README.md

metadata

license: mit
sdk: streamlit
sdk_version: 1.55.0

🧠 DataMind Agent

AI-Powered Data Analyst — LangChain + Gemini + Streamlit

Upload any data file (CSV, Excel, JSON) and chat with your data using natural language. The agent analyzes, visualizes, and explains your data powered by Google Gemini.

---

🚀 Features

Feature	Description
📂 Multi-format support	CSV, Excel (.xlsx/.xls), JSON
💬 Natural language Q&A	Ask anything, get intelligent answers
📊 Auto visualizations	AI picks the best chart for your question
🎨 Custom chart builder	Build any chart with dropdown controls
🔍 Data explorer	Filter, search, and download raw data
🧠 AI data summary	Executive summary generated by Gemini

---

📁 Project Structure

data-analyst-agent/
├── app.py              # Streamlit UI (main app)
├── core_agent.py       # LangChain + Gemini logic
├── requirements.txt    # Python dependencies
├── .env                # API key config
├── sample_data.csv     # Test dataset (sales data)
└── README.md           # This file

---

⚙️ Setup & Installation

Step 1 — Clone / download the project

cd data-analyst-agent

Step 2 — Create a virtual environment (recommended)

python -m venv venv

# On Windows:
venv\Scripts\activate

# On Mac/Linux:
source venv/bin/activate

Step 3 — Install dependencies

pip install -r requirements.txt

Step 4 — Get your free Gemini API key

1. Go to https://aistudio.google.com/app/apikey
2. Sign in with Google
3. Click "Create API Key"
4. Copy the key (starts with AIza...)

Step 5 — Add your API key

Either paste it directly in the app sidebar, OR add it to .env:

GOOGLE_API_KEY=AIzaYourKeyHere

Step 6 — Run the app

streamlit run app.py

The app opens at http://localhost:8501

---

🎯 How to Use

1. Paste your Gemini API key in the sidebar
2. Upload a data file (CSV, Excel, or JSON)
3. Dashboard tab — see auto-generated stats and charts
4. Chat tab — ask questions like:
   • "What are the top selling products?"
   • "Is there a correlation between age and spending?"
   • "Show me outliers in the sales column"
5. Charts tab — build custom visualizations
6. Raw Data tab — filter and download your data

---

💡 Example Questions to Ask

"What is the average profit by category?"
"Which region has the highest sales?"
"Are there any missing values I should worry about?"
"What trends do you see in the data over time?"
"Which customers are the most valuable?"
"Give me a statistical summary of all numeric columns"
"What correlations exist between the columns?"

---

🏗️ Architecture

User (Streamlit UI)
       │
       ▼
  app.py (UI Layer)
       │
       ├── core_agent.py
       │       ├── load_file()          → Parses CSV/Excel/JSON → DataFrame
       │       ├── profile_dataframe()  → Statistical profiling
       │       ├── ask_agent()          → LangChain → Gemini → Answer
       │       ├── make_plotly_chart()  → Renders visualizations
       │       └── ai_recommend_chart() → Gemini picks best chart
       │
       └── Google Gemini 1.5 Flash (via LangChain)

---

📦 Key Libraries Used

Library	Purpose
langchain	Agent framework, prompt management
langchain-google-genai	Gemini LLM integration
streamlit	Web UI
pandas	Data loading and manipulation
plotly	Interactive visualizations
openpyxl / xlrd	Excel file support

---

🔧 Customization Ideas

• Add PDF support using pdfplumber
• Add database connection (SQLite, PostgreSQL)
• Add export to PowerPoint for chart reports
• Add multi-file comparison mode
• Deploy to Streamlit Cloud (free hosting)

---

🆓 Free Tier Limits (Gemini 1.5 Flash)

• 15 requests per minute
• 1 million tokens per minute
• 1,500 requests per day

This is more than enough for personal data analysis projects!

---

Built with ❤️ using LangChain + Google Gemini + Streamlit