FarmHub - Enhancing the Urban Farming Lifestyle
FarmHub: Uniting generations through specialized agtech. Precision in holistic guidance, visual insights, and urban farming promotion for a smarter agricultural future.
Created on 28th January 2024
•
FarmHub - Enhancing the Urban Farming Lifestyle
FarmHub: Uniting generations through specialized agtech. Precision in holistic guidance, visual insights, and urban farming promotion for a smarter agricultural future.
The problem FarmHub - Enhancing the Urban Farming Lifestyle solves
FarmHub addresses the pressing challenge of bridging the generational gap in agriculture. Traditional farmers lack access to modern technology, hindering productivity. Simultaneously, the younger generation lacks essential traditional farming knowledge. This disconnect leads to a significant loss of valuable practices and knowledge.
Moreover, language disparities exacerbate the issue, impeding effective communication and knowledge transfer. The result is a critical shortage of agricultural guidance, limiting the potential for innovation and sustainable practices. The declining interest of the younger generation in agriculture stems from the lack of know-how, further widening the gap.
FarmHub's solution is an innovative application leveraging a specialized Large Language Model dedicated to agriculture. This user-friendly platform provides holistic farming guidance, incorporating visual insights through image recognition. Tailored for the unique needs of agriculture, FarmHub goes beyond conventional agtech by promoting urban farming, aligning with the evolving lifestyle.
By fostering knowledge exchange and empowerment, FarmHub acts as a bridge between generations, enabling efficient, sustainable, and technology-driven farming practices. The project envisions a future where traditional wisdom and cutting-edge technology coexist, ensuring the preservation and enhancement of agriculture for generations to come.
Challenges we ran into
- Establishing Seamless Connection using Websockets from backend to frontend
- Running a LLM Locally
- Training Images with limited resources
- embedding third party service providers in the webpage
- prompting the LLM to provide precise result for each query
- While making LLM work with previous conversation
