|
|
--- |
|
|
title: Csv Agent |
|
|
emoji: 🐢 |
|
|
colorFrom: green |
|
|
colorTo: gray |
|
|
sdk: gradio |
|
|
sdk_version: 5.15.0 |
|
|
app_file: app.py |
|
|
pinned: false |
|
|
license: mit |
|
|
short_description: A sample Agentic Data Analyst |
|
|
--- |
|
|
|
|
|
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference |
|
|
|
|
|
# 📊 CSV Agent with Cohere LLM and Langchain |
|
|
|
|
|
This application is developed as a demonstration of an Agentic system that acts as |
|
|
a Data Analyst. A csv file can be loaded and analyzed by asking questions. Charts can also |
|
|
be requested and should be displayed by the agent. |
|
|
|
|
|
The underlying LLM is a **Cohere Command-R** model, specifically **command-r-plus-08-2024**. The |
|
|
Agent also makes use of the LangChain framework. |
|
|
|
|
|
|
|
|
## 🎯 Key Features |
|
|
|
|
|
- **Dynamic CSV Upload:** Upload your CSV file effortlessly for instant analysis. |
|
|
- **Natural Language Queries:** Ask questions in plain English, and the agent responds with data insights. |
|
|
- **Chart Generation:** Visualize your data with auto-generated charts based on your queries. |
|
|
- **Interactive Interface:** User-friendly interface built with Gradio for easy interaction. |
|
|
- **Agent Reset:** Quickly reset the agent to upload new datasets without refreshing the page. |
|
|
|
|
|
## 🗂️ Installation |
|
|
|
|
|
1. Clone the repository: |
|
|
```bash |
|
|
git clone https://huggingface.co/spaces/nader01/csv-agent |
|
|
cd csv-agent |
|
|
``` |
|
|
|
|
|
2. Create a virtual environment and activate it: |
|
|
```bash |
|
|
python -m venv .venv |
|
|
source .venv/bin/activate # On Windows: .venv\Scripts\activate |
|
|
``` |
|
|
|
|
|
3. Install dependencies: |
|
|
```bash |
|
|
pip install -r requirements.txt |
|
|
``` |
|
|
|
|
|
4. Set up your `.env` file with the Cohere API key: |
|
|
```bash |
|
|
COHERE_API_KEY=your_cohere_api_key |
|
|
``` |
|
|
|
|
|
5. Run the application: |
|
|
```bash |
|
|
python csv_agent_with_chart.py |
|
|
``` |
|
|
|
|
|
## 🌐 How to Use |
|
|
|
|
|
1. **Upload a CSV File:** |
|
|
- Click on the **Upload CSV** button. |
|
|
- Select your CSV file to load the data. |
|
|
- View a preview of your data. |
|
|
|
|
|
2. **Ask a Question:** |
|
|
- Enter your question in the **Ask a Question** box. |
|
|
- Click **Submit Question** to receive a detailed answer. |
|
|
|
|
|
3. **View Charts:** |
|
|
- If the response includes a chart, it will be displayed below the response box. |
|
|
|
|
|
4. **Reset Agent:** |
|
|
- Click **Reset Agent** to clear data and upload a new CSV file without refreshing the page. |
|
|
|
|
|
## 🎨 User Interface Design |
|
|
|
|
|
- **Input & Output Boxes:** Light blue background with bold, dark blue labels for easy readability. |
|
|
- **Interactive Elements:** Buttons with responsive feedback for better user experience. |
|
|
|
|
|
 |
|
|
|
|
|
## 🧠 Powered By |
|
|
|
|
|
- **Cohere AI:** For natural language processing and data analysis. |
|
|
- **Gradio:** For building the interactive user interface. |
|
|
- **Pandas:** For efficient data handling. |
|
|
|
|
|
|
|
|
## 📜 License |
|
|
|
|
|
This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details. |
|
|
|
|
|
--- |
|
|
|
|
|
Enjoy exploring your data with this **CSV Agent**! 🚀 |
|
|
|
|
|
|
|
|
|
