---
title: Multilingual Static Word Embeddings Demo
sdk: gradio
app_file: app.py
pinned: false
---

# Multilingual Static Word Embeddings Demo

This Space loads a saved aligned multilingual embedding space and lets users
search translations and nearest neighbors with adjustable retrieval parameters.

Required artifact files:

- `aligned_all.faiss`
- `all_metadata.jsonl`
- `config.json`

The app does not use `aligned_all.vec`.

## Runtime configuration

By default, the app lists the newest artifact folder under:

`s3://131-component-staging/multilingual-static-word-embeddings/stage-6/`

Set these Hugging Face Space secrets for S3-compatible storage:

- `SE_ACCESS_KEY`
- `SE_SECRET_KEY`
- `SE_HOST_URL`

Optional environment overrides:

- `SPACE_ARTIFACT_S3_URI`: exact artifact folder, for example
  `s3://131-component-staging/multilingual-static-word-embeddings/stage-6/multilingual_space_20260521_133953.json`
- `SPACE_ARTIFACT_S3_PREFIX`: prefix to scan for the newest `multilingual_space_*.json`
- `ARTIFACT_CACHE_DIR`: local cache directory, default `/tmp/multilingual_space_artifacts`

Defaults for `top_k`, `min_score`, `csls_k`, `candidate_retrieval_k`,
`csls_prefetch_k`, and bidirectional consistency are read from `config.json`.