npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@orka-js/core

v1.5.1

Published

Core types, interfaces and classes for OrkaJS - TypeScript LLM framework

Downloads

236

Readme

@orka-js/core

Core types, interfaces, and utilities for the OrkaJS ecosystem — the foundation every package builds on.

Installation

npm install @orka-js/core

Quick Start

import { Orka, createOrka } from '@orka-js/core'
import { OpenAIAdapter } from '@orka-js/openai'

const orka = createOrka({
  llm: new OpenAIAdapter({ apiKey: process.env.OPENAI_API_KEY! }),
})

const response = await orka.chat([
  { role: 'user', content: 'Hello!' }
])
console.log(response.content)

RAG with Knowledge

import { Orka, Knowledge } from '@orka-js/core'

const knowledge = new Knowledge({ orka })

await knowledge.ingest([
  { id: 'doc-1', content: 'OrkaJS is a TypeScript AI framework.' }
])

const results = await knowledge.query('What is OrkaJS?', 3)

PII Guard (RGPD)

import { PIIGuard, detectPII, redactPII } from '@orka-js/core'

const guard = new PIIGuard()
const detected = guard.detect('My email is [email protected]')
// [{ type: 'email', value: '[email protected]', start: 12, end: 28 }]

const safe = redactPII('Call me at +1-555-1234')
// 'Call me at [PHONE]'

Streaming

import { consumeStream, parseSSEStream } from '@orka-js/core'

const stream = await llm.stream(messages)
const full = await consumeStream(stream)

// SSE from HTTP response
const events = parseSSEStream(response.body!)
for await (const event of events) {
  console.log(event)
}

Callbacks

import { CallbackManager } from '@orka-js/core'

const callbacks = new CallbackManager({
  onStart: (run) => console.log('Started', run.id),
  onEnd: (run) => console.log('Done in', run.duration, 'ms'),
  onError: (run, err) => console.error('Error', err),
  onToken: (token) => process.stdout.write(token),
})

Key Exports

| Export | Description | |--------|-------------| | Orka | Main entry point class | | createOrka(config) | Factory function | | Knowledge | Document ingestion and RAG | | LLMAdapter | Interface for custom LLM adapters | | VectorDBAdapter | Interface for custom vector DB adapters | | PIIGuard | PII detection and redaction | | detectPII(text) | Standalone PII detection | | redactPII(text) | Standalone PII redaction | | CallbackManager | Lifecycle hooks | | consumeStream(stream) | Collect full stream output | | parseSSEStream(body) | Parse SSE streams | | chunkDocument(doc, opts) | Split documents into chunks | | generateId() | Generate unique IDs | | OrkaError, OrkaErrorCode | Typed error classes |

Related Packages