-
The input and output of the LLM API contain sensitive information, so I don't want to send them to Datadog.
I would like to have an option to send data to Datadog with the input and output masked.
If …
-
Hi! We use the app extensively, but it lacks LLM observability functionality. There should be an easy way to gather user interactions within the AOAI app. [Langfuse](https://github.com/langfuse/langfu…
-
With Datadog LLM Observability and dd-trace-py 2.15.1, the LLM invocation span of the code snippet below will never finish, preventing the associated trace to be sent to the running agent and further …
-
As we begin to evaluate LLM assisted root cause analysis, we need a way to be able to evaluate the validity and usefulness of the results.
Historically, our process for evaluating these results has …
-
**Describe the bug**
We get an incorrect formatting error when attempting to import new data.
```
Validation error
Error at item 0: "llm.inputs.retrieved_context" key is expected in task data [ass…
-
Definetely want to add some observability to our spaceshiip. And, if [LangSmith](https://www.langchain.com/langsmith) still in closed beta we should looks for something more open for us.
My sugg…
-
I assume, because RayLLM runs on top of Ray Serve, I can follow [these steps](https://docs.ray.io/en/latest/cluster/kubernetes/k8s-ecosystem/prometheus-grafana.html) to get observability for LLM deplo…
-
### 🐛 What's Going Wrong?
> I'm using OpenTelemetry's auto-instrumentation with Grafana and Tempo to trace my application. However, when I run OpenLit, it starts logging traces for all API requests …
-
Given our example app that we're building, I was thinking that these are things we want to check off:
concepts to explain via first principles and thread into examples:
- [ ] - API call + knobs
…
-
# 🐛 Bug
from vllm import LLM, SamplingParams
llm = LLM(model=model_dir,enforce_eager=True)
then
```
File d:\my\env\python3.10.10\lib\site-packages\xformers\ops\fmha\_triton\splitk_kernels.…