Voxell

https://voxell.ai/docs
Admin
Voxell is a real-time data and AI platform that offers self-hosted cross-device state...
Tokens:1,597
Snippets:25
Trust Score:2.2
Update:2 months ago
Show doc for...
Tokens:
Raw
### Install Voxell Lux SDK

Source: https://voxell.ai/docs

Install the Lux client library via npm.

```shell
npm i @voxell/lux
```

--------------------------------

### Initialize and Use Voxell Lux

Source: https://voxell.ai/docs

Configure the Lux store with your broker endpoint and API key to enable real-time state synchronization.

```javascript
// local-first read, live push on change
import { lux } from '@voxell/lux'

const store = lux('prefs', {
  endpoint: 'https://YOUR-broker.run.app/api/lux',
  apiKey: 'fw live …', realtime: true,
})

store.load((data, meta) => render(data))
store.save({ theme: 'dark' })
```

--------------------------------

### Query Documents with Voxell Answers

Source: https://voxell.ai/docs

Upload documents for indexing and perform grounded queries to receive answers with citations.

```shell
# 1. load a document (auto-chunks + embeds)
curl https://api.voxell.ai/v1/answers/handbook/documents \
  -H "Authorization: Bearer $VOXELL_KEY" \
  -d '{"name":"policy.md","text":"..."}'

# 2. ask a question, get a grounded answer + sources
curl https://api.voxell.ai/v1/answers/handbook/query \
  -H "Authorization: Bearer $VOXELL_KEY" \
  -d '{"query":"How many vacation days?","mode":"answer"}'
```

--------------------------------

### POST /v1/answers/handbook/documents

Source: https://voxell.ai/docs/lux

Uploads and indexes a document for use in the RAG pipeline.

```APIDOC
## POST /v1/answers/handbook/documents

### Description
Uploads a document to be automatically chunked, embedded, and indexed for future queries.

### Method
POST

### Endpoint
https://api.voxell.ai/v1/answers/handbook/documents

### Request Body
- **name** (string) - Required - The name of the document.
- **text** (string) - Required - The content of the document.

### Request Example
{
  "name": "policy.md",
  "text": "..."
}
```

--------------------------------

### POST /v1/answers/handbook/query

Source: https://voxell.ai/docs/lux

Queries the indexed document corpus to receive a grounded answer with citations.

```APIDOC
## POST /v1/answers/handbook/query

### Description
Queries the previously uploaded document corpus to retrieve a grounded answer based on the content.

### Method
POST

### Endpoint
https://api.voxell.ai/v1/answers/handbook/query

### Request Body
- **query** (string) - Required - The question to ask.
- **mode** (string) - Required - The operation mode (e.g., "answer").

### Request Example
{
  "query": "How many vacation days?",
  "mode": "answer"
}
```

--------------------------------

### POST /v1/embed

Source: https://voxell.ai/docs/lux

Generates vector embeddings for the provided text using the specified model.

```APIDOC
## POST /v1/embed

### Description
Converts input text into vector embeddings using the specified model. This endpoint is OpenAI-compatible.

### Method
POST

### Endpoint
https://api.voxell.ai/v1/embed

### Request Body
- **texts** (array of strings) - Required - The list of text strings to embed.
- **model** (string) - Required - The model tier to use (e.g., "turbo").

### Request Example
{
  "texts": ["how do I reset my password?"],
  "model": "turbo"
}
```

--------------------------------

### Generate Embeddings with Forge

Source: https://voxell.ai/docs

Send text to the Forge API to generate vector embeddings using an OpenAI-compatible interface.

```shell
curl https://api.voxell.ai/v1/embed \
  -H "Authorization: Bearer $VOXELL_KEY" \
  -d '{"texts":["how do I reset my password?"],"model":"turbo"}'
```
Tokens:
Raw