Comfy UI Setup On AWS
I setup a comfy UI rig on an EC2 instance to play around with image generation using open source Flux, SDXL models and LoRAs. While setting up manually was excruciating, it was a good learning curve.
Stable Diffusion
ComfyUI
AWS
WhatsApp Companion Ava
Inspired by a YT tutorial, this multimodal project allows you to chat with a AI persona 'Ava'. Hypothetical day schedule is injected via context engineering to chat accordingly in different times of day.
Context Engineering
LangGraph
Website ChatBot Assistant
Website chatbot answers portfolio site queries using source PDF. 2 step RAG deployed on Docker, AWS EC2. Live on portfolio website via Chainlit. Evaluations, Prompt Caching, Cohere Reranking for RAG documents.
RAG
n8n
LangSmith
Pinecone
Resiliency Automation Framework
Automated load injection, chaos injection, monitoring, reporting to give back application team members 5-6 hours everyday during game-day activities for Chase Travel.
AWS
DB-Streams
Lambda
FIS
Gremlin
LoRA Training
Most multimodal GPTs were not able to generate the new Hyundai Tucson model with the new wing-like DRLs. I trained a LoRA model using Flux that generates accurate Hyundai Tucson renderings.
LoRA
Training
Flux
CivitAI
Media Server On Raspberry Pi
Raspberry Pi w USB setup to host NFS server on home LAN. Allows downloaded media (TV shows, Movies) to be copied to attached USB storage via phone, and can eventually be played on smart TV.
Raspberyy Pi
NFS Server
SSH
Termux