glibsonoran

I haven't left tested it with Ollama, but from their documentation it looks like it might work (I assume you're taking about Advanced Prompt Enhancer). Try using this URL: `http://localhost:11434/api`...

That error was from the `Local App (URL)` AI_Service. Did you try using both: `OpenAI compatible http POST` and `http POST Simplified Data`? I don't know if this will actually...

Looking again that documentation, you might also try these urls: ` * `http://localhost:11434/api/generate -d` * `http://localhost:11434/api/chat -d` In either case though they need to be used with the `OpenAI compatible...

Did it work for you Philmar?

CLOSED

I'm looking at your request, no promises implied yet, but I have a couple of questions: * Which services that APE supports would be able to interpret these response formats?...

OK, this is something I'd have to think about. It's fairly convoluted as to how to present this data to each service and which will actually accept them. Something that...

Ok, I have a rough prototype working on my dev side build. You have some specific prompt/system parameters you have to meet or chatGPT will kick your request out. I...

OK, so when using anything more than just json_object (i.e. Stuctured Output defined by a specific JSON) and a description in the prompt or system messages to describe how the...

Here's an example of using the plain json_object response_format with a descriptive prompt. I think it's reasonable: