Hi Jason, yes, you're right - in many cases the text2Cypher depends on the underlying LLM and the associated prompt (it takes a bit of prompt engineering to get better Cypher). There are also some fine-tuned Cypher generation LLMs these days, so that might be a good option too. The demo shown here was purely for demonstrating a workflow - you can look at the following repo for some ideas on custom prompts for Cypher generation: github.com/kuzudb/graph-rag-workshop

Hi @jpgarcia90. Sorry, we missed this comment. You're somewhat right. Our engineer building Explorer, built Explorer first and then published API server by writing a script to remove files form Explorer. We might refactor this at some point to do it the other way around.

Hi @DearGeorge3, thanks for checking out the video! There are a few reasons why we think updates/deletion with a native API is unlikely to be faster than Cypher. 1. Kùzu is not an in-memory system (it is fully disk-based), so updating/deleting by cursor/pointer does not mean we can directly update the memory object that the cursor is pointing to - we'd still need to go through the same thing at the storage level. 2. The Python API in Kùzu is a simple wrapper over C++. We do not parse / decode / plan queries in Python at any stage, but rather simply pass the query string to the C++ layer that does planning, binding and execution, so querying your database from Python should basically be roughly as fast as querying from any other API. 3. Compared to query execution (which can get really expensive real quick), query planning is the faster operation, and any additional overheads in Python are likely to be negligible. Please join us in Discord to discuss more details if required, and cheers!

Hi Naveen, you can run aggregation queries in Cypher like you might do in SQL (avg, max, min with group bys), though in those cases, the benefit of Cypher is not as apparent. SQL does the job great in those cases. Not to mention that analytical databases and query engines that implement SQL likely have many optimizations in place already for these use cases.

Thanks so much! We appreciate it. Let us know what other areas you might like covered.

Thanks. You are right. You cannot use owl in Kuzu. To be clear. This first set of videos are not about discussing the features of Kuzu. They are intended for a broad audience who want to learn the fundamentals of main classes of graph databases.

@@semihsalihoglu thanks ! Is it something you may plan in a future release ? I'd really need to create ontologies also, with a unique tool...Then Sparql at some point also for a deepter semantic reasonning ?

@@theseedship6147 We are not planning on supporting SPARQL natively within Kùzu for now - however, we do offer an interface within Kùzu that allows you to ingest your RDF data (from turtle files) into Kùzu and then query it using Cypher. Please reach out to us on Discord if you want to learn more! docs.kuzudb.com/rdf-graphs/

Thanks very much for the feedback!

Thanks for the feedback. We're working on improving each video as we go :)

Thanks. Let us know what other areas are of interest to you.

@@KuzuDB ingests to graphs and events out of graph ( event listeners) helps integrate to existing systems