Build an AI PDF Chat App using LangChain4J, Spring Boot and Astra DB
Vložit
- čas přidán 2. 01. 2024
- In this video, you will learn how to build an AI-powered application through which you can chat with a PDF document and ask questions based on the given PDF.
We will build this application using LangChain4J, AstraDB, and Spring Boot.
By the end of this tutorial, you will learn how to create AI-powered applications that can answer your questions based on a PDF document.
Use your business email address and get from $1,000- $3,000 in free credits and consulting with your subscription: dtsx.io/3vlLV8F
#DataStax #DataStaxPartner @DataStax
Link to Source Code: github.com/SaiUpadhyayula/lan...
Create a Basic RAG model AI chatbot using any open-source model available.
Database: Zilliz/Supabase or any Vector DB, of your choice.
Backend: Java
Frontend: HTML/CSS/JS (or anything you are familiar with)
Backend should haveAPI for:
• Upload a file or text - text should then be converted into chunks and then embeddings
(You can use any open-source embedding model or paid one too). Embedding should
then be stored in a vector DB with vector index of your choice (Cosine/ L2/KNN).
• Chat API -> prompt or user queries should be passed in this API and using prompt
engineering response should be derived from any Language model.
Frontend:
UI does not have to look pretty. basic pages should be there -
1. For uploading docs or text for training the RAG model.
2. Basic chat interface where user can send message and receive the response.
Sir please help me in this project🙏🙏🙏🙏🙏🙏
Great tutorial! I hope there will be a video demonstrating the integration of Spring Boot and LangChain, utilizing models from the Hugging Face repository instead of the OpenAI API.
Glad you are pumping high quality spring boot videos. I learned a lot from your videos. You are really making a huge impact. Thanks.
Great tutorial! Clear explanations on how to build the PDF chat application using Lang chain 4J and astrab. Excited to give it a try!
I'm looking forward to the microservices payment course. I think it's very interesting. Sorry, it has a tentative launch date and thank you for your work.
This is amazing integration with AI, thank you.
Nice video, thanks Sai.
we want more spring boot projects with ai
This is a TOP quality video. Well detailed explanation with implantation and demo . +1 subscriber
thanks a lot for this valuable content sir . really grateful :). god bless you
Wow! what an interesting tutorial!
Most useful video love you Bro by integrating Spring Boot with AI hope you to do more videos like this. ❤❤
Great thanks
After java brains u r my first choice to learn
Thanks for the nice tutorial
Amazing tutorial🔥🔥
Great stuff Sai, learned a lot from this video. Please prepare an extension video of AI PDF Chat App with an frontend UI.
Hi great stuff to learn Spring AI
Hey I am waiting for next video please provide the complete playlist as soon as possible Thank you so much.
Nice video
Nice video ❤
New sub!
I thought you again forgot your password thanks for sharing sir
and Happy New Year to you
Nice video. Please provide us an update on the Microservices course ? Is it coming along nicely ? Request you to slow down your phase a little bit in the Microservices course. 😊 Because you're giving so much information within a minute, at times it's difficult to follow along.
Hi, Thanks for the feedback, could you point to any specific video you found that the pace was fast ? Is the pace faster in this video or any other ones ? This helps me to refer back and reflect on how I can improve my content.
@@ProgrammingTechie yes Sai, i was referring to the very 1st Microservices video (not the 6 hour course). In that you were creating multiple instances of a microservice in Intellij apart from giving a couple of pointers for us to remember. Even though it was not a tough task, it might be difficult for someone as a a beginner. Your videos are simply excellent but the pace at that moment was much faster.
There is one more reason for this - generally most of your projects are very good and a bit in depth & hence it takes time for anyone to follow and understand unlike other channels where they focus on much simpler projects. So, obviously we need a little bit more time and that is why I said that.
Please remember this point and try to implement it in the new Microservices course. If possible also provide an update on the same.
Thanks, in the example you provided, I intentionally covered it quickly as I want to concentrate more on the Microservices part instead of the maven fundamentals on how to create different projects using Maven Multi Module projects.
In the paid course, I will for sure cover the majority of the concepts in detail.
I still cannot provide any date for the course, maybe you can expect the update Microservices course with Spring Boot 3 before the paid course.
yup, me too I would love to see new videos in the microsevices course
pro
i have a question how can i let the assistante retreive a specific record from the db , based on user , every user has it's own data ?
how do i run the code in intellij do i need any kind of setup?
How to solve errors? Log is not defines, astral version incompatible
Great tutorial ..can we do same with excel(csv/xlsx) instead of pdf??
Yes but you have to use may be some other dependencies to read the excel files
thanks for the nice tutorial, finally something in Java not only in Python. A question: is it possible to do all locally, I mean using a local vector database and without using external API key? I mean something like PrivateGPT... I think it should be possible... if so, can you illuminate us with an extension of this tutorial ;-) Thanks and congratulations for your courses. Great job. Happy 2024!
Thank you! Wish you also a happy 2024. Yes, its possible I will plan some videos in the future on those topics.
Hi Sai,
Thank you so much for the video.
I have tried to clone the repository and used my astraDB and openAI credetials, Iam getting error in the "AstraDbEmbeddingStore" object creation, is there anything I can do
Hi, I will check this and update the github repo if any changes are requierd
Why dont we go for a open source vector database and open source chat model ?
Check the GitHub repo I created a separate branch that connects to Ollama3 and uses vector pg database
can we use huggingface instead of chatgpt here?
Yes you can, in my GitHub repo, I created a branch where I used Llama3 and PGVector as the database you can check it out
It seems the github code is no more working. Possibly due to changes in Aastra DB side.
I will check and update the code
it say exceed quota is this not available in free in case of open api
Sorry, Have you fixed that error yet?
P R O M O S M