Open CamusGao opened 1 week ago
Version 0.0.7 is good, it seems that there is an issue with the logic of max_tokens.
Version 0.0.7 is good, it seems that there is an issue with the logic of max_tokens.
I disabled max_tokens option in dialog settings.
But I think max_tokens should be used to check before actually interacting with the model, and should not replace the judgment of different responses from the model service.
This is why RAGFlow says too long since xinference tells it so. {"index": 0, "delta": {"content": ""}, "finish_reason": "length"}
This is why RAGFlow says too long since xinference tells it so. {"index": 0, "delta": {"content": ""}, "finish_reason": "length"}
ragflow doesn't say it to the front end. ragflow stops to response with no content and no reason. RAGFlow says nothing
Is there an existing issue for the same bug?
Branch name
main
Commit ID
83803a7
Other environment information
Actual behavior
xinference's response was
and ragflow's response was
ragflow gave no message and finished while model provider gave a abort response.
Expected behavior
Ragflow tells user that the content is too long
Steps to reproduce
Additional information
No response