Core library powering a GUI providing an audio interface to GPT3.
Project description
Jabberwocky
This was not really designed to be used as a standalone library - it was mostly used as a convenient way to structure and import code in other parts of the project. Some components may be reusable for other projects combining GPT-3 with audio, however.
Project Description
The core library powering a GUI that provides an audio interface to GPT3. We support conversations with most public figures and provide a number of other pre-built tasks including:
- Summarization
- Explain like I'm 5
- Translation
- How To (step by step instructions for performing everyday tasks)
- Writing Style Analysis
- MMA Fight Analysis and Prediction
- Explain machine learning concepts in simple language
- Generate ML paper abstracts
Examples
In conversation mode, you can chat with a number of pre-defined personas or add new ones:
In task mode, you can ask GPT3 to perform a number pre-defined tasks. Written and spoken input are both supported. By default, GPT3's response is both displayed in writing and read aloud.
Transcripts of responses from a subset of non-conversation tasks can be found in the data/completions
directory.
Project Members
- Harrison Mamin
Repo Structure
jabberwocky/
├── data # Raw and processed data. Actual files are excluded from github.
├── notes # Miscellaneous notes stored as raw text files.
├── notebooks # Jupyter notebooks for experimentation and exploratory analysis.
├── reports # Markdown reports (performance reports, blog posts, etc.)
├── bin # Executable scripts to be run from the project root directory.
├── lib # Python package. Code can be imported in analysis notebooks, py scripts, etc.
└── services # Serve model predictions through a Flask/FastAPI app.
Start of auto-generated file data.
Last updated: 2021-09-12 13:53:34
File | Summary | Line Count | Last Modified | Size |
---|---|---|---|---|
__init__.py | _ | 1 | 2021-09-04 13:32:08 | 22.00 b |
config.py | Define constants used throughout the project. | 21 | 2021-07-22 20:29:41 | 564.00 b |
core.py | Core functionality that ties together multiple APIs. | 609 | 2021-09-06 13:39:53 | 24.21 kb |
external_data.py | Functionality to fetch and work with YouTube transcripts. | 281 | 2021-08-06 20:25:01 | 9.97 kb |
openai_utils.py | Utility functions for interacting with the gpt3 api. | 1320 | 2021-09-01 20:12:51 | 55.00 kb |
speech.py | Module to help us interact with mac's speech command. This lets the GUI read responses out loud. |
117 | 2021-08-20 21:05:11 | 4.16 kb |
utils.py | General purpose utilities. | 337 | 2021-08-04 20:02:18 | 10.93 kb |
End of auto-generated file data. Do not add anything below this.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.