Hi everyone, I have created a therapist chatbot on this new app called Rody. I want it to be the most human and professional as possible, and generally felt the most comfortable and trust-worthy for users. This is because I find AI therapist is the most suitable option for me, and if it’s more developed, and can help more people like me, especially when we only get more and more busy.
I hope you guys can try it and help me improve it. You can download the app on iOS and Android.
So recently, we have been experimenting with knowledge bases, and how information is structured is vital.
In some sense, it directly relates to the context and overall meaning. It also makes it easier for LLMs to answer questions accurately and reduces hallucination.
And so we created a few experiments, that you can play with and test it yourself.
But first, why does Information Structure Matter?
Imagine a library. One room has books strewn everywhere, titles mixed up, and no discernible order. In another room, the books are organized by subject, then by author, then by publication date. Which room would help you find the book you want more efficiently?
LLMs are similar. The way knowledge is presented and organized dictates not only their understanding but also their output.
Our recent experiments highlighted two crucial aspects:
Organization of Informational Taxonomies and Hierarchies:
This considers elements like URL structures, folders, and how information is interrelated. By defining the proper context, you can highlight what’s critical.
Organization Within a Document:
Delving deeper, this looks at the composition of individual pieces of information — from structure and semantics to formatting and summaries.
Let’s dive into our findings on the first aspect:
Hierarchical Structures: The Backbone of Knowledge
At its core, informational hierarchy is about context. Whether it’s a URL on a website or the structure of folders within a system, hierarchies set the scene and help LLMs understand the importance and relevance of different data points.
Consider this: – ChatbotConferences.com/conferences/2019/nyc suggests there are multiple events across different cities. – ChatbotConferences.com/new-york-city offers just a city, which, out of context, is ambiguous. – ChatbotConferences.com/nyc/2019 indicates multiple NYC events but omits a broader context.
The Great Hierarchy Test
We started on a quest to understand the weightage and importance hierarchies. We build two chatbots with their primary differentiation being the organization of their hierarchy:
– Bot 1: Trained on multiple pages, each representing a distinct event and year.
– Bot 2: Trained on a consolidated page that collates all the agendas.
Structure is just the tip of the iceberg. If you’re intrigued and keen to delve deeper into the art of building bots using knowledge bases, I have exciting news!
If you’ve ever built a chatbot, you’ve run into the question of how to give it “memory”.
Since LLMs are stateless by default, it falls on us to make sure our chatbots can recall information and have a fluid conversation.
I put together a quick guide with 4 different ways to give your chatbot more memory. Ranging from easy to implement, to more technical (Embeddings + RAG).
Feel free to check it out here, hope it’s helpful.
Artificial intelligence (AI) is revolutionising various industries, and education is no exception. Its key implications and relevance in today’s teaching landscape extend to both language learning and overcoming language barriers, critical in enhancing communication. The following sections will dive deeper into the transformational power of AI in language acquisition, bridge communication gaps, and discuss its role in promoting accessibility in education
Hi everyone, I just feel bored about the current AI chatbot apps that I’m using and want to try something new. Idk, more options for characters, suggestions while creating new bots,…Any recommendation would be appreciated.
I’m looking for an open-source project that helps me build complex chatbot flows without any association with messengers.
I need some core library for manipulation of conversation flows, like a Microsoft Bot Framework, but without any dependence on cloud platforms/other vendors or messengers.
![[link]](https://i.redd.it/a0m18qk29uvb1.png){kind=link}