Also known as: Retrieval Augmented Generation (RAG) · retrieval-augmented generation (RAG) · RAG · Retrieval-Augmented Generation (RAG)
La génération augmentée par retrieval (RAG) est une technique qui combine l’IA générative avec le retrieval à partir de sources de données externes. Le modèle utilise des documents, passages ou enregistrements récupérés comme contexte d’ancrage afin de produire des réponses plus actuelles, spécifiques et vérifiables. La RAG peut réduire les hallucinations, mais sa qualité dépend de la précision du retrieval, de la qualité des sources et de la manière dont le modèle utilise le contexte récupéré.
A technique that enables large language models (LLMs) to retrieve and incorporate new information.
A technique to improve the quality and accuracy of large language model (LLM) output by grounding it with sources of knowledge that are retrieved after the model was trained. RAG addresses LLM limitations such as factual inaccuracies, lack of access to current or specialized information, and inability to cite sources.
A technique allowing LLMs to access and reference knowledge sources to inform responses as they are being generated, enabling more up-to-date outputs.
A side-by-side comparison of Retrieval-Augmented Generation and Fine-Tuning. Understand when to retrieve external context at runtime and when to adapt a pretrained model through additional training.
A side-by-side comparison of Information Retrieval and Retrieval Augmented Generation. It explains how finding relevant information differs from using retrieved information to ground generative AI responses.