Terms | Description |
Tokens | Tokens are the finest granularity in natural language processing by large language models. Tokens can be thought of as pieces of words. Before the API processes the request, the input is broken down into tokens |
Vector Database | A vector database stores pieces of information as vectors. Vector databases cluster related items together, enabling similarity searches and the construction of powerful AI models |
AI Hallucination | Hallucination is a response generated by AI which contains false or misleading information presented as fact |
Prompt | A prompt is a natural language text that requests the generative AI to perform a specific task |
DAG | Directed Acyclic Graph. Tasks are executed in specific order always moving forward |
Generative AI | Generative artificial intelligence is artificial intelligence capable of generating text, images, videos, or other data using generative models, often in response to prompts. |
Explainable AI | Explainable artificial intelligence (XAI) is a set of processes and methods that allows human users to comprehend and trust the results and output created by machine learning algorithms. |
DSP | Directional Stimulus Prompting |
ReACT | Reasoning and acting – going to public knowledge and get data back {Thought, Action, Observation} |
Chain of Thought | [Few shot prompt technique] – Break down steps and arrive at response |
