Innovative Multi-Model Generative AI Platform with Orchestrator

Innovative Multi-Model Generative AI Platform with OrchestratorInnovative Multi-Model Generative AI Platform with Orchestrator

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

Rafi Ubaid Putra

• Mar 26

Built a multi-model generative AI platform for text, image, music, and video workflows with a structured orchestration system behind it. IMAGENA uses an orchestrator-worker architecture where a primary model coordinates specialized workers, routes requests based on context, and executes parallel subtasks when needed. Combined with RAG pipelines, OCR workflows, vector memory, and Redis-backed system logic, the platform was designed as a scalable fullstack AI product beyond a standard single-model chat experience. Live: https://imagena.ink

Full Stack Development LangChain Next.js Redis

BrightStudios ®

max

• Jun 1

Your next buyer will research you in ChatGPT before they ever open your homepage.

They type the problem, read the paragraph a model writes back, and shortlist the two companies it described most clearly.

You don't write that paragraph. The model does, by reading every surface you own at once and keeping whatever it trusts most.

If your homepage, your LinkedIn, and your Crunchbase don't tell the same story, it picks one. Sometimes the wrong one. Always with total confidence.

Brand consistency just stopped being a design preference and became whether a machine can describe you at all.

New BRIGHT Method is on this

Read on Substack Read on X Read on Linkedin

newsletter thebrightmethod ai

Atolani Adegbesan

• Jun 1

Inspiring!

Carola Cardozo

• Jun 1

I developed an MVP of a RAG application for querying PDF documents.

The flow is simple: the user uploads a PDF, the system extracts and splits the text into chunks, generates embeddings, stores them in Chroma, and when a question is asked, retrieves the most relevant information so the AI can respond with context.

For this project, I used React, Node.js, Express, LangChain, Gemini, and Chroma Cloud.

The main goal was to better understand concepts such as chunking, embeddings, vector search, and the integration of AI models with vector databases. This is a first version, but it serves as a foundation for more advanced RAG applications in the future.