Browse Comments — Clean (de-noised)

!!️ If you're serious about learning AI, - STAR the repository to follow the projects.

Indeed a very useful repo. Good to see practical usecases on RAG, AI Agents and AI + Cloud. Just hit the STAR button. Will share my learnings soon through a post :)

Thank you for the invaluable resource and unconditional support

The agent-reasoning and agentic_rag implementations in this repo are standout features. I'm currently deep in the trenches building an agentic RAG system for the AWS Well-Architected Framework, and moving past simple retrieval to 'Cognitive Architectures' (like ReAct or CoT) is where the real value is. It’s one thing to get an LLM to chat; it’s another to build a harness that ensures data integrity across 3,000+ chunks. Great share!

That's a very useful post. Thanks a lot for sharing this with us.

Thankyou Abhishek for sharing valuable insights 👏

Great reason Abhishek Veeramalla thanks

Your resources are also goldmine Abhishek Veeramalla

Thanks for sharing this amazing github repository on use cases of rag ai agents and cloud indeed this github repository will help me in learning agentops and llmsops In the future

Fantastic Abhishek. Learning by building real, production-ready AI agents is the best way to solidify concepts.

Thank you Abhishek veeramalla for sharing the resources

Thank you Abhishek for sharing valuable resource

Production-ready Agentic RAG isn't a suggestion anymore—it's the price of admission for 2026. Oracle’s move to open-source these specific implementations (FastAPI + Redis + 23ai) signals a massive shift in how we handle low-latency intelligence at scale. If you're still stuck in theoretical notebooks, you're already behind. Stop scrolling and start deploying.

Hi Abhishek Veeramalla, Thank you very much for sharing the information.. Most of the friends are Saying future is the AI and AI is the future 🔮.

Indeed very useful repo.

👏 This is truly a goldmine for anyone interested in learning AI practically rather than just theoretically. 🔥 What makes this repository valuable is the combination of real-world projects, production-ready implementations, hands-on workshops, and modern AI concepts like RAG, multi-agent systems, and memory engineering. Resources like these help learners bridge the gap between understanding concepts and actually building enterprise-grade AI solutions. Thanks for sharing this amazing resource! 🚀

One thing I'd add for anyone working through this: don't just run the notebooks in sequence. Pick the application closest to a problem you're already trying to solve and work backwards through the concepts. That reverse-engineering approach tends to build intuition faster than following a linear path.

This is the kind of resource that accelerates learning fast. The best way to learn AI today is by studying real implementations, architectures, and production-ready systems, not just watching tutorials.

Full video is here:

Hi Abhishek Veeramalla The repository appears highly valuable for accelerating practical AI engineering adoption. However, from enterprise security architecture, and AI governance perspective, this type of “production-ready AI” narrative must be evaluated very carefully because operational AI deployment risk is significantly more dangerous than experimental AI learning risk. The biggest concern is not whether the demos work. The real concern is whether developers unknowingly normalize insecure AI architecture patterns into enterprise production environments. Open-source AI acceleration without mandatory governance-by-design can create scalable technical debt, compliance exposure, and systemic AI security fragility at enterprise scale. What formal threat modeling methodology was used to validate the security posture of these “production-ready” AI architectures? What mechanisms ensure explainability, traceability, and auditability for autonomous reasoning frameworks such as ReAct, ToT, and CoT?