5 Steps to Build Your Own LLM Classification System

  Рет қаралды 15,979

Dave Ebbelaar

Dave Ebbelaar

Күн бұрын

Пікірлер: 32
@avidlearner8117
@avidlearner8117 7 ай бұрын
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
@daveebbelaar 7 ай бұрын
Wow, thanks!
@kenchang3456
@kenchang3456 Ай бұрын
This timely for me and brilliant, just what I need. Thank you very much!
@mksmurff
@mksmurff 3 ай бұрын
Very clear and real-world example too. Thank you
@farhanafridi8694
@farhanafridi8694 7 ай бұрын
Great! would love to see more of these.
@HerroEverynyan
@HerroEverynyan 6 ай бұрын
So cool that you make such great content, with clear explanations, and are so transparent
@daveebbelaar
@daveebbelaar 6 ай бұрын
I appreciate that!
@IdPreferNot1
@IdPreferNot1 6 ай бұрын
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!
@nexuslux
@nexuslux 7 ай бұрын
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
@mamadou-diandjalo6723
@mamadou-diandjalo6723 7 ай бұрын
This is exactly what i needed ! Thanks !!
@jeromedupourque6067
@jeromedupourque6067 7 ай бұрын
Congratulations this is just perfect!
@volt8399
@volt8399 6 ай бұрын
You did an amazin job, thank you so much for sharing this.
@MuhammadFaizanMumtaz3
@MuhammadFaizanMumtaz3 7 ай бұрын
great yar bhoat zbrdst.
@batigol_9
@batigol_9 2 ай бұрын
I tried following your script and I downloaded pip install -U instructor but I keep getting no module found instructor, have you faced this kind of errors any thoughts?
@lesptitsoiseaux
@lesptitsoiseaux 7 ай бұрын
You have 50 000 classes transcripts you need to do a recommendation engine. Best approach?
@sumitbindra
@sumitbindra 7 ай бұрын
Loved the content. What are the advantages of using this instead of function calling?
@daveebbelaar
@daveebbelaar 7 ай бұрын
@@sumitbindra streamlines prompt engineering, less code, and auto retries.
@sumitbindra
@sumitbindra 7 ай бұрын
@@daveebbelaar makes sense. thank you
@synergyai
@synergyai 7 ай бұрын
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
@daveebbelaar 6 ай бұрын
We use Azure OpenAI. Clients are generally okay with that in our experience.
@JasperPeters
@JasperPeters 9 күн бұрын
Azure OpenAI at least claims the data sent is not stored or used by Microsoft, OpenAI or any other third party. Claims is an important word if you really care, but it’s better than nothing.
@guilhermeveiga9345
@guilhermeveiga9345 7 ай бұрын
Good tip thnkss
@jppalmab
@jppalmab 7 ай бұрын
Gold
@erenyeager655
@erenyeager655 7 ай бұрын
combined it with fastapi to transform it to an endpoint and call in the frontend side ooooofff... faster development for machine learning web system
@AbdulBasit-ff6tq
@AbdulBasit-ff6tq 7 ай бұрын
Why don't you just just use the json response from openai directly?
@daveebbelaar
@daveebbelaar 7 ай бұрын
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
@AbdulBasit-ff6tq 7 ай бұрын
@@daveebbelaar How good or bad this solution is compared to other alternatives like langchain and llamaimdex output parsers?
@avidlearner8117
@avidlearner8117 7 ай бұрын
@@AbdulBasit-ff6tq I don't think it's related.
Building Reliable LLM Apps with OpenAI (Instructor Tutorial)
48:03
Dave Ebbelaar
Рет қаралды 14 М.
Improve RAG with This Simple API (code included)
16:53
Dave Ebbelaar
Рет қаралды 11 М.
1% vs 100% #beatbox #tiktok
01:10
BeatboxJCOP
Рет қаралды 67 МЛН
人是不能做到吗?#火影忍者 #家人  #佐助
00:20
火影忍者一家
Рет қаралды 20 МЛН
AI Is Making You An Illiterate Programmer
27:22
ThePrimeTime
Рет қаралды 170 М.
Why Agent Frameworks Will Fail (and what to use instead)
19:21
Dave Ebbelaar
Рет қаралды 117 М.
Transformers (how LLMs work) explained visually | DL5
27:14
3Blue1Brown
Рет қаралды 4,6 МЛН
host ALL your AI locally
24:20
NetworkChuck
Рет қаралды 1,6 МЛН
This LLM Factory Class Will Improve Your AI Apps
12:53
Dave Ebbelaar
Рет қаралды 6 М.
How to Build Effective AI Agents (without the hype)
24:27
Dave Ebbelaar
Рет қаралды 168 М.
AI Career Opportunities for Data Professionals - Time to Pivot?
23:59
Dave Ebbelaar
Рет қаралды 4,6 М.
The Secret to 90%+ Accuracy in Text Classification
10:34
Pritish Mishra
Рет қаралды 53 М.
I Analyzed My Finance With Local LLMs
17:51
Thu Vu
Рет қаралды 505 М.