The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Automated Bilingual Document Intelligence System (RAG + LLM)
Built a retrieval-augmented generation system that allows users to query a specialized document corpus in both English and Bengali. The pipeline ingests source documents, indexes them with vector embeddings, and returns accurate, context-aware answers via an LLM. Designed for real-world use in water, sanitation, and hygiene (WASH) program contexts. Deployed live on Streamlit Cloud.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
Unified Intelligence Frontier (UIF)
I build and deliver complete AI-powered lead automation systems for service businesses.
What I deliver:
Modern, high-converting website rebuilds
Custom AI agents that reply to every lead in under 60 seconds, 24/7
Intelligent qualification and automatic call booking
Real-time admin dashboard to find and manage leads
Current Capabilities:
Fully functional AI lead response system (email + SMS)
Powerful admin dashboard with Google Places integration for targeted lead generation
Clean, professional client-facing landing pages
End-to-end delivery: from lead discovery to automated booking
The screenshots show:
Right: Client-facing landing page (what businesses see)
Left: My private admin dashboard where I discover high-quality leads in real time
I specialize in turning outdated websites into automated revenue machines for HVAC, solar, plumbing, and other local service businesses.
Open to new projects.
Nice work
Dog Breed Classification System
Built a deep learning computer vision application capable of classifying 120 dog breeds from uploaded images.
Implemented transfer learning using ResNet and EfficientNet architectures with PyTorch and Torchvision.
Improved model performance from ~3% CNN baseline accuracy to 78.97% ensemble accuracy through optimization and fine-tuning.
Applied advanced deep learning techniques including label smoothing, gradual unfreezing, weight decay, learning rate scheduling, and Test Time Augmentation (TTA).
Deployed a production-ready Streamlit application with real-time image inference and probability predictions.
This is interesting! Which dog is the easiest to classify?
Trending
Claude
Claude has entered the design space. How are you using Claude Design?
Contra University
Learn from expert creatives how to earn more using next-gen AI tools.
creativeaiflow
Creative AI workflows are evolving. What tools do you use, and what are their strengths and weaknesses?
portfolioreview
The best portfolios tell a story, not just show a grid. Share yours for feedback.
freelancerlife
Freelancer life is wins, pivots, and everything in between. What’s yours right now?