RAG (Retrieval-Augmented Generation)
Définition
Retrieval-Augmented Generation (RAG) is a technique that enhances LLM outputs by retrieving relevant documents from a knowledge base and including them as context in the prompt. Instead of relying solely on the model's training data, RAG grounds responses in your organization's specific documents, policies, and data — reducing hallucination and increasing accuracy.
How RAG Works in JieGou
Upload documents (PDF, DOCX, Markdown, HTML, or URLs) to a knowledge base. JieGou chunks documents into passages, generates embeddings, and stores them. When a recipe runs, relevant chunks are retrieved by semantic similarity and injected into the prompt as context. The LLM sees your data alongside the task instructions.
Auto-Context
Knowledge bases can be scoped to departments, recipes, or workflows. Auto-context automatically includes relevant knowledge bases based on the scope — a Sales recipe automatically gets context from the Sales knowledge base without manual configuration.
Termes associés
Recettes IA
Découvrez ce que sont les recettes IA et comment elles fonctionnent dans JieGou. Les recettes sont des blocs de construction IA réutilisables à opération unique, avec des entrées et sorties structurées.
Prompt Template
A prompt template is a reusable, parameterized set of instructions for an LLM that accepts variable inputs and produces structured outputs.
Large Language Model (LLM)
A large language model (LLM) is an AI system trained on text data that can understand and generate human language, powering tasks like writing, analysis, and reasoning.
En savoir plus
Constatez par vous-même
Commencez dès maintenant à créer des automatisations IA avec des recettes et des workflows.