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
RAG-Based PDF Question Generator
Developed an AI-powered RAG (Retrieval-Augmented Generation) application that automatically generates questions from uploaded PDF documents. Users can upload any PDF, select the desired number of questions, and choose a difficulty level (Easy, Medium, or Hard). The system retrieves relevant information from the document and generates context-aware questions based only on the uploaded content, minimizing hallucinations and improving accuracy.
Key Features:
PDF upload and document processing
Retrieval-Augmented Generation (RAG) pipeline
Custom question count selection
Difficulty levels: Easy, Medium, Hard
Context-aware AI-generated questions
Fast, accurate, and document-grounded results
Tech Stack: Python, LangChain, Vector Database (FAISS/ChromaDB), LLM, PDF Processing, Embeddings
#AI #RAG #GenerativeAI #MachineLearning #Python #LangChain #LLM #PDF #NLP #OpenSource
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
Built a voice-first AI app in @usewonder.
The goal was simple: create something that makes people instantly think, "Damn, this feels like a real AI product."
I started with a few foundation screens, imported them into Wonder, then used Wonder Chat to expand the experience, refine the UX, and iterate much faster than I normally would.
My favorite feature has to be Shaders. It instantly made the interface feel more alive and premium. I also experimented with MCP + Codex to push the prototype further. Still learning that workflow, but it was fun to explore.
Here's a quick walkthrough of the project and how Wonder fit into my design process.
P.S. Ignore my grammar and occasional stuttering in the video. My brain renders thoughts faster than my mouth ships them. 😭
Perfect
Form Flow is a B2B SaaS for enterprise and financial teams where AI handles the full form logic. I built the AI layer that turns plain English into working software behavior.
The rule engine sends an admin's plain-English input to the OpenAI API, which generates executable JavaScript handlers from the description. Those handlers run inside a vm2 sandbox on Node.js, so AI-generated code executes without touching the rest of the app. It works like a locked box: code runs inside, nothing escapes. Rules chain in order and trigger status changes, alerts, and display actions. Getting output consistent enough to run in production without malformed handlers took real iteration, the careful side of AI integration.
A RAG layer reads the surrounding form structure and the exact field a user is on, then sends a prompt scoped to that field, so the AI assistant returns an answer that fits the question instead of something generic. On financial intake forms, this cut abandonment with no human agent involved.
Branding automation pulls colors, logos, and typography from any URL for white-label deployment. Identity verification runs through IDmission with live face matching for compliance.
What the client gets: non-technical admins define complex form logic in plain English, an AI assistant guides users field by field, and AI-generated code runs safely inside a sandbox.
Perfect
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.
fifaworldcup2026
The World Cup is here and the whole world's watching. How are you designing for the world stage?
creativeaiflow
Creative AI workflows are evolving. What tools do you use, and what are their strengths and weaknesses?
freelancerlife
Freelancer life is wins, pivots, and everything in between. What’s yours right now?