Voyage AI

Use Voyage AI’s embeddings and reranking models through Portkey.

Quick Start

Get started with Voyage AI in under 2 minutes:

Python

from portkey_ai import Portkey

# 1. Install: pip install portkey-ai
# 2. Add @voyage provider in model catalog
# 3. Use it:

portkey = Portkey(api_key="PORTKEY_API_KEY")

embedding = portkey.embeddings.create(
    model="@voyage/voyage-3",
    input="Name the tallest buildings in Hawaii"
)

print(embedding.data[0].embedding)

Tip: You can also set provider="@voyage" in Portkey() and use just model="voyage-3" in the request.

Add Provider in Model Catalog

Before making requests, add Voyage AI to your Model Catalog:

1. Go to Model Catalog → Add Provider
2. Select Voyage AI
3. Enter your Voyage API key
4. Name your provider (e.g., voyage)

Complete Setup Guide

See all setup options and detailed configuration instructions

---

Voyage AI Capabilities

Embeddings

Generate high-quality embeddings:

Python

from portkey_ai import Portkey

portkey = Portkey(api_key="PORTKEY_API_KEY", provider="@voyage")

embedding = portkey.embeddings.create(
    model="voyage-3",
    input="Name the tallest buildings in Hawaii"
)

print(embedding.data[0].embedding)

Reranking

Rerank documents for better search results:

Python

from portkey_ai import Portkey

portkey = Portkey(api_key="PORTKEY_API_KEY", provider="@voyage")

    response = portkey.post(
            "/rerank",
            model="rerank-2-lite",
            query="What is the capital of the United States?",
            documents=[
                "Carson City is the capital city of the American state of Nevada.",
        "The Commonwealth of the Northern Mariana Islands is a group of islands in the Pacific Ocean.",
        "Washington, D.C. is the capital of the United States.",
        "Capital punishment has existed in the United States since before it was a country."
            ]
        )

    print(response)

---

Supported Models

Voyage AI offers specialized embedding and reranking models:

Model	Type	Description
voyage-3	Embedding	Latest general-purpose embedding model
voyage-3-lite	Embedding	Faster, lighter version
voyage-code-3	Embedding	Optimized for code
rerank-2	Reranking	High-quality reranking
rerank-2-lite	Reranking	Faster reranking

Check Voyage AI’s documentation for the complete model list.

---

Next Steps

Gateway Configs

Add fallbacks, load balancing, and more

Observability

Monitor and trace your Voyage requests

Caching

Cache embeddings for faster responses

Metadata

Add custom metadata to requests

For complete SDK documentation:

SDK Reference

Complete Portkey SDK documentation