npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@vaicli/vai-workflow-multilingual-search

v1.0.0

Published

Translate a query into multiple languages, search in parallel, and merge results for cross-lingual retrieval.

Downloads

61

Vulnerabilities

Powered byPowered by Snyk
  • 0High
  • 0Medium
  • 0Low

Links

Git

Maintainers

merlynnmerlynn

Keywords

vai-workflowretrievalmultilingualtranslationparallelinternational

Readme

vai-workflow-multilingual-search

International knowledge bases contain documents in multiple languages. A user searching in English may miss highly relevant documents written in other languages. Voyage AI's embedding models handle multilingual content, but query-document language mismatch can reduce retrieval quality.

Install

vai workflow install vai-workflow-multilingual-search

How It Works

  1. Translate — An LLM translates the query into two additional target languages
  2. Parallel search — The original query and both translations are searched in parallel
  3. Merge — Results are deduplicated across languages
  4. Rerank — Final reranking against the original query normalizes relevance across languages

Execution Plan

Layer 1:             translate
Layer 2 (parallel):  search_original | search_lang1 | search_lang2
Layer 3:             merged
Layer 4:             final_rerank

Example Usage

vai workflow run vai-workflow-multilingual-search \
  --input query="What are the data privacy regulations for healthcare?" \
  --input collection="international_policy_docs" \
  --input language1="German" \
  --input language2="Japanese"

What This Teaches

  • LLM-generated translations are used as search inputs, demonstrating generate → query chaining
  • search_original depends only on inputs, so it can run in parallel with the translation-dependent searches
  • Cross-lingual reranking works because Voyage AI's rerank models handle multilingual input natively
  • Configurable inputs make the workflow adaptable without editing the JSON

License

MIT © 2026 Michael Lynn