Get the latest tech news

Show HN: SpRAG – Open-source RAG implementation for challenging real-world tasks


High-performance RAG framework for unstructured data - SuperpoweredAI/spRAG

spRAG achieves substantially higher accuracy than vanilla RAG baselines on complex open-book question answering tasks. For example, suppose you have a bunch of SEC filings in a knowledge base and you ask “What were Apple’s key financial results in the most recent fiscal year?” RSE will identify the most relevant segment as the entire “Consolidated Statement of Operations” section, which will be 5-10 chunks long. By default, spRAG uses OpenAI for embeddings, Claude 3 Haiku for AutoContext, and Cohere for reranking, so to run the code below you'll need to make sure you have API keys for those providers set as environmental variables with the following names: OPENAI_API_KEY, ANTHROPIC_API_KEY, and CO_API_KEY.

Get the Android app

Or read this on Hacker News

Read more on:

Photo of SpRAG

SpRAG

Photo of world tasks

world tasks