news.ycombinator.com
From zero to RAG engineer: 1200 hours of lessons so you don't repeat my mistakes | Hacker News
Bluesky · Hashtag
#RAG
202
posts · 30d
103
users
7
posts / day
2.0
posts / user
-6% vs last week
#RAG is an active hashtag on Bluesky. In the last 30 days, 103 people shared 202 posts with it — around 7 a day. Activity is down 6% versus the previous week, peaking on Jul 23 with 13 posts.
#RAG posts per day (last 30 days)
Related tags
Tags most often used together with #RAG.
Posts with #RAG
Hey fam 👋
In a new blog post, I wrote about my journey from zero to RAG engineer after 1200 hours building enterprise AI.
What actually works vs. what's just hype. Hard-learned lessons so you don't repeat my mistakes 👇
news.ycombinator.com/item….
#TechBlog #BuildInPublic #RAG #AI #LLM
3 9 58
Pair vector search with metadata layers for ID retrieval. This explicit matching handles identifiers alongside similarity scores. Hybrid retrieval combines dense vectors with sparse search, letting an exact match like 16-B override a near-duplicate embedding score.
#RAG #RAGTips #AgenticAI #LLMs
2 1 4
This week in #Science #Immunology: Luigi Notarangelo & >100 colleagues characterize the immune & molecular features of 157 patients w/ various forms of #RAG #immunodeficiency! This is a real tour de force!
@niaidnews.bsky.social
scim.ag
Multiomics dissection of human RAG deficiency reveals distinctive patterns of immune dysregulation but a common inflammatory signature
A multiomics approach reveals immune dysregulation signatures that characterize the clinical phenotypes of human RAG deficiency.
0 7 35
This system takes the RAG concept a step further by incorporating graph theory into the mix. Instead of treating data as isolated chunks, GraphRAG organizes information into a network of entities and relationships—a knowledge graph. #RAG #AI #ML #LLM
www.improving.com
GraphRAG Systems: The Future of Information Retrieval? | Improving
Discover how GraphRAG Systems revolutionize data retrieval with comprehensive, nuanced responses to complex queries.
0 4 32
What is RAG?
Retrieval-Augmented Generation helps AI find relevant information before generating an answer—making responses more accurate, grounded, and useful.
nyvoraai.github.io/ai-new….
#RAG #AI #GenerativeAI #LLM #MachineLearning #NyvoraAi
0 0 3
ragnar 0.3.0 is now on CRAN! 🚀 An R toolkit for RAG from your docs: faster ingestion, better retrieval, Azure OpenAI + Snowflake embeddings, and MCP serving. tidyverse.org/blog/2026/01...
#rstats #rag #ai
tidyverse.org
ragnar 0.3.0
The new release of ragnar adds faster ingestion, new embedding providers, improved retrieval, and new integrations for using ragnar stores from tools.
1 9 30
Part 8 of my mini local code agent with @docker.com Agent: I put the pieces together into a companion for learning #Rust.
A cookbook #RAG, an lsp toolset on rust-analyzer, and the context caps that keep a 2.5B model alive.
k33g.org/p/20260811-d...
#DockerAgent
k33g.org
A mini code agent with Docker Agent - Part 8: a local agent to learn Rust
Assemble a local Rust learning companion with Docker Agent: a cookbook RAG, a rust-analyzer LSP toolset, and the context caps that keep a small model alive.
1 2 4
Zennで新しい記事を公開しました
Gemini×NotebookLMの裏側： 見えるものと見えないもの、正しく使うための鉄則
#NotebookLM のノートブックを添付できるようになったから
ソースに大量に入れて #Gemini に送れば
全部まとめて処理してくれる、とか
GeminiでNotebookLMでのチャットを精査してもらおう、とか
そんなことはできません🥲
できることとできないことを理解して
これを読めばGemini×NotebookLMを
より効率的に利用できるようになるかもしれない✨
#aiart #RAG #LLM
0 3 27
On This Day In Jazz Age Music!
AUGUST 10TH...
onthisdayinjazzagemusic.s….
#AUGUST10TH #AUGUST10 #Music #MusicSky #JAZZ #JazzAge #MusicianSky #BritishDanceBand #Geraldo #JackHaley #TANGO #RobertHampton #RAG #Ragtime #RagtimeComposer #BillJohnson #RobertDeKers #BelgianJazz
onthisdayinjazzagemusic.substack.com
AUGUST 10TH
HAPPY BIRTHDAY GERALDO!
0 0 4
NEW! Leanpub Book LAUNCH 🚀 LLM Engineering, from Component to Production by Ali Aouf
youtu.be/mhxhId_dLQA
#books #leanpublishing #selfpublishing #LLMEngineering #RAG #AIAgents #GenerativeAI #MLOps
0 1 3
"RAG with OpenAI GPT on Amazon Bedrock" by William Quigley
#openai #openai-gpt #rag #knowledge-bases-for-bedrock
community.aws
RAG with OpenAI GPT on Amazon Bedrock
You have a Bedrock Knowledge Base full of documents and you want to build a question-answering system that grounds its responses in that corpus. Bedrock's built-in `RetrieveAndGenerate` API couples retrieval and generation into a single call, but you want more control: custom prompting, citation formatting, deduplication logic, or the ability to swap generation models independently of the retrieval layer.
0 0 0
Vector search ranks by what looks like the query. Not by what is still true.
Four dimensions similarity ignores: recency, access frequency, entity spreading activation, and confidence from contradiction.
www.adaptiverecall.com/co….
#RAG
0 0 1
A tool failure is obvious. Bad retrieval can be much quieter.
The agent finds a plausible document, produces a grounded answer—and is confidently wrong.
From The AI Agent Test Manual:https://amzn.eu/d/0blIkveq
#AIAgents #RAG #LLMEvaluation #SoftwareTesting
webdad.eu
The Agent Was Confident. The Data Was Wrong.
A retrieval call can succeed and still give an AI agent exactly the wrong evidence. This practical walkthrough shows how to test retrieval as its own quality surface, covering stale documents, missing exceptions, conflicting sources, query variations, evidence gates, and measurable before-and-after evaluation results.
0 0 0
🚨 Want a fully local RAG app in C#?
Part 1: Build it with Ollama + Qdrant no cloud, full control! 🤖
📚 Guide: www.ottorinobruni.com/bui….
Tried local RAG yet? 👇
#dotnet #CSharp #RAG #Ollama
www.ottorinobruni.com
Build a Local RAG Application in C# with Ollama and Qdrant - Part 1 - Ottorino Bruni
Learn how to build a local RAG application in C# using Ollama and Qdrant, from architecture and embeddings to vector search and private AI setup.
0 0 0
"From Raw Data to Relevant Context: Managing Data for Generative AI on AWS" by Swarali Chine
#gen-ai #amazon-bedrock #rag #vector-search
community.aws
From Raw Data to Relevant Context: Managing Data for Generative AI on AWS
A practical guide to Bedrock Data Automation, Data Wrangler, AWS Glue, Transcribe, Comprehend, Amazon S3, vector storage, databases, reranking, and CloudWatch.
0 0 0
Submission Link: openreview.net/group?id=ACM...
We welcome theory, empirics, and methods on graph-guided #llm, graph #rag, optimisation, benchmarking, and more.
openreview.net
ACM CIKM 2026 Workshop GaLM
Welcome to the OpenReview homepage for ACM CIKM 2026 Workshop GaLM
0 0 0
"From Foundation Models to Guardrails: Understanding Generative AI with Amazon Bedrock" by Swarali Chine
#amazon-bedrock #gen-ai #rag #prompt-engineering
community.aws
From Foundation Models to Guardrails: Understanding Generative AI with Amazon Bedrock
A practical mental model for understanding Amazon Bedrock, RAG, embeddings, vector stores, fine-tuning, LoRA, Knowledge Bases, prompts, and flows.
0 0 1
Your RAG bot answers only as well as its sources are formatted. Crawl messy docs into clean markdown so answers stay accurate when a page rewrites or disappears. 139 runs, 30/30. Pay Per Result.
apify.com/sleek_waveform/…
#RAG #LLM
0 0 0
Posts are pulled live from Bluesky and cached briefly. Posts with content labels are hidden.