Description
In https://github.com/opea-project/GenAIExamples/blob/main/CodeTrans/README.md
- Please generalize the architecture diagram to
a) replace TGI with Model-server (TGI or vLLM or other)
b) Instead of mentioning Xeon for CPU or Gaudi, leave it as hardware
Xeon => CPU or other Hardware
Gaudi => GPU( AMD ROCm, Intel Arc, Nvidia) or accelerator (Intel Gaudi)
Basically list options - Tracing and Monitoring points to README miscellaneous that has no mention of logging/tracing/. There must be a common README for set up and using Otelemetry, prometheus, graphana etc in ChatQnA. Re-use.
- Can even remove reference to GMC