Published: 15 Aug 2019 | Updated: 01 Sep 2020
We tested this component using the public "https://platform.uipath.com." UiPath Orchestrator.
We built this chatbot using "https://rasa.com/" Rasa. Rasa is an open source framework that provides machine learning tools for developers to build, improve, and deploy contextual chatbots and assistants. We also developed a Python connector for the "https://orchestrator.uipath.com/reference" UiPath Orchestrator API that makes calls to retrieve the information asked to the chatbot. Moreover, messages are stored in a "https://www.mongodb.com" MongoDB instance so they can be extracted, processed and used for re-training the Deep Learning models of Rasa. Once the user has asked something to the chatbot, it recognizes the user's intent applying a Deep Neural Network and the Python connector translates this information to make a query to the Orchestrator API. Finally, the Orchestrator's info is returned to the chatbot and displayed to the user in a user-friendly format. Furthermore, this chatbot can be connected to several messaging and voice channels easily. In this project, we provide configurations to deploy the Orchestrator Chatbot in a webchat (`webchat folder`) and in Google Assistant (`action.json file`), just for demo purposes. All dependencies are packed in a Docker container so that only Docker is required to use this component. Docker-CE: Used version: 19.03.1 Source of download: "https://docs.docker.com/install/" https://docs.docker.com/install/ License: Apache 2.0 "https://github.com/docker/docker-ce/blob/master/components/cli/LICENSE" https://github.com/docker/docker-ce/blob/master/components/cli/LICENSE
SupportUiPath Community Support