SimFG
SimFG
@xusheng-gong We try to reproduce this problem, but without success. you can try to install the latest development version to see if the problem is solved ``` # clone GPTCache...
@kennethleungty i will try, can you help me try to use the `dev` version to make sure the bug has been fixed
@kennethleungty you can update the `langchain` latest version, it's a compatibility issues `22916 - adapter.py-adapter:154 - WARNING: failed to save the data to cache, error: _update_cache_callback() got an unexpected keyword...
@kennethleungty We will improve the code in langchain to reduce the possibility of compatibility issues. For the problem of onnx, we will check it out. If it is possible, can...
@kennethleungty thank your feedback :)
@kennethleungty now you can try to use the context processor to handle the long prompt, like: ``` from gptcache.processor.context.summarization_context import SummarizationContextProcess from gptcache import cache context_process = SummarizationContextProcess() cache.init( pre_embedding_func=context_process.pre_process,...
More discussion will be in issue: #298
/lgtm /approve
/lgtm /approve
I use the `uer/albert-base-chinese-cluecorpussmall` model in the huggingface. There is a simple demo, you can try it. ```python import os import time from gptcache.embedding import Huggingface from gptcache import cache...