#RAG

Mastodon discussion Oct 7

When building LLM applications, we often rush to pass user data directly into our prompts or RAG...#llm #privacy #ai #co...

When building LLM applications, we often rush to pass user data directly into our prompts or RAG...#llm #privacy #ai #computervision #software #coding #development #engineering #in...

LLM RAG

27

Dev.to tutorial Oct 6

From JSON to Vector Search: What I Learned Storing Structured User Data for AI

When we were building SpendWise, one of the things we wanted was pretty simple: The AI should know...

RAG

20

Mastodon discussion Oct 6

289 lines of Python that turn a folder of PDFs into a queryable vector store. pypdf, OpenAI embeddings, ChromaDB. Advanc...

289 lines of Python that turn a folder of PDFs into a queryable vector store. pypdf, OpenAI embeddings, ChromaDB. Advanced. For engineers tired of grepping manuals.https://www.valt...

OpenAI RAG

18

Dev.to tutorial Oct 6

How Much Does a RAG Chatbot Cost to Run?

You built a "chat with your documents" app. It works on your laptop. Then someone asks: "What will...

RAG

12

Dev.to tutorial Oct 6

You do not need a vector database for your first RAG chatbot

For forty pages, or four hundred, BM25 keyword scoring, a synonym list and a pinned rules block are usually enough.

RAG

12

Mastodon discussion Oct 6

Before chunking a fetched page for RAG, check two things: did the fetch come back truncated, and is the character count ...

Before chunking a fetched page for RAG, check two things: did the fetch come back truncated, and is the character count plausible for that page? A tiny result usually means a JavaS...

RAG

9

Mastodon discussion Oct 6

Hybrid Search and Reranking: What Each One Actually Buys You#ai #rag #vectordatabase #aws #software #coding #development...

Hybrid Search and Reranking: What Each One Actually Buys You#ai #rag #vectordatabase #aws #software #coding #development #engineering #inclusive #communityHybrid Search and Reranki...

RAG

24

GitHub Trending repo Oct 6

Nikhil-creat/datapulse-ai: Agentic AI portfolio and data-science mission control: Groq-powered assistant (Nova), CSV data lab, RAG vault, in-browser CNN, live GitHub stats. Built by NIKHIL CHARY SRIRAMOJU......

Agentic AI portfolio and data-science mission control: Groq-powered assistant (Nova), CSV data lab, RAG vault, in-browser CNN, live GitHub stats. Built by NIKHIL CHARY SRIRAMOJU......

RAG Agents

39

Mastodon discussion Oct 6

Personal AI agents in enterprise multi-tenant deployments share a common vector store for long-term memory. Shared embed...

Personal AI agents in enterprise multi-tenant deployments share a common vector store for long-term memory. Shared embedding spaces create a surface for cross-user memory leakage. ...

RAG

9

Dev.to tutorial Oct 6

How I Tune RAG Pipelines with RAG-LCC: A Hands-On Local Guide

Most RAG frameworks tell you whether an answer was generated. RAG-LCC tries to show you why that...

RAG

12

Mastodon discussion Oct 5

————————————————————————————————————————————————————————————————————— A retraction,...#ai #security #rag #llm #software ...

————————————————————————————————————————————————————————————————————— A retraction,...#ai #security #rag #llm #software #coding #development #engineering #inclusive #community🤯 I T...

LLM RAG

24

Mastodon discussion Oct 5

CourseChat AI tutor picks 8B model over bigger rivalsLethbridge researchers built CourseChat, an on-premises RAG tutor f...

CourseChat AI tutor picks 8B model over bigger rivalsLethbridge researchers built CourseChat, an on-premises RAG tutor for six business courses, where bigger AI models failed the c...

RAG

9

Mastodon discussion Oct 5

RAG tip for web pages: when you convert HTML, keep tables as markdown tables, and index a one-line summary of each table...

RAG tip for web pages: when you convert HTML, keep tables as markdown tables, and index a one-line summary of each table next to it.The summary helps retrieval find the table. The ...

RAG

18

Mastodon discussion Oct 5

A legal team once sent my PDF-to-Markdown converter a 40-page services contract. Every desktop reader...#pdf #rag #error...

A legal team once sent my PDF-to-Markdown converter a 40-page services contract. Every desktop reader...#pdf #rag #errors #ai #software #coding #development #engineering #inclusive...

RAG

24

Mastodon discussion Oct 5

You upload your company handbook, or a folder of PDFs, or two years of notes. You ask it something...#ai #rag #llm #begi...

You upload your company handbook, or a folder of PDFs, or two years of notes. You ask it something...#ai #rag #llm #beginners #software #coding #development #engineering #inclusive...

LLM RAG

24

Dev.to tutorial Oct 5

AirNEET: Building an Airplane Mode Socratic Mentor for My Sister's NEET Prep (100% Offline RAG)

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I...

RAG

12

Dev.to tutorial Oct 5

Run AI Locally on Your Mac with Ollama: Chat, Tools, RAG and a Custom Model (Real Numbers from a Mac mini M4)

I wanted to know how far a plain Mac mini M4 with 16 GB can go with local AI. No cloud, no API key,...

RAG

12

Mastodon discussion Oct 5

Conclusion AIO Helper is an SEO operations SaaS we are building. It ingests search data,...#seo #ai #saas #rag #software...

Conclusion AIO Helper is an SEO operations SaaS we are building. It ingests search data,...#seo #ai #saas #rag #software #coding #development #engineering #inclusive #communityRunn...

RAG

24

Mastodon discussion Oct 5

This tutorial builds the retrieval core of a production RAG system. Not a notebook toy, but the...#ai #rag #python #tuto...

This tutorial builds the retrieval core of a production RAG system. Not a notebook toy, but the...#ai #rag #python #tutorial #software #coding #development #engineering #inclusive ...

RAG

27

Mastodon discussion Oct 5

Building a RAG Pipeline for Semantic Code SearchArticle URL: https://blog.jetbrains.com/ai/2026/09/building-a-rag-pipeli...

Building a RAG Pipeline for Semantic Code SearchArticle URL: https://blog.jetbrains.com/ai/2026/09/building-a-rag-pipeline-for-semantic-code-search-a-developer-diary-and-field-note...

Google RAG

18

Mastodon discussion Oct 5

A citation under an answer is only as good as whoever wrote it. If the model writes it, it's exactly...#rag #llm #ai #se...

A citation under an answer is only as good as whoever wrote it. If the model writes it, it's exactly...#rag #llm #ai #security #software #coding #development #engineering #inclusiv...

LLM RAG

24

Dev.to tutorial Oct 4

What 113 eval questions taught me building a fully local RAG

I built LocalCortex, a chat app for your own documents that runs entirely on a laptop: Ollama for...

RAG Benchmark

12

Mastodon discussion Oct 4

Building a RAG Pipeline for Semantic Code Searchhttps://blog.jetbrains.com/ai/2026/09/building-a-rag-pipeline-for-semant...

Building a RAG Pipeline for Semantic Code Searchhttps://blog.jetbrains.com/ai/2026/09/building-a-rag-pipeline-for-semantic-code-search-a-developer-diary-and-field-notes/#ai

RAG

9

GitHub Trending repo Oct 4

ronitgupta138/vectra-core: ⚡ In-Memory Vector Search Engine & HNSW ANN Graph in Java 21 Loom. Sub-millisecond KNN retrieval, 8-bit scalar quantization (SQ8), 16,000+ QPS.

⚡ In-Memory Vector Search Engine & HNSW ANN Graph in Java 21 Loom. Sub-millisecond KNN retrieval, 8-bit scalar quantization (SQ8), 16,000+ QPS.

RAG

43