README.md

metadata

title: Data Analyst Agent with OpenAI Assistants
emoji: 📊
colorFrom: blue
colorTo: red
sdk: gradio
python_version: '3.11'
app_file: app.py
pinned: false

🤖 Data Analyst Agent with OpenAI Assistants

This project demonstrates a powerful data analysis agent built using the official OpenAI Assistants API. The agent leverages the built-in Code Interpreter tool to analyze user-uploaded CSV files, answer questions, and generate visualizations.

The web interface is created with Gradio, and the project environment is managed by uv.

🚀 How to Use the Live Demo

1. Upload a CSV File: Use the file uploader to select a .csv file from your computer.
2. Ask a Question: In the textbox, ask a question about your data in plain English. For example:
   • "What is the average age in the dataset?"
   • "Create a pie chart showing the distribution of categories."
   • "What are the key insights from this data? Provide one recommendation."
3. Run Analysis: Click the "Run Analysis" button. The agent will process your file and question on OpenAI's servers and return a detailed text answer along with any generated plots.

---

🛠️ Local Setup and Execution (For Developers)

Follow these steps to run the application on your own machine.

1. Clone the Repository

git clone [https://github.com/Shiverion/Data-analysis-using-OpenAI-Assistant.git](https://github.com/Shiverion/Data-analysis-using-OpenAI-Assistant.git)
cd your-repo-name

2. Set Up the Environment with uv This project uses uv for fast and reproducible environment management.

First, install uv if you haven't already:

On macOS / Linux

curl -LsSf [https://astral.sh/uv/install.sh](https://astral.sh/uv/install.sh) | sh

On Windows

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Then, sync the environment. This command creates a virtual environment and installs the exact package versions from the uv.lock file.

uv sync

3. Set Up Your API Key

Create a file named .env in the root of the project and add your OpenAI API key to it: OPENAI_API_KEY='your-secret-key-here'

4. Run the Application

Use uv to run the app within the managed environment:

uv run app.py

---

Open the local URL (e.g., http://127.0.0.1:7860) in your browser.

📄 File Structure

• app.py: The main Gradio application script containing the agent logic.

• requirements.txt: A list of Python dependencies for Hugging Face Spaces.

• uv.lock: A definitive lockfile for reproducible environments with uv.

• .env: Local file for storing your secret API key (ignored by Git).

• .gitignore: Specifies files for Git to ignore.