README.md

metadata

title: Gemini Data Analysis Agent
emoji: 🤖📈
colorFrom: blue
colorTo: indigo
sdk: streamlit
app_file: app.py
license: mit
sdk_version: 1.51.0

🤖 Gemini Data Analysis Agent

This is a simple Streamlit application that uses the Google Gemini API and LangChain to create an AI agent.

You can upload any CSV file, and the agent will use a Gemini model to write and execute Python (Pandas) code to answer your questions about the data.

🚀 How to Use

1. Upload a CSV file using the file uploader.
2. The app will display the first few rows of your data.
3. Ask a question in the text box (e.g., "How many rows are there?" or "What is the average value in the 'sales' column?").
4. The agent will analyze the data and provide a plain-English answer.

🛠️ Tech Stack

• LLM (Brain): Google Gemini (via langchain-google-genai)
• Agent Framework: LangChain (specifically create_pandas_dataframe_agent)
• Frontend (UI): Streamlit
• Hosting: Hugging Face Spaces

🔑 Setup

This app requires a Google Gemini API key to function.

1. Create a Google AI Studio API key.
2. In your Hugging Face Space Settings, go to Repository secrets.
3. Add a new secret:
   • Name: GEMINI_API_KEY
   • Value: (Paste your API key)