Dragan Jovanović

I can tell you how I ran this "locally" if it helps. I used docker for the complete OA stack on my local server like: ```docker compose --profile frontend-dev --profile...

Hi, Plugin is not included in docker containers, as its just example for now, there is no internal agreement yet, how we would go about default 'out-of-the-box' plugins. You can...

All that you have done seems about right. I am not sure, why is not working for you, do you have errors on the docker logger?

> It would be cool if you or someone can make some automated "dev" chat sessions like: I or any dev, provide input messages as JSON files, drag over chat...

Yes there are some logs, like: in routes/config.py

I reverted it, will try rebase, to fix conflicts

I think that input_key="input" is fix that you are asking for! Just define memory like this or so... ```python memory = ConversationBufferMemory(memory_key="chat_history", input_key="input", output_key='output', ai_prefix='GPT-4', human_prefix='User')

Yes that is exactly what I meant. and it works... On Fri, Mar 24, 2023, 20:10 Willem ***@***.***> wrote: > @draganjovanovich Thanks for your > reply. But I think my...

Its forbidden by the ToS. On Thu, Feb 2, 2023, 05:48 YonV1943 曾伊言 ***@***.***> wrote: > OpenAI used *40 people* when training their own chatGPT, and the > annotation process...

And this is a prompt that I used when I needed to get tool usage with small models, which does not work with **langchain**, but it's also not great below...