Also github.com/QwenLM/Qwen2... gives prompts you can try such as "Read all the text in the image" (in case you were not aware of this notebook). Not sure this will lead to a drastic change.

What's the difference between your model and the MLX version?

And reviewing will be the bottleneck. Although we can use LLMs to help us write the reviews (not saying that the review should be made by the LLM alone).

Yes I was going to ask for more details about LangChain given how popular it seems to be.

Thanks for the pointer!

Really? mamba still seems to be faster than conda, I might just need to update my conda :)

Never mind I saw someone asked the same question below :)

Why is it considered anti pattern to have global environments?

Yes! I often do the same when I am in the debugger

Ok release updates cannot be automatic :)

Wow this is nice, thanks a lot for sharing! This configures automatic updates as well? What about release updates? I find myself stuck with old Ubuntu releases...

Here’s a little script I made which I use to get a server up and running automatically (after you answering a few questions, including “what’s your name”) in just a few minutes.

You can even fully automate it with a few environment variables.
github.com/AnswerDotAI/...

👋