Plantr

Inspiration

Our team wanted to address the challenge presented by Majestic, focusing on helping farmers and gardeners make informed crop decisions based on their location

What it does

Our project allows users to select a specific location, after which it returns the best crop to grow in that area. The system analyses weather data, soil conditions, and temperature as well as other data to provide an optimal recommendation. Additionally, users can interact with an LLM-powered chat for further details about the suggested crop. The gathered insights are then used to update the user’s daily calendar. Furthermore, our model predicts the price point of a particular yield to help with financial planning

How We built it

Our team utilised:

Geolocation APIs to determine the user's exact location
Weather and soil data APIs to analyse environmental conditions
A vector database for plant-related information
An LLM-powered chat interface for user interactions
A price prediction model for estimating yield value
A web-based frontend for ease of access

The project was deployed to a flask server for scalability and accessibility

Challenges We ran into

Integrating various APIs and ensuring data consistency
Optimising the crop recommendation algorithm to be accurate and responsive
Fine-tuning the price prediction model to provide realistic estimations
Designing an intuitive UI that enhances user experience

Accomplishments that we're proud of

Successfully integrating multiple data sources to deliver meaningful crop suggestions
Implementing a smooth and responsive chat interface powered by an LLM

- Creating a functional price prediction model to assist users in financial decision-making

What we learned

How to efficiently process and use geospatial data
Improved understanding of API integrations for weather, soil, and crop data
Implementing an LLM-powered chat system for an interactive user experience
Deploying a cloud-based service for wider accessibility

What's next for “Plantr”

Enhancing the crop recommendation engine with more data sources for better accuracy
Expanding the LLM chat capabilities to provide more localised and detailed farming insights
Implementing a community feature where users can share their experiences and best practices.