Skip to content

Latest commit

 

History

11 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 

Repository files navigation

Multimodal Question Answering – Research Repository

Python Status License

This repository contains research experiments for building a Multimodal Question Answering (QA) system capable of understanding information from documents, tables, and images.

The goal of this project is to explore different components required for a multimodal QA pipeline rather than delivering a finalized production system. Each collaborator worked on a different module of the system.


Project Goal

The objective of this research is to investigate how information from multiple modalities can be combined to answer questions from research documents.

The system explores three main capabilities:

  • Extracting text and layout information from document images
  • Retrieving knowledge from research papers using Retrieval-Augmented Generation (RAG)
  • Understanding visual information from images

These components together form the foundation for a Multimodal Question Answering pipeline.


Contributors & Work Distribution

This repository is a collaborative research effort.

OCR & Document Understanding

Explores text extraction and document structure analysis.

Technologies explored:

  • PaddleOCR
  • PaddleOCR-VL
  • Camelot (table extraction)

Focus areas:

  • OCR text detection
  • Table structure reconstruction
  • Document layout understanding

Branch: ocr-experiments


Research Paper RAG Assistant

A Retrieval-Augmented Generation system designed to analyze research papers.

Key capabilities:

  • Multi-PDF document processing
  • Semantic search using vector embeddings
  • Interactive CLI for asking questions about papers
  • Fast inference using Groq models
  • Structured extraction using GROBID

Technologies used:

  • FAISS vector database
  • HuggingFace embeddings
  • GROBID PDF parser
  • Groq LLM inference

Branch: Rag-System


Image Understanding Module

This module explores visual feature extraction techniques for integrating image understanding into the multimodal QA pipeline.

The current implementation includes two experimental approaches:

1. CLIP-Based Image–Text Embedding

  • Uses OpenAI CLIP (ViT-B/32) model
  • Generates normalized image embeddings
  • Generates normalized text embeddings
  • Computes cosine similarity between image and text representations

File:

  • image_embedding_hugging_face.py

2. YOLOv8-Based Visual Feature Extraction

  • Uses YOLOv8 backbone for extracting deep visual features
  • Applies Global Average Pooling to obtain compact image embeddings
  • Uses SentenceTransformer for generating text embeddings
  • Projects both modalities into a shared embedding space
  • Computes similarity scores between projected embeddings

File:

  • image_embedding_yolo.py

Branch:

  • feature/image-embedding-module

This module contributes toward building a unified multimodal representation space for document image understanding.

System Concept (High Level)

Document / Research Paper / Image -> Information Extraction

OCR Pipeline: Text + Table + Layout Extraction

RAG Pipeline: Semantic Retrieval + LLM Reasoning

Image Analysis: Visual Understanding


Repository Structure

multimodal-question-answering
│
├── ocr-experiments/      # OCR research using PaddleOCR & Camelot
├── rag-system/           # Research paper RAG assistant
├── image-module/         # Image understanding experiments (coming soon)
├── README.md

Current Status

This repository represents research exploration and experimentation toward a multimodal QA system.

Implemented components include:

  • OCR-based document text extraction
  • Table detection and filtering
  • Research paper question answering using RAG

Additional work on image understanding will be integrated in future updates.


Technologies Explored

Python PaddleOCR Camelot FAISS HuggingFace Embeddings GROBID Groq LLM Inference Docker


Future Work

  • Integrate OCR results into the RAG pipeline
  • Combine text, tables, and image understanding
  • Build an end-to-end multimodal QA system
  • Evaluate performance across research documents

Why This Repository Exists

This project was created to experiment with modern document intelligence and multimodal AI techniques.

It serves as:

  • a research exploration
  • a learning project
  • a demonstration of applied AI components for recruiters and collaborators.

Contributors

Name Contribution
Koushiki Chakraborty OCR experiments (PaddleOCR, PaddleOCR-VL, Camelot)
Ayan Mazumdar Research Paper RAG Assistant
Bristi Kundu Image understanding experiments

License

This project is open-source and available under the MIT License.

About

Collaborative research exploring multimodal question answering using OCR, RAG, and document/image understanding techniques.

Topics

Resources

Stars

2 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors