Loading...
Last updated on
Workflows often require LLMs to interact with external systems or perform specific actions and using tools with LLMs is a powerful way to accomplish that.
This guide will show examples of using tools with both @gensx/openai and @gensx/vercel-ai. You can also find similar examples in OpenAI examples and Vercel AI examples in the GitHub repo.
The @gensx/vercel-ai package provides a simple way to define and use tools with LLMs.
Start by defining your tool using the tool helper from the Vercel AI SDK:
import { tool } from "ai";
import { z } from "zod";
const weatherTool = tool({
description: "Get the weather in a location",
parameters: z.object({
location: z.string().describe("The location to get the weather for"),
}),
execute: async ({ location }: { location: string }) => {
console.log("Executing weather tool with location:", location);
await new Promise((resolve) => setTimeout(resolve, 100));
return {
location,
temperature: 72 + Math.floor(Math.random() * 21) - 10,
};
},
});generateTextYou can use tools with the generateText function by passing them in the tools prop:
const WeatherAssistant = gensx.Component(
"WeatherAssistant",
async ({ prompt }: { prompt: string }) => {
const result = await generateText({
messages: [
{
role: "system",
content: "You're a helpful, friendly weather assistant.",
},
{
role: "user",
content: prompt,
},
],
model: openai("gpt-4o-mini"),
tools: { weather: weatherTool },
maxSteps: 5,
});
return result.text;
},
);You can also use tools with streaming responses using streamText:
const StreamingWeatherAssistant = gensx.Component(
"StreamingWeatherAssistant",
({ prompt }: { prompt: string }) => {
const result = streamText({
messages: [
{
role: "system",
content: "You're a helpful, friendly weather assistant.",
},
{
role: "user",
content: prompt,
},
],
model: openai("gpt-4o-mini"),
tools: { weather: weatherTool },
maxSteps: 5,
});
const generator = async function* () {
for await (const chunk of result.textStream) {
yield chunk;
}
};
return generator();
},
);You can also use the @gensx/openai package to work with tools using OpenAI’s native tool-calling capabilities.
Define your tool:
const weatherTool = {
type: "function" as const,
function: {
name: "get_weather",
description: "get the weather for a given location",
parameters: {
type: "object",
properties: {
location: {
type: "string",
description: "The location to get the weather for",
},
},
required: ["location"],
},
parse: JSON.parse,
function: (args: { location: string }) => {
console.log("getting weather for", args.location);
const weather = ["sunny", "cloudy", "rainy", "snowy"];
return {
weather: weather[Math.floor(Math.random() * weather.length)],
};
},
},
};runToolsThe OpenAI SDK provides a runTools method that handles the tool calling process:
const WeatherAssistant = gensx.Component(
"WeatherAssistant",
async ({ prompt }: { prompt: string }) => {
const result = await openai.beta.chat.completions.runTools({
model: "gpt-4.1-mini",
messages: [
{
role: "system",
content: "You're a helpful, friendly weather assistant.",
},
{
role: "user",
content: prompt,
},
],
tools: [weatherTool],
});
return await result.finalContent();
},
);You can also use tools with streaming responses:
const StreamingWeatherAssistant = gensx.Component(
"StreamingWeatherAssistant",
async ({ prompt }: { prompt: string }) => {
const result = await openai.beta.chat.completions.runTools({
model: "gpt-4.1-mini",
messages: [
{
role: "system",
content: "You're a helpful, friendly weather assistant.",
},
{
role: "user",
content: prompt,
},
],
tools: [weatherTool],
stream: true,
});
return result;
},
);Then to consume the output of the component, you would do the following:
const streamToolsResult = await StreamingTools({
prompt,
});
for await (const chunk of streamToolsResult) {
process.stdout.write(chunk.choices[0].delta.content ?? "");
}For more examples of using tools with GenSX, see the following examples: