Arcsgit/ai-mandi-forecaster

A GenAI-powered advisory system for Karnataka farmers. # 🌾 AI Mandi Price Forecaster – Karnataka A GenAI-powered advisory system for Karnataka farmers. It ingests historical Mandi price data, runs a 7‑day price forecast, and generates a Kannada sell/hold advisory (with optional voice output). --- ## 🔍 Problem Statement Farmers in Karnataka often sell produce without knowing upcoming market prices, leading to distress sales. This project: - Ingests historical Mandi price data from CSV - Runs short-term (7‑day) price forecasts (Prophet) - Generates a plain-language advisory in Kannada - Highlights the best mandi based on recent prices Supported demo crops: - Tomato - Onion - Maize --- ## 🧱 Tech Stack - **Frontend**: Streamlit - **Data**: pandas, numpy - **Forecasting**: Prophet - **Charting**: Plotly - **Text Advisory**: Groq LLM (Kannada) - **Language**: Python 3.9+ --- ## 🚀 Setup & Run (Local) ### 1. Clone the repository ```bash git clone github.com cd ``` --- ### 2. Create and activate a virtual environment (recommended) ```bash python -m venv .venv source .venv/bin/activate ``` --- ### 3. Install dependencies ```bash pip install --upgrade pip pip install -r requirements.txt ``` --- ### 4. Configure environment variables The app uses two API keys: - `GROQ_API_KEY` – for Kannada advisory text Set this in your shell: ```bash export GROQ_API_KEY="your_groq_key_here" ``` --- ### 5. Ensure the data file is in place The main dataset should be: ```bash data/karnataka_3crops_clean.csv ``` If you are running this from a fresh clone, make sure this file exists and has the expected columns: - `Arrival_Date` - `State` - `District` - `Market` - `Commodity` - `Modal_Price` --- ### 6. Run the Streamlit app ```bash streamlit run app.py ``` Streamlit will start a local server and show a URL like: ```text Local URL: localhost ``` Open that in your browser. --- ## 🌐 Using the Web App 1. **Select Crop** (Tomato, Onion, Maize) from the sidebar. 2. …