ccat-api v0.10.6

Cheshire Cat AI API Client

API Client made in TypeScript to communicate with the Cheshire Cat AI.\ The package provides a class to interface with the Cheshire Cat AI backend.\ It can be used both in Browser and NodeJS environments.

Every endpoint is a CancelablePromise, which means you can cancel the request if you want.

Installation

npm install ccat-api
# OR
yarn add ccat-api
# OR
pnpm i ccat-api

Getting started

To set up the client, you must first import the CatClient class:

import { CatClient } from 'ccat-api'

const cat = new CatClient({
    baseUrl: 'localhost',
    user: 'user'.
    //... other settings
})

cat.send('Hello from a user!') // this will send a message to the /ws/user

cat.userId = 'new_user'

cat.send('Hello from a new user!') // this will send a message to the /ws/new_user

Client settings

API_KEY, CORE_HOST, CORE_PORT and CORE_USE_SECURE_PROTOCOLS refer to the CCAT Core .env file.

WebSocket settings

Then, for example, you can configure the LLM like this:

cat.api.settingsLargeLanguageModel.upsertLlmSetting('LLMOpenAIConfig', {
    openai_api_key: 'OPEN_API_KEY'
})

To send a message to the cat, you can:

cat.send('Hello my friend!')

You can listen to the WebSocket events:

cat.onConnected(() => {
    console.log('Socket connected')
}).onMessage(msg => {
    console.log(msg)
}).onError(err => {
    console.log(err)
}).onDisconnected(() => {
    console.log('Socket disconnected')
})

For example, you can get the list of plugins like this:

cat.api.plugins.listAvailablePlugins().then(plugins => {
    console.log(plugins)
})

Credits

Made for the Cheshire Cat AI organization.

This was possible thanks to openapi-typescript-codegen.