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
Project 4 — RAG Document Chatbot
Title: RAG Document Chatbot — LangChain · ChromaDB · Streamlit
Description: Fully local RAG application: PDF ingestion → 500-token semantic chunking → 73-chunk ChromaDB vector store → LangChain retrieval chain with source citations and multi-turn memory. Streamlit UI, no external API dependency.
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
Trending
retrofuturism
Share your favorite designs from the past exploring the distant future. Or your own take on the aesthetic 🚀
halftone
Dots. Texture. Grain. Let's see your designs using the halftone technique.
Midjourney
Creatives are showing off what they're making with Midjourney.
colorgrade
Video editors sound off: How do you enhance the mood of your video in color grading?
Related posts
E-Commerce Intelligence & Predictive Analytics Platform
What happens when an AI assistant needs answers from more than one source?
One of the challenges with building useful AI assistants isn't just generating a response.
It's making sure the response is based on the right information at the right time.
For FLT, the assistant needed to work across multiple data domains while supporting both text and voice interactions.
Instead of relying on a single static knowledge source, we built the system around a Retrieval-Augmented Generation (RAG) pipeline.
The approach connected authenticated APIs, SQL and JSON data sources so the assistant could retrieve relevant information before generating its response.
We also integrated:
→ Vapi for voice and chat interactions
→ Twilio for calls and SMS
→ RAG for contextual retrieval
→ SQL & JSON sources for dynamic data
→ Secure authentication for personalized experiences
The result was a full-stack AI assistant capable of delivering contextual responses across both chat and voice.
The key takeaway:
An AI assistant becomes much more useful when it can retrieve the right context instead of relying only on what the model already knows.
ai
rag
That's where the architecture behind the AI becomes just as important as the AI itself.
🍥 What if Naruto’s Rasengan could actually be controlled with your hands?
As a kid, it was just something I saw in anime.
This time, I decided to see if I could bring that idea to life with Python.
So I built Naruto Hand VFX Studio — a real-time computer vision project where hand gestures control:
🔵 Rasengan
⚡ Chidori
🔥 Fireball
💥 Energy Beam
And the interesting part?
These aren’t pre-recorded effects.
Using Python, OpenCV, MediaPipe, and NumPy, the system tracks my hand movements and generates the VFX in real time.
What started as a fun Naruto idea turned into a project where I got to combine computer vision, hand tracking, gesture recognition, animation logic, and procedural VFX in one application.
My setup isn’t a professional studio.
But this project reminded me that you don’t always need a perfect setup to build something interesting.
Sometimes, you just need an idea — and the willingness to build it.
#Python #ComputerVision #OpenCV #MediaPipe #NumPy #VFX #PythonProjects #MachineLearning #Programming #Naruto #BuildInPublic
