Recent searches

No recent searches

Search options

Only available when logged in.
toad.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
Mastodon server operated by David Troy, a tech pioneer and investigative journalist addressing threats to democracy. Thoughtful participation and discussion welcome.

Administered by:

Server stats:

291
active users

toad.social: AboutProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.4.3

#rag

5 posts4 participants0 posts today
Alvin Ashcraft 🐿️<p>The Future of AI: Evaluating and optimizing custom RAG agents using Azure AI Foundry</p><p><a href="https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/the-future-of-ai-evaluating-and-optimizing-custom-rag-agents-using-azure-ai-foun/4455215" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">techcommunity.microsoft.com/bl</span><span class="invisible">og/azure-ai-foundry-blog/the-future-of-ai-evaluating-and-optimizing-custom-rag-agents-using-azure-ai-foun/4455215</span></a></p><p><a href="https://hachyderm.io/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ai</span></a> <a href="https://hachyderm.io/tags/azure" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>azure</span></a> <a href="https://hachyderm.io/tags/cloud" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>cloud</span></a> <a href="https://hachyderm.io/tags/azureaifoundry" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>azureaifoundry</span></a> <a href="https://hachyderm.io/tags/rag" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>rag</span></a> <a href="https://hachyderm.io/tags/aiagents" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>aiagents</span></a></p>
Major Hayden 🤠<p>Wow, <a href="https://tootloop.com/tags/docling" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>docling</span></a> added support for Arabic and can handle complex documents with text that goes right to left!</p><p><a href="https://tootloop.com/tags/devconf_us" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>devconf_us</span></a> <a href="https://tootloop.com/tags/devconfus" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>devconfus</span></a> <a href="https://tootloop.com/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ai</span></a> <a href="https://tootloop.com/tags/rag" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>rag</span></a></p>
Major Hayden 🤠<p>Here's a recap of my <a href="https://tootloop.com/tags/devconf_us" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>devconf_us</span></a> talk from yesterday along with a link to slides and the recording:</p><p><a href="https://major.io/p/devconf-rag/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">major.io/p/devconf-rag/</span><span class="invisible"></span></a></p><p><a href="https://tootloop.com/tags/devconf" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>devconf</span></a> <a href="https://tootloop.com/tags/rag" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>rag</span></a> <a href="https://tootloop.com/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ai</span></a> <a href="https://tootloop.com/tags/presentation" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>presentation</span></a> <a href="https://tootloop.com/tags/talks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>talks</span></a></p>
Stefan Müller :verified:<p>Cool! So soll das sein. Nichts halluziniert. Wenn das Ding nichts weiß, dann sagt es auch nichts und es gibt Quellen!</p><p>Allerdings steht da irgendwo, dass es Dativ und Akkusativ gibt. Da muss ich noch weiterbasteln.</p><p><a href="https://climatejustice.social/tags/Hackaton" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Hackaton</span></a> <a href="https://climatejustice.social/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RAG</span></a> <a href="https://climatejustice.social/tags/KI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>KI</span></a></p>
techbash<p>You want AI? We've got some great AI sessions this year at TechBash. Rich Ross is presenting 2 great sessions on GraphRAG and GenAI architecture.</p><p>Register by 10/3 and save $100 on Standard registration with code LASTCALL100 - <a href="https://techbash.zohobackstage.com/techbash2025#/buyTickets?promoCode=LASTCALL100" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">techbash.zohobackstage.com/tec</span><span class="invisible">hbash2025#/buyTickets?promoCode=LASTCALL100</span></a> </p><p><a href="https://social.vivaldi.net/tags/devconference" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>devconference</span></a> <a href="https://social.vivaldi.net/tags/techbash" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>techbash</span></a> <a href="https://social.vivaldi.net/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ai</span></a> <a href="https://social.vivaldi.net/tags/rag" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>rag</span></a> <a href="https://social.vivaldi.net/tags/cloud" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>cloud</span></a> <a href="https://social.vivaldi.net/tags/techevent" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>techevent</span></a></p>
Technology Tales<p>5 creative RAG projects for beginners: Build with open-source models, create multimodal systems for PDFs with images/tables, develop on-device RAG with ObjectBox, construct real-time pipelines using Neo4j knowledge graphs, and implement agentic RAG with Llama-Index for multi-step reasoning. <a href="https://mstdn.social/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RAG</span></a> <a href="https://mstdn.social/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MachineLearning</span></a> <a href="https://mstdn.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://mstdn.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a> <a href="https://mstdn.social/tags/DataScience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DataScience</span></a> <a href="https://mstdn.social/tags/Python" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Python</span></a> <a href="https://mstdn.social/tags/BeginnerProjects" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>BeginnerProjects</span></a> <a href="https://mstdn.social/tags/TechTutorials" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TechTutorials</span></a> <a href="https://www.kdnuggets.com/5-fun-rag-projects-for-absolute-beginners" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">kdnuggets.com/5-fun-rag-projec</span><span class="invisible">ts-for-absolute-beginners</span></a></p>
Alex P Roe<p><span class="h-card" translate="no"><a href="https://mastodon.world/@ApostateEnglishman" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>ApostateEnglishman</span></a></span> <span class="h-card" translate="no"><a href="https://c.im/@dpnash" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>dpnash</span></a></span> <span class="h-card" translate="no"><a href="https://mastodon.green/@gerrymcgovern" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>gerrymcgovern</span></a></span> <a href="https://mastodon.world/tags/ChatGPT" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ChatGPT</span></a> now uses something called <a href="https://mastodon.world/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RAG</span></a> - which basically links to sources on the web - this reduces the probability of the <a href="https://mastodon.world/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a> making information up.</p>
Xavier Mareca<p>🚀 New LangChain Cheatsheet!<br>Build smarter LLM apps in Python with real examples:<br>✅ Chains &amp; Agents<br>✅ Memory &amp; Retrieval<br>✅ LangGraph<br>✅ API tools &amp; RAG</p><p>Code-ready, clean &amp; useful.<br>7-day thread starts tomorrow 🧠🧵</p><p><a href="https://mastodon.social/tags/LangChain" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LangChain</span></a> <a href="https://mastodon.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a> <a href="https://mastodon.social/tags/Python" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Python</span></a> <a href="https://mastodon.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://mastodon.social/tags/DataScience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DataScience</span></a> <a href="https://mastodon.social/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RAG</span></a> <a href="https://mastodon.social/tags/GenerativeAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GenerativeAI</span></a></p>
AI Sparkup<p><strong>GraphRAG로 AI가 드디어 ‘진짜 똑똑해졌다’ – 기업들이 열광하는 이유</strong></p> 기존 RAG의 한계를 극복한 GraphRAG 기술이 어떻게 작동하며, 실제 기업들이 어떤 성과를 내고 있는지, 그리고 우리 회사에서는 어떻게 도입할 수 있는지 실용적으로 설명한 완전 정복 가이드 <p><a href="https://aisparkup.com/posts/4652" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">aisparkup.com/posts/4652</span><span class="invisible"></span></a></p>
MottG<p>"Structuring PubMed Content into Knowledge Graphs for Enhanced Biomedical Intelligence"</p><p>This dissertation introduces the Genomic Literature Knowledge Base (GLKB), a large-scale biomedical knowledge graph curated from over 33 million PubMed articles. GLKB supports retrieval-augmented generation (RAG) methods that improve factuality and reduce hallucination. </p><p><a href="https://deepblue.lib.umich.edu/handle/2027.42/199147" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">deepblue.lib.umich.edu/handle/</span><span class="invisible">2027.42/199147</span></a></p><p>GLKB can be accessed at:</p><p><a href="https://glkb.dcmb.med.umich.edu/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">glkb.dcmb.med.umich.edu/</span><span class="invisible"></span></a></p><p><a href="https://researchbuzz.masto.host/tags/research" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>research</span></a> <a href="https://researchbuzz.masto.host/tags/medicine" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>medicine</span></a> <a href="https://researchbuzz.masto.host/tags/genomics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>genomics</span></a> <a href="https://researchbuzz.masto.host/tags/Pubmed" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Pubmed</span></a> <a href="https://researchbuzz.masto.host/tags/AItools" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AItools</span></a> <a href="https://researchbuzz.masto.host/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RAG</span></a></p>
Knut 🏳️‍🌈 🇳🇴🧸<p>If someone wants to <a href="https://mstdn.social/tags/rag" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>rag</span></a> the <a href="https://mstdn.social/tags/epstein" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>epstein</span></a> shit into an <a href="https://mstdn.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a> here ya go. I'm not going to poke through all of this. I'll wait for CNN to get me the juicies. :D <a href="https://drive.google.com/drive/folders/1TrGxDGQLDLZu1vvvZDBAh-e7wN3y6Hoz" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">drive.google.com/drive/folders</span><span class="invisible">/1TrGxDGQLDLZu1vvvZDBAh-e7wN3y6Hoz</span></a></p>
Benjamin Han<p>5/n</p><p>REFERENCES</p><p>[1] Orion Weller, Michael Boratko, Iftekhar Naim, and Jinhyuk Lee. 2025. On the theoretical limitations of embedding-based retrieval. <a href="https://arxiv.org/abs/2508.21038" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">arxiv.org/abs/2508.21038</span><span class="invisible"></span></a> </p><p>[2] Yifu Qiu, Varun Embar, Yizhe Zhang, Navdeep Jaitly, Shay B. Cohen, and Benjamin Han. 2025. Eliciting in-context Retrieval and reasoning for long-context large language models. <a href="https://machinelearning.apple.com/research/eliciting-in-context" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">machinelearning.apple.com/rese</span><span class="invisible">arch/eliciting-in-context</span></a> repo: <a href="https://github.com/apple/ml-icr2" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">github.com/apple/ml-icr2</span><span class="invisible"></span></a></p><p><a href="https://sigmoid.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://sigmoid.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a> <a href="https://sigmoid.social/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RAG</span></a> <a href="https://sigmoid.social/tags/Embeddings" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Embeddings</span></a> <a href="https://sigmoid.social/tags/Retrieval" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Retrieval</span></a> <a href="https://sigmoid.social/tags/RecSys" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RecSys</span></a> <a href="https://sigmoid.social/tags/Search" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Search</span></a> <a href="https://sigmoid.social/tags/AgenticAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AgenticAI</span></a> <a href="https://sigmoid.social/tags/paper" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>paper</span></a></p>
Benjamin Han<p>4/</p><p>4. Three ways out: (1) Cross-encoders—placing docs in the prompt of a Long-Context LM; accurate but costly. (2) Multi-vector retrieval. (3) Sparse retrieval.</p><p>For cross-encoders, this links directly to our earlier work on ICR² [2], where combining training data design with model re-architecting improved retrieval performance (see picture 4). Many other paths remain open!</p><p><a href="https://sigmoid.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://sigmoid.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a> <a href="https://sigmoid.social/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RAG</span></a> <a href="https://sigmoid.social/tags/Embeddings" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Embeddings</span></a> <a href="https://sigmoid.social/tags/Retrieval" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Retrieval</span></a> <a href="https://sigmoid.social/tags/RecSys" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RecSys</span></a> <a href="https://sigmoid.social/tags/Search" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Search</span></a> <a href="https://sigmoid.social/tags/AgenticAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AgenticAI</span></a> <a href="https://sigmoid.social/tags/paper" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>paper</span></a></p>
Benjamin Han<p>3/</p><p>3. LIMIT dataset: To stress-test real models, they construct the LIMIT dataset consisting of 50k docs and 1k queries, each with 2 relevant docs (picture1). All single-vector models fail badly, while BM25 and multi-vector methods perform much better (see picture 2).</p><p><a href="https://sigmoid.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://sigmoid.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a> <a href="https://sigmoid.social/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RAG</span></a> <a href="https://sigmoid.social/tags/Embeddings" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Embeddings</span></a> <a href="https://sigmoid.social/tags/Retrieval" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Retrieval</span></a> <a href="https://sigmoid.social/tags/RecSys" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RecSys</span></a> <a href="https://sigmoid.social/tags/Search" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Search</span></a> <a href="https://sigmoid.social/tags/AgenticAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AgenticAI</span></a> <a href="https://sigmoid.social/tags/paper" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>paper</span></a></p>
Benjamin Han<p>2/</p><p>2. Oracle experiment: They empirically confirm this bound by directly optimizing embeddings (“free embeddings”) against the relevance matrix. The critical corpus size grows only cubically with dimension. For example, with embedding dimension d = 1024, you can only represent all possible 2-doc query combinations up to about 4 million documents — far below typical web-scale retrieval needs.</p><p><a href="https://sigmoid.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://sigmoid.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a> <a href="https://sigmoid.social/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RAG</span></a> <a href="https://sigmoid.social/tags/Embeddings" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Embeddings</span></a> <a href="https://sigmoid.social/tags/Retrieval" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Retrieval</span></a> <a href="https://sigmoid.social/tags/RecSys" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RecSys</span></a> <a href="https://sigmoid.social/tags/Search" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Search</span></a> <a href="https://sigmoid.social/tags/AgenticAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AgenticAI</span></a> <a href="https://sigmoid.social/tags/paper" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>paper</span></a></p>
Benjamin Han<p>1/</p><p>Embeddings are the beating heart of modern AI—powering RAG and serving as memory for agentic AI. But a new paper [1] shows a ceiling:</p><p>1. Dot-product retrieval is bounded by embedding dimension d; if the relevance matrix has sign-rank r, then d &gt;= r is required—and no amount of training can avoid it.</p><p><a href="https://sigmoid.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://sigmoid.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a> <a href="https://sigmoid.social/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RAG</span></a> <a href="https://sigmoid.social/tags/Embeddings" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Embeddings</span></a> <a href="https://sigmoid.social/tags/Retrieval" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Retrieval</span></a> <a href="https://sigmoid.social/tags/RecSys" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RecSys</span></a> <a href="https://sigmoid.social/tags/Search" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Search</span></a> <a href="https://sigmoid.social/tags/AgenticAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AgenticAI</span></a> <a href="https://sigmoid.social/tags/paper" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>paper</span></a></p>
Robbie<p>Tired of your knowledge base being a static, dumb folder of Markdown files? I built `vault-mcp` to fix that.</p><p>It's a local RAG server that watches your notes and live-syncs changes using a file-level Merkle tree (so it only re-indexes what's new).</p><p>You can query in "static" mode (fast, full-section context) or "agentic" mode (LLM rewrites chunks for clarity).</p><p>Full write-up + quick-start:<br><a href="https://selfenrichment.hashnode.dev/vault-mcp-a-scrappy-self-updating-rag-server-for-your-markdown-hoard" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">selfenrichment.hashnode.dev/va</span><span class="invisible">ult-mcp-a-scrappy-self-updating-rag-server-for-your-markdown-hoard</span></a><br><a href="https://mastodon.social/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RAG</span></a> <a href="https://mastodon.social/tags/Python" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Python</span></a> <a href="https://mastodon.social/tags/OpenSource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OpenSource</span></a> <a href="https://mastodon.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://mastodon.social/tags/SelfHosting" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SelfHosting</span></a></p>
Joe Cotellese<p>New fav AI tool: Google NotebookLM. I can upload research papers and get an instant expert to chat with. Yes it’s <a href="https://jawns.club/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RAG</span></a> but with extra goodies. Generate mindmaps, exec overviews, video explainers and podcasts. Have Google Workspaces account? You may already have access.</p><p><a href="https://jawns.club/tags/generativeai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>generativeai</span></a> <a href="https://jawns.club/tags/ml" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ml</span></a></p>
Deutschland<p><a href="https://www.europesays.com/de/354088/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="">europesays.com/de/354088/</span><span class="invisible"></span></a> Neue Azubis in Essen bei Ruhrkohle AG #"GuteNachrichten"] #"Lokalnachrichten" #"NeueAzubis"] <a href="https://pubeurope.com/tags/Ausbildung" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Ausbildung</span></a> <a href="https://pubeurope.com/tags/DE" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DE</span></a> <a href="https://pubeurope.com/tags/Deutschland" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Deutschland</span></a> <a href="https://pubeurope.com/tags/Essen" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Essen</span></a> <a href="https://pubeurope.com/tags/Germany" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Germany</span></a> <a href="https://pubeurope.com/tags/NordrheinWestfalen" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NordrheinWestfalen</span></a> <a href="https://pubeurope.com/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RAG</span></a></p>
infoDOCKET<p>Research Article (preprint): “A Systematic Literature Review of Retrieval-Augmented Generation: Techniques, Metrics, and Challenges” <a href="https://www.infodocket.com/2025/08/11/research-article-preprint-a-systematic-literature-review-of-retrieval-augmented-generation-techniques-metrics-and-challenges/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">infodocket.com/2025/08/11/rese</span><span class="invisible">arch-article-preprint-a-systematic-literature-review-of-retrieval-augmented-generation-techniques-metrics-and-challenges/</span></a> <a href="https://newsie.social/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RAG</span></a> <a href="https://newsie.social/tags/LLMs" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLMs</span></a> <a href="https://newsie.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a></p>
TrendingLive feeds
About