Usage

Running Orionix.js

Start by creating an Orionix client that interacts with OpenAI’s API.

Example Code

javascriptCopy codeconst { Orionix } = require('openai-orionix-node');

const client = new Orionix(process.env.OPENAI_API_KEY);
client.run();

The run() function in Orionix.js is similar to OpenAI's chat.completions.create() function but with additional features like agent function execution, handoffs, context variables, and multi-turn conversations.

Arguments

Argument	Type	Description	Default
agent	Agent	The (initial) agent to be called.	(required)
messages	Array	A list of message objects, similar to Chat Completions API messages.	(required)
contextVariables	Object	Additional context variables available to agents.	{}
maxTurns	Number	Maximum number of conversational turns before returning.	Infinity
debug	Boolean	Enables debug logging if true.	false

Response Fields

Field	Type	Description
messages	Array	The list of messages generated during the conversation.
agent	Agent	The last agent to handle the conversation.
contextVariables	Object	The most up-to-date context variables, including any changes during the conversation.

Agents

An Agent encapsulates instructions and functions (tools). These agents drive the conversation and can decide whether to hand off to another agent.

Example Code

javascriptCopy codeconst agentA = new Agent({
  name: "Agent A",
  instructions: "You are a helpful agent.",
});

Functions

Functions enable agents to perform actions like processing transactions, looking up information, or transferring control to other agents. Functions are called when the agent needs to perform a specific task.

Example Code

javascriptCopy codeconst transferToAgentB = () => agentB;

const agentA = new Agent({
  name: "Agent A",
  instructions: "You are a helpful agent.",
  tools: [{ name: 'transferToAgentB', fn: transferToAgentB }],
});

Handoffs and Context Variables

Agents can transfer control to other agents or update contextVariables based on the conversation flow.

Example Code

javascriptCopy codeconst salesAgent = new Agent({ name: "Sales Agent" });

const agent = new Agent({
  functions: [
    () => new Result({ agent: salesAgent, contextVariables: { department: "sales" } }),
  ],
});

Function Schemas

Orionix.js automatically converts functions into JSON schemas, allowing OpenAI’s API to call the appropriate function based on the tool name.

Example Code

javascriptCopy codefunction lookUpItem(searchQuery) {
    /**
     * @description Use to find item ID. Search query can be a description or keywords.
     * @param {string} searchQuery - Description or keywords to search for the item.
     * @returns {string} - The found item ID.
     */

    return console.log(`Searching for item: ${searchQuery}`);
}

Streaming

You can enable streaming in Orionix.js to receive real-time responses from agents.

Example Code

javascriptCopy codeconst stream = client.run({ agent, messages, stream: true });
for await (const chunk of stream) {
    console.log(chunk);
}

Evaluations

Orionix.js supports various evaluation methods to test and validate your multi-agent systems. You can find example evaluations in the /examples directory.

Utils

Use the run_demo_loop utility to test your agents interactively in a REPL environment.

Example Code

javascriptCopy codeconst { run_demo_loop } = require('openai-orionix-node/utils');

run_demo_loop(agent);

Core Contributors

• Pulkit Garg (Node.js adaptation)

• OpenAI (original Python framework)

This README now emphasizes that Orionix.js is a Node.js implementation of OpenAI Orionix, while maintaining a high standard for documentation and usage clarity.