@orama/plugin-secure-proxy
v3.0.4
Published
Orama plugin for generating embeddings securely on the front-end
Downloads
1,510
Readme
Orama Secure Proxy Plugin
Orama plugin for generating embeddings and performing vector/hybrid search securely on the front-end.
Usage
For the complete usage guide, please refer to the official plugin documentation.
To use the Orama Secure Proxy Plugin, you will need to sign up for a free account at https://cloud.orama.com
import { create, insert, search } from '@orama/orama'
import { pluginSecureProxy} from '@orama/plugin-secure-proxy'
const db = await create({
schema: {
title: 'string',
description: 'string',
embeddings: 'vector[384]'
},
plugins: [
pluginSecureProxy({
apiKey: 'xyz',
embeddings: {
defaultProperty: 'embeddings',
model: 'orama/gte-small',
onInsert: {
generate: true, // Generate the embeddings at insert-time
properties: ['title', 'description'], // Properties to generate embeddings from
verbose: false
},
},
chat: {
model: 'openai/gpt-4o'
}
})
]
})
Available embeddings models:
| Model name | Provider | Dimensions |
| -------------------------------- | -------- | ---------- |
| orama/gte-small
| Orama | 384 |
| orama/gte-medium
| Orama | 768 |
| orama/gte-large
| Orama | 1024 |
| openai/text-embedding-ada-002
| Openai | 1536 |
| openai/text-embedding-3-small
| Openai | 1536 |
| openai/text-embedding-3-large
| Openai | 3072 |
Available chat models:
| Model name | Provider |
| -------------------------------- | -------- |
| openai/openai/gpt-4o
| Openai |
| openai/gpt-4o-mini
| Openai |
| openai/gpt-4-turbo
| Openai |
| openai/gpt-4
| Openai |
| openai/gpt-3.5-turbo
| Openai |
Mode models coming soon!
For the full configuration guide of this plugin, please follow the official plugin documentation.