Matteo Venditto

Implementations seem to be actually missing from the NuGet package (for Windows);:  I wonder if it is a consequence of the compilation problem with MinGW, as it seems the...

#### UPDATE I've got a bit of free time and I'm working to update the bindings and making it work with the latest backend version (with gpu support). Here is...

Weird, the build scripts are untouched. I'll try to make a clean clone and see if I can reproduce it; I've built multiple times yesterday while working on it without...

Was the build made with MinGW or msvc?

I'm working right now on providing an high-level API for chat message generation. ### UPDATE You can see here a [basic chat sample](https://github.com/mvenditto/gpt4all/blob/980cbd552278c938fecaee482eed41fa9338b742/gpt4all-bindings/csharp/Gpt4All.Samples/BasicChat/Program.cs#L73) with response regeneration (not upstream yet). __________________...

C# bindings will be fixed when #763 is merged

I'm going to take a look at this. But I think the problem is that with the Hermes model the underlying prompt context should be reused. Actually a new context...

> result = await model.GetStreamingPredictionAsync( > systemPrompt + " " + prompt2, > opts); Thanks for sharing. I'm looking fix this (and to revise and add a proper chat API...

Few weekends ago I had a bit of free time so I started working to update the bindings to the latest iteration of the backend (+ fixing the NuGet package)...

> Is this ready? Tested a couple more things. ready now