LangChain In Action: Real-World Use Case With Step-by-Step Tutorial

[@vijaynadkarni]

Awesome, easy-to-follow video on how to use LangChain for a real world application. Well done!

[@jarrodhroberson]

Very nice this is the first practical example of using these tools to do with a good at instead of what they’re hyped and not good at thank you

[@umeshtiwari9249]

great use case. Hats off. kindly make more more uses. i can image many people can watch your video and land some good job oppotunities. i really liked it. Thanks again

[@rabbitmetrics]

You're welcome, more use cases coming soon! Thanks for watching

[@kelvincht]

This video is mostly about setting up data rather than using Langchain features such as Agents and chaining. If you decided to have another video, please make this video part 1 of n

[@shaheerzaman620]

you can store text also as metadata. that way you get to avoid a local copy of the data.

[@crisgath3512]

Thanks for the content, your channel is on point with production themed ideas....

[@rabbitmetrics]

Glad to hear, thanks for watching!

[@VietTranIT]

Thanks for the great tutorial/introduction. Keep on the good work.

[@rabbitmetrics]

Thanks for watching!

[@kokoabassplayer]

Powerful! Appreciate you r VDO

[@rishabhupadhye]

This was wonderful! Looking forward to more such use-cases

[@ai50Connect]

I reach out using your calendar but it’s not available. I visited your website and had some inquiries about consulting.

[@rishabhupadhye]

@@ai50Connect yes tell me

[@supernewuser]

Great videos and presentation style.

[@IamMarcusTurner]

that was great looking at more solutions around structured data so thank you for this tutorial

[@rabbitmetrics]

Glad it was useful! Thanks for watching

[@mweishuhn]

If you are using a product that has over 4300 reviews, truncating them at 400 characters a piece, how are you then passing all of those reviews into gpt4 for analysis without hitting the token limit?

[@sandorkonya]

Could we use image embedings in vectore stores? Like... i have a text book (pdf) full with illustrations and figures, and i would like to search for images based on an query image?

[@gambaweb]

Yes it is possible

[@stefanb.2575]

Excellent. Do some more

[@cubibiris]

I really love your videos, just amazing work. Thanks.

[@rabbitmetrics]

Appreciate it! 🙏 Thanks for watching

[@angelo3108]

This is wonderful. How long would creating this app take? you made it look easy!

[@aarongreen39]

I'll be honest I only clicked this video because I had absolutely no clue what this was going of the title and thumbnail combination😅😅😅 I now realize it was a video about usi "error" "error" does not compute blue screen. Joking joking kinda 😂😂

[@user-wr4yl7tx3w]

Can OpenAI understand HuggingFace Embeddings?

[@atsileitumeleng]

Can you please cover the cost per user interaction if this is released out as a consumable application to users?

[@eracton]

You can have the customer use their own OpenAI API key

[@davidyoung623]

It's also going to differ greatly based on your specific use case, hosting, user base, etc...

[@ipxify]

do you have a coure to buy? need your knowledge !

[@roberthuff3122]

Excellent! Thank you.

[@rabbitmetrics]

You're welcome!

[@veliea5160]

Why did he train data with sklearn? did he create a vector store in memory with sklearn?

[@rohitagrawal769]

5:40 here is the answer

[@andreshofmann3434]

anyone else having issues with sentence_transformers? even when I installed it in many ways I keep getting an import error

[@RavitejaPuli-g8t]

can we use gpt 3.5 too?

[@rabbitmetrics]

Yes, you can switch out the language model by simply setting model="gpt-3.5-turbo"

[@jaivalani4609]

Thank you ! One q df['metadata']=df.apply(lambda row: dict(rating=row['overall']), axis=1) what values doe sthis leads to. In one your sections this field tend to had different values like genre and that.How does it builds it Pinecone

[@flyingfishinwater]

Thanks for the video

[@brianconnolly220]

What value does pinecone add here compared to the raw embeddings when running the "stuff" chain? I'm not clear what it's actually doing. Thanks for the tutorial.

[@rabbitmetrics]

In a production setting you will have (lots of) raw embedding data stored that you want your LLM to have access to

[@MiguelNFer]

Awesome video :) Is this possible without using paid models, such as gpt 4? Are there any free "chat type" models available in langchain?

[@gambaweb]

Use any model you want. Hugging face is one of them