Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/prabdeb/openai-iot-speech-chatbot
OpenAI GPT model to build your personal assistant in IoT devices. Just like Alexa, Google Assistant, Siri, etc. but with your own skills, custom voice, and custom personality.
https://github.com/prabdeb/openai-iot-speech-chatbot
azure azure-cognitive-services azure-openai bing gpt iot openai
Last synced: about 1 month ago
JSON representation
OpenAI GPT model to build your personal assistant in IoT devices. Just like Alexa, Google Assistant, Siri, etc. but with your own skills, custom voice, and custom personality.
- Host: GitHub
- URL: https://github.com/prabdeb/openai-iot-speech-chatbot
- Owner: prabdeb
- License: mit
- Created: 2023-07-18T11:28:56.000Z (over 1 year ago)
- Default Branch: master
- Last Pushed: 2023-08-07T05:16:00.000Z (over 1 year ago)
- Last Synced: 2024-04-17T11:30:08.931Z (8 months ago)
- Topics: azure, azure-cognitive-services, azure-openai, bing, gpt, iot, openai
- Language: Jupyter Notebook
- Homepage:
- Size: 52.6 MB
- Stars: 5
- Watchers: 2
- Forks: 3
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# OpenAI IoT Speech Chatbot
This project demonstrates how to use OpenAI GPT model to build your personal assistant in IoT devices. Just like Alexa, Google Assistant, Siri, etc. but with your own skills, custom voice, and custom personality.
You can also name your assistant, currently it is named as `Arya`, means `noble` in Sanskrit.
## Demo
https://github.com/prabdeb/openai-iot-speech-chatbot/assets/37529789/3e2673c1-887e-4ef7-8ac5-d36d0f07de07
## Architecture
![Architecture](./docs/images/architecture.png)
## Experiments and Evaluation
Developing the OpenAI Prompt is easy with Azure OpenAI Playground, ChatGPT, OpenAI Playground, or even a simple Python script. But, the real challenge is to evaluate the performance of the OpenAI Prompt. There could be again tons of possibilities for evaluation.
In this project, we have used the [Azure ML PromptFlow](https://learn.microsoft.com/en-us/azure/machine-learning/prompt-flow/overview-what-is-prompt-flow?view=azureml-api-2) to perform experiments and evaluate the performance of the OpenAI Prompt. The PromptFlow is a framework for building and evaluating OpenAI Prompt. It is built on top of Azure Machine Learning and Azure OpenAI Services.
Why PromptFlow? Why not? There are several Out of the Box evaluations that PromptFlow provides, few of them are used in this project.
For more details on the experiments and evaluation, please refer to [Experiments and Evaluation](./experiments/README.md).
## Development and Deployment
To get started with this solution follow the documentation as mentioned in [Azure IoT Solution](./azure_iot_solution/README.md).
## Demo Hardware Setup
![Demo Hardware](./docs/images/hardware.png)