Bug or new feature into Recursive Character Text Splitter?

Hello,

Under n8n 1.42.1 I see you may add an option into the node “Recursive Character Text Splitter” that directly needs to code option.
But then, nothing’s change (nor is related to the language)

Am I missing something ?

Thnaks for your help !

It looks like your topic is missing some important information. Could you provide the following if applicable.

  • n8n version:
  • Database (default: SQLite):
  • n8n EXECUTIONS_PROCESS setting (default: own, main):
  • Running n8n via (Docker, npm, n8n cloud, desktop app):
  • Operating system:

Hi @NiKoolass

This is definitely a feature :innocent:

We have built in this new option to utilize the LangChain support for programming languages in order to improve semantical chunking for the vector store.

Since this is a pre-setting, you will not see any direct changes in the UI. Rather, this setting will come into effect upon execution of the node.

You can find more information in the official langchain documentation here:

I hope this explains it well? :owl:

1 Like

That makes perfect sense ! Thanks a lot for this explanation ! :slight_smile:

This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.