eSapiens: A Platform for Secure and Auditable Retrieval-Augmented Generation

2025-07-13

AI Summary

Enterprises face significant challenges in deploying LLMs—including poor governance of proprietary data, weak knowledge retention, inadequate workflow integration, and lack of auditability. To address these, this paper proposes THOR, a secure and auditable Retrieval-Augmented Generation (RAG) platform. Methodologically, THOR introduces a unified THOR Agent for structured database querying, integrates hybrid vector retrieval with 512-token optimized chunking, and enables no-code AI pipeline orchestration via LangChain, supporting multi-model backends (e.g., OpenAI, Claude, Gemini, DeepSeek). Its key contributions are: (1) the first RAG architecture embedding native structured-query capability, enabling traceable, cross-modal (text + database) reasoning; and (2) end-to-end auditability via fine-grained execution logging and immutable chain-of-execution recording. Experiments on legal corpora show THOR achieves 91.3% Top-3 retrieval accuracy and improves TRACe factual alignment by 23%, significantly enhancing generation consistency and trustworthiness.

Technology Category

• Natural Language Processing: Safety and Robustness
• Machine Learning: Large Multimodal Models (LMMs)
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Security and Privacy: Data transparency and provenance

Abstract

We present eSapiens, an AI-as-a-Service (AIaaS) platform engineered around a business-oriented trifecta: proprietary data, operational workflows, and any major agnostic Large Language Model (LLM). eSapiens gives businesses full control over their AI assets, keeping everything in-house for AI knowledge retention and data security. eSapiens AI Agents (Sapiens) empower your team by providing valuable insights and automating repetitive tasks, enabling them to focus on high-impact work and drive better business outcomes. The system integrates structured document ingestion, hybrid vector retrieval, and no-code orchestration via LangChain, and supports top LLMs including OpenAI, Claude, Gemini, and DeepSeek. A key component is the THOR Agent, which handles structured SQL-style queries and generates actionable insights over enterprise databases. To evaluate the system, we conduct two experiments. First, a retrieval benchmark on legal corpora reveals that a chunk size of 512 tokens yields the highest retrieval precision (Top-3 accuracy: 91.3%). Second, a generation quality test using TRACe metrics across five LLMs shows that eSapiens delivers more context-consistent outputs with up to a 23% improvement in factual alignment. These results demonstrate the effectiveness of eSapiens in enabling trustworthy, auditable AI workflows for high-stakes domains like legal and finance.

Problem

• Secure AI platform for proprietary data control
• Automates tasks with retrieval-augmented generation insights
• Ensures auditable AI workflows for high-stakes domains

Innovation

• Hybrid vector retrieval for precise data access
• No-code orchestration via LangChain integration
• THOR Agent for SQL-style query handling