[Bug] There are more than 10,000 pieces of data in the table, and the number of rows read by the big model is inaccurate.

[fit2cloud-lijiaxin]

Contact Information

李佳鑫

MaxKB Version

v1.9.1

Problem Description

表格中数据过万条，大模型读取行数不准确。使用deepseek 和qwen 都测试过，不准确。20行数据可以统计成功，如果文档提取节点，分段传输，是否会影响大模型统计行数

Steps to Reproduce

The expected correct result

表格中数据过万条，不会影响大模型统计行数，可以成功统计

Related log output

Additional Information

No response

[baixin513]

感谢反馈，建议您写个函数处理一下文件内容分批发给大模型试试。

[shaohuzhang1]

Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑‍🤝‍🧑👫🧑🏿‍🤝‍🧑🏻👩🏾‍🤝‍👨🏿👬🏿

---

Thanks for the feedback, I suggest you write a function to process the file content and try to distribute it to the big model in batches.

[fit2cloud-lijiaxin]

意思是，文本提取节点是提取所有表格条目，统一推送给大模型吗？#2168 (comment)

[shaohuzhang1]

Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑‍🤝‍🧑👫🧑🏿‍🤝‍🧑🏻👩🏾‍🤝‍👨🏿👬🏿

---

Does the text extraction node extract all table entries and push them to the big model in a unified manner? #2168 (comment)