vai
FeaturesModelsCLIDesktop App
Open Source CLI Tool

Vai

Explore Voyage AI embeddings from your terminal — or your desktop.

CLI + Desktop App + Web Playground for Voyage AI embeddings, reranking, and MongoDB Atlas Vector Search.

Download Desktop App
$ vai embed "Hello, vector world!"
✓ Generated 1024-dim embedding in 142ms

Everything you need to work with embeddings

Six powerful tools in one CLI — from generating embeddings to benchmarking models.

Embed

Generate vector embeddings for any text using Voyage AI's state-of-the-art models.

⚖️
Compare

Measure cosine similarity, dot product, and euclidean distance between texts.

🔮
Multimodal

Compare images and text in the same vector space with multimodal embeddings.

🔍
Rerank

Re-order documents by semantic relevance to improve search quality.

Benchmark

Compare model latency, embedding quality, and costs across different models.

📚
Explore

Learn about embeddings, vector search, and RAG concepts with interactive guides.

Supported Models

Access the full range of Voyage AI models for text, multimodal, and reranking tasks.

Text Embedding
voyage-4-large
voyage-4
voyage-4-lite
voyage-code-3
voyage-finance-2
voyage-law-2
Multimodal
voyage-multimodal-3.5
Reranking
rerank-2.5
rerank-2.5-lite

Powerful from the command line

Simple, intuitive commands that get out of your way.

Terminal

$ vai embed "MongoDB Atlas provides vector search"
✓ Model: voyage-4 | Dimensions: 1024 | Latency: 142ms
$ vai compare "NoSQL database" "document store"
✓ Cosine: 0.8742 | Dot: 0.8612 | Euclidean: 0.5013
$ vai benchmark --models "voyage-4-large,voyage-4,voyage-4-lite"
✓ Benchmarked 3 models × 5 iterations — results saved
$ vai playground
✓ Playground running at http://localhost:3000
Desktop App

A full desktop experience

The Vai desktop app wraps the entire CLI experience in a beautiful Electron interface. Embed text, compare documents, run benchmarks, and explore vector search concepts — all with a visual interface.

Signed & notarized

Auto-updates

macOS.DMGWindows.EXELinux.AppImage

Vai Desktop

Embed
Compare
Benchmark
Explore

Enter text to embed...

[0.0234, -0.0891, 0.1456, 0.0023, ...]

voyage-4 · 1024 dimensions · 138ms