10 Nov 2025 06:04 PM
Hello everyone,
I’m bringing some monitoring configurations to Dynatrace related to our AI environment. Langfuse is a crucial part of this monitoring; however, I couldn’t find any official documentation or recommendations on how to implement it.
Any suggestions?
Thank you!
Solved! Go to Solution.
11 Nov 2025 07:41 AM - edited 11 Nov 2025 07:41 AM
Hi,
No information in Hub. I would say review Extend Dynatrace.
Best regards
11 Nov 2025 08:06 AM
@Mateusbmo1 I'd recommend looking at Openllmetry integration https://langfuse.com/guides/cookbook/otel_integration_openllmetry , similar as it is done for observability of other AI workloads.
11 Nov 2025
02:22 PM
- last edited on
16 Jun 2026
10:41 AM
by
IzabelaRokita
TL;DR: There's no official Dynatrace documentation for Langfuse specifically, but the practical path is OpenTelemetry-based. Langfuse's SDK can export telemetry via OpenTelemetry, so you can send those OTLP traces into Dynatrace (e.g. through an OpenTelemetry collector) to alert on and visualize them. An alternative instrumentation route is OpenLLMetry, which builds on the OpenTelemetry GenAI semantic attributes and has Dynatrace integration docs. Dynatrace also offers an AI Observability App in the Hub, currently geared toward OpenLLMetry - so confirm compatibility if you're relying on the Langfuse SDK path.
Hi! I'm working on a similar project here, but still early on so I haven't implemented much yet and don't have any working examples, but can share a bit about what I've found along the way. And I'm very curious to hear other's responses!
What are you looking to get from Langfuse? From what I've seen, there are two parts to the tool to deal with: the SDK in your application, and the UI/backend.
Langfuse's SDK allows for data export using OpenTelemetry. We have apps that are instrumented with this SDK already and we're looking to it to send OpenTelemetry traces to a collector and then onto dynatrace so that we can alert and visualize the data onto existing dashboards, etc. But there are several libraries that will do the same thing, most are built on the Gen AI OpenTelemetry attributes. One of those is OpenLLMetry, which Dynatrace does have docs for integration.
The UI/backend is where you have to do a lot more work. Langfuse seems to have more built into their UI to parse out spans and extract the data in a useful way. I think this is doable in Dynatrace, but you'd have to spend significant time on dashboards, openpipeline rules, and/or custom applications to get to where they are today.
Theres a new AI Observability App in the hub that looks quite promising, but its setup specifically for OpenLLMetry. If your app needs to use the Langfuse SDK, I'm not sure if you could use this app or not.
14 Nov 2025 05:41 PM
Hello, how are you? I apologize for the delay.
We are enriching our observability area with AI Agents, and some information goes through Langfuse.
In addition, we are integrating both Bedrock and OpenAI.
How did you do this on your side?
For Bedrock, we did it through CloudWatch Stream. For OpenAI, we still haven’t managed to. Doing it through the SDK didn’t seem like the best approach
Featured Posts