Adeniyi Victor

🧵 Thread: Introducing Xedlapay - Reimagining Trust in Online Payments Across Africa 1/ Online transactions in Africa are booming. But one big issue still holds people back: TRUST. How do you safely pay a stranger online without the fear of being scammed? Xedlapay to the rescue

8 RAG architectures for AI Engineers: (explained with usage) 1) Naive RAG - Retrieves documents purely based on vector similarity between the query embedding and stored embeddings. - Works best for simple, fact-based queries where direct semantic matching suffices. 2) Multimodal RAG - Handles multiple data types (text, images, audio, etc.) by embedding and retrieving across modalities. - Ideal for cross-modal retrieval tasks like answering a text query with both text and image context. 3) HyDE (Hypothetical Document Embeddings) - Queries are not semantically similar to documents. - This technique generates a hypothetical answer document from the query before retrieval. - Uses this generated document’s embedding to find more relevant real documents. 4) Corrective RAG - Validates retrieved results by comparing them against trusted sources (e.g., web search). - Ensures up-to-date and accurate information, filtering or correcting retrieved content before passing to the LLM. 5) Graph RAG - Converts retrieved content into a knowledge graph to capture relationships and entities. - Enhances reasoning by providing structured context alongside raw text to the LLM. 6) Hybrid RAG - Combines dense vector retrieval with graph-based retrieval in a single pipeline. - Useful when the task requires both unstructured text and structured relational data for richer answers. 7) Adaptive RAG - Dynamically decides if a query requires a simple direct retrieval or a multi-step reasoning chain. - Breaks complex queries into smaller sub-queries for better coverage and accuracy. 8) Agentic RAG - Uses AI agents with planning, reasoning (ReAct, CoT), and memory to orchestrate retrieval from multiple sources. - Best suited for complex workflows that require tool use, external APIs, or combining multiple RAG techniques. 👉 Over to you: Which RAG architecture do you use the most? _____ Share this with your network if you found this insightful ♻️ Find me → @akshay_pachaar ✔️ For more insights and tutorials on LLMs, AI Agents, and Machine Learning!

here are mobile application designs i worked on earlier. food delivery, dating, real estate and fashion e-commerce. i’m open to design gigs and roles, thanks you.

N300,000,000 a year for scholarships to Nigerian students. N300Million of his own personal money. And that was as at 2021. Do what you like with that information.

The strongest AI systems use all three in combination. A confident AI answer is not the same as a correct one. Always ask: is this model working from live data or from a frozen version of the world that no longer exists?

Best for internal wikis, product documentation, compliance data anywhere accuracy and citation matter. The mental model I use: → Fine-tuning shapes how the model thinks. → RAG shapes what it knows. → Tools shape what it can find out right now.

I asked ChatGPT if Trump could run for a second term. It said yes framing it as a future possibility. The problem? Trump is already IN his second term. Has been since January 2025. The model wasn't broken. It wasn't hallucinating. It was simply answering from frozen training

Lolss. Looking back now, when I started learning flutter. Why will I do this?

Huh, so that's why text is called a string

@ez0xai This is lovely

i built jarvis to FaceVerify - real-time hand tracking - virtual cursor - pinch to click - draggable panels controlled entirely with your webcam MediaPipe + Next.js try it: faceverify-app.vercel.app/jarvis works best on desktop

Smoothest Flutter sheet I've ever had. @expenapp