New ask Hacker News story: Ask HN: How would you architect a RAG system for 10M+ documents today?
Ask HN: How would you architect a RAG system for 10M+ documents today?
2 by Ftrea | 0 comments on Hacker News.
I'm tasked with building a private AI assistant for a corpus of 10 million text documents (living in PostgreSQL). The goal is semantic search and chat, with a requirement for regular incremental updates. I'm trying to decide between: Bleeding edge: Implementing something like LightRAG or GraphRAG. Proven stack: Standard Hybrid Search (Weaviate/Elastic + Reranking) orchestrated by tools like Dify. For those who have built RAG at this scale: What is your preferred stack for 2025? Is the complexity of Graph/LightRAG worth it over standard chunking/retrieval for this volume? How do you handle maintenance and updates efficiently? Looking for architectural advice and war stories.
2 by Ftrea | 0 comments on Hacker News.
I'm tasked with building a private AI assistant for a corpus of 10 million text documents (living in PostgreSQL). The goal is semantic search and chat, with a requirement for regular incremental updates. I'm trying to decide between: Bleeding edge: Implementing something like LightRAG or GraphRAG. Proven stack: Standard Hybrid Search (Weaviate/Elastic + Reranking) orchestrated by tools like Dify. For those who have built RAG at this scale: What is your preferred stack for 2025? Is the complexity of Graph/LightRAG worth it over standard chunking/retrieval for this volume? How do you handle maintenance and updates efficiently? Looking for architectural advice and war stories.
Comments
Post a Comment