Tweaked the test generator and updated the tests

Added the option to pause a failed endpoint in order to be able to kick it with a restart

Added the test question generator and increased the size of the question bank to 500

Added a missing comment

Fixed a bug where if the architecture had entirely failed and not generated a response the whole load of TestGroups would crash. Need to fix the root cause of the failure to generate a response, but also should be caught gracefully here in any event.

Refactored loading the TestGroups to make the structure of the json load and the DB load the same and clearer

Added comments throughout

Tweaked message

Switched endpoint control to use the writeable token as it was inconsistent with the normal token.

Added front page message about the endpoints being scheduled.

Fixed bug with default prompt style not being valid

Configured more architectures to try and debug the fine-tuning issue each with different prompt styles

Trying a different prompting style

Added possibility to change the prompt style via parameter as I try and debug the fine-tuning issue.

Password protected the system controls page

Tweaked the training data format to try and fix the issue of the model repeating the question over and over

Added ability to select which models to compare side by side, allowing for more flexibility in testing my fine-tuned llamas

Moved trace records to DB

Added a time/response length plot to the charts

Added loading of test groups from both the DB and the local file and merging these two

Added message to system status

Adding the sqlite db where I will archive the test results and added the archiving code

Added option to directly pass the HF hub token when wiping the trace file, so I can use it locally outside of streamlit. Defaulted to None avoid changing existing behaviour.

Added button to force reload of trace files

Fixed bugs from the refactor of repo access. Now it should save trace again.

Added the test reporting structure

Refactored to bring common variables together. Also added a utility to get all the trace records as a list of records

Fixed bold type on home page

Updated the Chroma DB with the baseline products

Fixed the time.time bug here. Also a call to reset the Chroma DB

Tweaked the way the prompt is formatted going into the LLM query, to avoid the fine-tuned model giving nonsense answers

Changed the name of the fine-tuned architecture

Update the URL for the fine-tuned api endpoint

Update the URL for the final fine-tuned api endpoint

Added a new placeholder page for basic reporting

Updated the home page message to reflect the available pages.

Flipped the default dataset to be the baseline not the "All products"

Added a test runner page which allows you to run a batch of test from the UI

Added ability to wipe the logs from the system status page

Added utility to serve up the test questions

Added the comment to the actual save

Added a series of test questions

Added ability to include comments on the saved trace

Fixed typo in train script generation

Added adapter merging to the fine-tuning script generation

Added an example of the training script which I would not normally check in, with the hugging face secret token dummied out.

Fixed issue in resolving sleep function caused by import time.time elsewhere

Added awareness of the 'failed' status for an endpoint

Removed decimals from group tag and moved where it is called in the side by side flow so they actually share the same ID

Fixed bug