Semantic Search Setup

Overview

This skill sets up vector embedding infrastructure for semantic search. Unlike keyword search (FTS5), semantic search finds conceptually similar content even without exact word matches.

Quick Start

from sentence_transformers import SentenceTransformer
import numpy as np

model = SentenceTransformer('all-MiniLM-L6-v2')

# Generate embeddings
texts = ["How to fix a bug", "Debugging software issues"]
embeddings = model.encode(texts, normalize_embeddings=True)

# Compute similarity
similarity = np.dot(embeddings[0], embeddings[1])
print(f"Similarity: {similarity:.3f}")  # ~0.85

When to Use

• Adding AI-powered search to document collections
• Finding conceptually related documents
• Preparing knowledge bases for RAG Q&A systems
• Building recommendation systems
• Enabling "more like this" functionality

Related Skills

• knowledge-base-builder - Build the document database first
• rag-system-builder - Add AI Q&A on top of semantic search
• pdf/text-extractor - Extract text from PDFs

Version History

• 1.1.0 (2026-01-02): Added Quick Start, Execution Checklist, Error Handling, Metrics sections; updated frontmatter with version, category, related_skills
• 1.0.0 (2024-10-15): Initial release with sentence-transformers, cosine similarity search, batch processing

Sub-Skills

• Best Practices

Sub-Skills

• Execution Checklist
• Error Handling
• Metrics
• Dependencies

Sub-Skills

• How Semantic Search Works
• Model Selection
• Step 1: Install Dependencies (+5)
• 1. CPU vs GPU (+3)
• Status Monitoring
• Example Usage