OpenAI for Remix

Import name: Sentry.openAIIntegration

This integration is enabled by default when tracing is enabled. If you'd like to modify your default integrations, read this.

The openAIIntegration adds instrumentation for the openai SDK to capture agent tracing gen_ai spans, recording model, token usage, latency, and (when enabled) inputs and outputs.

Sentry.init({
  dsn: "___PUBLIC_DSN___",
  // Tracing must be enabled for agent tracing to work
  tracesSampleRate: 1.0,
  integrations: [Sentry.openAIIntegration()],
});

Sentry.init({
  dsn: "___PUBLIC_DSN___",
  // Tracing must be enabled for agent tracing to work
  tracesSampleRate: 1.0,
  integrations: [Sentry.openAIIntegration()],
});

Supported Operations

By default, tracing support is added to the following OpenAI SDK calls:

• chat.completions.create() - Chat completion requests
• responses.create() - Response SDK requests
• embeddings.create() - Generate embeddings
• conversations.create() - Create conversations

Streaming and non-streaming requests are automatically detected and handled appropriately. chat.completions.create() and responses.create() produce the same span type: op gen_ai.chat, name like chat <model>.

Supported Versions

• openai: >=4.0.0 <8

Options

recordInputs

Type: boolean (optional)

Records inputs to OpenAI SDK calls (such as prompts and messages).

Defaults to true if dataCollection.genAI.inputs is true, which is the default.

recordOutputs

Type: boolean (optional)

Records outputs from OpenAI SDK calls (such as generated text and responses).

Defaults to true if dataCollection.genAI.outputs is true, which is the default.

Sentry.init({
  dsn: "___PUBLIC_DSN___",
  tracesSampleRate: 1.0,
  integrations: [
    Sentry.openAIIntegration({
      recordInputs: false,
      recordOutputs: false,
    }),
  ],
});

Sentry.init({
  dsn: "___PUBLIC_DSN___",
  tracesSampleRate: 1.0,
  integrations: [
    Sentry.openAIIntegration({
      recordInputs: false,
      recordOutputs: false,
    }),
  ],
});