voyageai
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- API key required for hosted models; local model voyage-4-nano requires Python 3.10+ and the optional [local] extra.
- 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.
License · maintenance · safety
MIT (permissive) — MIT license permits commercial use, modification, and distribution with minimal restrictions—suitable for most production applications.
last release 2026-07-10 (35 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 3,882,848 downloads/mo, #2,462 on PyPI
Alternatives
Verify before relying
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])- 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.
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 on this page. Verify before relying on it.
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
voyageai on PyPI
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.
API key required for hosted models; local model voyage-4-nano requires Python 3.10+ and the optional [local] extra.
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])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 the current Python release <3.15,>=3.9 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 9 packagesrequestsaiohttptenacitynumpyaiolimiterpillowpydantictokenizerslangchain-text-splitters |
| Maintenance | Actively maintained 35 days since the last release |
| First released | |
| Downloads | 3,882,848 / month, #2,462 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | License :: OSI Approved :: MIT LicenseProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.9 |
Evidence: voyageai-0.5.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “semantic search vectors”
- voyageaiProvides Python access to Voyage AI's embedding and reranking APIs…
- pinecone-textProvides sparse and dense text encoders for converting documents and…
- usearchUSearch provides approximate nearest-neighbor vector search using…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also FlagEmbedding · sentence-transformers · opentelemetry-instrumentation-voyageai · fastembed · pinecone-plugin-inference · pymilvus.model · weaviate-client · redisvl · FlashRank · colpali-engine