These series of videos on Spring AI are amazing. Thank you for the efforts you have put in. If possible, please add a video about unit testing these applications and best practices while writing Junits for Spring AI applications.
This is so cool - now the EmbeddingClient is making sense! Just for the life of me could not understand why you need so many different embedding clients. I was putting this embedding client in the wrong place in the picture. Time to start building some data consumption stuff and see what is going into the DB. Can't wait for the next video!
It's so cool, thank you very much for this series. This is a subject that i'm currently studying and this specific technical content and with Java is being very clear and giving awesome examples
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 doing this project 🙏🙏🙏🙏🙏🙏🙏🙏🙏🙏
Thanks a lot, Dan! These series are truly impressive and impactful. I have a question about RAG. What are the benefits of supplying the questions and answers ourselves? Where does the AI's strength lie in this scenario? For instance, when you asked about counting sports, the response was 'NA' and it provided the list we inputted. We envision being able to ask you about anything within the text I've included. I might sound a bit eager, but I'm keen to explore its capabilities and potential applications 😁😁
Think of the person who supplies the questions and answers as the web master, and the person who will end up asking the question as a web end user. Many websites store faqs for web users to read, but imagine instead of them reading through 100 faqs, they could just ask a question about your company, or whatever your website is about, and it would give them a direct answer. AI is providing custom and specific answers to the person who just happens by your website without making them go through your documentation. The benefit really starts to kick in when you have 1000s of pages of documents of information, and the user can get an answer to a question in 5 seconds instead of 2 hours of searching through documentation.
Dan, I have one doubt. Can we ask follow-up questions related to the previous question I asked? Will it give a relevant answer, or will it consider two questions as completely new?
I have a question: When I use embed, I use openai by default, the file that I can use would become in vectorstore but using openai to convert a embedding..I want to say that the file to convert in embbeding use Opeani ?
These series of videos on Spring AI are amazing. Thank you for the efforts you have put in.
If possible, please add a video about unit testing these applications and best practices while writing Junits for Spring AI applications.
This is so cool - now the EmbeddingClient is making sense! Just for the life of me could not understand why you need so many different embedding clients. I was putting this embedding client in the wrong place in the picture. Time to start building some data consumption stuff and see what is going into the DB.
Can't wait for the next video!
I had the same questions before I actually got my hands dirty. Glad you're enjoying the series Andre! Can't wait to hear about what you build 👏🏻
It's so cool, thank you very much for this series. This is a subject that i'm currently studying and this specific technical content and with Java is being very clear and giving awesome examples
Lovely! God bless you!
got this - Based on the documents provided, there are 32 sports included in the Olympic Games Paris 2024.
my favorite mentor dan vega . sir keep uploading new things. plz share chat system
terrific. really, really appreciate your work Dan. thanks very much
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 doing this project 🙏🙏🙏🙏🙏🙏🙏🙏🙏🙏
Yes Sir please
Is this homework?
Thanks a lot, Dan! These series are truly impressive and impactful.
I have a question about RAG. What are the benefits of supplying the questions and answers ourselves? Where does the AI's strength lie in this scenario? For instance, when you asked about counting sports, the response was 'NA' and it provided the list we inputted. We envision being able to ask you about anything within the text I've included.
I might sound a bit eager, but I'm keen to explore its capabilities and potential applications 😁😁
Think of the person who supplies the questions and answers as the web master, and the person who will end up asking the question as a web end user. Many websites store faqs for web users to read, but imagine instead of them reading through 100 faqs, they could just ask a question about your company, or whatever your website is about, and it would give them a direct answer. AI is providing custom and specific answers to the person who just happens by your website without making them go through your documentation. The benefit really starts to kick in when you have 1000s of pages of documents of information, and the user can get an answer to a question in 5 seconds instead of 2 hours of searching through documentation.
Thank you so much Dan for the RAG video
Thanks, I'm waiting for the video on the pg vector store
How can I create a new Implementation of ChatClient? The goal is to use it internally/privately in a company.
Nice one. Appreciate if you create also a tutorial to read on the database using Rest Api
Can we use Spring AI module with traditional spring 6 framework (without spring boot)? Any references will be appreciated!
Super helpful! Thanks!
Hay dan vega could you please use any opensource llm instead of openAi
So Spring AI is basically Spring version of LangChain4J
Dan, I have one doubt. Can we ask follow-up questions related to the previous question I asked? Will it give a relevant answer, or will it consider two questions as completely new?
ChatHistory abstraction yet land on Spring AI.
Thanks Mr Dan.
Hi Dan, Do you have any news about LangChain with spring?
Is there a way of logging the tokens used?
Fab Dan...
I could not able to run this program with open ai free limit.
I have a question: When I use embed, I use openai by default, the file that I can use would become in vectorstore but using openai to convert a embedding..I want to say that the file to convert in embbeding use Opeani ?
How to add frontend sir please tell me html
all we need is aiove