---
id: voyageai
version: "0.5.0"
license: MIT
license_treatment: permissive
maintenance: active
---

# voyageai

License: permissive · Maintenance: active · Downloads: 3.9M/mo

## What it is and what it does

Voyageai is a Python client for Voyage AI's embedding and reranking services. It converts unstructured data—documents, queries, images, audio, video, or tabular data—into dense numerical vectors that capture semantic meaning, or scores document relevance for reranking. These vectors are core building blocks for semantic search and retrieval-augmented generation (RAG) systems, where they integrate with vector stores and language models to improve retrieval accuracy.

The library supports both hosted API endpoints and a local voyage-4-nano model that runs without an API key on Python 3.10+. It handles input validation, token accounting, and batch limits transparently. The local path mirrors the hosted API's behavior, though some output data types are not yet supported locally. Runtime dependencies include requests, aiohttp, tenacity for retry logic, pydantic for validation, and langchain-text-splitters for text chunking.

Use it for:

- Build semantic search systems where user queries are embedded and matched against document vectors in a vector store.
- Implement RAG chatbots that retrieve relevant documents by embedding queries and reranking results for accuracy.
- Rerank initial retrieval results from lexical search to refine document relevance before passing to a language model.
- Convert multimodal data (documents, images, audio) into unified vector representations for cross-modal search.
- Prototype embedding-based applications locally using voyage-4-nano without API keys.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Provides Python access to Voyage AI's embedding and reranking APIs for converting documents and queries into semantic vectors and scoring document relevance.

Yes. Voyageai is actively maintained, has low install friction, carries a permissive MIT license, and integrates cleanly into RAG and semantic search workflows. The optional local model is a genuine advantage for prototyping. No known security vulnerabilities. Install it if you need embeddings or reranking from Voyage AI; the API-only path has minimal overhead.

## Install

pip install voyageai
uv add voyageai
poetry add voyageai

## Installing voyageai

Before you install: Low friction install with a pure-API baseline. Optional local model support requires Python 3.10+ and pulls in torch and sentence-transformers; API-only users incur no import cost from those dependencies. Active maintenance with a release 35 days ago.

License in practice: MIT license permits commercial use, modification, and distribution with minimal restrictions—suitable for most production applications.

Quickstart:

pip install voyageai

import voyageai

vo = voyageai.Client(api_key="your-key")
result = vo.embed(["Hello, world!"], model="voyage-4-nano", input_type="document")
print(result.embeddings[0])

API key required for hosted models; local model voyage-4-nano requires Python 3.10+ and the optional [local] extra.

Verify before relying:

- Exact list of supported embedding and reranking models beyond voyage-4-nano.
- Rate limits, batch size constraints, and pricing tier details for the hosted API.
- Performance characteristics (latency, throughput) of local vs. hosted models.
- Whether int8 and uint8 output dtypes are supported in hosted API endpoints.

## Package facts

- License: MIT (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 3.9M/month (top 5,000 on PyPI)
- Known vulnerabilities: none known

## Tags

embedding API client, semantic search vectors, document reranking, RAG retrieval, voyage AI embeddings, neural embedding models, vector representation API, embeddings, rag, semantic-search

[View on SkillFed](https://skillfed.io/packages/voyageai) · [View on PyPI](https://pypi.org/project/voyageai/)