In Bangladesh, many farmers still struggle to access timely, expert-level agricultural guidance. This paper presents KrishokBondhu, a voice-enabled, call-centre-integrated advisory platform built on a Retrieval-Augmented Generation (RAG) framework for Bengali-speaking farmers. The system combines agricultural handbooks, extension manuals, and NGO publications, processes them through an OCR-based pipeline, and indexes the curated content in a vector database for semantic retrieval. Through a phone-based interface, farmers can receive real-time, context-aware advice: speech-to-text converts the Bengali query, the RAG module retrieves relevant information, a large language model (Gemma 3-4B) generates a grounded response, and text-to-speech delivers the answer in spoken Bengali. In a pilot evaluation, KrishokBondhu produced high-quality responses for 72.7% of diverse agricultural queries. Compared to the KisanQRS benchmark, it achieved a composite score of 4.53 versus 3.13 on a 5-point scale, with a 44.7% improvement and especially large gains in contextual richness and completeness, while maintaining comparable relevance and technical specificity. Semantic-similarity analysis further showed a strong correlation between retrieved context and answer quality. KrishokBondhu demonstrates the feasibility of combining call-centre accessibility, multilingual voice interaction, and modern RAG techniques to deliver expert-level agricultural guidance to remote Bangladeshi farmers.

翻译：在孟加拉国，许多农民仍然难以获得及时、专家级的农业指导。本文介绍了KrishokBondhu，一个基于检索增强生成（RAG）框架构建的、支持语音并与呼叫中心集成的咨询平台，专为孟加拉语农民设计。该系统整合了农业手册、推广指南和非政府组织出版物，通过基于OCR的流程进行处理，并将整理后的内容索引至向量数据库以实现语义检索。通过电话界面，农民可以获得实时、情境感知的建议：语音转文本模块将孟加拉语查询转换为文本，RAG模块检索相关信息，大语言模型（Gemma 3-4B）生成基于检索内容的回答，文本转语音模块以孟加拉语语音形式输出答案。在一项试点评估中，KrishokBondhu对72.7%的多样化农业查询生成了高质量回答。与KisanQRS基准相比，其在5分制上获得了4.53的综合得分（基准为3.13），提升了44.7%，尤其在情境丰富性和完整性方面提升显著，同时保持了相当的相关性和技术特异性。语义相似性分析进一步表明，检索到的上下文与回答质量之间存在强相关性。KrishokBondhu证明了将呼叫中心的可访问性、多语言语音交互与现代RAG技术相结合，为孟加拉国偏远地区农民提供专家级农业指导的可行性。