Spaces:
Sleeping
title: multi-content-engine
emoji: 🎬
colorFrom: blue
colorTo: indigo
sdk: docker
app_port: 7860
🤖 AI Engineering Portfolio
Three production-grade AI systems — built end-to-end, deployed, and tested.
📂 Projects
| # | Project | What It Does | Stack | Status |
|---|---|---|---|---|
| 1 | RAG System | Chat with any PDF — grounded answers with page citations | Gemini · ChromaDB · LangChain · Streamlit | ✅ Live |
| 2 | Multimodal Engine | Convert long videos into vertical reels + blog posts | Gemini 2.5 · FFmpeg · Pydantic · Streamlit | ✅ Live |
| 3 | AI Safety Audit | LLM red-teaming, bias scanning, prompt injection defense | Custom framework · ragas | 🔧 In progress |
🗂️ Structure
├── rag-system/ # Phase 1 — RAG Pipeline
├── multimodal-engine/ # Phase 2 — Multimodal Content Engine
├── ai-saftey-audit/ # Phase 3 — AI Safety Toolkit
├── .env.example
├── .gitignore
└── README.md
Each project has its own detailed README with architecture, setup, and usage guides.
Phase 1 — RAG System
Upload any PDF and have a grounded, citation-backed conversation with it. Multi-LLM fallback chain (Ollama → HuggingFace → OpenAI → Gemini), persistent ChromaDB vector store, sentence-aware chunking, and streaming responses.
 |
 |
 |
 |
Phase 2 — Multimodal Content Engine
Upload an MP4 → get a 9:16 vertical reel and a CMS-ready blog post. Parallel audio/visual processing tracks, two-stage AI clip verification, and dual FFmpeg render modes.
 |
 |
 |
Phase 3 — AI Safety Audit
An alignment and auditing framework for stress-testing LLMs — prompt injection defense, bias and fairness auditing, toxicity guardrails, and jailbreak red-teaming.
Status: Architecture planned. Implementation in progress.
🛠️ Tech Across All Phases
| Category | Tools |
|---|---|
| Language | Python 3.12 |
| UI | Streamlit |
| LLMs | Google Gemini 2.5 Flash/Pro · OpenAI GPT-4o-mini · Ollama llama3 |
| Embeddings | HuggingFace all-MiniLM-L6-v2 |
| Vector DB | ChromaDB |
| Audio/Video | FFmpeg · Google Gemini 2.5 Flash/Pro |
| Validation | Pydantic v2 |
| Testing | pytest — 72 tests, 0 failures |
| Deployment | Streamlit Cloud · Hugging Face Spaces · Docker |
👤 Author
Built as a structured AI engineering roadmap — progressing from RAG fundamentals through multimodal systems to AI safety and evaluation.