Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{189770,
        author = {Gaurav Patil and Vivek Chaudhari and Rakesh Patil and Harsh Neve and K. D. Deore},
        title = {ORCA: Retrieval-powered AI Conversations},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {427-432},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=189770},
        abstract = {Conversational agents have evolved significantly with advancements in artificial intelligence and natural language processing, yet many chatbot development tools still require programming expertise. This creates barriers for educators, small organizations, and non-technical users seeking to harness conver- sational AI. This paper presents ORCA, a no-code platform that enables users to create intelligent, retrieval-augmented chatbots from diverse data sources including PDFs, URLs, JSON/CSV files, images, and hardcopy documents. ORCA employs a hybrid architecture combining a monolithic backend with microservices for high-compute tasks such as OCR and vector-based semantic search. The system integrates Groq’s high-speed llm inference engine and DataStax AstraDB for scalable embedding manage- ment.},
        keywords = {No-Code, AI, Chatbot, Conversational AI, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), Natural Language Processing (NLP), User-Centric Design},
        month = {January},
        }