PK

It would be very nice for [ollama.ai/library](https://ollama.ai/library) to provide a JSON API to query available model names and their tags (optionally also metadata like file-size, quantization etc.) , integrating Ollama...

> Thanks for the PR, @PhilKes. Can you please describe how you identified the properties that should be part of `OAuth2ClientConnectionDetails`? My first impression is that there are too many...

:+1: Any progress on this @jmorganca ? I think for most people a REST API would be the most benefitial, with pagination. I guess since many models have a lot...

> Apparently Llama 3 has already been trained on a lot more code than Llama 2. > > So, do we need a full blown Codellama 3 model, or do...

@carlrobertoh no idea why the `ChatToolWindowTabPanelTest.testSendingOpenAIMessageWithImage` fails, it succeeds locally. `No X11 DISPLAY variable was set, but this program performed an operation which requires it.` https://github.com/carlrobertoh/CodeGPT/actions/runs/9112340838/job/25051402045?pr=566#step:4:724

> Noice! 👍 > > It happens because the tests on the Github runner are executed in headless mode. You can replicate this by running `export JAVA_TOOL_OPTIONS='-Djava.awt.headless=true'` before executing the...

> The `dfp_telemetry_id` needs to be obtained from the You.com website and then must be passed into the Stytch request. > > > However, since You.com doesn't provide an actual...

This is fixed by https://github.com/carlrobertoh/CodeGPT/pull/531

You should be able to use Azure for code-completions now (https://github.com/carlrobertoh/CodeGPT/pull/476) In the Custom OpenAI Providers settings: 

> @reneleonhardt Yes, I have already tried it, it works. Thank you. That way is more comfortable for me to use completions rather than always on. But the downside of...