←back to thread

Show HN: I built an AI that turns GitHub codebases into easy tutorials

(github.com)
923 points zh2408 | 2 comments | 19 Apr 25 21:04 UTC | HN request time: 0.407s | source
Show context
fforflo ◴[20 Apr 25 16:05 UTC] No.43744642[source]▶
If you want to use Ollama to run local models, here’s a simple example:

from ollama import chat, ChatResponse

def call_llm(prompt, use_cache: bool = True, model="phi4") -> str: response: ChatResponse = chat( model=model, messages=[{ 'role': 'user', 'content': prompt, }] ) return response.message.content

replies(1): >>43744660 #
1. mooreds ◴[20 Apr 25 16:09 UTC] No.43744660[source]▶
Is the output as good?

I'd love the ability to run the LLM locally, as that would make it easier to run on non public code.

replies(1): >>43744828 #
2. fforflo ◴[20 Apr 25 16:38 UTC] No.43744828[source]▶
It's decent enough. But you'd probably have to use a model like llama2, which may set your GPU on fire.