Release 0.15

Refs #515, #525, #536, #537

gpt-4-turbo model ID, closes #493

Windows readline fix, plus run CI against macOS and Windows

* Run CI on Windows and macOS as well as Ubuntu, refs #407
* Use pyreadline3 on win32
* Back to fail-fast since we have a bigger matrix now
* Mark some tests as xfail on windows

Release 0.13

Refs #325, #351, #373, #376, #394, #396, #397, #404

Closes #402

Release 0.12

Refs #323, #324

Release 0.11.2

Refs #327

Release notes for 0.11.1

Refs #317, simonw/llm-gpt4all#16

Release 0.11

Refs #273, #274, #275, #280, #284, #286

Release 0.10

Refs #225, #229, #231, #254, #256, #259

Release 0.10a1

Refs #229, #244, #247, #248, #254, #256, #259, #263