🏆 View Winners 🌟 View Sponsors 👥 All Participants

Priyanshi Shah

Participant

Multi-Modal RAG Assistant

Votes6

Score10

🧠Community1×5= 5

🌐Public5×1= 5

Individual

December 3, 2025 at 06:10 PM

Project Demo

Submission Details

hear-about-us: Linkedin

name: Priyanshi Shah

College / University Name: Vellore Institute of Technology, Vellore

linkedIn-profile: http://www.linkedin.com/in/priyanshi-shah-a01156217

Project Title: Multi-Modal RAG Assistant

Describe what your project does?: RAG Assistant is a multi-modal AI document agent built with LangChain that enables intelligent search and question-answering across PDFs, Word files, Excel sheets, presentations, and even images/screenshots. It automatically extracts text (with OCR for images), chunks the content, generates embeddings, and stores them in a vector database. When a user asks a question, the agent retrieves the most relevant chunks using LangChain’s RAG pipeline and generates accurate, context-aware answers with GPT-5.1, along with full source attribution. This matters because organizations deal with massive amounts of unstructured data spread across many file formats. Manually searching these documents is slow and error-prone. RAG Assistant provides a fast, flexible, and production-ready solution for document intelligence — enabling research, analysis, data extraction, and knowledge retrieval in seconds.

Share a 3–5 minute HD demo video: https://drive.google.com/file/d/1c0LKC6C2-G6Ba_um8ZCYFvXjEpWC1PIT/view?usp=sharing

Hosted Project Link (if any): https://rag-vector.emergent.host/

GitHub Repository (if any): https://github.com/ps23456/RAG-Mini-Assistant

artifacts/ supporting material

Is this project your original and proprietary work?: Yes

Does your project include any private, sensitive, or restricted code or content?: No

Do you give us (AI Demos & partners) permission to feature your work on our website and share it with our community (with full credit)?: Yes

Do you consent to us showcasing your name/profile on our social media platforms and YouTube: Yes

Are you open to freelance, internship, or collaborative opportunities based on this project?: Yes, I’m interested

Comments (0)

Explore More

All Participants Hackathon Details

Get In Touch

Connect with Priyanshi Shah to learn more about their project.

LinkedIn Profile

Featured

FutureSmart Agent

A complete AI Agent system for real use cases. RAG, NL2SQL, API actions, multi-agent logic — everything in one place.

RAG Assistant is a multi-modal AI document agent built with LangChain that enables intelligent search and question-answering across PDFs, Word files, Excel sheets, presentations, and even images/screenshots. It automatically extracts text (with OCR for images), chunks the content, generates embeddings, and stores them in a vector database. When a user asks a question, the agent retrieves the most relevant chunks using LangChain’s RAG pipeline and generates accurate, context-aware answers with GPT-5.1, along with full source attribution. This matters because organizations deal with massive amounts of unstructured data spread across many file formats. Manually searching these documents is slow and error-prone. RAG Assistant provides a fast, flexible, and production-ready solution for document intelligence — enabling research, analysis, data extraction, and knowledge retrieval in seconds.