Right now all it does is handle returning if there's already a message
being generated, but I'll extend it with more logic that I want to move
out of Generate().
* Move StreamingProcessor constructor to the top
Typical code style is to declare the constructor at the top of the class
definition.
* Remove removePrefix
cleanupMessage does this already.
* Make message_already_generated local
We can pass it into StreamingProcessor so it doesn't have to be a global
variable.
* Consolidate setting isStopped and abort signal
Various places were doing some combination of setting isStopped, calling
abort on the streaming processor's abort controller, and calling
onStopStreaming. Let's consolidate all that functionality into
onStopStreaming/onErrorStreaming.
* More cleanly separate streaming/nonstreaming paths
* Replace promise with async function w/ handlers
By using onSuccess and onError as promise handlers, we can use normal
control flow and don't need to remember to use try/catch blocks or call
onSuccess every time.
* Remove runGenerate
Placing the rest of the code in a separate function doesn't really do
anything for its structure.
* Move StreamingProcessor() into streaming code path
* Fix return from circuit breaker
* Fix non-streaming chat completion request
* Fix Horde generation and quiet unblocking
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
We were using getDeviceInfo to check whether we were on a desktop or a
mobile device. This can be done more simply with isMobile, which means
we can stop exporting getDeviceInfo.
I'd like to migrate over to using "textgen" to mean text-generation APIs
in general, so I've renamed the /textgenerationwebui/* endpoints to
/backends/text-completions/*.
