MetorialDocs

Use providers with SDKs

Connect Metorial provider tools to an LLM and build a chat-enabled app.

After you configure provider access in Metorial, you can connect those tools to an LLM like ChatGPT.

In this guide, you'll learn how to build a chat-enabled app that automatically handles tool calls from your Metorial providers.

What you'll learn

  • How to use a Metorial provider
  • How to use the Metorial SDKs

Before you start

  • Create a Metorial project
  • Configure at least one provider or integration
  • Create an API key

1. Install the SDKs

Run the installer for your language of choice:

npm install metorial @metorial/openai openai

2. Configure clients

Instantiate both clients with your API keys and your provider deployment ID.

import { Metorial } from 'metorial';
import { metorialOpenAI } from '@metorial/openai';
import OpenAI from 'openai';

let metorial = new Metorial({
  apiKey: 'metorial_sk_io2h4...'
});

let openai = new OpenAI({
  apiKey: '...your-openai-api-key...'
});
from metorial import Metorial, metorial_openai
from openai import AsyncOpenAI

metorial = Metorial(api_key="metorial_sk_io2h4...")
openai = AsyncOpenAI(api_key="...your-openai-api-key...")

3. Fetch your provider tools

Create a session that exposes your deployed provider tools.

let session = await metorial.connect({
	adapter: metorialOpenAI.chatCompletions(),
	providers: [
		{ providerDeploymentId: '...your-provider-deployment-id...' }
	]
});

let tools = session.tools();
session = await metorial.connect(
    adapter=metorial_openai(),
    providers=[{"provider_deployment_id": "...your-provider-deployment-id..."}],
)
tools = session.tools()

4. Send your first prompt

Kick off the loop by sending an initial message.

let messages = [
  { role: "user", content: "Summarize the README.md file of the metorial/websocket-explorer repository on GitHub." }
];
messages = [
  {"role": "user", "content": "Summarize the README.md file of the metorial/websocket-explorer repository on GitHub."}
]

5. Loop & handle tool calls

  1. Send messages to OpenAI, passing the tools.
  2. If the assistant response contains tool_calls, invoke it:
let response = await openai.chat.completions.create({
  model: 'gpt-4o',
  messages,
  tools
});
let choice = response.choices[0]!;
let toolCalls = choice.message.tool_calls;
let toolResults = await session.callTools(toolCalls);
response = await openai.chat.completions.create(
  model="gpt-4o",
  messages=messages,
  tools=session.tools(),
)
choice = response.choices[0]
tool_calls = choice.message.tool_calls
tool_results = await session.call_tools(tool_calls)
  1. Append both the tool call requests and their results to messages.
  2. Repeat until the assistant's response has no more tool_calls.

6. Display the final output

Once there are no more tool calls, your assistant's final reply is in:

console.log(choice.message.content);
print(choice.message.content)