JacobHenry commited on
Commit
42b614f
1 Parent(s): 8eda170

Update README.md

Browse files

Dear Hugging Face Community,

my fellow student, Jan Bausback, and me are currently studying Leadership in Digital Innovation at the University of Arts in Berlin, Germany.
In the Course "AI and Creativity" we had the task to use AI-Technology hands-on in a very small case.

We figured, that the start of our company-internal virtual meetings is sometimes filled with awkward silence that disables a motivational kickstart into the meeting.
So we asked ourselves the question: Is there a way to avoid that awkward silence and instead fill the first minutes of a meeting with something connecting for the attendees?
We came up with the idea, that our Work Calendars may share similar non-work-related events, such as Vacation Plans or even Leisure Time Events like Yoga or Gym Activities. What if there was a way, for an AI tool to automatically propose a conversation starter about a matching calendar event of you and your colleagues. The way this conversation starter would pop-up on your screen was not in-scope of our project, since there are many possible ways for that, such as Synthesia-like Text-to-Video Avatars that directly start a conversation or just a Text that is sent to you specifically in the Chat Window including the conversation starter you could use in a situation of awkward silence.

We decided that the scope of our small-scale AI-project, was to code a model that extracts information from csv-files (calendar exports) and automatically proposes a conversation starter based on matching calendar events in the csv-exports of several calendar, possibly fellow employees. We used Langchain and the free trial version of the OpenAI-API to code this quiet simple model.


We kindly ask four your feedback and any improvements that could be made.

Jan & Jakob

Files changed (1) hide show
  1. README.md +8 -1
README.md CHANGED
@@ -1,3 +1,10 @@
1
  ---
2
  license: unknown
3
- ---
 
 
 
 
 
 
 
 
1
  ---
2
  license: unknown
3
+ language:
4
+ - en
5
+ pipeline_tag: document-question-answering
6
+ tags:
7
+ - code
8
+ - csv
9
+ - conversation
10
+ ---