101010.pl is one of the many independent Mastodon servers you can use to participate in the fediverse.
101010.pl czyli najstarszy polski serwer Mastodon. Posiadamy wpisy do 2048 znaków.

Server stats:

521
active users

#retrievalaugmentedgeneration

0 posts0 participants0 posts today
Brandon H :csharp: :verified:<p>via <span class="h-card" translate="no"><a href="https://dotnet.social/@dotnet" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>dotnet</span></a></span> : .NET AI Template Now Available in Preview</p><p><a href="https://ift.tt/BuZJmRp" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">ift.tt/BuZJmRp</span><span class="invisible"></span></a><br><a href="https://hachyderm.io/tags/DotNet" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DotNet</span></a> <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/ChatTemplate" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ChatTemplate</span></a> <a href="https://hachyderm.io/tags/AIDevelopment" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AIDevelopment</span></a> <a href="https://hachyderm.io/tags/VisualStudio" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>VisualStudio</span></a> <a href="https://hachyderm.io/tags/VisualStudioCode" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>VisualStudioCode</span></a> <a href="https://hachyderm.io/tags/DotNetCLI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DotNetCLI</span></a> <a href="https://hachyderm.io/tags/Blazor" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Blazor</span></a> <a href="https://hachyderm.io/tags/ChatApplication" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ChatApplication</span></a> <a href="https://hachyderm.io/tags/RetrievalAugmentedGeneration" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RetrievalAugmentedGeneration</span></a> <a href="https://hachyderm.io/tags/AzureAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AzureAI</span></a> <a href="https://hachyderm.io/tags/DataIngestion" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DataIngestion</span></a> <a href="https://hachyderm.io/tags/CSharp" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CSharp</span></a> <a href="https://hachyderm.io/tags/Coding" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Coding</span></a> <a href="https://hachyderm.io/tags/Tec" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Tec</span></a>…</p>
Brandon H :csharp: :verified:<p>via <span class="h-card" translate="no"><a href="https://dotnet.social/@dotnet" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>dotnet</span></a></span> : Announcing Chroma DB C# SDK</p><p><a href="https://ift.tt/UXHGRPJ" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">ift.tt/UXHGRPJ</span><span class="invisible"></span></a><br><a href="https://hachyderm.io/tags/ChromaDB" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ChromaDB</span></a> <a href="https://hachyderm.io/tags/CSharpSDK" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CSharpSDK</span></a> <a href="https://hachyderm.io/tags/AIApplications" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AIApplications</span></a> <a href="https://hachyderm.io/tags/DotNet" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DotNet</span></a> <a href="https://hachyderm.io/tags/SemanticSearch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SemanticSearch</span></a> <a href="https://hachyderm.io/tags/VectorSearch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>VectorSearch</span></a> <a href="https://hachyderm.io/tags/OpenSource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OpenSource</span></a> <a href="https://hachyderm.io/tags/Database" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Database</span></a> <a href="https://hachyderm.io/tags/RetrievalAugmentedGeneration" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RetrievalAugmentedGeneration</span></a> <a href="https://hachyderm.io/tags/ChromaClient" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ChromaClient</span></a> <a href="https://hachyderm.io/tags/NuGet" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NuGet</span></a> <a href="https://hachyderm.io/tags/Docker" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Docker</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/DataCommunity" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DataCommunity</span></a> <a href="https://hachyderm.io/tags/Developers" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Developers</span></a> <a href="https://hachyderm.io/tags/TechAn" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TechAn</span></a>…</p>
ndocist<p>Semantic Scholar<br>et Washington University ont développé un nouveau <a href="https://oc.todon.fr/tags/discoverytool" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>discoverytool</span></a> basé sur une <a href="https://oc.todon.fr/tags/ArtificialInteligence" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ArtificialInteligence</span></a> qui exploite un corpus documentaire scientifique <a href="https://oc.todon.fr/tags/RetrievalAugmentedGeneration" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RetrievalAugmentedGeneration</span></a> pour gérer l'inflation éditoriale <br>Testé avec un panel de scientifiques <br><a href="https://oc.todon.fr/tags/opensource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>opensource</span></a></p><p><a href="https://www.infodocket.com/2024/11/19/research-tools-prototype-university-of-washington-and-the-allen-institute-for-ai-the-people-behind-semantic-scholar-announce-launch-of-ai2-open-scholar/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">infodocket.com/2024/11/19/rese</span><span class="invisible">arch-tools-prototype-university-of-washington-and-the-allen-institute-for-ai-the-people-behind-semantic-scholar-announce-launch-of-ai2-open-scholar/</span></a></p>
Python Ireland<p>Have you seen the schedule for PyCon Ireland 2024?</p><p>Check out the schedule and book your ticket here: <br><a href="https://python.ie/pycon-2024/schedule/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">python.ie/pycon-2024/schedule/</span><span class="invisible"></span></a></p><p> <a href="https://mastodon.social/tags/PyConIE" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PyConIE</span></a> <a href="https://mastodon.social/tags/PyCon" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PyCon</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/Workshop" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Workshop</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/WebDev" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>WebDev</span></a> <a href="https://mastodon.social/tags/RetrievalAugmentedGeneration" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RetrievalAugmentedGeneration</span></a></p>
Nicolai Brodersen Hansen<p>My students are exploring <a href="https://hci.social/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ai</span></a> this semester, and while I have shown them some <a href="https://hci.social/tags/retrievalaugmentedgeneration" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>retrievalaugmentedgeneration</span></a> basics in like LM Studio, they understandably aren't very impressed. Is there any good open source or even commercial solutions that are sort of plug and play? These are not super technical students hence the question.</p>
IT News<p>Can a technology called RAG keep AI models from making stuff up? - Enlarge (credit: Aurich Lawson | Getty Images) </p><p>We’ve been livi... - <a href="https://arstechnica.com/?p=2028618" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">arstechnica.com/?p=2028618</span><span class="invisible"></span></a> <a href="https://schleuss.online/tags/retrievalaugmentedgeneration" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>retrievalaugmentedgeneration</span></a> <a href="https://schleuss.online/tags/artificialinteligence" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>artificialinteligence</span></a> <a href="https://schleuss.online/tags/confabulation" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>confabulation</span></a> <a href="https://schleuss.online/tags/generativeai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>generativeai</span></a> <a href="https://schleuss.online/tags/features" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>features</span></a> <a href="https://schleuss.online/tags/llms" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>llms</span></a> <a href="https://schleuss.online/tags/rag" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>rag</span></a> <a href="https://schleuss.online/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ai</span></a></p>
Mark Carrigan<p>As AI-generated content proliferates, leading to a degradation of online information reliability, AI search algorithms and conversational agents will increasingly rely on high-prestige sources to mitigate the risk of amplifying misinformation. Retrieval augmented generation (RAG) positions the existing web as a ground truth which can ensure the reliability of responses, while the mainstreaming of generative AI is simultaneously eroding that reliability at an accelerating rate. The result is that the relative value of existing high prestige sources will increase on social media and in search, standing out from a growing swamp of GAI-infused or GAI-created detritus. </p><p></p><p><a href="https://markcarrigan.net/2024/05/29/how-the-interaction-of-ai-search-social-media-and-generative-ai-will-entrench-existing-status-hierarchies/" class="" rel="nofollow noopener" target="_blank">https://markcarrigan.net/2024/05/29/how-the-interaction-of-ai-search-social-media-and-generative-ai-will-entrench-existing-status-hierarchies/</a></p><p><a rel="nofollow noopener" class="hashtag u-tag u-category" href="https://markcarrigan.net/tag/expertise/" target="_blank">#expertise</a> <a rel="nofollow noopener" class="hashtag u-tag u-category" href="https://markcarrigan.net/tag/generative-ai/" target="_blank">#generativeAI</a> <a rel="nofollow noopener" class="hashtag u-tag u-category" href="https://markcarrigan.net/tag/prestige/" target="_blank">#prestige</a> <a rel="nofollow noopener" class="hashtag u-tag u-category" href="https://markcarrigan.net/tag/retrieval-augmented-generation/" target="_blank">#retrievalAugmentedGeneration</a> <a rel="nofollow noopener" class="hashtag u-tag u-category" href="https://markcarrigan.net/tag/social-media/" target="_blank">#SocialMedia</a></p>
Jon Udell<p>I first learned about the pattern now called Retrieval Augmented Generation from (of course) <span class="h-card" translate="no"><a href="https://fedi.simonwillison.net/@simon" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>simon</span></a></span>: find chunks of documentation relevant to a question, and use them to augment an LLM's general knowledge.</p><p><span class="h-card" translate="no"><a href="https://indieweb.social/@bigdata" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>bigdata</span></a></span> points to this article (via <a href="https://thedataexchange.media/navigating-the-nuances-of-retrieval-augmented-generation/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">thedataexchange.media/navigati</span><span class="invisible">ng-the-nuances-of-retrieval-augmented-generation/</span></a>) as an essential guide: <br><a href="https://www.anyscale.com/blog/a-comprehensive-guide-for-building-rag-based-llm-applications-part-1" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">anyscale.com/blog/a-comprehens</span><span class="invisible">ive-guide-for-building-rag-based-llm-applications-part-1</span></a></p><p>That's for the DIY crowd. I expect there are (or soon will be) build-vs-buy options, and am curious to know more about that.</p><p><a href="https://social.coop/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a> <a href="https://social.coop/tags/RetrievalAugmentedGeneration" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RetrievalAugmentedGeneration</span></a> <a href="https://social.coop/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RAG</span></a></p>