PRANJALRANA11 / datamate

DataMate is your private data assistant. A conversational interface for your data where you can load clean transform and visualize without a single line of code. DataMate is open source and can be run entirely locally keeping your juicy data secrets fully private.

dataMate 💬📊

DataMate is your data assistant. A conversational interface for your data where you can load, clean, transform, and visualize without a single line of code.

Demo

datamate.mp4

Note: Demo above is Gemini-pro/vision, which sends the conversation to Google AI API. . Model can hallucinates answer or even can produce bugs

⇒ Try it now! Hosted public environment is live! (Click Here) ⇐

Features

• Persistent Juptyer kernel backend for data manipulation during conversation
• Natural language chat, visualizations/plots, and direct download of data assets
• Load multiple tables directly into the chat
• Search for data and load CSVs directly from github
• Export data as html file
• WIP: Rollback kernel state when undo using criu (re-execute all cells)
• TODO: Support for more data sources (e.g. SQL, S3, PySpark etc.)

Things you can ask DataMate

• Load data from a URL
• Clean data by removing duplicates, nulls, outliers, etc.
• Join data from multiple tables into a single output table
• Visualize data with plots and charts
• Ask whatever you want to your very own code-interpreter

Quickstart

To install locally.

1. Clone the repository

git clone https://github.com/PRANJALRANA11/datamate

2. Create a branch

git checkout -b temp

3. copy the .env.example to .env

cp .env.example .env

4. install the dependancies

pip install -r requirements.txt

5. activate the virtual environment

.venv/scripts/activate

6. Run Uvicorn and access localhost:8000/docs

Uvicorn app:app --reload

Contributions

Contributions are welcome! Feel free to submit a PR or open an issue.

Technologies used in the project:

fastapi Jupyter Kernels Google Cloud Gemini pro

🛡️ License

This project is licensed under the MIT