lumpenspace/raft helps make internal knowledge searchable and usable by assistants

Описание и применение

lumpenspace/raft: open-source проект в категориях Knowledge/RAG, AI/ML, Frontend. Практическое применение: index knowledge bases; improve search over documents. Уровень готовности: подходит для прототипа или внутреннего workflow, перед production нужна ручная проверка.

Задача

lumpenspace/raft helps make internal knowledge searchable and usable by assistants.

Результат

Medium: useful for prototypes or internal workflows, with dependency and maintenance checks before production.

Рабочий процесс

• index knowledge bases
• improve search over documents
• ground assistant answers

Доказательства

RAFT, or Retrieval-Augmented Fine-Tuning, is a method comprising of a fine-tuning and a RAG-based retrieval phase. It is particularly suited for the creation of agents that realistically emulate a specific human target.

Источник