What are Embeddings?
Listed inWhat are Embeddings?Embeddingson
Dense vectors that put semantically similar things near each other.
Beginner6 minDraft
#concepts
Page 7 of 11
Listed inWhat are Embeddings?Embeddingson
Dense vectors that put semantically similar things near each other.
Listed inWhat are AI Agents?AI Agentson
Systems where the model decides the next action instead of following a fixed script.
Listed inMultimodal Use CasesMultimodal AIon
Document extraction, visual QA, accessibility, and media generation.
Listed inRobust Prompt EngineeringSafety & Ethicson
Instructions that survive hostile input and long conversations.
Listed inZero-Shot PromptingPrompt Engineeringon
Asking cold, with no examples, and when that is genuinely enough.
Listed inCohere EmbedEmbeddingson
Multilingual embeddings plus a reranker that often beats a bigger index.
Listed inGoogle ADKAI Agentson
Google's Agent Development Kit for building and evaluating agents.
Listed inOpenAI Vision APIMultimodal AIon
Sending images in a request and controlling detail and cost.
Listed inReplitDevelopment Toolson
Browser-based environment with an agent that builds and deploys.
Listed inAnthropic ClaudeModels & Providerson
The Claude family, its long-context and tool-use strengths, and the Messages API shape.
Listed inIndexing EmbeddingsVector Databaseson
HNSW, IVF, and the recall/latency/memory triangle you're choosing a point on.
Listed inData LayerModel Context Protocolon
Tools, resources, and prompts — the three things a server can expose.
Listed inEvaluation MetricsEvaluationon
Faithfulness, relevance, latency, cost — picking metrics that map to the product.
Listed inLarge Language Models (LLMs)Introductionon
What goes into a request, what the model holds while answering, and what comes back. The context window is a shared budget for input and output, and some model limits can be fixed while others have to be designed around.
Listed inGemmaModels & Providerson
Google's small open models, sized for laptops and edge deployment.
Listed inQdrantVector Databaseson
Rust-based vector search with rich payload filtering and quantization.
Listed inPrompt vs Context EngineeringContext Engineeringon
Wording the ask vs assembling everything the model needs to answer it.
Listed inLLM ObservabilityObservabilityon
Seeing what your system actually did, not what you assumed it did.
Listed inContext WindowHow LLMs Workon
The hard budget every prompt shares, and what gets dropped when you exceed it.
Listed inHugging Face TasksModels & Providerson
Task taxonomy as a lookup table from problem to candidate models.