Derek Arends

Пікірлер

@ShivaniDwivedi-c7x 15 күн бұрын

can we use this code on our local?

@SaiRaviTejaAravapalli 21 күн бұрын

Thanks for the valuable session will this work for a document that consists of both text and images ?

@jackjames3650 Ай бұрын

Many steps are not there for newbies

@mehdishabaninejad3325 3 ай бұрын

Thanks, I am going to convert bunch of documents to fillable forms. do you think it is doable using Azure AI document intelligence?

@safwankarim1610 3 ай бұрын

Nice one. Do you know how to use computer vision on PDFs? Eg, i have PDF reports which also contains images which i'd like to get tags of to create a search index.

@sairpa5127 3 ай бұрын

Thanks for the video and awesome content. I have an invoice while using the prebuild model can I add custom fields and label them like (Secondary customer order or VAT) or do I need to use a a custom model and train all the fields ?

@knuckleheadmcspazatron4939 3 ай бұрын

What if a table spans more than one page? For example a long list of items on an invoice would scroll to a second page.

@DerekArends 3 ай бұрын

It has the ability to scan multiple pages, however, I do believe it would be considered another table so you would have to write some code to put the table data together from the response.

@Rajeshsingh-ws5th 4 ай бұрын

Very valuable for using it in day to day office work.

@조바이든-r6r 4 ай бұрын

Im trying to build community app rn and i think this is pretty cool for people who runs community but still not many people know…. Its kinda hidden gem

@DerekArends 4 ай бұрын

I would agree. I think it could give you a great advantage over other communities if you can flag things you know your community may be offended by.

@조바이든-r6r 4 ай бұрын

@@DerekArends nah i dont need flag im just going to block comment

@stanTrX 4 ай бұрын

You havent executed the result for few shot prompt example 6:47

@carthagely122 4 ай бұрын

Thank you

@DerekArends 4 ай бұрын

You're welcome! Let me know if there is anything I can do to make them better for ya!

@emailthistorob 6 ай бұрын

Thanks for a great video. I'm struglling to get the metadata filters (e.g. $eq, $in) to work. Could you do a video on that?

@DerekArends 5 ай бұрын

Hey hey! Let me take a look at that and see if that is something I can create a quick demo on.

@testbot6899 7 ай бұрын

At the place of DistanceStrategy.COSINE can we use DistanceStrategy.Locality_Sensitive_hashing ? Is it possible ? Locality_Sensitive_hashing is user_defined function. Sorry if my question is wrong.

@karthiks416 7 ай бұрын

Great video, don't stop doing such awesome ones

@DerekArends 7 ай бұрын

Thanks, going to start getting back into it. Appreciate the motivation!

@rabiko4147 8 ай бұрын

Thank you so much for sharing, especially Langchain, tutorials. They are extremely useful!

@DerekArends 7 ай бұрын

Glad you like them! Hopefully some future videos will help too!

@aiortairaan5458 8 ай бұрын

how to access multiple outputs from the parent chain(the chain which contains the sequence of the sub-chains)?

@CristianMolina 8 ай бұрын

Nice video. I liked that you just limited the do one thing and not a complete RAG chat. I'm a bit overwhelmed with so many parameters and diff. classes to do something, for instance, there is RecursiveCharacterTextSplitter. How it differs?

@darshanjogi5781 8 ай бұрын

Good explanation

@kotlaarunkumar4251 9 ай бұрын

Damn!! Didn't think of this kinda attack 😅. Thanks for the video

@yoto741 10 ай бұрын

The 2nd one is called storage collision

@joaogabriel6929 10 ай бұрын

It didn't work here. Did i do something wrong?

@DerekArends 10 ай бұрын

Hey Joao, can you give me a little more context? It didn't prevent the reentry, or the sample code didn't work?

@joaogabriel6929 10 ай бұрын

@@DerekArends Hi! I managed to make it work. My bad. But there's one thing that i still don't understand. Why do i need to use 1 ether to make the attack work?

@lazerusmfh 10 ай бұрын

ChatGPT had made me a ton of money 😅

@nicholasbarnes6370 11 ай бұрын

Awesome work! can't wait to see what's next

@arpitapramanik4679 11 ай бұрын

How to access a user defined table where i have stored vector of text.with vector type as a column.

@DerekArends 10 ай бұрын

So sorry for delay in reply. The easiest way I have found to do it is use the VS Code extension called SQL Tools, install the Postgres Connector, and connect to the database that way. This will give you the ability to see database schema.

@RealEstate3D 11 ай бұрын

I appreciate your work. Surprised to have found your channel so “late”. From my POV your channel is underrated.

@DerekArends 11 ай бұрын

I appreciate that!

@adrickjone6472 Жыл бұрын

👏 "promosm"

@LearningWorldChatGPT Жыл бұрын

Thank you very much, Derek! Excellent tutorial ! Using PGEmbedding would be very similar to PGVector, right ? ... and from what I've read, PGEmbedding has a better performance, right?

@DerekArends Жыл бұрын

Yeah, I believe it would be very similar. From a code perspective Langchain would need to have a tool for it but otherwise the concept is the same. I haven't tried it out but it does say it is more performant than PGVector. I may have to try it out and create a video on it. Thank you for pointing this project out!

@kirubhakaranv459 Жыл бұрын

cannot import name 'SlackToolKit' from 'slack_toolkit'

@DerekArends Жыл бұрын

I may need more help for this, when I pulled a fresh repo down, I did have to add an issue with arbitrary types. That has been updated. Let me know if that doesn't help and if you can past more of the error message that would be helpful.

@domyu6418 Жыл бұрын

Hi Derek, quick question. When I try to install the "vector" extension in VS Code, it tells me that "extension 'vector' is not available. Even when I manually search for it, I cannot seem to find it. Do you have any insight here? Thank you and great video!

@DerekArends Жыл бұрын

Hey! Are you running "ankane/pgvector" as the docker image? If not, try that or github.com/pgvector/pgvector as steps for how to install it in other situations.

@FebiMettasari Жыл бұрын

Nice demonstration!

@DerekArends Жыл бұрын

Thank you!

@SMCGPRA Жыл бұрын

fed up of seeing openai why can't use open-source LLMs

@DerekArends Жыл бұрын

I will try to make a few with other LLM and see what magic happens!

@CristianMolina 8 ай бұрын

at least he used an OSS vector DB ;)

@ernie_hudds Жыл бұрын

So just to be clear - its not really using AI fanciness its just finding a close match from documents based on a query, right?

@DerekArends Жыл бұрын

Correct, nothing too fancy here. It is just using vector embeddings and doing a similarity match. Next steps would be to take those matches and send it to AI to do summary/answer questions. I will get a video out about why you may want to do this and how to do it.

@ernie_hudds Жыл бұрын

@@DerekArends I think that would be a superb and helpful video.

@diapetes3935 Жыл бұрын

Really great video and clear code - thank you! Have been trying to get ConversationBufferMemory to work with SequentialChains to no avail. Would love to see a video explaining how to get that working!

@pruff3 Жыл бұрын

OMG I was looking for this exact thing and you did it, thanks friend

@DerekArends Жыл бұрын

No problem 😊

@shah_mori Жыл бұрын

This was very easy to understand, I love it! I have a question tho, is it possible to update the postgresql vector database based on a collection name?

@DerekArends Жыл бұрын

If you want to update the database collection when loading the documents you can set the parameter "pre_delete_collection" to true and it will delete that collection and insert a new one db = PGVector.from_documents( documents=data, embedding=embeddings, collection_name=collection_name, connection_string=connection_string, distance_strategy=DistanceStrategy.COSINE, openai_api_key=api_key, pre_delete_collection=True )

@nicholasprod2012 Жыл бұрын

Great content. Please make more! Love the pace, format and clear and concise code.

@DerekArends Жыл бұрын

Thanks, will do!

@georgesanchez8051 Жыл бұрын

More! There aren’t too many on YT yet creating this type of higher-level langchain content. I’d say James Briggs, Sam Witteveen, Data Independent, Echohive, and Dave Ebbelaar are some of the only standouts. Nonetheless, the market is over saturated with clickbait videos and QA over docs, this is definitely more like it.

@DerekArends Жыл бұрын

Hey George, thanks for the feedback. I will plan to keep this up!