Best 15 mins of my day! You explained every single component in the code clear and crisp! Excited to check the other videos of yours. Thanks a bunch
@MaazBhatti-g8t
7 ай бұрын
The most productive 14 minutes of my day watching and learning from this video :)
@codingcrashcourses8533
7 ай бұрын
great! Thanks for your comment
@henkhbit5748
7 ай бұрын
Very informative.👍 Love the umap visualization 2 see the query and the embeddings.
@fuba44
7 ай бұрын
UniqueList = list(set(ListWithDuplicates)) to replace those nested for loops. Love your content!
@codingcrashcourses8533
7 ай бұрын
Does not work for complex objects in that way probably;)
@roguesecurity
7 ай бұрын
This channel is a gem 💎
@Canna_Science_and_Technology
7 ай бұрын
Thanks for the video. Perfect timing…. Need this for tomorrow.
@kenchang3456
5 ай бұрын
This video is terrific, I'll give it a try!
@codingcrashcourses8533
5 ай бұрын
Thank you!
@samyio4256
4 ай бұрын
Youre vids are insanely good. I doubt there is a better ai-prog-tuber
@codingcrashcourses8533
4 ай бұрын
Thank you so much :)
@micbab-vg2mu
7 ай бұрын
Thank you for the great video:)
@codingcrashcourses8533
7 ай бұрын
Thanks for your comment. Glas you enjoyed it :)
@felipecordeiro8531
3 ай бұрын
I don't know the umap library, its very interesting. Good explanation about RAG advanced techniques, sucess for you!
@codingcrashcourses8533
3 ай бұрын
thank you :)
@austinpatrick1871
7 ай бұрын
Awesome video. So I glad I found this channel. Long shot question: After testing several chunk/overlaps, my experimentation indicates an optimal chunk_size=1000 and overlap=200. My RAG contains about 10 medical textbooks (~50,000 pages). However, every video I see on RAG nobody uses chunks anywhere near that large. Does it seem improbable that my ideal chunk size is 1,000, or is there likely another variable at play?
@sivi3883
4 ай бұрын
Did you find anything? At least from my experience so far, with fixed chunk methodology (whatever be the chunk size or overlap) its easier to do POC but not for production grade quality. Did you try semantic chunking or chunking based on sections/headings and then capture relationship between the chunks via graph database?
@Reality_Check_1984
Ай бұрын
This isn't backed in any data that I found but brute force trial and error I found that I am served better with different chunk sizes for different document types. Something like sentiment is fine at rather large chunk sizes. Something like a spec sheet I will actually place it multiple times with different chunk sizes. I am not saying this is the way but certainly found an improvement with finer details and critical information if I do that. My sweet spot has been 1k/1.5k/2k depending on the document type. I am sure less works but I don't need to with most context windows and the greater context of the larger chunk does have a quality aspect. You have to tame that idea by not going too large when you need more than a general pointing direction from your chunk otherwise you start to get sentiment and not the finer details.
@Reality_Check_1984
Ай бұрын
@@sivi3883 how much latency do the added layers add? Are you running locally or API calls?
@StnImg
7 ай бұрын
Can u please make a video on retrieving data from SQL using SQL agents & Runnable using LCEL. If not possible here, if you can update the same in the udemy course. It helps alot
@codingcrashcourses8533
7 ай бұрын
I would rather do it here than on my udemy course, since it´s quite specific. Give me some time to do something like that please ;-)
@Sonu007OP
7 ай бұрын
Looking for a similar video with LangChain templates. Production level SQL-ollama app. Greatly appreciated 🙏❤
@codingcrashcourses8533
7 ай бұрын
@@Sonu007OP have not worked with ollama yet, i am afraid my 7 year old computer wont get it running ^^
@codingcrashcourses8533
6 ай бұрын
Video about this topic will be released on 03/25 and 03/28 :)
@maxlgemeinderat9202
7 ай бұрын
Thank, always nice videos! Do you have a favorite german cross-encoder?
@codingcrashcourses8533
7 ай бұрын
No, I don´t! I did not work that much with cross encoders to be honest
@andreypetrunin5702
7 ай бұрын
Спасибо!!
@codingcrashcourses8533
7 ай бұрын
Your welcome andreij:)
@andreypetrunin5702
7 ай бұрын
@@codingcrashcourses8533 I cannot run the code in VSCode. When running the import: From langchain_community.document_loaders import TextLoader, DirectoryLoader Error: File c:\Python311\Lib\enum.py:784, in EnumType.__getattr__(cls, name) 782 return cls._member_map_[name] 783 except KeyError: --> 784 raise AttributeError(name) from None AttributeError: COBOL I have installed the langchain-community library.
@vinaychitturi5183
4 ай бұрын
Thanks for the video.. But while genering queries using llm_chain.invoke(query), facing exception related to output parser. OutputParserException: Invalid json output:
@vinaychitturi5183
4 ай бұрын
I resolved it temporarily by removing parser al together and formatted the output in the next step. Thank you again for the video. It is helpful.
@codingcrashcourses8533
4 ай бұрын
Weird. Normally i never have Problems with that parser
@verybigwoods
5 ай бұрын
How much computation resource (specifically GPU) required in running this cross encoder model?
@codingcrashcourses8533
5 ай бұрын
It also works on a cpu
@sumangautam4016
3 ай бұрын
LLMChain() is deprecated and the output_parser in the examples also cause json output error. Would be nice, if you could update the github code. Thank you If anyone having issue with json output, here is a fix: from langchain_core.output_parsers import BaseOutputParser class LineList(BaseModel): lines: list[str] = Field(description="Lines of text") class LineListOutputParser(BaseOutputParser[LineList]): def __init__(self) -> None: super().__init__(pydantic_object=LineList) def parse(self, text: str) -> list[str]: lines = text.strip().split(" ") return lines
@erenbagc9164
7 ай бұрын
What's the best way to evaluate this RAG?
@codingcrashcourses8533
7 ай бұрын
Difficult topic. Performance or output Quality?
@erenbagc9164
7 ай бұрын
@@codingcrashcourses8533 well it should be advanced as much as possible since I got an advanced rag . I saw many cases that people used ragas,trulens etc. I'm indecisive
Пікірлер: 41