RAG in LLMs

The cluster centers on discussions about Retrieval-Augmented Generation (RAG), including its necessity, implementations, limitations, alternatives, and tools like RAGFlow and llama_index in the context of large language models.

➡️ Stable 1.7x AI & Machine Learning
2,712
Comments
6
Years Active
5
Top Authors
#8744
Topic ID

Activity Over Time

2020
2
2022
6
2023
528
2024
1,257
2025
878
2026
41

Keywords

e.g CPU LLM LegalBench GPU towardsai.net AI TF RAG ZeroEntropy rag llm retrieval model context chatbot vector data prompt fine tuning

Sample Comments

osigurdson Jan 12, 2025 View on HN

Wouldn't this just be foundational model + RAG in the limit?

alex_young Dec 30, 2025 View on HN

Doesn't Claude already use RAG on the backend?

mooktakim Apr 29, 2024 View on HN

Aren't the LLM's already trained on the whole web? no need to RAG, in theory.

pknerd Apr 20, 2025 View on HN

Interesting..would you like to share some technical details? it did not seem you have used RAG here?

torginus Apr 16, 2025 View on HN

Trust me bro, you don't need RAG, just stuff your entire codebase into the prompt (also we charge per input token teehee)

yeahwhatever10 Feb 6, 2025 View on HN

Do you get meaningful insights with current RAG solutions?

owenpalmer Jan 6, 2025 View on HN

Have you tried RAG on the docs?

ravenstine Mar 6, 2024 View on HN

Is RAG just a fancy term for sticking an LLM in front of a search engine?

How is this different than using RAG with my own data?

jerrygoyal Apr 18, 2024 View on HN

no need for separate RAG tools anymore?