Rabbitt.ai Launches ChanceRAG, a No-Code Retrieval Augmented Generation Solution

Indian genAI startup, Rabbitt.ai has announced the launch of ChanceRAG, a no-code Retrieval Augmented Generation (RAG) solution designed to simplify the integration of large language models (LLMs) with document retrieval systems. 

Harneet Singh, chief AI officer at Rabbitt.ai, highlighted the product as an “enterprise-grade solution for building RAG.”

“We noticed that traditional retrieval methods, whether semantic or keyword-based, weren’t providing the depth and accuracy needed for complex queries. With ChanceRAG, we’ve created a fusion retrieval technique that delivers unparalleled precision and context, something that no current method achieves on its own,” he said.

ChanceRAG allows users to upload PDF documents and connect their LLMs to these documents through a vector database. The product introduces an Advanced Fusion Retrieval technique, which blends semantic understanding with keyword matching for enhanced performance.

Singh explained that the motivation behind ChanceRAG stemmed from the challenges businesses face in building effective RAG pipelines. He noted that existing retrieval methods were inefficient for real-world applications like customer support chatbots and AI sales agents. ChanceRAG seeks to eliminate trial-and-error in RAG implementation, enabling organisations to launch LLM applications with minimal effort.

The solution has undergone industry benchmarking, delivering high precision in document retrieval. Tests showed nDCG@5 = 5, a precision rate of 80%, and accurate responses without hallucination. A live demo of ChanceRAG is available on HuggingFace for users to test its capabilities.

ChanceRAG is built around key features such as PDF processing, vector store creation, BM25 indexing, and the fusion of retrieval methods. These elements work together to deliver precise and relevant query results. Users can further customize retrieval options by adjusting chunk size, overlap settings, and selecting retrieval and reranking methods.

Rabbitt.ai plans to release additional RAG advancements in the coming weeks, including dynamic query expansion, multimodal document summarization, adaptive re-ranking, and context-driven document segmentation.

Founded by Singh, Rabbitt.ai focuses on generative AI solutions, including custom LLM development, RAG fine-tuning, and MLOps integration. The company recently raised $2.1 million from TC Group of Companies.