Mastodawn

From the .NET blog...

Avi Chawla (@_avichawla) on X

RAG vs. Graph RAG, explained visually! RAG has many issues. For instance, imagine you want to summarize a biography, and each chapter of the document covers a specific accomplishment of a person (P). This is difficult with naive RAG since it only retrieves the top-k relevant

X (formerly Twitter)

sayzard Mar 12

Avi Chawla (@_avichawla)

AWS에서 RAG 앱 구축 방법을 설명하는 게시물로, RAG(검색 보강 생성)는 지식 준비(ingestion)과 질의(querying)의 두 단계로 작동하며, 각 단계를 AWS의 기존 서비스로 구현하는 구체적 흐름을 시각적으로 제시한다.

https://x.com/_avichawla/status/2031994916667363580

#aws #rag #retrievalaugmentedgeneration #nlp #vectorsearch

Avi Chawla (@_avichawla) on X

How to build a RAG app on AWS! The visual below shows the exact flow of how a simple RAG system works inside AWS, using services you already know. At its core, RAG is a two-stage pattern: - Ingestion (prepare knowledge) - Querying (use knowledge) Below is how each stage works

X (formerly Twitter)

InfoQ Mar 10

To improve the relevance of responses produced by Dropbox Dash, engineers at #Dropbox started using #LLMs to augment human labeling - a crucial step in identifying which documents should be used to generate answers.

Their approach offers useful insights for anyone building systems with #RetrievalAugmentedGeneration (RAG).

Learn more: https://bit.ly/3P1nEyj

#InfoQ #AI

sayzard Feb 27

Avi Chawla (@_avichawla)

AI 엔지니어를 위한 8가지 RAG(검색 보강 생성) 아키텍처 시리즈를 소개하는 글의 시작으로, 첫 번째 예시인 'Naive RAG'는 쿼리 임베딩과 저장된 임베딩 간의 벡터 유사도로 문서를 검색하여 단순 사실 기반 질의에 적합하다고 설명합니다.

https://x.com/_avichawla/status/2027270775494082936

#rag #retrievalaugmentedgeneration #embeddings #vectorsearch

Avi Chawla (@_avichawla) on X

8 RAG architectures for AI Engineers: (explained with usage) 1) Naive RAG - Retrieves documents purely based on vector similarity between the query embedding and stored embeddings. - Works best for simple, fact-based queries where direct semantic matching suffices. 2)

X (formerly Twitter)

chribonn Feb 23

AG (Retrieval Augmented Generation) is the solution. Here's how to build your own RAG server from scratch using ollama, Open WebUI and Chroma DB!

✅ Document processing ✅ Vector embeddings ✅ Smart retrieval ✅ Production-ready API

Tutorial 👉 https://medium.com/@chribonn/how-to-create-a-local-rag-enabled-llm-server-that-provides-safe-access-to-your-documents-788a3c8fb447

#RetrievalAugmentedGeneration #RAG #AIEngineering #LLM #Python #TTMO #OpenSource #AI

How to create a local RAG-enabled LLM server that provides safe access to your documents

This tutorial explains how to set up a headless RAG-enabled large language model (LLM) on an Ubuntu server. By the end, you will be able to…

Medium

Duncan Stephen Feb 23

Words and pictures in the history of user experience and the future of artificial intelligence

Modern artificial intelligence tools are largely rooted in text-based interactions. But the history of user experience, information and even humanity shows us that AI will have to go beyond text if it’s going to become relevant.

https://duncanstephen.net/words-and-pictures-in-the-history-of-user-experience-and-the-future-of-artificial-intelligence/

InfoQ Feb 20

The #Dropbox team just shared a deep dive into the architecture of Dropbox Dash.

Highlights:
• A shift toward index-based retrieval
• Knowledge graph–derived context
• Continuous evaluation to support enterprise #AI at scale

🔗 Learn more about the architecture and engineering decisions driving this evolution: https://bit.ly/3OnGEH6

#InfoQ #SoftwareArchitecture #AI #LLMs #DistributedSystems #RetrievalAugmentedGeneration

AI Daily Post Feb 17

SurrealDB 3.0 now packs agent memory, business logic, and multimodal data into a single Rust‑powered engine. It blends graph queries, vector search and retrieval‑augmented generation, letting AI agents store context and act without juggling separate stores. Dive into the details and see how this open‑source DB could reshape your stack. #SurrealDB #RetrievalAugmentedGeneration #VectorSearch #MultiModalData

🔗 https://aidailypost.com/news/surrealdb-30-stores-agent-memory-business-logic-multimodal-data-one-db