Game Asset Deals Deal Finder for the Unity Asset Store™
Semantic Search View on Asset Store

Package details

Latest version
1.0.0
Last updated
First released
Unity version
6000.3.7 or later
Package size
119.6 MB
Files
22
Favorites
2
Views in the past week
6

Price tracking

Last checked
Tracked since
Lowest recorded
$13.99 on

Keywords

Semantic Search

by Prism Labs

No ratings yet

Native offline semantic search for Unity powered by MiniLM. Understands meaning instead of keywords with zero servers, zero APIs, and blazing-fast on-device AI inference.

$19.99

Buy on Asset Store

Affiliate link · Purchases support this site

Price history

Last 6 months

USD
Price history for Semantic Search, 6 months Current $19.99; lowest $13.99; highest $19.99 in this period. $0 $10 $20 Sep Oct Nov

Asset preview

1 / 11

Semantic Search screenshot 1

Semantic Search screenshot 1

About this asset

Semantic Search is a fully native AI-powered semantic search engine built exclusively for Unity. Unlike traditional keyword search, it understands the meaning behind user queries, allowing users to find relevant content even when exact words don't match. Everything runs completely offline using a lightweight MiniLM model through Unity Sentis, eliminating the need for cloud services, API keys, or backend infrastructure.

Designed for games, XR applications, enterprise software, education, and AI-powered tools, Semantic Search provides intelligent document retrieval with an incredibly simple workflow. Generate embeddings directly inside the Unity Editor, drop a prefab into your scene, and start searching using an intuitive async C# API.

Whether you're building an NPC knowledge system, offline documentation, product search, or Retrieval-Augmented Generation (RAG) pipeline, Semantic Search delivers fast, accurate, and privacy-friendly AI search on every supported platform.

Key Features

  • AI-powered semantic search that understands intent instead of keywords
  • Fully offline with no internet, cloud services, or API keys required
  • Native Unity implementation using Unity Sentis
  • Lightweight MiniLM model optimized for on-device inference
  • One-click embedding generation directly inside the Unity Editor
  • Supports TXT, Markdown, HTML, JSON, DOCX, and PDF documents
  • Automatic document chunking for improved retrieval quality
  • Runtime document indexing and semantic search
  • Flexible storage using Resources, StreamingAssets, or PersistentDataPath
  • Fast CPU execution with optional GPU acceleration
  • Quantized and full-precision model support
  • Clean async C# API with simple prefab integration
  • Built-in Editor tools, index manager, and search testing window
  • Demo scenes included for rapid learning and integration

Perfect For

  • NPC dialogue and knowledge systems
  • Offline help centers and FAQ applications
  • AI-powered RAG retrieval pipelines
  • In-game inventory and item search
  • Product catalogs and e-commerce search
  • Enterprise document search
  • Educational applications
  • Medical and legal reference systems
  • Chat history and conversation search
  • XR, VR, and AR applications
  • Smart content recommendation systems

From the publisher's Asset Store listing.

Technical details

  • Minimum Unity Version: Unity 2022.3 LTS or newer (including Unity 6.x)
  • Render Pipelines: Built-in, URP, HDRP
  • Supported Platforms: Windows, macOS, Linux, Android, iOS, WebGL, VisionOS
  • Programming Language: C#
  • AI Runtime: Unity Sentis (Unity Inference Engine)
  • Machine Learning Model: MiniLM Embeddings
  • Model Formats: ONNX and Sentis (.sentis)
  • Model Size: Approximately 45 MB (Quantized) / 90 MB (Standard)
  • Inference: Fully On-Device
  • Internet Required: No
  • Backend Server Required: No
  • Cloud API Required: No
  • Offline Support: Yes
  • GPU Required: No (CPU supported)
  • Runtime Indexing: Yes
  • Editor Embedding Generation: Yes
  • Automatic Text Chunking: Yes
  • Cosine Similarity Ranking: Yes
  • Supported Document Formats: TXT, MD, HTML, JSON, DOCX, PDF
  • Storage Options: Resources, StreamingAssets, PersistentDataPath
  • Prefab Included: Yes
  • Demo Scenes Included: Yes
  • Documentation Included: Yes
  • External Dependencies:Unity Sentis package (required)
    TextMeshPro (demo scenes only)

Compatibility

Unity version Built-in URP HDRP Custom
6000.3.7f1

As listed on the Asset Store.