In this video I have demonstrated and shown how to convert a search-related question asked to a @Slackhq Chatbot into a search with a pre-filter applied to make the search results more relevant.
I have used @LangChain 's Self-Querying feature that can convert a question like this:
"Can you find me that thread where Vinit Agrawal talked about AI Safety on the General channel?"
to
"from: @VinitAgrawal88 in:#general AI Safety"
This will reduce the search space significantly and improve the quality and relevance of search results.
I'm not sure why you got downvoted, because that's actually something in my post. Thanks for the compliment, and sorry for your downvotes. Take this thank you instead. :(
It's surprisingly simple. Split testing tools are really just feature toggles with RNG and a little tracking.
The stats and maths are mostly on the reporting side. We just rely on a bunch of Chi-squared hypothesis tests - that's about the hardest part to an A/B testing system.
Thank you! The mechanics sort of work ok, but it needs graphics and animation now. It is definitely good Javascript practice - I look at the early code when starting it, and think Ugh
I feel the pricing structure of MailChimp has become very complex. It reminds me of the pricing structure of intercom. Very difficult to clearly understand what am I being charged for. I don't know why they are doing this. They should work on making new features and charge more for that.
I have used @LangChain 's Self-Querying feature that can convert a question like this:
"Can you find me that thread where Vinit Agrawal talked about AI Safety on the General channel?"
to
"from: @VinitAgrawal88 in:#general AI Safety"
This will reduce the search space significantly and improve the quality and relevance of search results.
Read more about LangChain's Self-Querying Retriever here: https://python.langchain.com/docs/modules/data_connection/re...