List: RAG | Curated by CP Lu, PhD

Jul 17, 2024
62 stories
RAG
Cobus Greyling
Speculative RAG By Google ResearchThis study shows how to enhance Retrieval Augmented Generation (RAG) through Drafting
Jul 12, 2024
1
Jul 12, 2024
1
Bijit Ghosh
Designing high-performing RAG systemsDesigning high-performing Retrieval Augmented Generation (RAG) systems, structured across the 5 main pillars :
Mar 31, 2024
1
Mar 31, 2024
1
Cobus Greyling
RAT — Retrieval Augmented ThoughtsSynergising RAG With Sophisticated Long-Horizon Reasoning
Mar 13, 2024
2
Mar 13, 2024
2
Cobus Greyling
Please Stop Saying Long Context Windows Will Replace RAGAnd I’m curious to know if anyone has innovative approaches to using long context windows efficiently?
Mar 18, 2024
3
Mar 18, 2024
3
In
TDS Archive
by
Michał Oleszak
Designing RAGsA guide to Retrieval-Augmented Generation design choices.
Mar 14, 2024
10
Mar 14, 2024
10
Cobus Greyling
Agentic RAG: Context-Augmented OpenAI AgentsLlamaIndex has coined the phrase Agentic RAG…Agentic RAG can best be described as adding autonomous agent features to a RAG implementation.
Mar 14, 2024
Mar 14, 2024
Ming
Why RAG is bigLLMs know a lot, but nothing about you. You may fine-tune, but that’s costly. Alternative? RAG. Plus, “ReAct” democratizes it for everyone.
Jan 2, 2024
Jan 2, 2024
In
Level Up Coding
by
Gao Dalie (高達烈)
LangGraph + Corrective RAG + Local LLM = Powerful Rag ChatbotOne of the concerns with modern AI chatbots is their hallucinations This means they might give answers that are wrong or made-up.
Feb 15, 2024
3
Feb 15, 2024
3
DataStax
Building an Image Search App with a Vector Database and CLIP ModelsBy Aaron Ploetz
Feb 6, 2024
Feb 6, 2024
In
AI Advances
by
Kennedy Selvadurai, PhD
Visualizing FAISS Vector Space to Understand its Influence on RAG PerformanceVisualizing embeddings using renumics-spotlight reveals useful insights into RAG generation behavior.
Feb 26, 2024
4
Feb 26, 2024
4
Cobus Greyling
Language Model Quantization ExplainedSmall Language Models (SLMs) are very capable for NLG (Natural Language Generation, logic & common-sense reasoning, language understanding…
Feb 27, 2024
1
Feb 27, 2024
1
Bijit Ghosh
ActiveRAG — Active LearningThe advent of large language models (LLMs) has ushered in a new era of conversational AI. These models can generate remarkably human-like…
Feb 26, 2024
1
Feb 26, 2024
1
Cobus Greyling
Agentic RAG With LlamaIndexThe topic of Agentic RAG explores how agents can be incorporated into existing RAG pipelines for enhanced, conversational search and…
Jan 30, 2024
3
Jan 30, 2024
3
Cobus Greyling
Fine-Tuning or RAG?Comparing different LLM knowledge injection methods…
Feb 21, 2024
1
Feb 21, 2024
1
In
WhyHow.AI
by
Chia Jeng Yang
Why Gemini 1.5 (and other large context models) are bullish for RAGOptimization via RAG: How to overcome Accuracy, Cost, Latency and other performance limitations of large context models.
Feb 18, 2024
8
Feb 18, 2024
8
In
Level Up Coding
by
Fareed Khan
100x Faster — Scaling Your RAG App for Billions of EmbeddingsComputing Cosine Similarity in parallel
Feb 15, 2024
1
Feb 15, 2024
1
In
TDS Archive
by
Dr. Varshita Sher
Using LangChain ReAct Agents for Answering Multi-hop Questions in RAG SystemsUseful when answering complex queries on internal documents in a step-by-step manner with ReAct and Open AI Tools agents.
Feb 15, 2024
8
Feb 15, 2024
8
Cobus Greyling
T-RAG = RAG + Fine-Tuning + Entity DetectionThe T-RAG approach is premised on combining RAG architecture with an open-source fine-tuned LLM and an entities tree vector database. The…
Feb 15, 2024
11
Feb 15, 2024
11
Neum AI
Retrieval Augmented Generation at scale — Building a distributed system for synchronizing and…Technical and architectural details of how we synced and embedded 1 billion vectors for a RAG workflow
Sep 28, 2023
2
Sep 28, 2023
2
In
LlamaIndex Blog
by
Jerry Liu
Using LLM’s for Retrieval and RerankingSummary
May 17, 2023
6
May 17, 2023
6