An Intelligent PDF Question-Answering System; A Retrieval-Augmented Generation Approach

Multimodal Hybrid Retrieval-Augmented Generation for Scientific Document Understanding using Open-Source SLMs

Large Language Models tend to hallucinate when answering domain-specific ques tions from scientific documents without prior fine-tuning. Currently, methods such as Retrieval-Augmented Generation partially solve this problem but face different challenges: limited context knowledge, difference between sparse and dense retrieval, and retrieval noise. This paper presents an Advanced Multimodal Retrieval-Augmented Generation system that aims to solve those challenges and im prove the accuracy of information extraction. The proposed architecture introduces a multimodal ingestion pipeline that leverages an open-source Vision-Language Model (Qwen2-VL-2B-Instruct) to generate textual summaries of tables and fig ures. The retrieval phase integrates HNSW-based semantic search with GIN-based lexical search, unified through Reciprocal Rank Fusion and refined using Cross Encoder reranking to minimize retrieval noise. To ensure conversational coherence across multi-turn interactions, a Query Condenser module is employed. Evaluation is conducted by independently assessing the ingestion, retrieval and generation stages using the MMLongBench benchmark, a BeIR-format synthetic dataset and the DeepEval framework. Moreover, results demonstrate a 157% improvement in retrieval quality over a Naive-RAG baseline, with only 50 ms additional la tency, while Qwen2-VL-2B-Instruct achieved results comparable to cloud-based models in BERTScore. These findings validate that open-source optimized SLMs, paired with advanced retrieval strategies, can provide competitive performance for document understanding without relying on cloud-based models.

Optimized Hybrid Retrieval-Augmented Generation Framework using Semantic Search and Re-ranking for Reliable LLM Responses

Building question-answering systems that can read a document and answer naturally phrased questions about it is difficult when retrieval is left to either keyword matching or dense vector search alone, since each method has blind spots that surface as missed context, near-miss answers, or content invented by the underlying language model. This paper describes an optimized hybrid Retrieval-Augmented Generation (RAG) pipeline built to reduce these failure modes by combining two complementary retrieval signals: dense semantic similarity computed over a FAISS vector index, and sparse lexical scoring computed with BM25. Candidates returned by both retrievers are merged and passed through a Cross-Encoder re-ranking stage that scores each query-passage pair jointly, pushing the most contextually relevant chunks to the top before they reach the language model. Final answers are produced by Google’s Gemini model under a prompt that restricts it to the supplied context, which keeps the output tied to the source document rather than to whatever the model already “knows.” The pipeline is exposed through a Streamlit application that lets a user upload a PDF and ask questions about it in plain language, returning each answer alongside a confidence estimate and the page it came from. Evaluation on a multi-page technical PDF document shows that the hybrid retrieval and re-ranking stages together raise retrieval precision and reduce irrelevant or unsupported answers compared with retrieval limited to a single method, supporting the use of this approach for reliable, document-grounded question answering.

A Multimodal Retrieval-Augmented Generation Framework for Context-Aware Semantic Querying

Retrieval-Augmented Generation (RAG) has established itself as a compelling strategy for grounding large language model outputs in documentary evidence. However, production deployments continue to rely almost exclusively on homogeneous text corpora, even as enterprise repositories grow increasingly heterogeneous blending technical schematics, radiological images, annotated diagrams, and unstructured prose within the same archival system. This mismatch between system design and data reality motivates the present work. We propose a Multimodal RAG framework that unifies text and image retrieval through four tightly coupled components: a dual-stream embedding engine, a learned four-class AI query router, an adaptive confidence threshold, and a session-aware context store. Text is encoded with the allmpnet-base-v2 Sentence Transformer; images are embedded in the same 768-dimensional space via a domain-adapted CLIP ViT-L/14 model fine-tuned on approximately 120,000 technical and clinical text-image pairs. Concatenating 768-d vectors yields a 1,536-d composite query that drives a single approximate nearest-neighbor (ANN) search simultaneously across both modalities. A fine-tuned DistilBERT router assigns each query to one of four retrieval pathways text-only, image-only, hybrid, or conversational at 91.3% accuracy. Experiments were run on three enterprise corpora (engineering manuals, clinical case summaries, and legal paperwork) with the results being a mean F1@5 of 0.90, an increase of 22% over a dense text-only baseline, and a reduction of 49% in the number of hallucinations. The median first-token latency is 1.34s, which meets the interactive-use target deployment-contexts. These results show that it is possible to implement modality-aware retrieval in a simple and realistic setting with real-world organizational constraints and that the results are reproducible.

Intelligent Document Processing Platform Using Retrieval-Augmented Generation (RAG)

The rapid growth of digital documents across enterprises, educational institutions, healthcare organizations, and research environments has created significant challenges in information retrieval and knowledge management. Traditional keyword-based search systems often fail to capture the semantic meaning and contextual relationships present in large collections of unstructured documents, resulting in inefficient information access and reduced productivity. This study presents an Intelligent Document Processing Platform using Retrieval-Augmented Generation (RAG) to enable accurate, context-aware, and reliable document intelligence. The proposed system integrates document ingestion, text extraction, preprocessing, chunking, embedding generation, vector-based semantic retrieval, and Large Language Models (LLMs) within a unified framework. Uploaded documents are transformed into vector embeddings and stored in a vector database, enabling efficient similarity-based retrieval. When a user submits a natural language query, the system retrieves the most relevant document segments and augments them as contextual knowledge for response generation. This retrieval-grounded approach reduces hallucinations, improves factual accuracy, and enhances the relevance of generated answers. The platform is implemented using Python, Streamlit, LangChain, embedding models, and vector databases to provide an interactive and scalable solution for document-centric knowledge discovery. Experimental evaluation demonstrates improved retrieval effectiveness, faster access to relevant information, and enhanced user experience compared with conventional document search approaches. The proposed system offers a practical and scalable framework for intelligent document understanding, semantic search, and AI-assisted question answering in modern knowledge management environments.

DocuMind: An Offline Multilingual Retrieval-Augmented Generation System for Document Question Answering Using Local Large Language Models

DocuMind is a fully offline, privacy-preserving, multilingual Document Question Answering system built on the Retrieval-Augmented Generation (RAG) architecture, enabling true cross-lingual retrieval without any translation step.

Leveraging Language Models for Textual Retrieval in the TREC 2025 DRAGUN Track