- Keeps processing in different flows separate so that data can go to different stores / collections etc.
- Potentially supports different processing flows
- Tidies the processing API with common base-classes for e.g. LLMs, and automatic configuration of 'clients' to use the right queue names in a flow
* Separate memgraph query/write modules to optimise for memgraph
* Used 1GB memory for Memgraph
* Deployed specialised memgraph query/write processors, created memgraph indexes
* One triple is loaded as a single transaction
* Fixed index creation