokamoto",
"license": "ISC",
"description": "",
"license": "MIT",
"description": "A collection of utility libraries for easily retrieving and processing Stripe data",
"repository": {
"type": "git",
"url": "https://github.com/wpkyoto/stripe-docs-loader"
},
"bugs": {
"url": "https://github.com/wpkyoto/stripe-docs-loader/issues"
},
"homepage": "https://github.com/wpkyoto/stripe-docs-loader#readme",
"devDependencies": {
"@types/node": "^22.13.10",
"prettier": "^3.2.5",
Expand Down
25 changes: 22 additions & 3 deletions packages/core/package.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,10 +18,29 @@
"scripts": {
"dev": "vite build --watch",
"build": "vite build && tsc --emitDeclarationOnly",
"test": "vitest run"
"test": "vitest run",
"prepublishOnly": "npm run build"
},
"keywords": [],
"keywords": [
"stripe",
"documentation",
"sitemap",
"processor",
"utility"
],
"author": "hideokamoto",
"license": "MIT",
"description": "Core library for Stripe loaders"
"description": "Core library for Stripe loaders",
"repository": {
"type": "git",
"url": "https://github.com/wpkyoto/stripe-docs-loader",
"directory": "packages/core"
},
"bugs": {
"url": "https://github.com/wpkyoto/stripe-docs-loader/issues"
},
"homepage": "https://github.com/wpkyoto/stripe-docs-loader/tree/main/packages/core#readme",
"publishConfig": {
"access": "public"
}
}
30 changes: 24 additions & 6 deletions packages/langchain-stripe-loader/package.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,18 +18,36 @@
"scripts": {
"dev": "vite build --watch",
"build": "vite build && tsc --emitDeclarationOnly",
"test": "vitest run"
"test": "vitest run",
"prepublishOnly": "npm run build"
},
"dependencies": {
"@langchain/core": "^0.3.42",
"stripe-loaders-core": "*",
"turndown": "^7.2.0"
"node-html-markdown": "^1.3.0",
"stripe-loaders-core": "^0.0.0"
},
"keywords": [],
"keywords": [
"stripe",
"documentation",
"loader",
"langchain",
"llm",
"ai",
"document-loader"
],
"author": "hideokamoto",
"license": "MIT",
"description": "LangChain loader for Stripe data",
"devDependencies": {
"@types/turndown": "^5.0.5"
"repository": {
"type": "git",
"url": "https://github.com/wpkyoto/stripe-docs-loader",
"directory": "packages/langchain-stripe-loader"
},
"bugs": {
"url": "https://github.com/wpkyoto/stripe-docs-loader/issues"
},
"homepage": "https://github.com/wpkyoto/stripe-docs-loader/tree/main/packages/langchain-stripe-loader#readme",
"publishConfig": {
"access": "public"
}
}
9 changes: 6 additions & 3 deletions packages/langchain-stripe-loader/src/StripeComLoader.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
import { SitemapProcessor } from 'stripe-loaders-core';
import { BaseDocumentLoader } from '@langchain/core/document_loaders/base';
import { Document } from '@langchain/core/documents';
import Turndown from 'turndown';
import { NodeHtmlMarkdown } from 'node-html-markdown';
import { extractBodyFromHTML } from './utils';

/**
Expand Down Expand Up @@ -95,9 +95,12 @@ export class StripeComDocumentLoader extends BaseDocumentLoader {
const articles = urls
? await this.fetchArticlesFromURLs(urls, locale)
: await this.fetchArticlesFromSitemap(resource, locale);
const encoder = new Turndown();

// NodeHtmlMarkdownを使用してHTMLをMarkdownに変換
const nhm = new NodeHtmlMarkdown();

const documents = articles.map(article => {
const markdownContent = encoder.turndown(article.content);
const markdownContent = nhm.translate(article.content);
Comment on lines 102 to +103
Copy link

@gemini-code-assist gemini-code-assist bot Mar 11, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

high

Consider adding error handling around the nhm.translate function. If this function throws an error, it could crash the application. Wrapping it in a try-catch block would make the code more robust.

    const documents = articles.map(article => {
      let markdownContent;
      try {
        markdownContent = nhm.translate(article.content);
      } catch (error) {
        console.error("Error converting HTML to Markdown:", error);
        markdownContent = ""; // Or some default value or error handling
      }
      return new Document({

return new Document({
pageContent: markdownContent,
metadata: {
Expand Down
9 changes: 6 additions & 3 deletions packages/langchain-stripe-loader/src/StripeDocsLoader.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
import { SitemapProcessor } from 'stripe-loaders-core';
import { BaseDocumentLoader } from '@langchain/core/document_loaders/base';
import { Document } from '@langchain/core/documents';
import Turndown from 'turndown';
import { NodeHtmlMarkdown } from 'node-html-markdown';
import { extractArticleFromHTML } from './utils';
/**
* Interface representing a Stripe documentation article
Expand Down Expand Up @@ -61,9 +61,12 @@ export class StripeDocsDocumentLoader extends BaseDocumentLoader {
*/
async load(locale: string = 'en-US'): Promise<Document[]> {
const articles = await this.fetchArticlesFromSitemap(locale);
const encoder = new Turndown();

// NodeHtmlMarkdownを使用してHTMLをMarkdownに変換
const nhm = new NodeHtmlMarkdown();

const documents = articles.map(article => {
const markdownContent = encoder.turndown(article.content);
const markdownContent = nhm.translate(article.content);
Comment on lines 68 to +69
Copy link

@gemini-code-assist gemini-code-assist bot Mar 11, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

high

Consider adding error handling around the nhm.translate function. If this function throws an error, it could crash the application. Wrapping it in a try-catch block would make the code more robust.

    const documents = articles.map(article => {
      let markdownContent;
      try {
        markdownContent = nhm.translate(article.content);
      } catch (error) {
        console.error("Error converting HTML to Markdown:", error);
        markdownContent = ""; // Or some default value or error handling
      }
      return new Document({

return new Document({
pageContent: markdownContent,
metadata: {
Expand Down