Vercel AI
Adds instrumentation for Vercel AI SDK.
This integration only works in the Node.js and Bun runtimes. Requires SDK version 8.43.0
or higher.
Import name: Sentry.vercelAIIntegration
The vercelAIIntegration
adds instrumentation for the ai
library by Vercel to capture spans using the AI SDK's built-in Telemetry
.
Sentry.init({
integrations: [new Sentry.vercelAIIntegration()],
});
To enhance the spans collected by this integration, we recommend providing a functionId
to identify the function that the telemetry data is for. For more details, see the AI SDK Telemetry Metadata docs.
const result = await generateText({
model: openai("gpt-4-turbo"),
experimental_telemetry: { functionId: "my-awesome-function" },
});
By default this integration adds tracing support to all ai
function callsites. If you need to disable span collection for a specific call, you can do so by setting experimental_telemetry.isEnabled
to false
in the first argument of the function call.
const result = await generateText({
model: openai("gpt-4-turbo"),
experimental_telemetry: { isEnabled: false },
});
If you want to collect inputs and outputs for a specific call, you must specifically opt-in to each function call by setting experimental_telemetry.recordInputs
and experimental_telemetry.recordOutputs
to true
.
const result = await generateText({
model: openai("gpt-4-turbo"),
experimental_telemetry: {
isEnabled: true,
recordInputs: true,
recordOutputs: true,
},
});
ai
:>=3.0.0 <5
Our documentation is open source and available on GitHub. Your contributions are welcome, whether fixing a typo (drat!) or suggesting an update ("yeah, this would be better").