🌈 Social 📸 Photography 🌈

petersuberUpdate. This new study compares two <a href="https://fediscience.org/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI</a> tools (<a href="https://fediscience.org/tags/LLMs" class="mention hashtag" rel="nofollow noopener" target="_blank">#LLMs</a> with <a href="https://fediscience.org/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#RAG</a>) on the task of predicting the citation impact of scholarly articles. <a href="https://aclanthology.org/2025.sdp-1.11/" rel="nofollow noopener" translate="no" target="_blank">https://aclanthology.org/2025.sdp-1.11/</a>

Sarah LeaLLMs don’t know your PDF. They don’t know your company wiki either. Or your research papers.What they can do with RAG is look through your documents in the background and answer using what they find.But how does that actually work? Here’s the basic idea behind RAG: :blobcoffee: Chunking: The document is split into small, overlapping parts so the LLM can handle them. This keeps structure and context. :blobcoffee: Embeddings & Search: Each part is turned into a vector (a numerical representation of meaning). Your question is also turned into a vector, and the system compares them to find the best matches. :blobcoffee: Retriever + LLM: The top matches are sent to the LLM, which uses them to generate an answer based on that context.<a href="https://techhub.social/tags/llm" class="mention hashtag" rel="nofollow noopener" target="_blank">#llm</a> <a href="https://techhub.social/tags/largelanguagemodel" class="mention hashtag" rel="nofollow noopener" target="_blank">#largelanguagemodel</a> <a href="https://techhub.social/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#ai</a> <a href="https://techhub.social/tags/ki" class="mention hashtag" rel="nofollow noopener" target="_blank">#ki</a> <a href="https://techhub.social/tags/rag" class="mention hashtag" rel="nofollow noopener" target="_blank">#rag</a> <a href="https://techhub.social/tags/tech" class="mention hashtag" rel="nofollow noopener" target="_blank">#tech</a> <a href="https://techhub.social/tags/technology" class="mention hashtag" rel="nofollow noopener" target="_blank">#technology</a> <a href="https://techhub.social/tags/vector" class="mention hashtag" rel="nofollow noopener" target="_blank">#vector</a> <a href="https://techhub.social/tags/datascience" class="mention hashtag" rel="nofollow noopener" target="_blank">#datascience</a> <a href="https://techhub.social/tags/vectorsearch" class="mention hashtag" rel="nofollow noopener" target="_blank">#vectorsearch</a> <a href="https://techhub.social/tags/vector" class="mention hashtag" rel="nofollow noopener" target="_blank">#vector</a> <a href="https://techhub.social/tags/machinelearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#machinelearning</a>

Sarah LeaWant to really understand how RAG, vector search & chunking work?Then stop reading theory and build your own chatbot.This guide shows you how to create a local PDF chatbot using: ☕ LangChain☕ FAISS (vector DB)☕ Mistral via Ollama☕ Python & StreamlitStep-by-step, from environment setup to deployment. Ideal for learning how Retrieval-Augmented Generation works in practice.👉 <a href="https://medium.com/data-science-collective/rag-in-action-build-your-own-local-pdf-chatbot-as-a-beginner-96c2833869ff" rel="nofollow noopener" translate="no" target="_blank">https://medium.com/data-science-collective/rag-in-action-build-your-own-local-pdf-chatbot-as-a-beginner-96c2833869ff</a>Comment “WANT” if you need the friends link to the article, as you don’t have paid Medium.<a href="https://techhub.social/tags/rag" class="mention hashtag" rel="nofollow noopener" target="_blank">#rag</a> <a href="https://techhub.social/tags/tech" class="mention hashtag" rel="nofollow noopener" target="_blank">#tech</a> <a href="https://techhub.social/tags/Technology" class="mention hashtag" rel="nofollow noopener" target="_blank">#Technology</a> <a href="https://techhub.social/tags/chatbot" class="mention hashtag" rel="nofollow noopener" target="_blank">#chatbot</a> <a href="https://techhub.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI</a> <a href="https://techhub.social/tags/ki" class="mention hashtag" rel="nofollow noopener" target="_blank">#ki</a> <a href="https://techhub.social/tags/python" class="mention hashtag" rel="nofollow noopener" target="_blank">#python</a> <a href="https://techhub.social/tags/vector" class="mention hashtag" rel="nofollow noopener" target="_blank">#vector</a> <a href="https://techhub.social/tags/langchain" class="mention hashtag" rel="nofollow noopener" target="_blank">#langchain</a> <a href="https://techhub.social/tags/datascience" class="mention hashtag" rel="nofollow noopener" target="_blank">#datascience</a> <a href="https://techhub.social/tags/DataScientist" class="mention hashtag" rel="nofollow noopener" target="_blank">#DataScientist</a> <a href="https://techhub.social/tags/streamlit" class="mention hashtag" rel="nofollow noopener" target="_blank">#streamlit</a>

JaschaHello World! <a href="https://infosec.exchange/tags/introduction" class="mention hashtag" rel="nofollow noopener" target="_blank">#introduction</a> Work in cybersec for 25+ years. Big OSS proponent. Latest projects:VectorSmuggle is acomprehensive proof-of-concept demonstrating vector-based data exfiltration techniques in AI/ML environments. This project illustrates potential risks in RAG systems and provides tools and concepts for defensive analysis. <a href="https://github.com/jaschadub/VectorSmuggle" rel="nofollow noopener" translate="no" target="_blank">https://github.com/jaschadub/VectorSmuggle</a>SchemaPin protocol for cryptographically signing and verifying AI agent tool schemas to prevent supply-chain attacks (aka MCP Rug Pulls). <a href="https://github.com/ThirdKeyAI/SchemaPin" rel="nofollow noopener" translate="no" target="_blank">https://github.com/ThirdKeyAI/SchemaPin</a><a href="https://infosec.exchange/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#ai</a> <a href="https://infosec.exchange/tags/AiResearch" class="mention hashtag" rel="nofollow noopener" target="_blank">#AiResearch</a> <a href="https://infosec.exchange/tags/aisecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#aisecurity</a> <a href="https://infosec.exchange/tags/rag" class="mention hashtag" rel="nofollow noopener" target="_blank">#rag</a> <a href="https://infosec.exchange/tags/mcp" class="mention hashtag" rel="nofollow noopener" target="_blank">#mcp</a> <a href="https://infosec.exchange/tags/mcpserver" class="mention hashtag" rel="nofollow noopener" target="_blank">#mcpserver</a>

Alvin Ashcraft 🐿️Smarter SK Agents with Contextual Function Selection.<a href="https://devblogs.microsoft.com/semantic-kernel/smarter-sk-agents-with-contextual-function-selection/" rel="nofollow noopener" translate="no" target="_blank">https://devblogs.microsoft.com/semantic-kernel/smarter-sk-agents-with-contextual-function-selection/</a> <a href="https://hachyderm.io/tags/semantickernel" class="mention hashtag" rel="nofollow noopener" target="_blank">#semantickernel</a> <a href="https://hachyderm.io/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#ai</a> <a href="https://hachyderm.io/tags/aiagents" class="mention hashtag" rel="nofollow noopener" target="_blank">#aiagents</a> <a href="https://hachyderm.io/tags/dotnet" class="mention hashtag" rel="nofollow noopener" target="_blank">#dotnet</a> <a href="https://hachyderm.io/tags/csharp" class="mention hashtag" rel="nofollow noopener" target="_blank">#csharp</a> <a href="https://hachyderm.io/tags/rag" class="mention hashtag" rel="nofollow noopener" target="_blank">#rag</a>

DiSC_uibkIf you start using the Rankify toolkit, feel free sharing your experience with us or let us know if you have any feedback or questions! 🤓 <a href="https://social.uibk.ac.at/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#RAG</a> <a href="https://social.uibk.ac.at/tags/DataScience" class="mention hashtag" rel="nofollow noopener" target="_blank">#DataScience</a> <a href="https://social.uibk.ac.at/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI</a> <a href="https://social.uibk.ac.at/tags/research" class="mention hashtag" rel="nofollow noopener" target="_blank">#research</a>

DiSC_uibkHave you ever struggled to find the best document retrieval model for your project? Or had to combine multiple frameworks just to get a basic <a href="https://social.uibk.ac.at/tags/InformationRetrieval" class="mention hashtag" rel="nofollow noopener" target="_blank">#InformationRetrieval</a> pipeline running?Check out Rankify, developed by Abdelrahman Abdallah from the <a href="https://social.uibk.ac.at/tags/DataScience" class="mention hashtag" rel="nofollow noopener" target="_blank">#DataScience</a> Group <a href="https://social.uibk.ac.at/@uniinnsbruck" class="u-url mention" rel="nofollow noopener" target="_blank">@uniinnsbruck</a>, which provides an all-in-one retrieval, re-ranking, and retrieval-augmented generation toolkit: <a href="https://www.doi.org/10.48763/000013" rel="nofollow noopener" translate="no" target="_blank">https://www.doi.org/10.48763/000013</a><a href="https://social.uibk.ac.at/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI</a> <a href="https://social.uibk.ac.at/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#MachineLearning</a> <a href="https://social.uibk.ac.at/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#RAG</a> <a href="https://social.uibk.ac.at/tags/OpenSource" class="mention hashtag" rel="nofollow noopener" target="_blank">#OpenSource</a> <a href="https://social.uibk.ac.at/tags/FOSS" class="mention hashtag" rel="nofollow noopener" target="_blank">#FOSS</a> <a href="https://social.uibk.ac.at/tags/NLP" class="mention hashtag" rel="nofollow noopener" target="_blank">#NLP</a> <a href="https://social.uibk.ac.at/tags/research" class="mention hashtag" rel="nofollow noopener" target="_blank">#research</a>

Bob 🇨🇦🇲🇽🇺🇦<a href="https://www.theregister.com/2025/05/27/opinion_column_ai_model_collapse/" rel="nofollow noopener" translate="no" target="_blank">https://www.theregister.com/2025/05/27/opinion_column_ai_model_collapse/</a><a href="https://infosec.exchange/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#ai</a> <a href="https://infosec.exchange/tags/machinelearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#machinelearning</a> <a href="https://infosec.exchange/tags/rag" class="mention hashtag" rel="nofollow noopener" target="_blank">#rag</a>

Nicole HennigWhy enterprise RAG systems fail: Google study introduces ‘sufficient context’ solution <a href="https://venturebeat.com/ai/why-enterprise-rag-systems-fail-google-study-introduces-sufficient-context-solution/" rel="nofollow noopener" translate="no" target="_blank">https://venturebeat.com/ai/why-enterprise-rag-systems-fail-google-study-introduces-sufficient-context-solution/</a> <a href="https://techhub.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI</a> <a href="https://techhub.social/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#RAG</a> <a href="https://techhub.social/tags/hallucination" class="mention hashtag" rel="nofollow noopener" target="_blank">#hallucination</a>

Chris VitalosIf true, <a href="https://sigmoid.social/tags/hallucinations" class="mention hashtag" rel="nofollow noopener" target="_blank">#hallucinations</a> cast serious doubt on whether the end goal of <a href="https://sigmoid.social/tags/AGI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AGI</a> can be achieved with today’s <a href="https://sigmoid.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#LLM</a> architectures and training methods.While ongoing research explores <a href="https://sigmoid.social/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#RAG</a> and hybrid models and inference techniques, no implementation to date has fully eliminated flawed reasoning.What consumer would trust mission-critical decisions if an AGI is known to confidently state falsehoods?<a href="https://www.newscientist.com/article/2479545-ai-hallucinations-are-getting-worse-and-theyre-here-to-stay/" rel="nofollow noopener" translate="no" target="_blank">https://www.newscientist.com/article/2479545-ai-hallucinations-are-getting-worse-and-theyre-here-to-stay/</a><a href="https://sigmoid.social/tags/GenAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#GenAI</a> <a href="https://sigmoid.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI</a>

Alvin Ashcraft 🐿️Retrieval-augmented generation with Llama Stack and Node.js.<a href="https://developers.redhat.com/articles/2025/04/30/retrieval-augmented-generation-llama-stack-and-nodejs" rel="nofollow noopener" translate="no" target="_blank">https://developers.redhat.com/articles/2025/04/30/retrieval-augmented-generation-llama-stack-and-nodejs</a> <a href="https://hachyderm.io/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#ai</a> <a href="https://hachyderm.io/tags/nodejs" class="mention hashtag" rel="nofollow noopener" target="_blank">#nodejs</a> <a href="https://hachyderm.io/tags/javascript" class="mention hashtag" rel="nofollow noopener" target="_blank">#javascript</a> <a href="https://hachyderm.io/tags/llama" class="mention hashtag" rel="nofollow noopener" target="_blank">#llama</a> <a href="https://hachyderm.io/tags/rag" class="mention hashtag" rel="nofollow noopener" target="_blank">#rag</a> <a href="https://hachyderm.io/tags/llm" class="mention hashtag" rel="nofollow noopener" target="_blank">#llm</a>

MottGCitegeist is a free tool that helps you find articles related to a topic you are interested in. You need to seed it by entering the abstract of a relevant article or by uploading a relevant article. Citegeist not only finds related articles, but it generates a short report with info from the related articles also! Citegeist works by using RAG info retrieval on the arxiv corpus of research papers.<a href="https://citegeist.org" rel="nofollow noopener" translate="no" target="_blank">https://citegeist.org</a><a href="https://researchbuzz.masto.host/tags/research" class="mention hashtag" rel="nofollow noopener" target="_blank">#research</a> <a href="https://researchbuzz.masto.host/tags/science" class="mention hashtag" rel="nofollow noopener" target="_blank">#science</a> <a href="https://researchbuzz.masto.host/tags/2ndOrderSearch" class="mention hashtag" rel="nofollow noopener" target="_blank">#2ndOrderSearch</a> <a href="https://researchbuzz.masto.host/tags/Citegeist" class="mention hashtag" rel="nofollow noopener" target="_blank">#Citegeist</a> <a href="https://researchbuzz.masto.host/tags/arxivTools" class="mention hashtag" rel="nofollow noopener" target="_blank">#arxivTools</a> <a href="https://researchbuzz.masto.host/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#RAG</a>

Major Hayden 🤠I finally cobbled all my thoughts about retrieval-augmented generation, or RAG, together in one place. So many people claimed it was so easy, but it's not.This post is a high level overview of my lessons learned and some suggestions for you if you go down this path. 🧗‍♂️<a href="https://major.io/p/dont-tell-me-rag-is-easy/" rel="nofollow noopener" translate="no" target="_blank">https://major.io/p/dont-tell-me-rag-is-easy/</a><a href="https://social.lol/tags/rag" class="mention hashtag" rel="nofollow noopener" target="_blank">#rag</a> <a href="https://social.lol/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#ai</a> <a href="https://social.lol/tags/llm" class="mention hashtag" rel="nofollow noopener" target="_blank">#llm</a> <a href="https://social.lol/tags/vector_database" class="mention hashtag" rel="nofollow noopener" target="_blank">#vector_database</a>

Manel GuerraGenerar contingut amb IA per contrarrestar l'excés de cerques amb IA. Què pot sortir malament? Al blog: Bloquejar cerques d'IA embrutant (també) dades <a href="https://www.manelguerra.com/blog/bloquejar-cerques-ia/" rel="nofollow noopener" translate="no" target="_blank">https://www.manelguerra.com/blog/bloquejar-cerques-ia/</a><a href="https://mastodont.cat/tags/blog" class="mention hashtag" rel="nofollow noopener" target="_blank">#blog</a> <a href="https://mastodont.cat/tags/ia" class="mention hashtag" rel="nofollow noopener" target="_blank">#ia</a> <a href="https://mastodont.cat/tags/rag" class="mention hashtag" rel="nofollow noopener" target="_blank">#rag</a> <a href="https://mastodont.cat/tags/datapoisoning" class="mention hashtag" rel="nofollow noopener" target="_blank">#datapoisoning</a>

Alvin Ashcraft 🐿️Understand Retrieval Augmented Generation in Under 8 Minutes with Michael Jolley.<a href="https://www.youtube.com/watch?v=DUCW0Aeo1AI" rel="nofollow noopener" translate="no" target="_blank">https://www.youtube.com/watch?v=DUCW0Aeo1AI</a><a href="https://hachyderm.io/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#ai</a> <a href="https://hachyderm.io/tags/rag" class="mention hashtag" rel="nofollow noopener" target="_blank">#rag</a>

Ben Lorica 罗瑞卡🆕 Tom Smoker of WhyHow.ai on building better AI systems with structured data and knowledge graphs <a href="https://indieweb.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#LLM</a> <a href="https://indieweb.social/tags/GraphRAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#GraphRAG</a> <a href="https://indieweb.social/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#RAG</a> <a href="https://indieweb.social/tags/search" class="mention hashtag" rel="nofollow noopener" target="_blank">#search</a> <a href="https://indieweb.social/tags/vectorDB" class="mention hashtag" rel="nofollow noopener" target="_blank">#vectorDB</a> <a href="https://thedataexchange.media/whyhow-tom-smoker/" rel="nofollow noopener" translate="no" target="_blank">https://thedataexchange.media/whyhow-tom-smoker/</a>

Aria Burrell 🇨🇦Tool for populating your <a href="https://xn--xxa.computer/tags/OpenWebUI" class="mention hashtag" rel="nofollow noopener" target="_blank">#OpenWebUI</a> <a href="https://xn--xxa.computer/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#RAG</a> with data from <a href="https://xn--xxa.computer/tags/RSS" class="mention hashtag" rel="nofollow noopener" target="_blank">#RSS</a> feeds.Saves pulled content to files as well so it can all be resubmitted if you change embedding models.I'm using it with <a href="https://xn--xxa.computer/tags/DeepSeek" class="mention hashtag" rel="nofollow noopener" target="_blank">#DeepSeek</a>-R1 and <a href="https://xn--xxa.computer/tags/nomic" class="mention hashtag" rel="nofollow noopener" target="_blank">#nomic</a>-embed-text<a href="https://github.com/litui/rss-rag-ingest" rel="nofollow noopener" translate="no" target="_blank">https://github.com/litui/rss-rag-ingest</a>

Pierre BoudesDernier sujet : la mal-nommée intelligence artificielle générative. Plus précisément, les grands modèles de langages (LLM) et RAG (récupération-génération documentaire) dans un contexte ESR. On est en train de mettre en place infrastructures et services avec une objectivation de l'impact environnemental. L'UNIF est pour le moment juste en soutien pour le montage, l'hébergement et sur les mesures de l'impact. Est-ce qu'un service de <a href="https://universites.social/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#RAG</a> spécifique à l'ESR vous semble pertinent/nécessaire ?

PrivacyDigest<a href="https://mas.to/tags/Anthropic" class="mention hashtag" rel="nofollow noopener" target="_blank">#Anthropic</a> builds <a href="https://mas.to/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#RAG</a> directly into <a href="https://mas.to/tags/Claude" class="mention hashtag" rel="nofollow noopener" target="_blank">#Claude</a> models with new <a href="https://mas.to/tags/Citations" class="mention hashtag" rel="nofollow noopener" target="_blank">#Citations</a> <a href="https://mas.to/tags/API" class="mention hashtag" rel="nofollow noopener" target="_blank">#API</a> <a href="https://mas.to/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#ai</a> <a href="https://arstechnica.com/ai/2025/01/anthropic-adds-citations-in-bid-to-avoid-confabulating-ai-models/" rel="nofollow noopener" translate="no" target="_blank">https://arstechnica.com/ai/2025/01/anthropic-adds-citations-in-bid-to-avoid-confabulating-ai-models/</a>

Recent searches

Search options

Administered by:

Server stats:

#rag