This week we’re highlighting a new tool for generative contextual conversations from Google’s Kate Compton, creator of Tracery.
Prior to joining Google, Kate “GalaxyKate” Compton developed the open source Tracery, ”a super-simple tool and language to generate text.” She took inspiration from this previous project, as well as from the Cheap Bots, Done Quick! Bot-hosting platform and open source interactive fiction tool Twine when formulating what would become Bottery.
Compton’s Bottery, like Tracery, is a syntax used to write the script of a conversation with JSON that provides the backbone for a Cheap Bots-like interpreter to generate a simulated conversation.
The JSON “maps” that users write are separated into four components: a list of states, information about what to do when the states are entered, a set of initial “blackboard” values and optional grammar based on Tracery.
“The goal of Bottery is to help everyone, from designers to writers to coders, be able to write simple and engaging contextual conversational agents, and to test them out in a realistic interactive simulation, mimicking how they’d work on a ‘real’ platform like DialogFlow,” Compton wrote on the project’s GitHub page.
If this peaks your interest, head over the Compton’s project page, where she provides example code and conversations for you to get started simulating conversations.
Top 5 trending projects on GitHub this week:
#1. charts: simple, responsive, modern SVG Charts with zero dependencies
#2. Mask_RCNN: mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
#3. tailwindcss: a utility-first CSS framework for rapid UI development
#4. ant-design-pro: an out-of-box UI solution for enterprise applications
#5. Front-End-Checklist: Front-End Checklist for modern websites and meticulous developers