Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/alishobeiri/thread
AI-powered Jupyter Notebook — use local AI to generate and edit code cells, automatically fix errors, and chat with your data
https://github.com/alishobeiri/thread
ai analysis analytics data-science jupyter jupyter-notebook jupyter-notebooks jupyterhub jupyterlab ollama python react reactjs
Last synced: 2 days ago
JSON representation
AI-powered Jupyter Notebook — use local AI to generate and edit code cells, automatically fix errors, and chat with your data
- Host: GitHub
- URL: https://github.com/alishobeiri/thread
- Owner: alishobeiri
- License: agpl-3.0
- Created: 2024-05-21T20:18:22.000Z (7 months ago)
- Default Branch: main
- Last Pushed: 2024-10-24T16:46:43.000Z (about 2 months ago)
- Last Synced: 2024-12-13T02:03:19.376Z (9 days ago)
- Topics: ai, analysis, analytics, data-science, jupyter, jupyter-notebook, jupyter-notebooks, jupyterhub, jupyterlab, ollama, python, react, reactjs
- Language: JavaScript
- Homepage:
- Size: 69.6 MB
- Stars: 1,075
- Watchers: 13
- Forks: 56
- Open Issues: 7
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
AI-powered Jupyter Notebook
Vizly Notebook is a Jupyter alternative that integrates an AI copilot into your Jupyter Notebook editing experience.
Best of all, Vizly Notebook runs locally and can be used for free with [Ollama](https://github.com/ollama/ollama) or your own API key. To start:
```
pip install vizly-notebook
```
To start vizly-notebook, run the following
```
vizly-notebook
```
or
```
jupyter vizly-notebook
```
or
```
jupyter thread
```
# Key features
### 1. Familiar Jupyter Notebook editing experience
### 2. Natural language code edits
### 3. Generate cells to answer natural language questions
### 4. Ask questions in a context aware chat sidebar
### 5. Automatically explain or fix errors
# Demo
https://github.com/squaredtechnologies/vizly-notebook/assets/18422723/b0ef0d7d-bae5-48ad-b293-217b940385fb
# Feature Roadmap
These are some of the features we are hoping to launch in the next few month. If you have any suggestions or would like to see a feature added, please don't hesitate to open an issue or reach out to us [via email](mailto:[email protected]) or [discord](https://discord.gg/ZuHq9hDs2y).
- [ ] Add co-pilot style inline code suggestions
- [ ] Data warehouse + SQL support
- [ ] No code data exploration
- [ ] UI based chart creation
- [ ] Ability to collaborate on notebooks
- [ ] Publish notebooks as shareable webapps
- [x] Add support for Jupyter Widgets
- [ ] Add file preview for all file types
# Cloud
Eventually we hope to integrate Vizly Notebook into a cloud platform that can support collaboration features as well hosting of notebooks as web application. If this sounds interesting to you, we are looking for enterprise design partners to partner with and customize the solution for. If you're interested, please reach out to us [via email](mailto:[email protected]) or [join our waitlist](https://waitlist.thread.dev).
# Development instructions
To run the repo in development mode, you need to run two terminal commands. One will run Jupyter Server, the other will run the NextJS front end.
To begin, run:
```
yarn install
```
Then in one terminal, run:
```
sh ./run_dev.sh
```
And in another, run:
```
yarn dev
```
Navigate to `localhost:3000/vizly-notebook` and you should see your local version of Vizly Notebook running.
If you would like to develop with the AI features, navigate to the `proxy` folder and run:
```
yarn install
```
Then:
```
yarn dev --port 5001
```
# Using Vizly Notebook with Ollama
You can use [Ollama](https://github.com/ollama/ollama) for a fully offline AI experience. To begin, install and run vizly-notebook using the commands above.
Once you have run vizly-notebook, in the bottom left, select the Settings icon:
Next, select the Model Settings setting:
This is what you will see:
Navigate to Ollama and enter your model details:
Use Ctrl / Cmd + K and try running a query to see how it looks!