<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title><![CDATA[RSS Feed]]></title><description><![CDATA[RSS Feed]]></description><link>http://direct.ecency.com</link><image><url>http://direct.ecency.com/logo512.png</url><title>RSS Feed</title><link>http://direct.ecency.com</link></image><generator>RSS for Node</generator><lastBuildDate>Sun, 12 Apr 2026 15:35:52 GMT</lastBuildDate><atom:link href="http://direct.ecency.com/created/embedding/rss.xml" rel="self" type="application/rss+xml"/><item><title><![CDATA[Chroma向量数据库完全手册(更新) / ai #38]]></title><description><![CDATA[Chroma 向量数据库 Chroma 基本使用 Chroma embedding Chroma docker docker权限认证 修改docker的配置 langchain中的使用 添加文本 更新和删除数据 相关度数值检索 metadata数据过滤 直接存入数据库和查询 httpClient 向量数据库 Chroma github | 文档 | chroma使用指南 | 参考 ｜ 过滤条件 ｜]]></description><link>http://direct.ecency.com/hive-105017/@lemooljiang/h94tmfd7</link><guid isPermaLink="true">http://direct.ecency.com/hive-105017/@lemooljiang/h94tmfd7</guid><category><![CDATA[hive-105017]]></category><dc:creator><![CDATA[lemooljiang]]></dc:creator><pubDate>Fri, 15 Nov 2024 10:14:09 GMT</pubDate><enclosure url="https://images.ecency.com/p/7ohP4GDMGPrUMp8dW718tJBTEaJiCZqta5CwEEUk1XQ5c5strK8PYX6MF8TAkZiWVpDsy1QVY4FQYwgNH9PmnFdyTfUmH1C67mzE?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[Are you present(ing)?]]></title><description><![CDATA[While in the PYPT after party last night @alessandrawhite was checking in about how to post a presentation on Hive, specifically a presentation made in Canva. @shadowspub suggested, from her own experience]]></description><link>http://direct.ecency.com/proofofbrain/@brijwhiz/are-you-presenting</link><guid isPermaLink="true">http://direct.ecency.com/proofofbrain/@brijwhiz/are-you-presenting</guid><category><![CDATA[proofofbrain]]></category><dc:creator><![CDATA[brijwhiz]]></dc:creator><pubDate>Fri, 26 Apr 2024 06:52:45 GMT</pubDate><enclosure url="https://images.ecency.com/p/3DLAmCsuTe3ba2VJAE1ZhN2oVhekeqoshg9DUnSyUd2Cnt4YtUMpZp3rMBtMsxqzBQsVX9AXtpaFhsm6WDDRafCVzqRtiEKV8gn4AjK8AqvmGuhgnCVwrkz1Vot6aLenvcnCC2xKBhAq4fqnoN7oQuwuXFD4Q46?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[【大伟说AI】什么是AI？什么是大模型？]]></title><description><![CDATA[AI之所以这么智能，就是因为它背后有大模型这个聪明的大脑袋。 　　 　　而大模型之所以这么聪明，上知天文，下知地理，会中文，懂外语，文武双全，无所不能，主要取决于以下两个方面因素： 　　 　　一是大模型的训练参数。 　　 　　二是Embedding。 　　 　　训练参数，是指大模型训练时的最多参数，一般目前从百亿，到千亿，甚至上万亿参数，据说最新即将发布的gpt5的训练参数更是高达上十万亿。]]></description><link>http://direct.ecency.com/hive-105017/@rivalhw/v44uk-ai</link><guid isPermaLink="true">http://direct.ecency.com/hive-105017/@rivalhw/v44uk-ai</guid><category><![CDATA[hive-105017]]></category><dc:creator><![CDATA[rivalhw]]></dc:creator><pubDate>Wed, 10 Apr 2024 03:46:27 GMT</pubDate><enclosure url="https://images.ecency.com/p/PB8ro82ZpZP35bVGjGoE93K3E4U5KX8KtMBJ2rgxwcjS7HECMcxfw1DfMRzbs8rELfK6xtSBFjzeDRooewdjzJVECVqQPnFJWMdzr39PkWAQHkgv?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[百川向量算法与LangChain的集成/ ai #34]]></title><description><![CDATA[随着国内大模型的发展，有些大模型的功能已开始向OpenAI靠拢了，其中向量算法就是其中之一。去年在做向量数据库的测试和部署时就没有发现足够好用的国产向量算法，只得采用OpenAI的向量算法。现在，向量算法完全可以转向国内的算法啰，百川的向量算法就很不错。 在实际的应用中，一般会与LangChain进行集成，开发出你需要的应用或是agent。下面是集成的向量存储和查询代码，大家可以做些参考。 pip]]></description><link>http://direct.ecency.com/hive-105017/@lemooljiang/cchv4mdq</link><guid isPermaLink="true">http://direct.ecency.com/hive-105017/@lemooljiang/cchv4mdq</guid><category><![CDATA[hive-105017]]></category><dc:creator><![CDATA[lemooljiang]]></dc:creator><pubDate>Thu, 04 Apr 2024 13:46:00 GMT</pubDate><enclosure url="https://images.ecency.com/p/7ohP4GDMGPrUMp8dW718tJBTEaJiCZqta5CwEEUjzdkY35Yk6awCTA9sxm8hBmEA5uGUkAQpNwTkh8vmziVxatQ5znqBNpaKNeTK?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[向量模型大比拼，如何获取关联性 / ai #20]]></title><description><![CDATA[在本地知识库的构建中，其中重要的一环是对文本的向量计算，然后存入数据库备查。在这种知识库的项目中除了知识文本的重要性之外，向量计算几乎占据了绝大多数的比重，可以说：成败在此计算。 现在比较流行的有三个向量计算库：OpenAIEmbeddings、shibing624/text2vec-base-chinese和GanymedeNil/text2vec-large-chinese。接下来就实际测试下看看。]]></description><link>http://direct.ecency.com/hive-105017/@lemooljiang/pxg3achi</link><guid isPermaLink="true">http://direct.ecency.com/hive-105017/@lemooljiang/pxg3achi</guid><category><![CDATA[hive-105017]]></category><dc:creator><![CDATA[lemooljiang]]></dc:creator><pubDate>Mon, 21 Aug 2023 11:30:51 GMT</pubDate><enclosure url="https://images.ecency.com/p/7ohP4GDMGPrUMp8dW718tJBTEaJiCZqta5CwEEUjyf2jui5fmu6k28HGhi1kvc9uQYthpuzdi531YW4c2Z8D4hMqtzfVmviop6MM?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[Chroma向量数据库完全手册 / ai #19]]></title><description><![CDATA[这里算是做一个汇总，以及对它的细节做补充。Chroma向量数据库具备传统数据库所有的功能，还有它自身独特的特点。它还在不断的开发完善，在使用中也略有bug。 在项目中，我们可能不是单独使用，而是和langchain这样的工具一起使用，所以，在项目中，它们会结合在一起。 向量数据库 Chroma简介 bug 基本使用 Chroma embedding Chroma docker langchain中的使用]]></description><link>http://direct.ecency.com/hive-105017/@lemooljiang/cenguclk</link><guid isPermaLink="true">http://direct.ecency.com/hive-105017/@lemooljiang/cenguclk</guid><category><![CDATA[hive-105017]]></category><dc:creator><![CDATA[lemooljiang]]></dc:creator><pubDate>Fri, 18 Aug 2023 11:35:45 GMT</pubDate><enclosure url="https://images.ecency.com/p/7ohP4GDMGPrUMp8dW718tJBTEaJiCZqta5CwEEUk1urP587pgy5kK2PHs1nagkSxpfZTaa6eHNfXWt7muhwQErDd8oBp9s4CUDs9?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[Chroma文本相拟度检索 / ai #18]]></title><description><![CDATA[向量数据库的查询并不复杂，简单几条命令就可以搞定。而且，向量数据库的使用和传统数据库的使用逻辑相差不大，都是增删改查这一套。唯一有不同的就是向量计算和检索这块。 先简单来下Chroma在langchain中的检索： from langchain.vectorstores import Chroma import sentence_transformers from]]></description><link>http://direct.ecency.com/hive-105017/@lemooljiang/fsfcf54c</link><guid isPermaLink="true">http://direct.ecency.com/hive-105017/@lemooljiang/fsfcf54c</guid><category><![CDATA[hive-105017]]></category><dc:creator><![CDATA[lemooljiang]]></dc:creator><pubDate>Sun, 30 Jul 2023 13:20:39 GMT</pubDate><enclosure url="https://images.ecency.com/p/7ohP4GDMGPrUMp8dW718tJBTEaJiCZqta5CwEEUk1urP587pgy5kK2PHs1nagkSxpfZTaa6eHNfXWt7muhwQErDd8oBp9s4CUDs9?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[适合的才是最好的：几款不同AI向量数据库对比感受]]></title><description><![CDATA[最近在学习跟AI相关，说到AI，自然避免不了要使用到向量数据库，今天我就拿市面上几款向量数据库做下对比，也来谈下自己粗浅的感受吧。 Google上对向量数据库的解释如下，]]></description><link>http://direct.ecency.com/hive-105017/@rivalhw/2fdqij-ai</link><guid isPermaLink="true">http://direct.ecency.com/hive-105017/@rivalhw/2fdqij-ai</guid><category><![CDATA[hive-105017]]></category><dc:creator><![CDATA[rivalhw]]></dc:creator><pubDate>Wed, 12 Jul 2023 05:02:00 GMT</pubDate><enclosure url="https://images.ecency.com/p/PB8ro82ZpZP35bVGjGoE93K3E4U5KX8KtMBJ2rh4qnYrP34bYyyLAKMQmgBhKwVLTnEQ63KrNjH4ytYSfiH55BfrT2SYKpJ9P1Pg9qH4Cy6goZfC?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[如何使ChatGPT成为俄乌"砖家" / ai #6]]></title><description><![CDATA[参考： youtube-gpt | Chatbot 我们都知道现阶段ChatGPT的数据是只到2021年，之后的事情它就不知道了。那么，怎么解决这个问题呢？同样，在特别专门的领域，如何使ChatGPT更专业呢？这时，嵌入（Embeddings）就要出场了。]]></description><link>http://direct.ecency.com/hive-105017/@lemooljiang/q7317fl2</link><guid isPermaLink="true">http://direct.ecency.com/hive-105017/@lemooljiang/q7317fl2</guid><category><![CDATA[hive-105017]]></category><dc:creator><![CDATA[lemooljiang]]></dc:creator><pubDate>Sat, 11 Mar 2023 10:12:27 GMT</pubDate><enclosure url="https://images.ecency.com/p/7ohP4GDMGPrUMp8dW718tJBTEaJiCZqta5CwEEUk1CA9AfVZSLFVncAVFCXKkJd8tcUB6hCSAhpknU9AxMa9HX8runuTYkPgTKie?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[Can Steem blogs be embedded into websites?]]></title><description><![CDATA[Green greetings Steemians, I just wanted to know if it’s possible to link my steem blog to my organizational website so that each time I blog on Steem, it appears on my organization’s website as a blog]]></description><link>http://direct.ecency.com/steem/@thegreens/can-steem-blogs-be-embedded-into-websites</link><guid isPermaLink="true">http://direct.ecency.com/steem/@thegreens/can-steem-blogs-be-embedded-into-websites</guid><category><![CDATA[steem]]></category><dc:creator><![CDATA[thegreens]]></dc:creator><pubDate>Sun, 12 Jan 2020 20:12:12 GMT</pubDate><enclosure url="https://images.ecency.com/p/7ohP4GDMGPrU6KTuuW27axCzEyjZonWtNibTWSX2VjAC8vxecq51Ep3XnuzqXHJA7APpk2X1j97SiwkB6NGwFU7YPLktLpuUn1c2?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[Proses Pengekleman Kertas]]></title><description><![CDATA[Para Pekerja Terlihat sedang melakukan Pekerjaan nya dalam proses kerja Pengekleman Kertas Plastik Kertas Plastik ini digunakan sebagai Pelapisan atas Tanah, agar Air dalam Tambak tidak Meresab kedalam]]></description><link>http://direct.ecency.com/esteem/@sainiulma/proses-pengekleman-kertas-a0f57c9d7b2ab</link><guid isPermaLink="true">http://direct.ecency.com/esteem/@sainiulma/proses-pengekleman-kertas-a0f57c9d7b2ab</guid><category><![CDATA[esteem]]></category><dc:creator><![CDATA[sainiulma]]></dc:creator><pubDate>Sat, 14 Apr 2018 06:03:15 GMT</pubDate><enclosure url="https://images.ecency.com/p/o1AJ9qDyyJNSpZWhUgGYc3MngFqoAN2m6nAqk9duvBYxh5cKg?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[Modern architecture in the 21st century]]></title><description><![CDATA[The term "modernity" refers to various trends, some of which merge into one another and often cannot be clearly distinguished from each other, such as the Bauhaus style, Expressionism or New]]></description><link>http://direct.ecency.com/development/@antonia.ryan/modern-architecture-in-the-21st-century</link><guid isPermaLink="true">http://direct.ecency.com/development/@antonia.ryan/modern-architecture-in-the-21st-century</guid><category><![CDATA[development]]></category><dc:creator><![CDATA[antonia.ryan]]></dc:creator><pubDate>Tue, 06 Feb 2018 22:34:12 GMT</pubDate><enclosure url="https://images.ecency.com/p/MG5aEqKFcQi5xsGsUDYUN1LNu9Qi8onYittfhSMCpK247CjiYRrg9SJkfCDXQbQiCQ1fn9s6sccTowS6vd7cXqkkojfuUE5KC?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[Linking to Videos in facebook.]]></title><description><![CDATA[Click on ... Click on </> embed Copy the URL (in blue) and eliminate the tag information and clean it so it looks like this: It is possible to make it pretty by doing a print screen or have an image]]></description><link>http://direct.ecency.com/steemit/@dwarrilow2002/linking-to-videos-in-facebook</link><guid isPermaLink="true">http://direct.ecency.com/steemit/@dwarrilow2002/linking-to-videos-in-facebook</guid><category><![CDATA[steemit]]></category><dc:creator><![CDATA[dwarrilow2002]]></dc:creator><pubDate>Fri, 02 Feb 2018 12:10:30 GMT</pubDate><enclosure url="https://images.ecency.com/p/2gsjgna1uruvUuS7ndh9YqVwYGPLVszbFLwwpAYXYgzEKYT1H4bUCsLCrmeLAXzED1cb4Q2fopDuAzYSMpAx6dP2RdoMonZJHLdfV4Mw2dkNcy7sFc?format=match&amp;mode=fit" length="0" type="false"/></item><item><title><![CDATA[Embed Test]]></title><description><![CDATA[Seems to be working on Esteem mobile app but not yet any mobile browsers like Google Chrome or the native Android mobile browser.]]></description><link>http://direct.ecency.com/browser/@phusionphil/embed-test-2017927t54932751z</link><guid isPermaLink="true">http://direct.ecency.com/browser/@phusionphil/embed-test-2017927t54932751z</guid><category><![CDATA[browser]]></category><dc:creator><![CDATA[phusionphil]]></dc:creator><pubDate>Wed, 27 Sep 2017 11:49:36 GMT</pubDate></item><item><title><![CDATA[Experimenting with embedding pictures shows curious results]]></title><description><![CDATA[My first question is where are embedded content like photos or videos stored? Are they on the server where the content originally sits making only a link or sitting on the blockchain? My initial experiment]]></description><link>http://direct.ecency.com/embedding/@michaeldodridge/experimenting-with-embedding-pictures-shows-curious-results</link><guid isPermaLink="true">http://direct.ecency.com/embedding/@michaeldodridge/experimenting-with-embedding-pictures-shows-curious-results</guid><category><![CDATA[embedding]]></category><dc:creator><![CDATA[michaeldodridge]]></dc:creator><pubDate>Wed, 27 Jul 2016 07:10:06 GMT</pubDate></item><item><title><![CDATA[Embedding video and copyright]]></title><description><![CDATA[It seems there is fair use senarios regarding copyright. From what I can gather to sample a few seconds is reasonable but to play the whole video would seem not. This would make embedding a video created]]></description><link>http://direct.ecency.com/embedding/@michaeldodridge/embedding-video-and-copyright</link><guid isPermaLink="true">http://direct.ecency.com/embedding/@michaeldodridge/embedding-video-and-copyright</guid><category><![CDATA[embedding]]></category><dc:creator><![CDATA[michaeldodridge]]></dc:creator><pubDate>Wed, 27 Jul 2016 00:21:27 GMT</pubDate></item><item><title><![CDATA[Steemit Protocolo or etiquette with YouTube embedding?]]></title><description><![CDATA[If you find a great YouTube video but it's not your content but would enhance your post what is the Steemit etiquette regarding embedding? Is it acceptable if you credit the source?]]></description><link>http://direct.ecency.com/embedding/@michaeldodridge/steemit-protocolo-or-etiquette-with-youtube-embedding</link><guid isPermaLink="true">http://direct.ecency.com/embedding/@michaeldodridge/steemit-protocolo-or-etiquette-with-youtube-embedding</guid><category><![CDATA[embedding]]></category><dc:creator><![CDATA[michaeldodridge]]></dc:creator><pubDate>Tue, 26 Jul 2016 21:55:06 GMT</pubDate></item></channel></rss>