#RAG

Mastodon discussion Oct 9

RAG-Stress is a diagnostic protocol that tests how retrieval-augmented generation models rely on evidence.Source: arXiv ...

RAG-Stress is a diagnostic protocol that tests how retrieval-augmented generation models rely on evidence.Source: arXiv cs.CLhttps://arxiv.org/abs/2610.11183#MachineLearning

RAG

9

Dev.to tutorial Oct 9

Your RAG Pipeline Is a Data Leak Waiting to Happen

Your multi-tenant app is probably well isolated. Every query is scoped to a tenant, enforced...

RAG

20

Mastodon discussion Oct 9

Long Context Did Not Kill RAG: The Real Architecture Decision When I first plugged a LLM...#ai #architecture #machinelea...

Long Context Did Not Kill RAG: The Real Architecture Decision When I first plugged a LLM...#ai #architecture #machinelearning #enterprise #software #coding #development #engineerin...

LLM RAG

24

Dev.to tutorial Oct 8

Vector database showroom. Part 3 Qdrant — The Hot Hatchback That Carries More Than It Looks

🏎️ Qdrant — The Hot Hatchback That Carries More Than It Looks Sharp acceleration, precise...

RAG

12

Mastodon discussion Oct 8

This week on AMD Mini-Challenge 3: citation-by-necessity RAG on ROCm Notes from building a...#amd #rocm #rag #machinelea...

This week on AMD Mini-Challenge 3: citation-by-necessity RAG on ROCm Notes from building a...#amd #rocm #rag #machinelearning #software #coding #development #engineering #inclusive...

RAG

18

Dev.to tutorial Oct 8

When does an agent beat RAG? We benchmarked three pipelines on a TigerGraph knowledge graph

Agentic GraphRAG Hackathon by TigerGraph, Round 1. Code:...

RAG

12

Mastodon discussion Oct 8

Benchmarking a deterministic 3-tiered Graph-RAG system against standard vector pipelines exposes critical failure modes ...

Benchmarking a deterministic 3-tiered Graph-RAG system against standard vector pipelines exposes critical failure modes on fact-dense queries. Measuring these gaps is essential bef...

RAG

9

GitHub Trending repo Oct 8

IoTSec-AI/knowledge-driven-iot-fault-diagnosis: Knowledge-driven IoT fault diagnosis system combining real-time sensor telemetry, MQTT, rule-based monitoring, RAG, and local Generative AI.

Knowledge-driven IoT fault diagnosis system combining real-time sensor telemetry, MQTT, rule-based monitoring, RAG, and local Generative AI.

RAG

35

Dev.to tutorial Oct 8

My RAG system didn't need more agents. It never saw the evidence

GroundedDocs answers questions over a document set with exact citations and refuses when the evidence...

RAG

12

Dev.to tutorial Oct 8

Retrieval confidence can't tell your RAG chatbot when the answer is missing

I ran 65 questions against our own knowledge base and checked which ones the retrieved text actually...

RAG

12

GitHub Trending repo Oct 8

cporter202/ai-agent-data-apis: A mega collection of 2,070 AI agent data APIs: MCP servers, LLM tools, RAG pipelines, live web data, vision & voice. Give your AI agent live web data.

A mega collection of 2,070 AI agent data APIs: MCP servers, LLM tools, RAG pipelines, live web data, vision & voice. Give your AI agent live web data.

LLM Multimodal RAG

39

GitHub Trending repo Oct 8

mahshad123/generative-ai-projects: Multimodal LLM moderation agent and NASA RAG assistant, with structured outputs, LLM-as-a-judge evals, and RAGAS scoring.

Multimodal LLM moderation agent and NASA RAG assistant, with structured outputs, LLM-as-a-judge evals, and RAGAS scoring.

LLM Multimodal RAG

32

Dev.to tutorial Oct 8

My Eval Said RAG Made Things Up. My Eval Was Wrong.

I maintain django-explain-errors, a Django middleware that catches unhandled exceptions in...

RAG Benchmark

12

Mastodon discussion Oct 7

What if an AI search application could retrieve information from internal documentation, source code,...#ai #python #rag...

What if an AI search application could retrieve information from internal documentation, source code,...#ai #python #rag #machinelearning #software #coding #development #engineerin...

RAG

24

Dev.to tutorial Oct 7

OpsPilot AI: Building RAG and Agents Without Giving the LLM Authority

The decisions behind OpsPilot AI: evidence-grounded retrieval, deterministic authorization, approval bound to the exact action, and reconciliation of ambiguous external writes.

LLM RAG

12

Dev.to tutorial Oct 7

Why a Financial Advisor App Needs a RAG Vault, Not Just a Chatbot

When I started building Vicquant, the core design principle was simple and non-negotiable: the AI...

RAG

20

Mastodon discussion Oct 7

Build a small evaluation set before you ship a RAG feature. That means 50 to 100 real questions, each...#rag #ai #python...

Build a small evaluation set before you ship a RAG feature. That means 50 to 100 real questions, each...#rag #ai #python #testing #software #coding #development #engineering #inclu...

RAG

24

Mastodon discussion Oct 7

Choose reranking with a strict evidence gate when RAG hallucination makes an ask-your-docs chatbot...#rag #llm #sre #sof...

Choose reranking with a strict evidence gate when RAG hallucination makes an ask-your-docs chatbot...#rag #llm #sre #software #coding #development #engineering #inclusive #communit...

LLM RAG

18

Mastodon discussion Oct 7

We Built an Alternative to Vector RAG for AI Agent Memoryhttps://www.claix.dev/blog/rag-for-ai-agents-agentic-retrieval#...

We Built an Alternative to Vector RAG for AI Agent Memoryhttps://www.claix.dev/blog/rag-for-ai-agents-agentic-retrieval#HackerNews #Tech #AI

RAG Agents

24

Dev.to tutorial Oct 7

Hybrid Retrieval in C#: Combining Vector Search, Graph Traversal, and Reranking for Agent Memory

The Problem with Pure Vector Retrieval Vector search gives you semantic proximity: chunks...

RAG

12

Dev.to tutorial Oct 7

I found the optimal top-k for my RAG system. Then I ran it again.

I built a small retrieval-augmented generation system over a corpus of research papers and wanted to...

RAG

12

Mastodon discussion Oct 7

Private LangGraph RAG on Kubernetes: Running a Local LLM with Full Observability (OpenTelemetry, Prometheus, Grafana)#ku...

Private LangGraph RAG on Kubernetes: Running a Local LLM with Full Observability (OpenTelemetry, Prometheus, Grafana)#kubernetes #observability #llm #opentelemetry #software #codin...

LLM RAG

18

Mastodon discussion Oct 7

The free (as in beer / no login-wall) #LLM #GPT 6 Luna, with RAG, via #DuckDuckGo / duck.ai, is pretty good.It even anal...

The free (as in beer / no login-wall) #LLM #GPT 6 Luna, with RAG, via #DuckDuckGo / duck.ai, is pretty good.It even analyses photos of my BIOS settings.

LLM RAG

9

Dev.to tutorial Oct 7

Do you need a vector database? Brute-force search benchmarked from 10k to 1M vectors

Exact numpy search over 100k embeddings takes 3.5 ms on 2 vCPUs. Measured latency, memory and HNSW recall to show when an index actually pays off.

RAG

12