EP 24: Understanding Your AI Spend
Вставка
- Опубліковано 2 лис 2024
- In this week's stream, Robert goes through some best practices for understanding your AI Spend, and how to monitor which actions in the studio are consuming AI tokens.
This was originally streamed on our Discord server on March 12th, 2024. (join us live sometime!)
🤖 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.
🙏Thank you so much for this helpful video and all the other fantastic tutorials👍👋❗
Can you please tell if extracting information from DataTables by using execute code card / FindRecords table charge any tokens ?
If yes then is that token utilisation compared to utilising tables from knowledge base?
The answer to both of your questions is yes, as they're both knowledge base queries!
I built a bot and from the start it goes to an autonomous node that figures out what the user is trying to do for example request room service or make a review and when it detects your trying to make a review it takes you to a different workflow and there you can complete your review and returns to the main workflow and the only way i can get it to return is by using a workflow logic card in the main workflow and not a execute workflow node and if i use the exit in the logic card and path it to the start of my main workflow it just starts a endless rapid cycle by it self through my workflows and eats through my ai spend limit it happened twice and i lost about 2 -3 dollars by that happening and even if i restart the conversation in the emulator it just starts it again and completes the cycle a few times before stoping so the only way i got it to work is by turning the exit in the workflow logic off and using the nodes exit to connect to the start but it inly works for my 1 workflow if i try to do the same for 1 of ny other workflows it just ends the conversation and doesnt return to the main workflow even though its set up the same as the other one
I am currently in the process of creating a bot for my personal use using your platform. As part of this, I anticipate storing confidential and sensitive personal information in the bot's knowledge base.
Could you please clarify the security measures in place to ensure that this information is solely accessible to me and the designated bot users? I want to ensure that this data remains confidential and is not accessible by the BotPress admin or your team. Additionally, are there robust security layers in place to prevent any potential leaks of my personal and confidential information?
You can learn more about our privacy policies on the Legal section of our website.
Hello. Where i can write about one bug with PL language?
You can get in touch with us on our Discord server. :-)
Why does it say in the free plan that we have 2000 incoming messages and events per month? I've only been testing my chatbot on the backend for a few days and I'm already at 82% of my AI spend... You really can't do anything with the free plan!
Those are separate limits - messages and events are measured separately from the tokens used to power AI actions, like knowledge base queries and summarizing. You can see a detailed breakdown of your usage in your bot's logs.