@voicenter-team/nuxt-llms-generator 0.1.0 → 0.1.1

package/README.md

@@ -237,12 +237,13 @@ npm run build
 
 ### Generation Options
 
-| Option               | Type      | Default                      | Description                            |
-|----------------------|-----------|------------------------------|----------------------------------------|
-| `enableIndividualMd` | `boolean` | `true`                       | Generate individual .md files per page |
-| `enableLLMSFullTxt`  | `boolean` | `true`                       | Generate combined llms-full.txt file   |
-| `maxConcurrent`      | `number`  | `5`                          | Maximum concurrent API requests        |
-| `anthropicModel`     | `string`  | `claude-3-5-sonnet-20241022` | Claude model to use                    |
+| Option                 | Type      | Default                      | Description                              |
+|------------------------|-----------|------------------------------|------------------------------------------|
+| `enableIndividualMd`   | `boolean` | `true`                       | Generate individual .md files per page  |
+| `enableLLMSFullTxt`    | `boolean` | `true`                       | Generate combined llms-full.txt file    |
+| `enableHtmlToMarkdown` | `boolean` | `true`                       | Convert HTML content to markdown using [node-html-markdown](https://www.npmjs.com/package/node-html-markdown) |
+| `maxConcurrent`        | `number`  | `5`                          | Maximum concurrent API requests          |
+| `anthropicModel`       | `string`  | `claude-3-5-sonnet-20241022` | Claude model to use                      |
 
 ### Cleanup Options
 
@@ -518,7 +519,16 @@ ls -la public/UmbracoData.json
    {
      enableAutoCleanup: true,
      cleanupOrphaned: true,
-     cleanupHidden: true
+     cleanupHidden: true,
+     enableHtmlToMarkdown: true  // Clean HTML from CMS content
+   }
+   ```
+
+4. **HTML Content Processing**:
+   ```typescript
+   {
+     enableHtmlToMarkdown: true,  // Convert <p>, <h1>, etc. to clean markdown
+     enableHtmlToMarkdown: false  // Keep HTML as-is (if AI already generates clean content)
    }
    ```
 
@@ -566,6 +576,7 @@ interface LLMSConfig {
   maxConcurrent?: number;             // 5
   enableLLMSFullTxt?: boolean;        // true
   enableIndividualMd?: boolean;       // true
+  enableHtmlToMarkdown?: boolean;     // true
   enableAutoCleanup?: boolean;        // true
   cleanupOrphaned?: boolean;          // true
   cleanupHidden?: boolean;            // true

package/dist/chunks/llms-files-generator.mjs

@@ -1,10 +1,11 @@
 import { existsSync, mkdirSync, readFileSync, writeFileSync } from 'fs';
-import { join, dirname } from 'path';
+import { join, dirname, basename } from 'path';
 import Mustache from 'mustache';
 import Anthropic from '@anthropic-ai/sdk';
 import { createHash } from 'crypto';
 import { JSONPath } from 'jsonpath-plus';
-import { T as TemplateError, E as ErrorCode, w as withErrorHandling } from '../shared/nuxt-llms-generator.dc009f50.mjs';
+import { T as TemplateError, E as ErrorCode, w as withErrorHandling } from '../shared/nuxt-llms-generator.3c82efc0.mjs';
+import { NodeHtmlMarkdown } from 'node-html-markdown';
 import '@nuxt/kit';
 import 'zod';
 
@@ -1067,6 +1068,11 @@ class TemplateGenerator {
   promptAnalyzer;
   cache;
   config;
+  nhm = new NodeHtmlMarkdown(
+    {},
+    void 0,
+    void 0
+  );
   constructor(config) {
     this.config = config;
     this.anthropicClient = new AnthropicClient(config);
@@ -1211,7 +1217,11 @@ class TemplateGenerator {
   async renderTemplate(template, data) {
     return withErrorHandling(async () => {
       const validatedTemplate = await templateValidationPipeline.validateAndFix(template);
-      return Mustache.render(validatedTemplate, data);
+      const renderedContent = Mustache.render(validatedTemplate, data);
+      if (this.config.enableHtmlToMarkdown) {
+        return this.nhm.translate(renderedContent);
+      }
+      return renderedContent;
     }, {
       template: template.substring(0, 200) + "...",
       dataKeys: Object.keys(data)
@@ -1502,8 +1512,8 @@ class LLMSFilesGenerator {
     return filename;
   }
   getLLMSFilePath(fullPath) {
-    const filename = fullPath.split("/").pop() || "";
-    return `llms/${filename}`;
+    const filename = basename(fullPath);
+    return `/llms/${filename}`;
   }
   getOutputDir() {
     return this.config.finalOutputDir || "dist";

package/dist/module.d.mts

@@ -13,6 +13,7 @@ interface LLMSConfig {
     enableAutoCleanup?: boolean;
     cleanupOrphaned?: boolean;
     cleanupHidden?: boolean;
+    enableHtmlToMarkdown?: boolean;
 }
 interface UmbracoUrlItem {
     nodeID: number;

package/dist/module.d.ts

@@ -13,6 +13,7 @@ interface LLMSConfig {
     enableAutoCleanup?: boolean;
     cleanupOrphaned?: boolean;
     cleanupHidden?: boolean;
+    enableHtmlToMarkdown?: boolean;
 }
 interface UmbracoUrlItem {
     nodeID: number;

package/dist/module.json

@@ -4,5 +4,5 @@
   "compatibility": {
     "nuxt": "^3.0.0"
   },
-  "version": "0.1.0"
+  "version": "0.1.1"
 }

package/dist/module.mjs

@@ -1,4 +1,4 @@
-export { l as default } from './shared/nuxt-llms-generator.dc009f50.mjs';
+export { l as default } from './shared/nuxt-llms-generator.3c82efc0.mjs';
 import '@nuxt/kit';
 import 'fs';
 import 'path';

package/dist/shared/{nuxt-llms-generator.dc009f50.mjs → nuxt-llms-generator.3c82efc0.mjs}

@@ -19,7 +19,8 @@ const LLMSConfigSchema = z.object({
   enableIndividualMd: z.boolean().optional().default(true),
   enableAutoCleanup: z.boolean().optional().default(true),
   cleanupOrphaned: z.boolean().optional().default(true),
-  cleanupHidden: z.boolean().optional().default(true)
+  cleanupHidden: z.boolean().optional().default(true),
+  enableHtmlToMarkdown: z.boolean().optional().default(true)
 }).strict();
 class SchemaValidator {
   static validateConfig(config) {
@@ -210,7 +211,8 @@ const DEFAULT_OPTIONS = {
   finalOutputDir: "public",
   enableAutoCleanup: true,
   cleanupOrphaned: true,
-  cleanupHidden: true
+  cleanupHidden: true,
+  enableHtmlToMarkdown: true
 };
 const llmsModule = defineNuxtModule({
   meta: {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@voicenter-team/nuxt-llms-generator",
-  "version": "0.1.0",
+  "version": "0.1.1",
   "description": "Nuxt 3 module for automatically generating AI-optimized documentation files (llms.txt, llms-full.txt, and individual .md files) from Umbraco CMS data using Anthropic's Claude API.",
   "repository": "your-org/my-module",
   "license": "MIT",
@@ -42,8 +42,11 @@
     "@anthropic-ai/sdk": "^0.30.0",
     "@nuxt/kit": "^3.11.2",
     "@voicenter-team/eslint-config-ts": "^1.0.22",
+    "i": "^0.3.7",
     "jsonpath-plus": "^8.0.0",
     "mustache": "^4.2.0",
+    "node-html-markdown": "^1.3.0",
+    "npm": "^11.6.0",
     "zod": "^4.1.9"
   },
   "devDependencies": {