[Bug]: Custom entity types cannot be properly invoked during graph parsing.

[MarcusYuan]

Self Checks

• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report (Language Policy).
• Non-english title submitions will be closed directly ( 非英文标题的提交将会被直接关闭 ) (Language Policy).
• Please do not modify this template :) and fill in all the required fields.

RAGFlow workspace code commit ID

baf3b9b

RAGFlow image version

v0.17.2-166-gdf389082 slim

Other environment information

ubuntu docker

Actual behavior

Expected behavior

I hope the filled entity list can be loaded properly/normally.

Steps to reproduce

Add non-default entities for testing.

Additional information

No response

[dosubot]

Custom entity types cannot be properly invoked during graph parsing in RAGFlow because the graph_extractor is hardcoded to use default entity types instead of custom ones. To resolve this issue, you need to modify the self._prompt_variables in the graph_extractor to use the custom entity_types instead of DEFAULT_ENTITY_TYPES. Here is the code change required:

Change from:

self._prompt_variables = {
    "entity_types": entity_types,
    self._tuple_delimiter_key: DEFAULT_TUPLE_DELIMITER,
    self._record_delimiter_key: DEFAULT_RECORD_DELIMITER,
    self._completion_delimiter_key: DEFAULT_COMPLETION_DELIMITER,
    self._entity_types_key: ",".join(DEFAULT_ENTITY_TYPES),
}

To:

self._prompt_variables = {
    self._tuple_delimiter_key: DEFAULT_TUPLE_DELIMITER,
    self._record_delimiter_key: DEFAULT_RECORD_DELIMITER,
    self._completion_delimiter_key: DEFAULT_COMPLETION_DELIMITER,
    self._entity_types_key: ",".join(entity_types),
}

This change should allow the system to properly recognize and invoke custom entity types during graph parsing ^[1].

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other}