
FutureSmart Agent
A complete AI Agent system for real use cases. RAG, NL2SQL, API actions, multi-agent logic — everything in one place.
SynapseSearch – AI-Powered Search Engine
Individual
December 9, 2025 at 03:27 PM
hear-about-us
name
Rohan Jain
College / University Name
Jadavpur University, Kolkata
linkedIn-profile
Project Title
SynapseSearch – AI-Powered Search Engine
Describe what your project does?
NIM-RAG Explorer is an interactive Streamlit application that demonstrates Retrieval-Augmented Generation using NVIDIA NIM models. It loads PDF documents, creates semantic embeddings using NVIDIA’s nv-embedqa-e5-v5, stores them in a FAISS vector database, and allows users to ask natural-language questions. The system retrieves the most relevant document chunks and generates accurate, context-aware answers using the Llama-3.3-70B-Instruct model. This project matters because it provides a simple, practical way to explore how modern AI models can search, understand, and summarize real documents with high accuracy—making it useful for research, knowledge management, and intelligent document query systems.
Share a 3–5 minute HD demo video
Hosted Project Link (if any)
GitHub Repository (if any)
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