KrishokBondhu: A Retrieval-Augmented Voice-Based Agricultural Advisory Call Center for Bengali Farmers

TL;DR

KrishokBondhu is a voice-based, retrieval-augmented platform that provides Bengali farmers with real-time, expert agricultural advice through a call center, combining OCR, semantic retrieval, and large language models.

Contribution

It introduces a novel voice-enabled advisory system using RAG techniques tailored for Bengali farmers, integrating multiple content sources and achieving high-quality, context-aware responses.

Findings

Achieved 72.7% high-quality response rate in pilot evaluation.

Outperformed benchmark KisanQRS with a 44.7% improvement in composite score.

Demonstrated feasibility of combining call-centre, multilingual voice, and RAG for agricultural guidance.

Abstract

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.