Week 19, year 2025
- Function calling using LLMs - While LLMs excel at generating cogent text based on their training data, they may also need to interact with external systems. Kiran Prakash describes how we get them to construct external function calls to do this. The LLM does not execute these calls directly, instead it creates a data structure that describes the call, passing that to a separate program for execution and further processing. The LLM's prompt includes details about possible function calls and when they should be used. [Martin Fowler]
- LangGraph Checkpointer on KurrentDB - Overview KurrentDB is well-suited for agentic workflows thanks to its append-only storage of all state transitions as events in streams. This approach ensures a complete historical record, enabling reconstruction of any process or entity's journey, unlike CRUD systems that only retain the latest state. The document illustrates how KurrentDB can serve as a LangGraph checkpointer that enhances observability for internal checkpointing processes in complex agentic systems. If you are already familiar with how KurrentDB works, you can skip to how LangGraph works, how KurrentDB can be used to solve checkpointing problems, and the associated Python Notebook below or in our examples folder: https://github.com/kurrent-io/langgraph-checkpoint-kurrentdb/tree/master/examples [Event Store blog]
- Archiving: Keep your data hot and cold - In this blog post, we’ll walk you through using Archiving, our latest cool feature, available from KurrentDB 25.0. Archiving can save you a tremendous amount of disk space on your KurrentDB nodes by moving old chunk files from the local disk to an external archive such as S3. [Event Store blog]
- Derek Comartin explains Event Sourcing on Code Opinion - Derek Comartin presents videos on a range of software architecture and design topics in his YouTube channel Code Opinion and on his Twitter feed. His videos are accessible and effective explanations of complicated topics and can improve your understanding of important concepts. [Event Store blog]
- Why Event Sourcing? - What if you could scale and distribute data freely, without forming a tightly coupled mess? And what would you say if we told you that your application is only capturing the tip of the iceberg when it comes to your data, yet it's capable of so much more? We expect you'd ask us how. In just 30 minutes, you can find out! [Event Store blog]
- How To Get The Current Entity State From Events - In Event Sourcing, the application state is stored in events. When we add an event, it is placed at the end of a structure called an append-only log. Events are the source of truth. This has many advantages, such as: [Event Store blog]
- What is Event Sourcing? - Event Store Blog - Event Sourcing is an alternative way to persist data. In contrast with state-oriented persistence that only keeps the latest version of the entity state, Event Sourcing stores each state mutation as a separate record called an event. [Event Store blog]