#RAG

Mastodon discussion Sep 15

🤖 Combining RAG with Continued Pretraining of LLMsFor leaning purposes, I ran an experiment where I used Unsloth to trai...

🤖 Combining RAG with Continued Pretraining of LLMsFor leaning purposes, I ran an experiment where I used Unsloth to train a model on a new domain using continued pretraining. Then ...

RAG

18

Dev.to tutorial Sep 15

My RAG system's refusal threshold was having no effect. I only found out because I measured it.

I'm a Java backend engineer. Three years of Spring Boot, Kafka and Postgres in a regulated healthcare...

RAG

12

Dev.to tutorial Sep 15

Taming Agent Context Inflation: Integrating OpenViking for Cache-Aligned RAG and Token Optimization

How treating agent context as a structured database with OpenViking slashed redundant prompt tokens by 82% and stabilized latency cliffs.

RAG

12

Mastodon discussion Sep 15

Как устроен RAG для юридических документов и почему одной LLM оказалось недостаточноПервый вариант системы выглядел впол...

Как устроен RAG для юридических документов и почему одной LLM оказалось недостаточноПервый вариант системы выглядел вполне стандартно: документы разбиваются на фрагменты, для них с...

LLM RAG

9

Mastodon discussion Sep 15

I would rag on software engineering as a profession for how the body of workers is handling #AI but my professional life...

I would rag on software engineering as a profession for how the body of workers is handling #AI but my professional life has been deep in #epidemiology for years and, well, you see...

RAG

9

Mastodon discussion Sep 15

GIN 인덱스 적용 후 120 ms → 45 ms, 검색 속도가 2.7배 빨라졌어요. 새로 만든 RAG 파이프라인에서는 벡터 DB 재인덱스를 수행한 뒤 반드시 `REINDEX` 명령을 돌리세요 🔧. 여러분은 현재 어...

GIN 인덱스 적용 후 120 ms → 45 ms, 검색 속도가 2.7배 빨라졌어요. 새로 만든 RAG 파이프라인에서는 벡터 DB 재인덱스를 수행한 뒤 반드시 `REINDEX` 명령을 돌리세요 🔧. 여러분은 현재 어떤 인덱스 최적화 고민 중인가요? #AI #RAG

RAG

9

Mastodon discussion Sep 15

What is RAG? Retrieval-augmented generation pairs a vector search step with an LLM so it can answer from your own data. ...

What is RAG? Retrieval-augmented generation pairs a vector search step with an LLM so it can answer from your own data. Here's the real mechanism.#ai #rag #llm #ollama #software #c...

LLM RAG

9

Mastodon discussion Sep 15

Полгода экспериментов с ИИ: RAG, AI-ревью, автотесты, агенты и автообработка счетовМы вhttps://habr.com/ru/companies/cyn...

Полгода экспериментов с ИИ: RAG, AI-ревью, автотесты, агенты и автообработка счетовМы вhttps://habr.com/ru/companies/cynteka/articles/1082412/#искусственный_интеллект #внедрение_ИИ...

RAG

9

Mastodon discussion Sep 15

🚀 Fastest-growing AI projects today1. The iamzulx/crypto-rag repository stands out as one of the most active projects th...

🚀 Fastest-growing AI projects today1. The iamzulx/crypto-rag repository stands out as one of the most active projects thweek,...2. The iamzulx/crypto-rag project an Indonesian-lang...

RAG

9

Dev.to tutorial Sep 15

Fine-Tuning vs RAG vs Prompting: What Each Costs

The fine-tuning vs RAG question usually arrives as a statement: "we need to fine-tune a model on our...

RAG

12

Mastodon discussion Sep 15

The fine-tuning vs RAG question usually arrives as a statement: "we need to fine-tune a model on our...#ai #machinelearn...

The fine-tuning vs RAG question usually arrives as a statement: "we need to fine-tune a model on our...#ai #machinelearning #openai #api #software #coding #development #engineering...

OpenAI RAG

27

Dev.to tutorial Sep 15

Why Production RAG Pipelines Need More Than a Vector Database on AWS

My first RAG prototype did exactly what the tutorials suggested. The API received a document, split...

RAG

12

Dev.to tutorial Sep 15

Why RAG Fails for Ground-Truth Data | Nainik Mehta

The Vector Database Trap: Why RAG Isn't Always the Answer In the current gold rush of...

RAG

12

Mastodon discussion Sep 14

In the comparison articles (part 1 and part 2) I put my own RAG against five other systems. The...#ai #rag #llm #python ...

In the comparison articles (part 1 and part 2) I put my own RAG against five other systems. The...#ai #rag #llm #python #software #coding #development #engineering #inclusive #comm...

LLM RAG

24

Dev.to tutorial Sep 14

I built a Mac app that turns document folders into RAG-ready Markdown — locally

I kept hitting the same wall: I have a folder of PDFs, Word files and spreadsheets, and I want them...

RAG

12

Dev.to tutorial Sep 14

Indirect prompt injection in a RAG pipeline: one attack, step by step, and what actually stopped it

Most write-ups about prompt injection show you the attacker typing something clever into the chat...

RAG

12

Mastodon discussion Sep 14

Agentic RAG vs Traditional RAG in .NET (2026) — When Each Wins, Semantic Kernel Code, Production Metrics#ai #dotnet #rag...

Agentic RAG vs Traditional RAG in .NET (2026) — When Each Wins, Semantic Kernel Code, Production Metrics#ai #dotnet #rag #machinelearning #software #coding #development #engineerin...

RAG Agents

24

Mastodon discussion Sep 14

“Data-driven decision making.” Cool. Now go find the data. 😐 That was one of the reasons I started...#rag #pydantic #ai ...

“Data-driven decision making.” Cool. Now go find the data. 😐 That was one of the reasons I started...#rag #pydantic #ai #python #software #coding #development #engineering #inclusi...

RAG

24

Dev.to tutorial Sep 14

Give your agent a vector database without giving it a Python runtime

Every MCP server for Qdrant until now has been a Python process: an interpreter, a virtualenv and a...

RAG

12

Dev.to tutorial Sep 14

I Tried to Learn RAG and Got Stuck on API Costs. Turns Out My CPU Could Do the Expensive Bit.

A few months ago, I started building a Retrieval-Augmented Generation application because I wanted to...

RAG API

12

Mastodon discussion Sep 14

A few months ago, I started building a Retrieval-Augmented Generation application because I wanted to...#rag #ai #python...

A few months ago, I started building a Retrieval-Augmented Generation application because I wanted to...#rag #ai #python #machinelearning #software #coding #development #engineerin...

RAG

27

Dev.to tutorial Sep 13

How I Built a Bilingual RAG-Powered AI Calling & Chat Agent (With a Full Admin Ops Center)

Most "AI chatbot" projects stop at a demo: a widget, an OpenAI/Gemini call, a canned prompt. Getting...

OpenAI Google RAG

12

Mastodon discussion Sep 13

Most "AI chatbot" projects stop at a demo: a widget, an OpenAI/Gemini call, a canned prompt. Getting...#ai #rag #automat...

Most "AI chatbot" projects stop at a demo: a widget, an OpenAI/Gemini call, a canned prompt. Getting...#ai #rag #automation #saas #software #coding #development #engineering #inclu...

OpenAI Google RAG

27

Dev.to tutorial Sep 13

A RAG chatbot on your company knowledge base: what it is and when it pays off

The request I hear most often this year sounds the same every time: "We want a bot that answers from...

RAG

12