> ## Documentation Index
> Fetch the complete documentation index at: https://apie.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Vercel AI SDK

> Track LLM generations from the Vercel AI SDK with Apie telemetry.

You use the Vercel AI SDK for streaming generations. Track each generation as an LLM call inside an Apie run.

<CodeGroup>
  ```ts TypeScript theme={null}
  import { withVercelAiGeneration } from "@apie-sh/sdk";

  await apie.withRun({ inputSummary: "Generate response" }, async (run) => {
    const result = await withVercelAiGeneration(
      apie,
      {
        runId: run.id,
        model: { provider: "openai", name: "gpt-4o" },
        inputSummary: "Summarize incident feed",
      },
      async () => generateText({ model: openai("gpt-4o"), prompt: "Summarize..." }),
    );
  });
  ```

  ```python Python theme={null}
  from apie import with_vercel_ai_generation

  def work(run):
      return with_vercel_ai_generation(
          apie,
          {
              "runId": run.id,
              "model": {"provider": "openai", "name": "gpt-4o"},
              "inputSummary": "Summarize incident feed",
          },
          lambda: generate_text(model="gpt-4o", prompt="Summarize..."),
      )

  apie.with_run({"inputSummary": "Generate response"}, work)
  ```
</CodeGroup>

Events: `agent.llm.called`, `agent.llm.completed`, `agent.llm.failed`

### What you'll see

LLM generation events in the run timeline with model provider, name, and input summary.

<Note>
  The Vercel AI SDK is primarily a JavaScript ecosystem. The Python wrapper exists for API parity but is most relevant in JS/TS projects.
</Note>

## Next steps

<CardGroup cols={2}>
  <Card title="Custom telemetry" icon="chart-line" href="/observe/custom-telemetry">
    LLM calls and workflow steps.
  </Card>

  <Card title="Integrations hub" icon="plug" href="/integrations/index">
    All integrations.
  </Card>
</CardGroup>