BliBly

+1

> Hi there, > > could you provide more info, like embedding model and prompt used? prompt: you are an analyst ，you will give a report about {{input}} embedding :...

> We will take a look into this issue. :) > > ---- Update---- The model did not provide a setting called `max_token`, so it shouldn't be able to display...

> I have a question about the version, we are currently using v0.3.33, And you said you are using 0.3.2? Do you mean 0.3.32? yes ,i mean 0.3.32. Thanks

> Retrieval is done on a per-query basis by design, so it's expected that your second search won't return documents relevant to your first search. > > However, in an...

> We use chat history as input context for chat model to better understand user query. That is not achieved through rewriting the user query. this could not take advantage...