The exponential growth of unstructured textual data, particularly in portable document format (PDF),
presents significant challenges in extracting, summarizing, and retrieving actionable knowledge. This
research presents an intelligent, lightweight, and scalable web-based application—Multiple PDF
Streamlit—that bridges traditional document handling with cutting-edge AI capabilities. Powered by
Large Language Models (LLMs) and enhanced through Retrieval-Augmented Generation (RAG), the
system enables seamless ingestion, parsing, and semantic interrogation of multiple PDF documents
in parallel. By employing a hybrid architecture that combines text chunking, embedding-based vector
search, and context-aware generation, the platform offers dynamic question-answering,
multi-document summarization, and an interactive user interface for knowledge exploration. The backend
pipeline leverages modern frameworks like LangChain and FAISS/Chroma for efficient retrieval, while
the front-end is built using Streamlit, providing a real-time, user-friendly interface. This synthesis of
NLP, semantic search, and interactive AI creates an end-to-end system capable of transforming static
PDFs into a living, searchable knowledge base. The application not only democratizes access to LLMpowered
insights but also exemplifies the future of explainable and interactive document intelligence
systems.
