Jeru Liu

看看安装得pytorch是否GPU版本，不是得话自己重装一下

这个repo bug太多，requirement.txt都装不上去，你们是不是装了最新版本的sciki learn? 是的话改这里： ``` # Find the optimal assignment between the two sets of elements matching = linear_sum_assignment(-scores) # Convert the matching matrix to a matrix of integers matching...

> **🤖 AI-generated response by [Steercode](https://steercode.com/) - chat with Langchain codebase** _Disclaimer: SteerCode Chat may provide inaccurate information about the Langchain codebase._ > > If you want to create an...

There is a more fundamental fix for this issue: retriever=VectorStoreRetriever(vectorstore=vectorstore, search_kwargs={"filter":{"type":"filter"},"k":3},), I guess it will work for qdrant as well

Thanks again @votrumar, sounds like a reasonable solution. but unfortunately i got an error: ValidationError: 1 validation error for StuffDocumentsChain k extra fields not permitted (type=value_error.extra) And I throw this...

I just have a quick check on langchain api reference, probably i should say k param is not supported in RetrievalQAWithSourcesChain

@votrumar Thanks a lot, are you the owner of steercode? it's cool app, I will introduce this website in my coming conference presentation

Take a reference from chat-langchain source code.

> @tugot17 is there any ideas now? i have the same issue。 https://github.com/hwchase17/chat-langchain/blob/master/callback.py - line 16 https://github.com/hwchase17/chat-langchain/blob/master/main.py - line 39

@20001LastOrder Thanks, it must be embedding issue for Chinese content, I've tried ada-embedding, huggingface sententce embedding, and chromadb default embedding, among these three solutions ada-embedding seems outperforms a little, but...