Deep dive into ADK building blocks: custom tools, memory patterns, and state management. Learn to build production-ready agents with database integration, conversation memory, and intelligent caching.
Read more →Search Results for: title
Embedding Space Analysis: Visualizing and Understanding Vector Representations
Introduction: Understanding embedding spaces is crucial for building effective semantic search, RAG systems, and recommendation engines. Embeddings map text, images, or other data into high-dimensional vector spaces where similar items cluster together. But how do you know if your embeddings are working well? How do you debug retrieval failures or understand why certain queries return […]
Read more →International Patient Summary (IPS): Cross-Border Healthcare in the EU
The EU Cross-Border Healthcare Challenge EU eHealth Digital Service Infrastructure (eHDSI) IPS FHIR Bundle Structure Generating IPS in .NET Ireland’s Participation in eHDSI EU Member State Participation Standards and References Related Articles in This Series Conclusion
Read more →Function Calling Deep Dive: Building LLM-Powered Tools and Agents
Introduction: Function calling transforms LLMs from text generators into action-taking agents. Instead of just describing what to do, the model can actually do it—query databases, call APIs, execute code, and interact with external systems. OpenAI’s function calling (now called “tools”) and similar features from Anthropic and others let you define available functions, and the model […]
Read more →HL7 v3: Understanding RIM and Why v3 Failed to Replace v2
Executive Summary HL7 v3 was designed in the 1990s as the successor to HL7 v2, promising a rigorous, model-driven approach based on the Reference Information Model (RIM). Despite 20+ years of development and standardization, v3 never achieved widespread adoption. Understanding why v3 failed—and where it still matters—is crucial for architects navigating healthcare interoperability standards. 🏥 […]
Read more →Tool Use and Function Calling: Extending LLM Capabilities with External Actions
Introduction: Function calling transforms LLMs from text generators into action-taking agents. Instead of just producing text responses, models can now decide when to call external functions, APIs, or tools to accomplish tasks. This capability enables building assistants that can search the web, query databases, send emails, execute code, and interact with any system that exposes […]
Read more →