lumpenspace/raft
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.
This tool helps you create AI conversational agents that sound remarkably like a specific person. You provide interview transcripts with the target person and their past writings (like essays or tweets). The system processes this information to fine-tune a language model, resulting in an agent that can engage in dialogue in that person's distinctive style.
167 stars. No commits in the last 6 months.
Use this if you need to build a highly personalized AI assistant or chatbot that accurately mimics the conversational patterns and knowledge of a particular individual.
Not ideal if you're looking for a general-purpose chatbot or a tool for simple content generation without the need for specific human persona emulation.
Stars
167
Forks
22
Language
Python
License
—
Category
Last pushed
Aug 31, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/lumpenspace/raft"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
NirDiamant/RAG_Techniques
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG)...
VectorInstitute/fed-rag
A framework for fine-tuning retrieval-augmented generation (RAG) systems.
RUC-NLPIR/FlashRAG
⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)
ictnlp/FlexRAG
FlexRAG: A RAG Framework for Information Retrieval and Generation.
Andrew-Jang/RAGHub
A community-driven collection of RAG (Retrieval-Augmented Generation) frameworks, projects, and...