Labeling from code

This functionality is available from v0.5.0.

​

Example 1. Labeling a span created with automatic instrumentation

from lmnr import Laminar

with Laminar.with_labels(["my_label", "another_label"]):
    openai_client.chat.completions.create(...)

Note that any spans created within the with_labels block will inherit the labels, including auto-instrumented spans or any calls to observed functions.

​

Example 2. Labeling a span created manually

with Laminar.start_as_current_span(name="foo", labels=["my_label", "another_label"]):
    # your code here
    pass

Note that only the span created by this Laminar.start_as_current_span call will have the labels.

This functionality is available from v0.5.0.

​

Example 1. Labeling a span created with automatic instrumentation

import { Laminar, withLabels} from '@lmnr-ai/lmnr';

// This can be both a function or an async function
await withLabels(["my_label", "another_label"], (message: string) => {
  return openaiClient.chat.completions.create({
    messages: [{ role: 'user', content: message }],
      // ...
    });
}, userMessageValue);

Note that any spans created within the withLabels function will inherit the labels, including auto-instrumented spans or any calls to observed functions.

​

Example 2. Labeling a span created manually

import { Laminar } from '@lmnr-ai/lmnr';

const span = Laminar.startSpan('foo', { labels: ["my_label", "another_label"] });
// elsewhere
Laminar.withSpan(span, () => {
    // your code here
})

Note that only the span created by this Laminar.startSpan call will have the labels.