Abstract :

The Intelligent Document Question Answering System Presents An Implementation-focused RetrievalAugmented Generation (RAG) Framework That Transforms Static Document Repositories Into An Interactive Conversational Interface. The System Processes Uploaded Documents Through Text Extraction, Cleaning, And Segmentation Before Generating High-dimensional Vector Embeddings. These Embeddings Are Stored In ChromaDB To Enable Semantic Similarity Search That Surpasses Traditional Keyword-based Retrieval. During Query Processing, User Questions Are Converted Into Embeddings, The Most Relevant Segments Are Retrieved, And A Grounded Prompt Is Constructed For A Selectable Large Language Model Backend (OpenAI Or Ollama). The Integration Of Semantic Retrieval, Modular Architecture, And Context-aware Generation Ensures Improved Factual Accuracy, Reduced Hallucination, And Domain Adaptability. Keywords: Retrieval-Augmented Generation, Vector Embeddings, ChromaDB, LangChain, Large Language Models, Document Question Answering

Published:

31-3-2026

Issue:

Vol. 26 No. 3 (2026)

Page Nos:

1119-1125

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite