Fairly straightforward. In the spirit of the repo, I've kept things simple rather than also automatically add everything (like optional Anthropic libraries or others).

I think asking beginners to modify directlycall_llm poses a risk of them putting their private keys on Github, so it's better to have them learn how to use environment variables to avoid taking chances.

xiongyuwuand others added2 commits

April 24, 2025 11:57

update call_llm() to use environ variable for choosing LLM provider (…

7cf0f05

…and model)

switch provider based on env variables

d66d976

Le09 mentioned this pull request

Apr 24, 2025

Ability to use local LLM(LM Studio or Ollama)#13

Open

Copy link

Member

zachary62 commentedApr 24, 2025

Thank you! I'm a bit worried thatenv will add friction to semi-technical people, but will add notes about security issue

eliliam approved these changes

Apr 24, 2025

View reviewed changes

Copy link

eliliam left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

Nice and clean, very extensible too if anyone wanted to add new providers down the line.

samin-irtiza approved these changes

Apr 27, 2025

View reviewed changes

Copy link

redliu312 commentedApr 30, 2025

hihi@Le09

do you think it is required to add

from dotenv import load_dotenvload_dotenv()

in the top section of the call_llm.py

I tried your branch and it seems this is needed for load the .env file when the script executed

Copy link

Author

Le09 commentedApr 30, 2025

@redliu312 Oh, I see.
Environment variables are variables that are set in you terminal. So a standard development workflow is to do

workon Tutorial-Codebase-Knowledge-venv# activate your virtual environment with the correct set of python dependenciessource .env# load the API keyspython file.py

If done this way, the variables are available in everything that you do in this terminal. Sopython main.py andpython utils.call_llm.py would both get variables.
If you do the call from main, then main loads the variable first so call_llm should get them.
So, the issue is that callingutils/call_llm directly does not get them from main; since this is for testing purpose, theload_dotenv() should indeed be added to this file, but under theif __name__ == "__main__": line.