Neural Network

A vector database is a specialized database optimized for storing, indexing, and querying high-dimensional vector embeddings. They enable fast similarity search, which is critical for RAG systems, recommendation engines, and semantic search applications. Popular vector databases include Pinecone, Weaviate, Qdrant, and pgvector for PostgreSQL.

In the context of AI language models, a token is the basic unit of text that a model processes — typically a word, subword, or character depending on the tokenizer. LLM pricing, context windows, and rate limits are all measured in tokens. Understanding tokenization is essential for optimizing costs and staying within model context limits when building AI-powered applications.

Orchestration is the automated coordination of multiple services, tasks, or systems to execute a complex workflow. An orchestrator acts as a central controller that manages the sequence, parallelism, error handling, and retries of individual steps. In the context of AI agents, orchestration involves chaining LLM calls, tool use, and decision-making steps; in DevOps, it coordinates container deployment, scaling, and service discovery.

In AI, hallucination refers to when a language model generates confident-sounding but factually incorrect or fabricated information. This occurs because LLMs predict statistically likely text rather than retrieving verified facts. Mitigation strategies include RAG, grounding responses in source documents, structured output validation, and using temperature settings to reduce creative deviation.

ETL (Extract, Transform, Load) is an automated data processing pattern where data is extracted from source systems, transformed into a desired format or structure, and loaded into a target system like a data warehouse. Modern variations include ELT, where raw data is loaded first and transformed in place. ETL pipelines are essential for automating data integration, reporting, and feeding clean data into ML training workflows.

Computer vision is a field of AI that trains machines to interpret and understand visual information from images and videos. Applications include object detection, facial recognition, autonomous driving, and medical image analysis. Modern computer vision leverages deep learning models like CNNs and vision transformers (ViT), and increasingly integrates with language models in multimodal AI systems.