[FEATURE] AI-Powered Search & Content Discovery

Problem

Developers need semantic search capabilities to help users find relevant content using natural language queries instead of exact keyword matching.

Goal

Integrate dotCMS's AI search functionality into the SDK, enabling semantic content discovery with relevance scoring.

Target Personas

• Developer teams
• Content teams

Demo Expectations

// What can be demonstrated in bi-weekly demo
const searchResults = await client.ai.search('articles about renewable energy');
const relatedContent = await client.ai.search.related('sustainability trends');

// Show: semantic matching, content scores, extracted text
console.log(searchResults.map(item => ({
  title: item.title,
  score: item.score,
  extractedText: item.aiContent
})));

User Stories

• As a developer, I want to implement intelligent search in applications, so that users can find content using natural language instead of exact keywords
• As a content team member, I want better content discoverability in headless applications, so that users can more easily find relevant content
• As a developer, I want relevance scoring and semantic matching, so that search results are ranked by actual relevance rather than just keyword matching

Acceptance Criteria

• Semantic search endpoints implemented with full TypeScript support
• Related content search functionality
• Relevance scoring included in search results
• Support for content type filtering and field-specific search
• Integration with existing dotCMS content structures
• Pagination and result limiting capabilities
• Extracted text and AI content summaries in results

Links

• dotAI Search API

Start with the linked dotAI Search API and locate the existing SDK content structures; the issue names no files or tests. Done means the demonstrated AI search and related-content calls support the listed filtering, scoring, pagination, extracted-content, and TypeScript requirements.