Hello World, I'm Ajay. I'm a Principal SWE. Of all the tech savvy things I do, sharing is my hobby.
🎥 TechPrimers is an educational channel to provide insights on latest technology implementations and advancements. ⌨️ The topics of interest include AI, Spring Boot, DevOps, Cloud, Architecture, Tips & tricks, etc.,
🕹 How can you navigate the channel? - Explore the playlist for topics you are looking for. - Skip to exact timestamps ⏱ (in description) to be more productive. - Use the Github link in each video to take a look at the code used in the corresponding video.
Finally Learn, Code and Share..! --------------------------------------------------- Disclaimer/Policy: The content may or may not match your expectations and level of pronunciation/understanding. The content/views/opinions posted here are solely mine and the code samples created by me are open sourced. All the videos posted here are copyrighted. You cannot re-distribute videos on this channel in other platforms
Login part that you are explaining is I guess OIDC because OAuth alone is just meant for Authorization, it is basically OIDC that enforces login and hence the Authentication
Gr8 info buddy for beginners. I want to use microsoft azure openai with custom data and rag too. Also need a custom chatbotot (own). Can you help me with desing? How to build my app in python, call 3rd party api, how to use RAG, how to expose API to custom chatbot etc ?
Thanks for the video, few things are unclear from the demo, does the Spring AI talk to your local ollama ? What happens if ollama is not installed or running that model at that point of time ?
Informative as usual, I think python & its framework would be more suitable for AI content at least for quick PoC. Definitely this video will help Java fans😊
Good one , but imagine my backend is supporting a application, and my offline running ai model is as connected to my backend springboot, now how can I train the offline running ai model about the application and create a chat bot which gives response to the request only about the trained data i.e the application
Great question. Take a look at my video on RAG architecture on how it can solve the dynamic data source updates in the LLM model. I will make a video on that soon with handson
You are a key contributor in the java space, pls continuing doing awesome work. Requesting you to extend this video with some sample trained data. Data that could be fed to this llm eg we can store in our repository like top destination as per the time of the year / events/ weather etc,
If you're hosting your services on Aws for example, would each micro service seat on it's own EC2 instance? Someone should please link me to a video that explains how to go about the hosting of the different microservices and how to manage redundant server cost after creating the microservices
Thanks for this guide, it's really helpful. If you could make a guide on how to use these models practically, that would be great. I'd also love to hear your thoughts on the SpringAI framework aswell
Thanks for such kinds of video. We will be really happy to be interested to see how we can use SLM, if you have free time please create some of the videos related to that. 😊 Thank You 🥰
You have a great way/voice of explaining the topics, and it is so clear that anyone can understand what it is, you have covered, actuators, health monitoring, circuit-breaker patterns and fallback, in a very simple way. Good job.
Thanks for the informative video. Since last week, I am trying to download different models and trying to run. But no luck, sometimes getting some module errors or laptop is hanging. Now I will try models which you have provided (aim is to prepare data model which can understand my project's technical & functional information. So that every developer(new)/BA/manager can clarify queries in efficient way)
Tried phi-3, facing some issues with pytorch versions and DLL files, somehow resolved. But later i realised that I don't have nvidia graphic card. So, next I want to try with docker, not sure it will work or not. Bt with CPU, it is very slow.
Client side load balancing is used for inter communication between with in micro services where as server side load balancer comes into picture where it makes call from external Ajax api from react js or postman or browser, traditional it was used Nginx load balancer, now spring cloud api gateway handle with client side and server side load balancing , no worries
