Context window

Language models

The context window is the maximum amount of text (in tokens) a model can take into account at once: the conversation, the supplied documents, its own answers. Beyond it, information falls out of scope. Its size conditions the ability to work on long documents and keep track of an exchange.

In practice at Gensai

Gensai designs its RAG systems to inject only the useful passages into the window: more precise, faster and cheaper.

Same theme

LLM (Large Language Model)SLM (Small Language Model)DLLM (Diffusion Large Language Model)Hallucination (AI)Prompt chaining Pre-trained model Foundation model Generative AI Transformer Token Prompt Prompt engineering Context (AI)Memory (AI)Fine-tuning