Large Language Model (LLM)
定義
A large language model (LLM) is a neural network trained on massive text corpora that can understand instructions, reason about data, and generate human-quality text. LLMs power the AI capabilities in platforms like JieGou — when a recipe runs, it sends a structured prompt to an LLM (such as Claude, GPT, or Gemini) and receives a text response that is parsed into structured output fields.
Multi-Model Support
JieGou supports 9+ LLM providers: Anthropic (Claude), OpenAI (GPT), Google (Gemini), Mistral, and self-hosted models via Ollama or vLLM. Each recipe can use a different model, and AI Bakeoffs let you compare model performance on the same task to find the best fit.
BYOK (Bring Your Own Key)
With BYOK, organizations use their own API keys for LLM providers, giving them direct billing control, enterprise rate limits, and data processing agreements with the model provider. JieGou encrypts all API keys with AES-256-GCM.
関連用語
AIレシピ
AIレシピとは何か、JieGouでどのように機能するかをご紹介します。レシピは構造化された入出力を持つ、再利用可能な単一操作のAIビルディングブロックです。
BYOK（Bring Your Own Key）
BYOKがAI自動化にとってどのような意味を持つかをご紹介します。Bring Your Own Keyにより、自分のLLM APIキーをJieGouに接続し、完全なコスト管理とデータプライバシーを実現できます。
Prompt Template
A prompt template is a reusable, parameterized set of instructions for an LLM that accepts variable inputs and produces structured outputs.