RAG

Creator

Creator

Created

Created

2023 Oct 25 11:31

Editor

Editor

Edited

Edited

2025 May 6 14:0

Refs

Refs

Information retrieval

In-context Retrieval

Prompt Engineering Tool

Contextual Compression

Retrieval-Augmented Generation

RAG is not Memory

Better retrieval performance ≠ Better performance

Challenges

retrieval latenyc

system complexity

RAG Notion

Retrieval Accuracy

https://arxiv.org/pdf/2309.01431.pdf

RAG Usages

Embedding Transformation

Retrieve Augmented Learning

https://arxiv.org/pdf/2312.10997v1.pdf

https://arxiv.org/pdf/2312.10997v1.pdf

Beyond dot product

https://www.youtube.com/watch?v=mE7IDf2SmJg

Stanford CS25: V3 I Retrieval Augmented Language Models

December 5, 2023 Douwe Kiela, Contextual AI Language models have led to amazing progress, but they also have important shortcomings. One solution for many of these shortcomings is retrieval augmentation. I will introduce the topic, survey recent literature on retrieval augmented language models and finish with some of the main open questions. More about the course can be found here: https://web.stanford.edu/class/cs25/ View the entire CS25 Transformers United playlist: https://www.youtube.com/playlist?list=PLoROMvodv4rNiJRchCzutFw5ItR_Z27CM

Stanford CS25: V3 I Retrieval Augmented Language Models

https://www.youtube.com/watch?v=mE7IDf2SmJg&list=PLoROMvodv4rNiJRchCzutFw5ItR_Z27CM&index=25

Stanford CS25: V3 I Retrieval Augmented Language Models

Intro of Retrieval Augmented Generation (RAG) and application demos

Introduction of Retrieval Augmented Generation, Jupyter Notebook three demos of Basic RAG, Sentence-window retrieval, Auto-merging…

Intro of Retrieval Augmented Generation (RAG) and application demos

https://medium.com/@henryhengluo/intro-of-retrieval-augmented-generation-rag-and-application-demos-c1d9239ababf

Intro of Retrieval Augmented Generation (RAG) and application demos

NVIDIA Research: RAG with Long Context LLMs

This blog post dives into NVIDIA’s recent study comparing retrieval-augmentation with and without long-context LLMs.

NVIDIA Research: RAG with Long Context LLMs

https://blog.llamaindex.ai/nvidia-research-rag-with-long-context-llms-7d94d40090c4

NVIDIA Research: RAG with Long Context LLMs

KBQA,
Knowledge Graph

ML Blog - Improve ChatGPT with Knowledge Graphs

Leveraging knowledge graphs for LLMs using LangChain

https://mlabonne.github.io/blog/posts/Article_Improve_ChatGPT_with_Knowledge_Graphs.html

llama-recipes/recipes/use_cases/agents/langchain at main · meta-llama/llama-recipes

Scripts for fine-tuning Meta Llama3 with composable FSDP &amp; PEFT methods to cover single/multi-node GPUs. Supports default &amp; custom datasets for applications such as summarization an...

llama-recipes/recipes/use_cases/agents/langchain at main · meta-llama/llama-recipes

https://github.com/meta-llama/llama-recipes/tree/main/recipes/use_cases/agents/langchain

llama-recipes/recipes/use_cases/agents/langchain at main · meta-llama/llama-recipes

Base model is better at retrieval than

Instruction Tuning model

https://arxiv.org/pdf/2406.14972

Recommendations

///////