Skills azure-search-documents-ts
📦

azure-search-documents-ts

Safe

Build Azure AI Search Applications

Implement powerful search capabilities with Azure AI Search SDK. Create vector indexes, hybrid search, and semantic ranking for intelligent document retrieval.

Supports: Claude Codex Code(CC)
📊 71 Adequate
1

Download the skill ZIP

2

Upload in Claude

Go to Settings → Capabilities → Skills → Upload skill

3

Toggle on and start using

Test it

Using "azure-search-documents-ts". Search for products matching 'wireless headphones' with category filter

Expected outcome:

Returns ranked product results with relevance scores, filtered by Electronics category, including title, price, and description snippets

Using "azure-search-documents-ts". Vector search for documents similar to a query embedding

Expected outcome:

Returns semantically similar documents ranked by vector distance, even without exact keyword matches

Security Audit

Safe
v1 • 2/25/2026

This skill contains documentation for Azure AI Search SDK with TypeScript code examples. All static analyzer findings are false positives caused by misinterpreting markdown code fences. The skill reads environment variables for configuration, which is standard practice for Azure SDK authentication.

1
Files scanned
272
Lines analyzed
0
findings
1
Total audits
No security issues found
Audited by: claude

Quality Score

38
Architecture
100
Maintainability
87
Content
32
Community
100
Security
91
Spec Compliance

What You Can Build

Product Search with Semantic Ranking

Build an e-commerce search that combines text matching with vector similarity for relevant product discovery.

Document Retrieval System

Create a knowledge base search with hybrid search for finding relevant documents by meaning and keywords.

Autocomplete and Suggestions

Implement search-as-you-type with Azure Search suggesters for improved user experience.

Try These Prompts

Basic Index Setup 
Create an Azure Search index for a products catalog with fields for id, title, description, category, and price. Make title and description searchable.
Vector Search Implementation 
Add vector search to my Azure Search index. I have 1536-dimensional embeddings from Azure OpenAI. Show me how to configure the vector field and perform similarity search.
Hybrid Search Configuration 
Implement hybrid search that combines keyword matching with vector similarity. Show me how to tune the results and rank by relevance.
Semantic Search with Answers 
Configure semantic search on my Azure Search index to return extractive answers and captions. Explain the semantic configuration and query options needed.

Best Practices

  • Use hybrid search combining text and vector for best relevance across query types
  • Enable semantic ranking to improve results for natural language queries
  • Batch document operations using uploadDocuments instead of single document calls

Avoid

  • Do not upload documents one at a time - use batch operations for efficiency
  • Avoid using includeTotalCount in production queries as it impacts performance
  • Do not skip index field configuration - properly mark searchable, filterable, and facetable fields

Frequently Asked Questions

What Azure Search tier do I need for vector search?
Vector search requires Azure Search Basic tier or higher. Semantic search requires Standard tier or higher.
How do I authenticate to Azure Search?
Use DefaultAzureCredential for production with managed identity, or admin/query API keys for development. Store credentials in environment variables.
What embedding models work with Azure Search vector fields?
Any embedding model that produces numeric vectors. Azure OpenAI embeddings (text-embedding-ada-002) produce 1536-dimensional vectors commonly used with Azure Search.
How do I update existing documents in the index?
Use mergeOrUploadDocuments with the document key. Azure Search merges fields you provide and preserves existing values for unspecified fields.
Can I filter vector search results?
Yes, combine vectorSearchOptions with filter parameter. Filtering happens before vector search, reducing the candidate set for similarity matching.
What is the difference between semantic and vector search?
Vector search finds similar content using embeddings. Semantic search uses AI to understand query intent, extract answers, and provide captions. They can be used together for best results.

Developer Details

Author

sickn33

License

MIT

Repository

https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/azure-search-documents-ts

Ref

main

File structure

📄 SKILL.md