Vercel AI
Adds instrumentation for Vercel AI SDK.
Requires SDK version 10.6.0 or higher for Node.js, Cloudflare Workers, Vercel Edge Functions and Bun. Requires SDK version 10.12.0 or higher for Deno.
Don't use the AI SDK's registerTelemetry API (AI SDK v7 and above) together with this integration. Sentry's vercelAIIntegration already instruments the AI SDK, so registering telemetry separately will result in duplicate spans.
Import name: Sentry.vercelAIIntegration
The vercelAIIntegration adds instrumentation for the ai SDK by Vercel to capture spans using the AI SDK's built-in Telemetry.
This integration is not enabled by default. You need to manually enable it by passing Sentry.vercelAIIntegration() to Sentry.init:
Sentry.init({
dsn: "____PUBLIC_DSN____"
tracesSampleRate: 1.0,
integrations: [Sentry.vercelAIIntegration()],
});
Sentry.init({
dsn: "____PUBLIC_DSN____"
tracesSampleRate: 1.0,
integrations: [Sentry.vercelAIIntegration()],
});
To correctly capture spans, pass the experimental_telemetry object with isEnabled: true to every generateText, generateObject, streamText, and ToolLoopAgent call. For more details, see the AI SDK Telemetry Metadata docs.
const result = await generateText({
model: openai("gpt-4o"),
experimental_telemetry: {
isEnabled: true,
recordInputs: true,
recordOutputs: true,
},
});
const result = await generateText({
model: openai("gpt-4o"),
experimental_telemetry: {
isEnabled: true,
recordInputs: true,
recordOutputs: true,
},
});
The integration also captures spans for the ToolLoopAgent class. Each call to generate() or stream() creates an agent span with individual LLM requests and tool executions as child spans.
Pass experimental_telemetry with isEnabled: true to the ToolLoopAgent constructor to correctly capture spans:
const agent = new ToolLoopAgent({
model: openai("gpt-4o"),
tools: {
/* ... */
},
experimental_telemetry: { isEnabled: true },
});
const result = await agent.generate({
prompt: "What is the weather in San Francisco?",
});
const agent = new ToolLoopAgent({
model: openai("gpt-4o"),
tools: {
/* ... */
},
experimental_telemetry: { isEnabled: true },
});
const result = await agent.generate({
prompt: "What is the weather in San Francisco?",
});
In order to make it easier to correlate captured spans with the function calls we recommend setting functionId in experimental_telemetry in all generation function calls:
const result = await generateText({
model: openai("gpt-4o"),
experimental_telemetry: {
isEnabled: true,
functionId: "my-awesome-function",
},
});
const result = await generateText({
model: openai("gpt-4o"),
experimental_telemetry: {
isEnabled: true,
functionId: "my-awesome-function",
},
});
For ToolLoopAgent, set functionId in the constructor:
const agent = new ToolLoopAgent({
model: openai("gpt-4o"),
tools: {
/* ... */
},
experimental_telemetry: {
isEnabled: true,
functionId: "weather-agent",
},
});
const agent = new ToolLoopAgent({
model: openai("gpt-4o"),
tools: {
/* ... */
},
experimental_telemetry: {
isEnabled: true,
functionId: "weather-agent",
},
});
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-4o"),
experimental_telemetry: { isEnabled: false },
});
const result = await generateText({
model: openai("gpt-4o"),
experimental_telemetry: { isEnabled: false },
});
If you set experimental_telemetry.recordInputs and experimental_telemetry.recordOutputs it will override the default behavior of collecting inputs and outputs for that function call.
const result = await generateText({
model: openai("gpt-4o"),
experimental_telemetry: {
isEnabled: true,
recordInputs: true,
recordOutputs: true,
},
});
const result = await generateText({
model: openai("gpt-4o"),
experimental_telemetry: {
isEnabled: true,
recordInputs: true,
recordOutputs: true,
},
});
ai:>=3.0.0 <=7
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").