[Bug]: When using the openai compatible model, the model supports and the maximum token is set to 128000, but it is still stuck within 8000 tokens and truncated.

[stelvetica]

Is there an existing issue for the same bug?

• I have checked the existing issues.

RAGFlow workspace code commit ID

how to find it

RAGFlow image version

v0.16.0 full

Other environment information

window

Actual behavior

Expected behavior

No response

Steps to reproduce

RT

Additional information

No response

[hpx502766238]

我也有个差不多的问题：解析知识库文件的时候，如果嵌入模型序列长度是512的，即使分块大小设置远小于512，请求模型时候还是很容易超过512导致解析失败

[zbaos260]

会不会是api提供方的限制？

[KevinHuSh]

Disable the max token.