Supercharging RAG with Generative Feedback Loops from Weaviate

  Рет қаралды 4,775

AI Coffee Break with Letitia

AI Coffee Break with Letitia

Күн бұрын

Пікірлер: 17
@DerPylz
@DerPylz 5 ай бұрын
Cool! I love these hands-on videos with code examples! Thanks for sharing the notebook!
@nogueirad
@nogueirad 5 ай бұрын
Awesome! Thanks for sharing!
@femkeplantinga3726
@femkeplantinga3726 5 ай бұрын
Great video! 🤌
@guimaraesalysson
@guimaraesalysson 4 ай бұрын
Great video Letitia
@AICoffeeBreak
@AICoffeeBreak 4 ай бұрын
Thank you! 😁
@connor-shorten
@connor-shorten 5 ай бұрын
Awesome!!
@marcfruchtman9473
@marcfruchtman9473 5 ай бұрын
Thanks for the video. So, is Weaviate a database service that is leveraging the LLM to generate natural language queries to access the data? So, basically rather than hiring an SQL programmer, you just feed Weaviate the data (somehow), and use the LLM to gen the queries, which are then fed back to Weaviate so it can provide the query results?
@AICoffeeBreak
@AICoffeeBreak 5 ай бұрын
Thanks for watching it and for your question! Weaviate is a vector database (we've made a whole video on that topic, it's linked in the description, if you're interested), which means in addition to storing structured and unstructured data, like a "classical" database, it also stores the vector embeddings of the items. This way you can find related terms and use natural language queries. The default way to interact with Weaviate as a developer would be through GraphQL, or one of the other APIs (e.g. Python). Do check out our video on the topic, if you want to know more details!
@marcfruchtman9473
@marcfruchtman9473 5 ай бұрын
@@AICoffeeBreak Ah Thanks!
@encapsulatio
@encapsulatio 3 ай бұрын
Are there any LLM's out there that are specialized on teaching(potential students) and optimized by collaborating with people that are specialists in pedagogical frameworks and pedagogical tools?
@AICoffeeBreak
@AICoffeeBreak 3 ай бұрын
Haven't heard of something like this, except Khan Academy who announced they will use LLMs in teaching. Also, check out Karpathy's new company. x.com/karpathy/status/1813263734707790301?t=1Fng5bSgI4Bm5tcoJdHIYA&s=19
@elinetshaaf75
@elinetshaaf75 4 ай бұрын
nice one
@Ben_D.
@Ben_D. 5 ай бұрын
@user-wr4yl7tx3w
@user-wr4yl7tx3w 5 ай бұрын
but is the benefit worth the potential negatives? surely, there are tradeoffs here.
@TemporaryForstudy
@TemporaryForstudy 5 ай бұрын
nice video. I am from India. I am working in the AI field. do you have any remote opportunities for me?
@elpepemandioca
@elpepemandioca 5 ай бұрын
Hey letitia. I think you should consider changing the logo. It kinda looks like a turd
@AICoffeeBreak
@AICoffeeBreak 5 ай бұрын
GaLore EXPLAINED: Memory-Efficient LLM Training by Gradient Low-Rank Projection
11:38
AI Coffee Break with Letitia
Рет қаралды 9 М.
DALL-E 3 is better at following Text Prompts! Here is why. - DALL-E 3 explained
8:03
AI Coffee Break with Letitia
Рет қаралды 4,1 М.
When Cucumbers Meet PVC Pipe The Results Are Wild! 🤭
00:44
Crafty Buddy
Рет қаралды 58 МЛН
Introduction to LlamaIndex with Python (2024)
39:57
Alejandro AO - Software & Ai
Рет қаралды 24 М.
How modern search engines work - Vector databases explained! | Weaviate open-source
14:12
AI Coffee Break with Letitia
Рет қаралды 19 М.
Chunking with Generative Feedback Loops
19:49
Connor Shorten
Рет қаралды 1,3 М.
The Best RAG Technique Yet? Anthropic’s Contextual Retrieval Explained!
16:14
Transformers explained | The architecture behind LLMs
19:48
AI Coffee Break with Letitia
Рет қаралды 27 М.
MAMBA and State Space Models explained | SSM explained
22:27
AI Coffee Break with Letitia
Рет қаралды 53 М.
Chunking Best Practices for RAG Applications
53:45
KX
Рет қаралды 11 М.
RAG But Better: Rerankers with Cohere AI
23:43
James Briggs
Рет қаралды 62 М.
Stealing Part of a Production LLM | API protects LLMs no more
18:49
AI Coffee Break with Letitia
Рет қаралды 17 М.