Ideas & society2021 · shared on Hacker News

RAG: Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

Explore RAG: Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.

The conversation around the idea.

Links found in the discussion

Show HN: I made a better Perplexity for developers

What I learned using private LLMs to write an undergraduate history essay

Show HN: Ragdoll Studio (fka Arthas.AI) is the FOSS alternative to character.ai

Anthropic - Introducing 100K Token Context Windows, Around 75,000 Words

Grok

Headstart accelerates software development by up to 100x with Claude

Emerging Architectures for LLM Applications

Is anyone using self hosted LLM day to day and training it like a new employee

Show HN: Devv – AI search engine for devs, built on a custom search index

GPU-Accelerated LLM on a $100 Orange Pi

How do domain-specific chatbots work? A retrieval augmented generation overview

Teach your LLM to answer with facts, not fiction

Jina AI Launches First Open-Source 8K Text Embedding, Rivaling OpenAI

RAG: Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

We taught a small LLM to throw away 68% of our RAG context

Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

Wolfram Alpha as the Way to Bring Computational Knowledge Superpowers to ChatGPT

How to implement Q&A against your docs with GPT3 embeddings and Datasette

One idea leads to another.