search

HKUDS / LightRAG

"LightRAG: Simple and Fast Retrieval-Augmented Generation"
https://arxiv.org/abs/2410.05779
MIT License
9.63k stars 1.19k forks source link

exceed the token limitation: This model's maximum context length is 32768 tokens #203

Closed geoconst closed 2 weeks ago

geoconst commented 3 weeks ago

An error occurred: Error code: 400 - {'object': 'error', 'message': "This model's maximum context length is 32768 tokens. However, you requested 32796 tokens in the messages, Please reduce the length of the messages.", 'type': 'BadRequestError', 'param': None, 'code': 400}

i was using lightrag_openai_compatible_demo.py

image

model: vllm qwen2.5:3b embedding: bge-m3

dont known why ? anyone help ?

geoconst commented 3 weeks ago

finally, i fix it with

image