Retrieval Augmented Generation - Techniques and Applications

Dive into a comprehensive podcast episode exploring Retrieval Augmented Generation (RAG) with Syed Asad, Lead AI/ML Engineer at KiwiTech. Gain insights on semantic vector searches, vector databases, and cutting-edge RAG techniques reshaping AI capabilities. Learn about production issues, CSV file handling risks, embedding model challenges, and inference layer experiments. Explore AWS services, OpenAI customization, differences between Olama and VLLM, and fine-tuning small language models. Discover evaluation frameworks, MLOps for efficient machine learning, tool pricing strategies, and dependency risk management. Understand the evolving role of ML engineers in the AI landscape and explore the hard framework for AI development.

[] Syed's preferred coffee
[] Takeaways
[] Please like, share, leave a review, and subscribe to our MLOps channels!
[] A production issue
[] CSV file handling risks
[] Embedding models not suitable
[] Inference layer experiments and use cases
[] AWS service handling the issue
[] Salad testing and insights
[] OpenAI vs Customization
[] Difference between Olama and VLLM
[] Fine-tuning of small LLMs
[] Evaluation framework
[] MLOps for efficient ML
[] Determining the pricing of tools
[] Manage Dependency Risk
[] Get in touch with Syed on LinkedIn
[] ML Engineers are now all AI Engineers
[] The hard framework
[] Wrap up