RAG

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

This model was published in HF papers on 2020-05-22 and contributed to Hugging Face Transformers on 2020-11-16. Retrieval-Augmented Generation (RAG) combines a pretrained language model (parametric memory) with access to an external data source (non-parametric memory) by means of a pretrained neural retriever. RAG fetches relevant passages and conditions its generation on them during inference. This often makes the answers more factual and lets you update knowledge by changing the index instead of retraining the whole model. You can find all the original RAG checkpoints under the AI at…

related reading

• Code a simple RAG from scratchhuggingface.co
• Patterns for Building LLM-based Systems & Productseugeneyan.com
• [2005.11401] Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasksarxiv.org
• What is Retrieval Augmented Generation (RAG)? | Databricksdatabricks.com
• Advanced Retriever Techniques to Improve Your RAGs | Towards Data Sciencetowardsdatascience.com
• Retrieval Augmented Generation: Streamlining the creation of intelligent natural language processing modelsai.facebook.com
• Retrieval-augmented generation - Wikipediaen.wikipedia.org
• Hugging Face – The AI community building the future.huggingface.co
• Parsed | Custom, interpretable AI systems that continuously learnparsed.com
• Building Performant RAG Applications for Production | Developer Documentationdocs.llamaindex.ai
• Towards Data Sciencetowardsdatascience.com
• RAG Architecture Deep Divelinkedin.com