Відео

amazing Tool for exchange faces right now in 2024, thanks Ian, i'm a beginner in this technology and of course i'm totally agree with you... this scares but makes me smile too.

I'm not sure how to check for outdated packages with uv?

uv does not have a built-in command to list all virtual environments. Unlike Conda that provide commands like 'conda env list'.

I prefer putting the .venv folder in a separate directory (on Linux: ~/.virtualenvs). Can we tell uv to behave like this? I store my projects in Dropbox and I don't want to litter it with huge virt. environments. If it's possible, I would switch from poetry.

I can't understand language. Speak English like a real American. :)

Thank you, indeed. It worked.

My cartrige, where the RPI 2W sits gets a little hot, thats fine right? I dont think a heatsink fits there anyway :/

Great video!

Ollama on my M1 just refused to run. How do I get around this??

Thanks for finding and explaining this, its such a different model from langchain (which I like. The side-by-side comparison with openai, langchain, ell was great. Ell is so much simpler for what you showed. Would be interesting to see how to use it in complex agent architectures, like plan-and-execute or CRAG.

How do you create a new project that I can put on github and have others then install using uv run? I'm trying to switch from pipx to uv for distributing apps.

I don't understand how they calculate price per million tokens for the open llm's and I can't find any information about it. Are they considering the current electricity prices / prices for solar panels / windmills / gpu's ?

I appreciate you showing the actual inference speed, other videos usually cut around it, making it unrealistically fast.

Great! this looks super slick! will use in one of the project I am working on!

I was literally planning to build something like this. Thank you!

nice. another tool rye from same developer.. on top of uv also good

We don't need no frameworkation. aider's CONVENTIONS markdown text file has done all this for AI-years, by adding a single sentence: "If a prompt seems to want to write a short story, {insert system prompt or executable script path}." Epic presentation, fantastic video, love your style and explanatory precision, but every time I think a framework can do more than aider I get a cold bucket of water and realize that aider is the pinnacle of human achievement, never to be underdone. Wait until you use aider to edit it's own CONVENTIONS markdown based on user input. Or give your PHP an aider() function which can edit the self-same app's own source code.Then users can make changes to the web app's behaviour that weren't preordained by the developer. Interesting to explore.

It's awesome and it's missing a context manager

I was playing with ell the past days. It's a very fresh approach. Very clean code. But I find the multi-turn tool usage quite complicated and I was unable to use the structured output with OpenAI compatible APIs. I hope these two points are being addressed.

it's nice but you save few lines of code hiding the actual interaction with openai api, which can be a limitation when you are trying to bend your code to particulary funky specs. I wonder how this library would behave when I need functions and structures output

These videos are beneficial. I have not yet had the opportunity to review the documentation in detail. Are there any prompt tuning or fine-tuning capabilities within this framework?

👍 I like your videos, will you cover GUI using AI options❓ like ---- PC GUI using AI's, Web using AI's --- Windows GUI and apps as a tool 👍 Also cover projects to duplicate OpenAI 01 (strawberry)

I love this as much as I hate the long lines in my code for a simple prompt.

Richard Mountains

You're very resourceful Ian! Nice find.

Excellent framework review, Ian. Thanks for sharing.

love it, thanks for sharing!! a new follower to your content! :)

Fantastic Ian

Ell? As in El? Yeah, we may be building the Demiurge. LOL

Can we have Typescript support please!

Excellent demo!

I cannot wait to give this a spin. Ell is so Elegant. :D

Wow

Her name was Lila She was a coder .....

Can I store and run standardized queries on pdfs? Say I have 4 or 5 standard questions to ask of a pdf, maybe the even follow on one from the next. Can I store the queries and then load in a pdf for the queries to run on?

Wow this is fabulous. One of those things you wonder "why didn't I do this myself?". I'm sure this is going to be big. Thanks so much for covering this!

this combined with Langroid would be so wonderful. I guess i need to refactor my code again.

With a standardized syntax it would probably be possible to move towards using the web interface to construct flows into code. That would be in incredibly powerful system and spell the end of dev jobs even faster!

Looks amazing. I just wish it worked with other languages besides just python.

Can I customize the voice to sound like me?

Very cool. Ive had the m1 varieties and 2012, got a i7 quad now with 16gb and 512ssd. seems to run alot faster than the other i5 2012

I wonder if this is compatible with the AI kit you can add to the pi5 for many times faster AI in other tasks

You are real hero

--add script is also amazing!

--with [module_name] => amazing!

i was looking for vids on using pyenv... well hello, uv :)

Great vid. Would you say there's a need for 96 GB RAM on a m2 or would 64 GB be enough for big models like mixtral

I created at a retro pie image for my raspberry pi 0. Would my image work on a pie zero 2

man, these commenters you have in your site are nasty! hahaha

did you try if phi3:mini model runs faster? (as you show it seems run faster than my notebook) but did you check if it is running over gpu or cpu? (here on notebook it is running on cpu)