Waqas Ahmed’s Post

A trick in retrieval-augmented generation (RAG) is to use the output of RAG as extra context information to perform second RAG query to get better retrieval result and eventually get a better output. In my interpretation it is a resampling of documents in the vector storage to get more relevant documents as the result of retrieval. And I think we can do the same by querying the vector storage using the embedding output of ReRanker for better retrieval without large cost overhead using text generation. Thanks Paul Tsoi for the paper https://lnkd.in/g8NFdZBg

ARAGOG: Advanced RAG Output Grading Retrieval Augmented Generation (RAG) = how to incorporate external knowledge sources into text generation process, thus enhancing the models’ ability to produce contextually relevant and in formed outputs.

This weekend, learn about 5 different ways of evaluating your RAG systems. zhaozhiming takes you through a comprehensive tour of the different RAG evaluation methods using LLM-as-a-judge (which have corresponding LlamaIndex implementations): 1. Answer Relevance 2. Context Relevance 3. Faithfulness 4. Correctness 5. Pairwise Comparison Along with synthetic dataset generation. Check it out here: https://lnkd.in/gdQ3fZ2W

Very useful when considering RAG evaluation.

Added 2 new multi-agent papers to the Awesome Multi-Agent Papers Repository - [Agent-as-a-Judge: Evaluate Agents with Agents ](https://buff.ly/4f1c5iZ) - [Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence](https://buff.ly/4h5fiiP ) What papers are we missing? Like, repost, and share with this friends ✨

Added 2 new multi-agent papers to the Awesome Multi-Agent Papers Repository - [Agent-as-a-Judge: Evaluate Agents with Agents ](https://buff.ly/4f1c5iZ) - [Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence](https://buff.ly/4h5fiiP ) What papers are we missing? Like, repost, and share with this friends ✨

In this blog, Zain Hasan breaks down RAG into indexing, retrieval, and generation components and proposes 2 to 3 practical steps to improve each part of your RAG pipeline. Covering everything from chunking techniques, filtered search, and hybrid search to reranking, fine-tuning embedding models, and generating metadata for your text chunks! https://lnkd.in/dqfKWfiu

Well, it's true that people get some better results by applying these techniques, but for each use case, it is still important to have enough tests to find the best way for his/her best approach. The application and effect of new technologies is not really linear. Practice is the best way to prove. Thank you for sharing the paper!

This survey is amazing, and helpful! I already worked with Classic VDB + LLM Rerank, but what particularly caught my attention were the insights into native LlamaIndex techniques, including sentence window retrieval and the document summary index, which offer promising benefits in terms of both retrieval precision and answer similarity, with intriguing tradeoffs.

\#LeManTrendHist - indicator MetaTrader 5 https://lnkd.in/d4ZvTGaR \# Real author: LeMan The LeManTrend implemented as a histogram of the smoothed difference between its signal lines. The indicator uses SmoothAlgorithms.mqh library classes \(copy it to \<terminal\_data\_folder\>\MQL5\Include\). The use of the classes was tho...