Unite.AI

The Real Reason Your RAG Pipeline Keeps Hallucinating

You know the ritual. The pipeline hallucinated in front of a customer, so you swapped the embedding model. Then you upgraded ...
IEEE

CarbonWise CX: An Agentic AI Framework for Carbon-Aware Customer Support Analytics Using RAG and LLM-Based Code Generation

Abstract: Organizations accumulate sufficient amounts of structured and unstructured customer support data, but current systems like SQL queries and fixed dashboards still generate actionable insights ...
GitHub

ProjectBEA — AI VTuber Engine

ProjectBEA is a modular, fully autonomous AI VTuber engine. It powers a living AI persona — Bea — that can hold live conversations, monologue to her audience when idle, join Discord voice calls, play ...
IEEE

Permission-Aware RAG: Identity and Access Management (IAM)-Based Access Filtering in Multi-Resource Environments

Abstract: Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating external knowledge sources, which significantly improves response accuracy and contextual relevance.
GitHub

Multigranular Adaptive Graph Evidence for Agentic Multimodal RAG in Long-Document QA

MAGE-RAG is an agentic graph RAG framework for multimodal question answering over long PDF documents. Evidence in long-document multimodal QA is often both sparse and heterogeneous: Sparse evidence: ...