add laminar observability integration

[dinmukhamedm]

Title

Laminar observability docs

Relevant issues

Pre-Submission checklist

Please complete all items before asking a LiteLLM maintainer to review your PR

• I have Added testing in the tests/litellm/ directory, Adding at least 1 test is a hard requirement - see details
• I have added a screenshot of my new test passing locally
• My PR passes all unit tests on make test-unit
• My PR's scope is as isolated as possible, it only solves 1 specific problem

Type

📖 Documentation

Changes

• Add new page with Laminar observability
• Remove outdated Laminar / OpenTelemetry guide

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Comments	Updated (UTC)
litellm	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	Jul 1, 2025 1:38pm

[krrishdholakia]

why does a user need to pip install your sdk to send you logs?

Isn't it OTEL compatible? if so - a simple callback should work too?

[dinmukhamedm]

@krrishdholakia Laminar is indeed OTel-compatible, but so are many other integrations in the folder (e.g. Arize AI, Braintrust).

The raw OTel callback didn't fit our needs completely, mostly in terms of the attributes standards and shapes. In addition, it has a small issue that has not been addressed for quite a while: #8169

From Laminar SDK, we simply import LaminarLiteLLMCallback (link), which just implements CustomBatchLogger. Again, this is similar to many other observability integrations.