Can I filter results by relevance?

Yes, you can set a 'min_score' threshold to filter out low-relevance results and ensure only high-quality matches are returned.

What is hybrid search in this context?

Hybrid search combines the power of semantic vector embeddings (understanding intent) with traditional BM25 keyword matching (finding exact terms) to provide more accurate results.

What commerce entities can be searched?

The skill supports searching across Products, Customers, Orders, and Inventory items, including their metadata, notes, and descriptions.

Which embedding model does this skill use?

It utilizes OpenAI's 'text-embedding-3-small' model, which generates 1536-dimensional vectors for high-performance semantic analysis.

Commerce Vector Search

Name: Commerce Vector Search
Author: stateset

bystateset

•

전자상거래 솔루션

Performs hybrid semantic and keyword searches across products, customers, and orders using natural language queries.

This skill empowers Claude to perform advanced data retrieval within the StateSet iCommerce ecosystem by combining vector-based semantic similarity with traditional full-text keyword matching. By leveraging OpenAI's text-embedding-3-small model and SQLite FTS5 (BM25), it enables users to find products, customer profiles, order histories, and inventory items through natural language descriptions rather than exact term matches. This is ideal for building intelligent storefronts, streamlining warehouse management, and enhancing customer support tools with highly relevant search results ranked by a combined relevance score.

주요 기능

01Hybrid search combining semantic similarity and BM25 full-text keyword matching

02Comprehensive search statistics for managing embedding coverage across entities

03OpenAI-powered embeddings using the text-embedding-3-small model

041 GitHub stars

05Multi-entity support for products, customers, orders, and inventory data

06Configurable scoring thresholds to ensure result relevance

사용 사례

01Performing inventory discovery across various attributes and storage locations

02Locating specific customer records or order notes based on contextual similarity

03Finding products using vague or natural language descriptions like 'warm winter gear'

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add stateset/stateset-icommerce commerce-vector-search

For use in Claude.ai and ChatGPT

Download Skill