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

Source: [KrishokBondhu: A Retrieval-Augmented Voice-Based Agricultural Advisory Call Center for Bengali Farmers](<https://www.sota2.com/research/paper/68fa7c521e209131cea8d8b5>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-17T05:00:05.807Z

Authors: Mohd Ruhul Ameen, Akif Islam, Farjana Aktar, M. Saifuzzaman Rafat

Published: 2025-10-21T07:24:55.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Agricultural Question Answering on KrishokBondhu Agricultural QA Dataset 1.0 (Evaluation set)](<https://www.sota2.com/research/sota/agricultural-question-answering-on-krishokbondhu-agricultural-qa-dataset-1-0-evaluation-set.md>): Agricultural Question Answering; KrishokBondhu Agricultural QA Dataset 1.0 (Evaluation set); Relevance: 5.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2510.18355>)

[PDF](<https://arxiv.org/pdf/2510.18355.pdf>)
