田常@蚂蚁

> 您好，我这边突然发现之前成功的案例也出现抽取写入失败的问题。 > 操作：重启了一下那三个服务mysql、neo4j、server后使用一篇做实验，可以成功抽取并写入了。 > 问题：请问这三个服务有什么限制吗？为什么之前xlsx中有两篇成功，其他五篇失败呀，xlsx中content文本有字数限制吗？我这边七篇文章，平均20000字，是不是字数限制导致的问题呀？ > 需要对content里的内容进行预处理吗？比如删除多余空行。 > 非常期待您的回复！ > […](#) LLM may return a non-standard JSON format with a certain probability, which may cause parsing errors. You can...

> ### Search before asking > * [x] I had searched in the [issues](https://github.com/OpenSPG/KAG/issues?q=is%3Aissue) and found no similar issues. > > ### Operating system information > Linux > > ###...

> 要不我来改改吧 .. cc @northmachine thanks for your advice, you can create a pull request to merge your code

we provide [user guide for customizing planner of kag-solver](https://openspg.yuque.com/ndx6g9/docs_en/ui1vgeez17zuqxsa#SghtN)

> [new.txt.txt](https://github.com/user-attachments/files/18021126/new.txt.txt) 问题是：Do Yang Bin and Peng Huagang know each other? Have they participated in activities together? Could you tell us how to reproduce your experiments, including your llm conf、embedding...

> 我是根据文档中新场景快速开始步骤建了一个测试项目https://openspg.yuque.com/ndx6g9/0.5/vbbdp80vg0xf5n3k 下图是llm conf  下图是schema  下图是build/indexer.py  项目B的数据集就是上面发的new.txt，项目A在抽取new.txt之前还抽取了另外两个文档（随便找两个都可以） 由于单位网络问题，无法复制，只能以拍照形式呈现，还请谅解 I can not reproduce your problem. KAG 0.7 has released and solved some bugs in retrieval, could you have...

[KAG 0.8](https://openspg.github.io/v2/blog/recent_posts/release_notes/0.8) has been released at 2025-06-27. In which version, we have improved the management of private domain knowledge base indexing, incorporating multiple foundational index types such as Outline, Summary,...

> 根据上面地址中给的例子进行测试，发现pdf文本的"graph_stat": {"num_nodes": 0, "num_edges": 0, "num_subgraphs": 0}，docx和md格式文件上述参数是有数值的，为什么pdf是0？ > > 另外我上传自己的pdf测试时出现了以下报错 `INFO:kag.interface.common.llm_client:Error 'name' during invocation: Traceback (most recent call last): File "/home/xxx/project/KAG/kag/interface/common/llm_client.py", line 110, in invoke result = prompt_op.parse_response(response, model=self.model,...

KAG provide [schema-free extraction and schema-constraint extraction ](https://openspg.yuque.com/ndx6g9/docs_en/orwiw49glgg6gebx#cjAQU), user can chose either one of them.

> 对于图搜索是使用的规则匹配，还是向量搜索呀，为啥在给的V0.5的用户规则手册里面，上面文字写规则匹配，例子给出向量搜索呀？同理文本块在论文里边，被当作一个实体放在图中，那是如何进行向量检索的，这里的向量检索是指啥？ Kag supports index definition of entity Properties in [Schema file](https://github.com/OpenSPG/KAG/blob/master/kag/examples/hotpotqa/schema/HotpotQA.schema). Kag-solver translates user query into logicForm, which can be executed by the combination of kg_retrieval and chunk_retrieval, you...