The previous chapters have provided the components needed to construct complete, text-based LLM applications, from generation and RAG to autonomous agents. This final chapter offers a look at several specialized capabilities for extending your applications further.
You will be introduced to three distinct topics:
These sections provide a practical starting point for incorporating more sophisticated features into your projects.
11.1 Processing Image Inputs with Multimodal Models
11.2 Benchmarking LLM Outputs with Evaluation Metrics
11.3 Preparing Datasets for Fine-Tuning
© 2026 ApX Machine LearningEngineered with