Government Schemes Recommendation with Multi-Language Chatbot Using RAG Vector Search and Conversational AI

Faiz Ahamed Sheriff M; Varun P; Dr. V Kavitha

doi:10.36948/ijfmr.2026.v08i03.79624

Government Schemes Recommendation with Multi-Language Chatbot Using RAG Vector Search and Conversational AI

Author(s)	Mr. Faiz Ahamed Sheriff M, Prof. Dr. Varun P, Dr. V Kavitha
Country	India
Abstract	The design and commissioning of a smart, end to end government scheme proposal and advice framework that incorporates web-based user interaction, secure authentication, semantic information retrieval and large language model driven chat support are introduced in this paper. The system proposed is a system of a modern React front-end, a Node.js authentication back-end with the usage of the JSON Web Token token and a FastAPI-based artificial intelligence service with the application of a vector similarity search and generative AI models. The structured metadata of a scheme stored in a relational database is enhanced with unstructured policy documents in the form of JSON files and considered with a FAISS-based vector store to provide the opportunity to perform a semantic correspondence of a user query. A hybrid scheme recommendation approach is created with the integration between embedding-based similarity search and the rule-based eligibility filtering based on independent demographic factors including age, gender, and category preferences. In addition to recommendation, it adds a multi-step dialogue that is interactively controlled and takes the user through the scheme knowledge, eligibility, application form, document submission and readily asked questions, and with multi-lingual support facilitated through neural translation. The architecture shows that modular separation of services, retrieval-enhanced generation, and conversational state control can be taken together in an effort to provide scalable, understandable, and user-friendly e-governance support. The functional integration outcomes of experimental evaluation provides support that the system is effective and meets the information accessibility gaps, and enhance the usability and complexity of the government welfare information to different users.
Keywords	semantic search, schemes recommendation by the government, vector embeddings, FAISS, Fast API, conversational AI, large language models, eligibility filtering, e-governance, generative search by retrieval augmentation.
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 8, Issue 3, May-June 2026
Published On	2026-05-29
DOI	https://doi.org/10.36948/ijfmr.2026.v08i03.79624

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 8 Isu 3 Cover Page Vol 8 Isu 2 Cover Page Vol 8 Isu 2

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Government Schemes Recommendation with Multi-Language Chatbot Using RAG Vector Search and Conversational AI

Share this