Description

To help customers debug OPEA issues, we create a Triage Tool to test and gather needed information for debugging.
Mainly target on Docker Compose scenarios.

For the first draft, it is for ChatQnA.

How to Use:
Under root folder of OPEA Examples.
Xeon :
python .Triage.py ChatQnA/testsChatQnA_Xeon.json
Gaudi :
python .Triage.py ChatQnA/tests/ChatQnA_Gaudi.json
only need to change json file for different architectures like Gaudi

The Triage Tools will run some simple tests including:

1. health_check
2. micorservice testings
3. statistics

Below information will be gather after above testings

1. system info
2. env variable info
3. all docker logs for microservices
4. (optional) profiling results like vllm pytorch profiling

Report:
plan to have a HTML report.
Right now we have

1. simple console output
2. simple html report with all docker logs embedded

console output
Below is the screenshot for console output.

Xeon

Gaudi

html report with all docker logs embedded and profile log for vllm

Xeon

Gaudi

Other info:

1. all input, output, port configurations are in data.json file. no need to change codes for configurations and data
2. each example will be implemented as a seperate python class

ToDo:

1. need to make html report better
2. make sure all microservices are tested on both Xeon and Gaudi
3. move files into right folder
4. apply to all examples

Issues

n/a.

Type of change

List the type of change like below. Please delete options that are not relevant.

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds new functionality)
• Breaking change (fix or feature that would break existing design and interface)
• Others (enhancement, documentation, validation, etc.)

Dependencies

NA

Tests

Manual Testing

vllm profiling result from Triage Tool