EP 20: Query Knowledge Base & Saving Data to Table

In this week's stream, Robert demonstrates how to use the Query Knowledge Base card and save user-submitted data to a Botpress Table.
This was originally streamed on our Discord server on February 13th, 2024.
🤖 Try Botpress now for free: hubs.la/Q01Lf4-J0
🔔 Subscribe for more Botpress tips, tutorials and features: hubs.la/Q01Lf74q0
-------------
👉 Follow Botpress on LinkedIn: hubs.la/Q01Lf6Wm0
👉 Find us on Twitter: hubs.la/Q01Lf6Y70
👉 Join the conversation on our Discord server: hubs.la/Q01Lf6V-0
About Botpress:
Botpress is a user-friendly platform that empowers individuals and teams of all sizes to design, build, and deploy AI-powered chatbots for various applications. As a pioneer in the chatbot industry, we embrace the power of large language models (LLM) and generative AI to create personalized, engaging chatbot experiences for any purpose. Available in 100+ languages and with a GPT-native suite of tools to help you unlock your creativity, Botpress supports you in achieving your goals and transforming the way you communicate.

[@azer0013]

Did you have a video for extract the data from the table please??

[@UmaShankar-ke3hm]

I tried as you have done in the video but the variables I have created are not being displayed to assign to the specified column names in the table. Can anyone tell me why?

[@user-ie4vm1ch9z]

I want to build a chatbot using flutter. Can i get API to use this chatbot as that provided by the Gemini or Openai it possible to remember the previous chat before the next query?

[@user-ie4vm1ch9z]

is there any plan to publish dart integration?

[@UnuAlex]

Lovely stream!

[@louismathews6831]

When I create a tiny little table with 2 rows and 2 columns in it and query it, then the debugger states im using 1000-4500 tokens. What does a local table have to do with LLM tokens and why so many? That means we are paying for every local database query, that doesnt make sense to me.

[@bex1335]

Hi Robert!
I'm currently working on building a chatbot for a company that sells pre cooked meals.
The idea of this chatbot is that it can build custom made meal plans for the users and clients. So I made it first capture all the user's info, such as: weight, height, purpose (like loose weight, gain muscle, eat healthier) and other and save all this info in variables. I have also created a couple KBs containing tables with all the dishes they sell, the calories, and other useful info.
My question is: how do I integrate the user's info and the KB at the same time, so it generates a meal plan according to the user's data and also to the products they sell? Do I need an AI task and a KB query task? thanks for the help ^^

[@relaxingfireplacesounds]

Safe all the customer information in variables. Then in the Query Knowledge Bases card, use the variables in the query. In your case the query should look something like this: "generate a meal plan for @weight, @height, @purpose". You probably need to play around with the wording of the query a little bit, till you get the best results.

[@kubakelly3536]

@@relaxingfireplacesounds hey do you know how i can simply show a user all of his previous made inputs, so that he can confirm or make changes?

[@THESHORTS508]

hi i have one question
i need to make a chatbot logic like if he find the answer in knowledge base it will continue else it will send the msg sorry. how would i do that ?

[@Botpress]

We've got other videos about this on our channel: check out "ChatGPT Fallback"

[@dmiller2036]

Yeah sorry tables/kb are horrible broken.