Results 4 issues of agan

### Search before asking - [X] I had searched in the [issues](https://github.com/OpenSPG/KAG/issues?q=is%3Aissue) and found no similar feature requirement. ### Description 1.目前KAG拆解子问题,是通过logic_form_plan.py来进行,使之转为函数执行;这里有没有办法**不使用通用大模型甚至不使用大模型**,因为这边通用大模型会有幻觉等通用弊端,在未来KAG版本是否有其它思路实现。 a.不使用大模型,使用传统NLP,类似LazyGraphRag; b.训练一个SequenceToSql模型,但是训练样本如何整理? 还是有其它方案? > 在KAG分享会上,田常大佬说后续说会有新的思路,具体是什么呢? 2.拆解成子问题的函数,后续是否考虑支持udf,比如spg一些函数或自定义函数等等 ### Are you...

@youdonghai 您好,我在测试类[FilmBaseTestData](https://github.com/OpenSPG/openspg/blob/b05c57b4511eb9bd1897b6601785631c0f69384d/reasoner/runner/local-runner/src/test/java/com/antgroup/openspg/reasoner/runner/local/main/basetest/FilmBaseTestData.java#L48) 我在概念增加了isA关系,代码如下: ```java schema.put( "PopularFilmStar", Convert2ScalaUtil.toScalaImmutableSet(Sets.newHashSet("id", "age", "name", "gender"))); schema.put( "PopularFilmStar_isA_FilmStar",//把popularFilmStart的上位词为FilmStart Convert2ScalaUtil.toScalaImmutableSet(Sets.newHashSet())); ``` 并在实例图FilmGraphGeneratorTopK中,把L1_1_start的label改成popularFilmStart,代码如下: ```java constructionVertex("L1_1_star", "FilmStar", "age", 60, "gender", "男"), //改成如下 constructionVertex("L1_1_star", "PopularFilmStar", "age", 60, "gender", "男"), ```...

很期待你们能回复。 我下载KAG代码以及spg代码,均用master分支, 环境信息:mysql和neo4j(docker),运行机器为windows; 目前代码能正常run起来,但是在执行example[黑产任务](https://openspg.yuque.com/ndx6g9/0.5/haf99dg5w8wrkvop) ``` MATCH (phone:STD.ChinaMobile) Set(), anonymous_4 -> Set(), phone -> Set()) com.antgroup.openspg.reasoner.common.exception.SchemaException: Cannot find phone in Map(u -> Set(), anonymous_4 -> Set(), phone -> Set()) at com.antgroup.openspg.reasoner.lube.logical.validate.Validator$$anonfun$com$antgroup$openspg$reasoner$lube$logical$validate$Validator$$fieldToVar$1.apply(Validator.scala:132)...