Interactive AI engineering experiments by Shriyash Sharma — from retrieval pipelines and embeddings to semantic search, reasoning, and system design.
This space contains hands-on AI engineering experiments built to make complex concepts easier to understand through visualization and interaction.
Retrieval-Augmented Generation, step by step
Learn how Retrieval-Augmented Generation works step-by-step by exploring chunking, embeddings, vector search, retrieval, prompt construction, and answer generation.
Compare prompts and see how outputs shift
Experiment with system prompts, few-shot examples, and constraints to understand how prompt structure changes model behavior.
See text projected into vector space
Visualize how AI converts text into vectors and groups semantically similar concepts together.
Watch similarity ranking happen live
Inspect cosine similarity, top-k retrieval, and how index parameters trade off recall against latency.
Keyword vs. semantic retrieval
Compare traditional keyword search and AI-powered semantic search using the same dataset.
Trace tool-calling and reasoning loops
Step through an agent's plan, tool calls, and observations to understand how multi-step reasoning is orchestrated.
Budget tokens across a prompt
Understand token limits, context windows, truncation, and how modern LLMs process large documents.
A quick primer on the building blocks these tools make tangible. Go deeper with the RAG Explorer, Embedding Visualizer, and other experiments below. Long-form reading lives in the blog.
Retrieval-Augmented Generation (RAG) pairs a search system with a language model. Instead of answering only from memorized training data, the model first retrieves relevant passages from a knowledge source and answers from that evidence — keeping responses current, accurate, and traceable.
Run the RAG ExplorerAn embedding turns text into a vector of numbers that captures meaning. Texts with similar meaning get similar vectors, which is why embeddings power semantic search: they match ideas rather than exact keywords, finding the right passage even when the wording is different.
Explore the Embedding VisualizerVector search ranks stored vectors by how close they are to a query vector, usually with cosine similarity. A vector database compares the question against every chunk and returns the closest matches in milliseconds — the retrieval step that makes real-time RAG possible.
Try the Semantic Search PlaygroundA production assistant ingests documents ahead of time — chunking, embedding, and storing them. At query time it embeds your question, retrieves the most relevant chunks, and builds a grounded prompt so the model answers from real sources instead of guessing.
See context window limits
