https://github.com/dataherald/streamlit-app
https://github.com/dataherald/streamlit-app
Last synced: 8 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/dataherald/streamlit-app
- Owner: Dataherald
- Created: 2023-09-14T13:30:33.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2024-04-03T16:55:58.000Z (about 2 years ago)
- Last Synced: 2025-04-06T17:05:13.991Z (about 1 year ago)
- Language: Python
- Size: 214 KB
- Stars: 16
- Watchers: 2
- Forks: 20
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Dataherald Community App 🛠️
Welcome to the Dataherald Community App! This Streamlit-based web application allows users to interact with the Dataherald engine through a user-friendly interface, making it easier to work with your structured data. 🔥🔥🔥
## Table of Contents 📚
- [Features](#features) 🚀
- [Prerequisites](#prerequisites) ⚙️
- [Installation](#installation) 🚀
- [Usage](#usage) 📈
- [How it works?](#how) 🧐
- [Contributions](#contribution) 🤝
## Features 🚀
- **Ask your Questions:** 💡 Connect to various databases by providing their connection details and ask any questions that have on top of your mind from Dataherald's powerful NL-to-SQL engine.
- **Add Golden records:** 💎 In order to boost the performance of the engine even higher, add verified Question/SQL pairs. These pairs are going to be used by the agent at inference time.
- **View and Remove Golden records:** 📜 This application provides a user-friendly interface for viewing, searching, and removing Question/SQL pairs to control the agent's behavior.
- **Table Scanning:** 🗃️ Scan tables in connected databases by specifying the table name. Scanned tables are used by the agent to generate answers.
- **Viewing Tables:** 📊 View descriptions and details of tables within connected databases. Understand the structure and number of columns of each table easily.
## Prerequisites ⚙️
Before running Dataherald, ensure that you have the following prerequisites:
- **Dataherald engine:** 💻 Make sure you have Dataherald engine running since this application calls the endpoints provided by the Dataherald engine.
- **Python 3.x:** 🐍 Make sure you have Python 3.x installed on your system. You can download it from the [official Python website](https://www.python.org/downloads/).
## Installation 🚀
To get started with Dataherald, follow these steps:
1. **Clone the repository to your local machine:**
```shell
git clone https://github.com/Dataherald/streamlit-app.git
cd streamlit-app
2. **Create a virtual environment (optional but recommended):**
```shell
python -m venv venv
source venv/bin/activate # On Windows, use `venv\Scripts\activate`
```
3. **Install required packages: 📦 This app relies on several Python packages. Install them by running the following command within the project directory:**
```shell
pip install -r requirements.txt
```
## Usage 📈
To use Dataherald Community App and interact with databases, follow these steps:
Change the following code parts based on your current implementation of Dataherald engine:
```python
DEFAULT_DATABASE = "RealEstate" # change this to your default database
HOST = st.sidebar.text_input("Engine URI", value="https://streamlit.dataherald.ai") #change the value to your localhost or server URI where your engine is deployed
```
Start the Dataherald Community App application:
``` shell
streamlit run 🏠_Home.py
```
## How it Works 🧐
If you want to know how the app works, you can take a look at the following figure:
## Contributions 🤝
We are extremely open to contributions, be it through new features, new pages, or improved documentation.
We are currently developing this repository, you can take a look at the roadmap we have for this app, and we will appreciate your contribution for the future works that we have. You can find the roadmap [here](https://github.com/Dataherald/streamlit-app/blob/main/contributions.md#roadmap-%EF%B8%8F).