Skip to main content
Follow one path to a visible result. Choose your language tab.

​
Prerequisites:

  • Node.js 18+ or Python 3.10+
  • Valid Moss project credentials (MOSS_PROJECT_ID, MOSS_PROJECT_KEY)
  • JS: @moss-dev/moss; Python: moss
1

Install

npm install @moss-dev/moss
2

Configure credentials

From the Moss portal, copy your project credentials. Set them as env vars:
export MOSS_PROJECT_ID="your_project_id"
export MOSS_PROJECT_KEY="your_project_key"
3

Create and query an index

Save and run npx tsx quickstart.ts or python quickstart.py):
import { MossClient, DocumentInfo } from '@moss-dev/moss'
const client = new MossClient(process.env.MOSS_PROJECT_ID!, process.env.MOSS_PROJECT_KEY!)
const documents: DocumentInfo[] = [
  { id: 'doc1', text: 'How do I track my order? You can track your order by logging into your account.', metadata: { category: 'shipping' } },
  { id: 'doc2', text: 'What is your return policy? We offer a 30-day return policy for most items.', metadata: { category: 'returns' } },
  { id: 'doc3', text: 'How can I change my shipping address? Contact our customer service team.', metadata: { category: 'support' } },
]
const indexName = 'faqs'
await client.createIndex(indexName, documents, { modelId: 'moss-minilm' }) // default; use 'moss-mediumlm' for higher accuracy
await client.loadIndex(indexName)
const results = await client.query(indexName, 'How do I return a damaged product?', { topK: 3 })
console.log(results.docs[0])

​
Example output

{
  "id": "doc2",
  "score": 0.88,
  "text": "What is your return policy? We offer a 30-day return policy for most items."
}
Need keyword-heavy results? In the Python SDK, use alpha=0.0 for pure keyword, alpha=1.0 for pure semantic, or a blend in between (see Retrieval for details).

​
Next steps

You just created a cloud index and queried it. Moss does much more:

Core concepts

Indexes, embeddings, retrieval, sessions, and sync in one place.

Sessions

Local-first, real-time indexing during a live interaction.

Hybrid search

Blend semantic and keyword scoring with alpha.

Metadata filtering

Narrow results with $eq, $in, $near, and more.

Custom embeddings

Bring your own vectors instead of the built-in model.

Multi-index search

Query several indexes at once for a global top-K.

Data hydration & sync

Hydrate on-device indexes and keep them fresh.

SDK Overview

Full per-language API: Python, JavaScript, Swift, Elixir, Browser, C.