Hacker Newsnew | past | comments | ask | show | jobs | submit | RHab's commentslogin

Yeah, also my impression.


I wanted something like this for my knowledge wiki, nexidion: https://github.com/HabermannR/Nexidion Will look how hard it is to combine next week, thanks!


I am looking forward to getting feedback from you. I can't give any guarantees though))


I am working on something similar. I was also not aware Obsidian is not open source. Something never clicked for me with Obsidian. Will check out your code later. My repo: https://github.com/HabermannR/Nexidion


I just ended my contract with them. I could not reach my own raspberry pi Homepage which uses cloudflare. They called me and asked why I ended the contract, I told them about cloudflare, but that my cancellation is final, and magically my Homepage now works again!


A llm backend fantasy game. It uses structured output and supports Openai, Anthropic and LM Studio. Gemini support is ending, at the moment it is not working reliable. https://github.com/HabermannR/Fantasy-Tribe-Game


That’s a fun idea. I may try this one.


I am trying to understand structured output from LLMs, and as training I am building a text game.

OpenAI is using pydantic to create objects directly in its beta branch, it's quite nice. Anthropic is a bit more involved, as you need to involve tool calling.

LM Studio 0.3.5 introduced a bug for structured output when using pydantic and enums or literals, I created a workaround.

Also Gemini is not using Pydantic at all, instead TypedDict to create the json scheme.

And Gemini does not have a system message.

I am quite proud to have everything working, if you want to check out my code please take a look: https://github.com/HabermannR/Fantasy-Tribe-Game

Here is the backend: https://github.com/HabermannR/Fantasy-Tribe-Game/blob/main/L...

For example, this is how I call Gemini:

completion = model.generate_content(

messages[0]['content'] + ": " + messages[1]['content'],

generation_config=genai.GenerationConfig(

response_mime_type="application/json", response_schema=response_types.typed_dict

),

)

result = response_types.pydantic_model.model_validate_json(completion.text)

Happy for any feedback!


Hi, I am programming as a hobby since I am seven, and I always wanted to program a game, but never finished anything. I am super fascinated by LLMs, and made a small interactive text-based strategy game, where the player can choice a tribe and then gets presented 3 choices, which will shape the development of the tribe from humble beginnings to god like ascension. Everything is done procedurally by an LLM using structured output. I support OpenAI, Anthropic, and local LLM, tested with LM Studio. Please take a look and give me some feedback, thanks! https://github.com/HabermannR/Fantasy-Tribe-Game


Abaqus for example is by core, I am severly limited, for me this makes totally sense.


Würselen! The world is small :D


No, I could only get 2.7B to run on 8GB VRam unfortunatly.


it is 2.7B


Loading seems to have worked on my laptop's RTX 3070, `nvidia-smi` shows `5188MiB / 8192MiB` in memory usage.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: