5 Steps to Build Your Own LLM Classification System

Подписаться 90 тыс.

Просмотров 6 тыс.

50% 1

Want to get started with freelancing? Let me help: www.datalumina.com/data-freel...
Need help with a project? Work with me: www.datalumina.com/consulting
🔗 GitHub Gist
gist.github.com/daveebbelaar/...
👋🏻 About Me
Hi there! I'm Dave, an AI Engineer and the founder of Datalumina. On this channel, I share practical coding tutorials to help you become better at building intelligent systems. If you're interested in that, consider subscribing!

Наука

Опубликовано:

3 июл 2024

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист

Посмотреть позже

Комментарии : 26

@avidlearner8117 26 дней назад

Maaaaaan.... You have THE BEST content, HANDS DOWN, for Gen AI Development. Clear, concise, every step explained, context.... Context is key... Bravo! And thanks a lot for this, it's inspiring.

@daveebbelaar 26 дней назад

Wow, thanks!

@farhanafridi8694 25 дней назад

Great! would love to see more of these.

@IdPreferNot1 24 дня назад

Such great content. I was going to gist this and then i see that's even how you're sharing it! I wanted to get a use case for Instructor library as looked interesting, but wasnt sure what it added beyond pydantic. ... and here it is. Thanks!

@mamadou-diandjalo6723 26 дней назад

This is exactly what i needed ! Thanks !!

@MuhammadFaizanMumtaz3 26 дней назад

great yar bhoat zbrdst.

@volt8399 24 дня назад

You did an amazin job, thank you so much for sharing this.

@jeromedupourque6067 26 дней назад

Congratulations this is just perfect!

@nexuslux 26 дней назад

Excellent video. Can you go into a bit more detail of how a database of this type of information might look and operate. Or any type of automation that would be involved? You mentioned sentiment or you mentioned doing analytics

@HerroEverynyan 24 дня назад

So cool that you make such great content, with clear explanations, and are so transparent

@daveebbelaar 24 дня назад

I appreciate that!

@guilhermeveiga9345 26 дней назад

Good tip thnkss

@synergyai 26 дней назад

How do you deal with the objections of sending this 'sensitive' data to OpenAI? We are doing a project now where we have to clean the data before sending it to openAI which is a big challenge. Curious to hear other people thoughts on this...

@daveebbelaar 25 дней назад

We use Azure OpenAI. Clients are generally okay with that in our experience.

@sumitbindra 26 дней назад

Loved the content. What are the advantages of using this instead of function calling?

@daveebbelaar 26 дней назад

@@sumitbindra streamlines prompt engineering, less code, and auto retries.

@sumitbindra 26 дней назад

@@daveebbelaar makes sense. thank you

@lesptitsoiseaux 26 дней назад

You have 50 000 classes transcripts you need to do a recommendation engine. Best approach?

@AbdulBasit-ff6tq 26 дней назад

Why don't you just just use the json response from openai directly?

@daveebbelaar 26 дней назад

This unifies your data structures without relying on prompt engineering. You still have to provide a JSON schema when using the JSON response with OpenAI, and there is also no automated retry mechanism if it fails to load your Pydantic model afterwards. Overall, this streamlines the development experience, especially if you're working with multiple developers who might all have slightly different prompting styles for JSON. Instructor uses the JSON response and Function Calling under the hood.

@AbdulBasit-ff6tq 26 дней назад

@@daveebbelaar How good or bad this solution is compared to other alternatives like langchain and llamaimdex output parsers?

@avidlearner8117 26 дней назад

@@AbdulBasit-ff6tq I don't think it's related.