C-LARA

Here is this week’s roundup:

UniSA server

The thing I’ve spent most time on this week is the UniSA server, which has made a great deal of progress. Almost everything is now installed, and a lot of it is working. It’s possible to use the core modules to create an internal project, use the AI to write and annotate the text, and render the result. This means that the core Python modules, the Postgres database, GPT-4 access and Google Cloud TTS access are now all up and running.

I’ve installed the webserver components (Nginx, Gunicorn) – I’m currently trying to get that part to work, I think we’re fairly close. ChatGPT-4 is as usual being very helpful.

Conference presentations

Alex’s students have created two short (1-2 minute) videos for WORLDCALL , and Catia should have everything she needs for the presentation.

I put together a draft presentation for ALTA. Alex is going to change the example (the Mandarin is apparently not totally convincing), and we will discuss and finalise at this week’s Zoom.

Melbourne student projects: Annotated Images

I still need to do the cleaning up to make it possible to attach more than one image to a text.

Another feature we should add is access to DALL-E-3, which is now available through the GPT-4 API. This would let us automatically input the text, or a part of the text, and get an image for it.

Memory and plugins

AskTheCode can now list the functions/methods in a file and get the definition of any given one. This is obviously extremely useful.

I exchanged a couple of mails with Papr Memory. They like the idea of “shared memories” and think this feature may be available fairly soon.

Next Zoom call

Note to Southern Hemisphere people: two hours later than winter time, i.e. same time as last week.

Thu Nov 9, 2023, 20:00 Adelaide (= 09.30 Iceland = 09.30 Ireland/Faroe Islands = 10.30 Europe = 11.30 Israel = 13.00 Iran = 17.30 China = 20:30 Melbourne/New Caledonia)