Is prompt engineering dead?
5:06
8 ай бұрын
Пікірлер
@SQLTalk
@SQLTalk 2 сағат бұрын
Very helpful. Thank you!
@mohamedkarim-p7j
@mohamedkarim-p7j Ай бұрын
Thank for sharing👍
@synthoelectro
@synthoelectro Ай бұрын
it's so bad that it continues to interrupt you when you use it. It's local and yet wants to ensure your safety in al ways, continually policing you.
@raphaelpaulian
@raphaelpaulian Ай бұрын
animals don't have language
@sansorno1910
@sansorno1910 Ай бұрын
hi alex, i am currently doing a stage and your video helped me thanks:), but i had a question, i dont understand what is the best method to obtain all the embedding, and i dont seem to find the api to know what should i put in the body of the request , can you help me?
@TheLibin27
@TheLibin27 2 ай бұрын
I have been using langchain for a long time, and I honestly dont see how this differs to it . I understand there is a slight implementation difference. but apart from that only other benefit I see is C# support
@cyberslot
@cyberslot 2 ай бұрын
You could save yourselves the political/propaganda element. From all uncounted number of articles available, the choice of this particular topic is more than flashy. It's ridiculous for techie persons who are expected to be smart in general...
@rhowardstone
@rhowardstone 2 ай бұрын
Why are Elon, Democrats, and Republicans authorship hard coded into the algorithm? How is that "the town square" ?
@marshallduvall1102
@marshallduvall1102 2 ай бұрын
If any call is questioned the electronic tracking system can check.
@marshallduvall1102
@marshallduvall1102 2 ай бұрын
All it is, they are eliminating people they have to pay ! That is ALL this is about !
@vishalaiml1649
@vishalaiml1649 2 ай бұрын
Hi @alexchaomander, Is there a python version instead of .NET version as a backend, I have being looking for it, and could not find. Can you point me to any github or knowledge base?
@Cedric_0
@Cedric_0 2 ай бұрын
Any upadte on that streamlit code , that would be helpful thanks
@VanCliefMedia
@VanCliefMedia 2 ай бұрын
I started watching this a year ago when you dropped this series and I am coming back to it to share with other developers and such. Since then we implemented some awesome features in our own software and creating a weird collaborative environment that is using semantic Kernal to edit the documents generated by multiple agents and people in a single environment. Its bee a wild journey and we found some unexpected features so just wanted to say thank you for these videos!
@giovanniemanuelenocco7475
@giovanniemanuelenocco7475 2 ай бұрын
Simple, clear, and useful. Thanks a lot
@thomasandre6864
@thomasandre6864 3 ай бұрын
Love that SK supports C# in addition to Python and JAVA. It is a really clean architecture that merges so well in existing .NET Core apps.
@crioss6803
@crioss6803 3 ай бұрын
Hi, how about the abstract ideas visualization in multidimensional space eg. some mathematical ideas and relations to other ideas - eg. in form of knowledge graph and/or deeper details research possibilities tools? Are there any such tools based on ai?
@adilgun2775
@adilgun2775 3 ай бұрын
great research topics but as an hands-on nlp engineer on ner boosted knowledge graphs and LLMs , my experiences say too naive to believe that it would work in productions systems
@snehotoshbanerjee1938
@snehotoshbanerjee1938 3 ай бұрын
Great Demo!
@asilusx24
@asilusx24 3 ай бұрын
I already know Apples mason rat and its escape route to Australia. Why does every name i look up its always some software engineer or IoT tech... AI engineer... it doesnt stay believable. I've been waiting for Tara - a rat(arat) to be useful. I guess it did.
@Cedric_0
@Cedric_0 4 ай бұрын
Streamlit code would be great, thanks
@beep_beep_beep
@beep_beep_beep 4 ай бұрын
It's crap. No where near as nuanced for modern war as necessary.
@joydeepbhattacharjee3849
@joydeepbhattacharjee3849 4 ай бұрын
Very nice presentation and explanation
@ir43
@ir43 4 ай бұрын
Are there any accelerators to convert a typical knowledge corpus of unstructured text to a knowledge graph conducive for graph rag? I understand we need to extract entities and figure out relationships but who does that work? An LLM?
@DriBiz
@DriBiz 4 ай бұрын
I think this is a similar situation when Kodak was trying to sell film in a digital world. When they tried to pivot to digital, it was too late. Chegg is trying to pivot to AI, but it might be too late with too much competition. The value Chegg offered 5 years ago is not the same value today.
@tylerd1297
@tylerd1297 4 ай бұрын
I dont like chris Christie but that was actually pretty funny. Vivek got him even better on the return
@soydecaracas
@soydecaracas 4 ай бұрын
Is there a demo of how to setup it?
@nguyenanhnguyen7658
@nguyenanhnguyen7658 5 ай бұрын
Very buggy. Even fundamental parameters as temperature, n, top_p are ignored !!! Expects next release.
@gutihernandez7868
@gutihernandez7868 Ай бұрын
Is this still an issue?
@energyexecs
@energyexecs 5 ай бұрын
Thanks for the video. I can see a Use Case in my energy industry. Does GraphRAG work across all "modes" and "modalities"?
@historia_tego_swetra
@historia_tego_swetra 5 ай бұрын
first of all, there is no MOVEMENT but state sponsored Russian proxies like the Yemenis. a very wrong choice of a dataset. second thing - there is NO NOVOROSSIA
@MrSikesben
@MrSikesben 5 ай бұрын
This is agreat demo Alex. I am going to try it out today
@madacol
@madacol 5 ай бұрын
Wow, I feel like I got a memory lapse, I am exactly the same person I was 42 seconds ago
@tee_iam78
@tee_iam78 5 ай бұрын
Thank you for your info.
@anthonyanalytics
@anthonyanalytics 5 ай бұрын
This is amazing!
@lesptitsoiseaux
@lesptitsoiseaux 5 ай бұрын
Its a month later, where's the code you promised? Please?
@CraigPulliam
@CraigPulliam 5 ай бұрын
Finally 🎉
@vcool
@vcool 5 ай бұрын
Admit it: y'all built graphrag first for use by the CIA. This is not a joke.
@Ian_Arden
@Ian_Arden 5 ай бұрын
Where did you get the body for this? This whole text is taken from some chief Russian propaganda bureau 😅
@swyxTV
@swyxTV 5 ай бұрын
this video could have been a tweet
@phatchenh1100
@phatchenh1100 5 ай бұрын
I call dip!!!!
@3ti65
@3ti65 5 ай бұрын
appreciate the open sourcing! keep it up :)
@ysy69
@ysy69 5 ай бұрын
This is powerful!
@PsyoPhlux
@PsyoPhlux 5 ай бұрын
Pretty soon, everyone will be graphragging their podcasts. Jre will be neat.
@bicepjai
@bicepjai 5 ай бұрын
Why do we need other faces on screen ? Hope they know they are just distractions :)
@nikharmalik6090
@nikharmalik6090 5 ай бұрын
And I hope you know that you can zoom in to the screen to not see them and that it's always better not to say anything if you don't have anything nice or useful to say 😊
@youcaio
@youcaio 5 ай бұрын
è bellissimo!
@ClancyWhittle
@ClancyWhittle 5 ай бұрын
Excellent! Can't wait to give this a try.
@TheLastRoseThatRaisedMe
@TheLastRoseThatRaisedMe 5 ай бұрын
put it in kernelmemory...
@randomswedishdude
@randomswedishdude 5 ай бұрын
Python 😞
@steveking4878
@steveking4878 5 ай бұрын
Amazing, I’ve been stoked about this! Thanks! 👍🏻
@alexchaomander
@alexchaomander 5 ай бұрын
To learn more about GraphRAG, watch the deep-dive on the tech behind the system with the team here! kzbin.info/www/bejne/qGGcpX2chLNpoac
@umaRfarooq407
@umaRfarooq407 5 ай бұрын
But how to do it? Lots of videos are there, but none of them telling actually how to do it?