Published on: June 2026
CROPCARE-RAG 2.0: A MULTIMODAL AGRICULTURAL ADVISORY SYSTEM INTEGRATING VISION-LANGUAGE MODELS WITH RETRIEVAL-AUGMENTED GENERATION
Nishmitha K
Dr Dayananda R.B
Article Status
Available Documents
Abstract
Agriculture plays a critical role in ensuring global food security; however, farmers often face significant challenges in accessing accurate, timely, and reliable information for crop disease identification and management. Traditional agricultural advisory systems and standalone large language models (LLMs) frequently lack domain-specific grounding, leading to generic or potentially inaccurate recommendations. To address these limitations, this paper presents CropCare-RAG 2.0, a multimodal agricultural advisory system that integrates vision-language models with retrieval-augmented generation (RAG) to provide knowledge-grounded and context-aware responses.
The proposed system extends conventional text-based RAG frameworks by incorporating image-based crop disease detection using a pre-trained Contrastive Language–Image Pretraining (CLIP) model. Given an input image of a crop leaf, the system performs zero-shot classification by computing similarity between image embeddings and predefined disease labels, enabling flexible and scalable disease identification without the need for task-specific training. A key contribution of this work is the dynamic query augmentation mechanism, where the detected disease is automatically appended to the user’s textual query, thereby improving retrieval relevance and ensuring that subsequent responses are tailored to the identified crop condition.
How to Cite this Paper
K, N. (2026). Cropcare-RAG 2.0: A Multimodal Agricultural Advisory System Integrating Vision-Language Models with Retrieval-Augmented Generation. International Journal of Creative and Open Research in Engineering and Management, <i>02</i>(6). https://doi.org/10.55041/ijcope.v2i6.123
K, Nishmitha. "Cropcare-RAG 2.0: A Multimodal Agricultural Advisory System Integrating Vision-Language Models with Retrieval-Augmented Generation." International Journal of Creative and Open Research in Engineering and Management, vol. 02, no. 6, 2026, pp. . doi:https://doi.org/10.55041/ijcope.v2i6.123.
K, Nishmitha. "Cropcare-RAG 2.0: A Multimodal Agricultural Advisory System Integrating Vision-Language Models with Retrieval-Augmented Generation." International Journal of Creative and Open Research in Engineering and Management 02, no. 6 (2026). https://doi.org/https://doi.org/10.55041/ijcope.v2i6.123.
Search & Index
References
- Liu, Y. Zhang, and H. Chen, “A Retrieval-Augmented Large Language Model for Yunnan Arabica Coffee Cultivation,” Agriculture, vol. 15, no. 22, 2025.
- Li, K. Zhao, and S. Chen, “Research on Sem-RAG: A Corn Planting Knowledge Question-Answering Algorithm,” Applied Sciences, vol. 15, no. 19, 2025.
- Andersson, I. Eriksson, and P. Nilsson, “Enhancing Environmental Control in Broiler Production Using Retrieval-Augmented Generation with Large Language Models,” Animals, vol. 7, no. 1, 2025.
- Gupta and R. Patel, “RAP-RAG: A Retrieval-Augmented Generation Framework with Adaptive Retrieval Task Planning,” Electronics, vol. 14, no. 21, 2025.
- Verma and S. Iyer, “Layered Query Retrieval: An Adaptive Frame-work for Retrieval-Augmented Generation in Complex Question An-swering,” Applied Sciences, vol. 14, no. 23, 2024.
- Kumar and N. Mehta, “A Retrieval-Augmented Generation Chatbot for Comprehensive Medicinal Plant Insights,” Expert Systems with Applications, vol. 233, 2024.
- Thapa, S. Adhikari, and P. Kandel, “Integrating Machine Learning and RAG-Based Chatbot for Mandarin Orange Disease Detection,” Journal of Environmental Science and Agricultural Research, 2025.
- Lewis and M. Brown, “Are Re-Ranking Strategies Impactful for Small Agriculture Question-Answering Datasets?,” in Proceedings of the International Workshop on AI for Agriculture, 2025.
- A. Bakar, S. N. A. Baharom, and M. T. Ahmad, “Retrieval-Augmented Generation Data Query Technique for Pineapple Cultiva-tion,” Journal of Engineering and Sustainable Development, 2024.
- Silva, P. Andrade, and J. Costa, “AgroLLM: Connecting Farmers and Agricultural Practices Using Large Language Models,” arXiv preprint arXiv:2503.04788, 2025.
Ethical Compliance & Review Process
- •All submissions are screened under plagiarism detection.
- •Review follows editorial policy.
- •Authors retain copyright.
- •Peer Review Type: Double-Blind Peer Review
- •Published on: Jun 11 2026
This article is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. You are free to share and adapt this work for non-commercial purposes with proper attribution.