imbajin commented on code in PR #84:
URL:
https://github.com/apache/incubator-hugegraph-ai/pull/84#discussion_r1794937663
##########
hugegraph-llm/src/hugegraph_llm/operators/kg_construction_task.py:
##########
@@ -60,16 +59,17 @@ def fetch_graph_data(self):
return self
def chunk_split(
- self,
- text: Union[str, List[str]], # text to be split
- split_type: Literal["paragraph", "sentence"] = "paragraph",
- language: Literal["zh", "en"] = "zh"
+ self,
+ text: Union[str, List[str]], # text to be split
+ split_type: Literal["document", "paragraph", "sentence"] = "document",
Review Comment:
> Why is the default value changed to `document`, does it have a better
effect?
handle it in next PR (we need refactor the split logic for better effect)
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
