If you want to learn RAG Beyond Basics, checkout this course: prompt-s-site.thinkific.com/courses/rag
@ilaydelrey3122
Ай бұрын
a nice open source and self hosted version would be great
@AI-Teamone
Ай бұрын
Such an insightful information, Eagerly waiting for more multimodel approches.
@aerotheory
Ай бұрын
Keep going with this approach, it is something I have been struggling with.
@waju3234
Ай бұрын
Me too. For my case, the answer is normally hidden behind the data, context and the images.
@legendchdou9578
Ай бұрын
Very nice video but if you can do it with open source embedding model it would be very cool. thank you for the video
@ScottzPlaylists
11 күн бұрын
Need to do it all in open source. No API Keys.
@tasfiulhedayet
Ай бұрын
We need more videos on this topic
@ArdeniusYT
Ай бұрын
Hi your videos are very helpful thank you
@engineerprompt
Ай бұрын
Glad you like them!
@ignaciopincheira23
Ай бұрын
It is essential to conduct a thorough preprocessing of the documents before entering them into the RAG. This involves extracting the text, tables, and images, and processing the latter through a vision module. Additionally, it is crucial to maintain content coherence by ensuring that references to tables and images are correctly preserved in the text. Only after this processing should the documents be entered into a LLM.
@engineerprompt
Ай бұрын
agree!
@jtjames79
Ай бұрын
That's a lot of work. Can an AI do this?
@engineerprompt
Ай бұрын
@@jtjames79 Yup :)
@ai-touch9
Ай бұрын
I appreciate your effort. Pl create one to fine tune the model for efficient retrieval if possible, with lang chain.
@vinayakaholla
Ай бұрын
Can you pls dive deeper into why qdrant was used and other vector dbs limitations to store both text and image embeddings, thx
@engineerprompt
Ай бұрын
will see if I can create a video on it.
@Techn0man1ac
Ай бұрын
What about make same, but using LLAMA3 or less local LLM?
@RolandoLopezNieto
Ай бұрын
Lots of good info, thanks
@garfield584
Ай бұрын
Thanks
@mohsenghafari7652
Ай бұрын
it's great job! Thanks
@engineerprompt
Ай бұрын
thanks :)
@RedCloudServices
2 күн бұрын
do you think all of this is now replaced with Gemini ?
@BACA01
Ай бұрын
Thanks your videos are very helpful. I have several Gigs of pdf ebooks that i would like to process with RAG. What do you think what approach would be the best, this or a graphrag. In my case i'm looking only for local models as the costs would be very high. What if to convert all pdf pages into images first and then process them with local model like phi 3 vision and then process it with Graphrag, would it work out?
@JNET_Reloaded
Ай бұрын
wheres the code used?
@BarryMarkGee
24 күн бұрын
Out of interest what is the application called that you used to illustrate the flows? (2:53 in the video) thanks.
@engineerprompt
24 күн бұрын
I am using mermaid code for this.
@BarryMarkGee
24 күн бұрын
@@engineerprompt thanks. Great video btw 👍🏻
@amanharis1845
Ай бұрын
Can we do this method using Langchain ?
@engineerprompt
Ай бұрын
Yes, will be creating a video on it.
@codelucky
Ай бұрын
Is it better than GraphRAG? How does the output quality compare to it?
@engineerprompt
Ай бұрын
You could potentially create a graphRAG on top of it.
@RickySupriyadi
Ай бұрын
I except image generation will be have another kind of breed... image gen based on image understanding based on facts
@redbaron3555
Ай бұрын
This approach is not good enough to add value. The pictures and text needs to be referenced and linked in both vector stores to create better similarities.
Пікірлер: 38