Harald Klinke<p>Neo4j treibt mit GraphRAG, Vektor-Indizes & Agentic RAG die <a href="https://det.social/tags/KI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>KI</span></a>-Entwicklung voran. Ob <a href="https://det.social/tags/LangChain" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LangChain</span></a>, <a href="https://det.social/tags/LlamaIndex" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LlamaIndex</span></a>, <a href="https://det.social/tags/SpringAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpringAI</span></a> oder <a href="https://det.social/tags/VertexAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>VertexAI</span></a> – das neue Python-Paket und das Model Context Protocol (MCP) verknüpfen Graphdaten nahtlos mit <a href="https://det.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a>-Anwendungen.<br><a href="https://det.social/tags/Neo4j" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Neo4j</span></a> <a href="https://det.social/tags/GenAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GenAI</span></a> <a href="https://det.social/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RAG</span></a> <a href="https://det.social/tags/GraphQL" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GraphQL</span></a> <a href="https://det.social/tags/Cypher" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Cypher</span></a> <a href="https://det.social/tags/VectorSearch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>VectorSearch</span></a> <a href="https://det.social/tags/AgenticAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AgenticAI</span></a><br><a href="https://www.bigdata-insider.de/leistungssprung-bei-graph-datenbanken-mit-ki-integration-cloud-skalierung-und-terabyte-graphen-a-2307ed20cfaf562a1a0094b712b5be95/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">bigdata-insider.de/leistungssp</span><span class="invisible">rung-bei-graph-datenbanken-mit-ki-integration-cloud-skalierung-und-terabyte-graphen-a-2307ed20cfaf562a1a0094b712b5be95/</span></a></p>
mastodon.ie is one of the many independent Mastodon servers you can use to participate in the fediverse.
Irish Mastodon - run from Ireland, we welcome all who respect the community rules and members.
Administered by:
Server stats:
1.6Kactive users
mastodon.ie: About · Profiles directory · Privacy policy
Mastodon: About · Get the app · Keyboard shortcuts · View source code · v4.4.2
#llamaindex
0 posts · 0 participants · 0 posts today
Markus Eisele<p>🔥 Docling: AI-powered document processing! 🔥<br>🤯 PDFs & DOCXs in your AI workflow? Docling makes it easy! Converts to markdown & JSON for RAG and more. Blazing fast! 🚀</p><p><a href="https://youtu.be/zSCxbqgqeJ8?si=mede5eJL_iGRFwAJ" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">youtu.be/zSCxbqgqeJ8?si=mede5e</span><span class="invisible">JL_iGRFwAJ</span></a></p><p><a href="https://mastodon.online/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://mastodon.online/tags/Docling" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Docling</span></a> <a href="https://mastodon.online/tags/DocumentProcessing" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DocumentProcessing</span></a> <a href="https://mastodon.online/tags/OpenSource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OpenSource</span></a> <a href="https://mastodon.online/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RAG</span></a> <a href="https://mastodon.online/tags/LlamaIndex" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LlamaIndex</span></a> <a href="https://mastodon.online/tags/Efficiency" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Efficiency</span></a> <a href="https://mastodon.online/tags/Workflows" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Workflows</span></a></p>
Ferdinando Simonetti <p><span>[ A story from Plaban Nayak on Medium ]<br>Read this story from Plaban Nayak on Medium: </span><a href="https://medium.com/the-ai-forum/multi-document-agentic-rag-using-llama-index-and-mistral-b334fa45d3ee" rel="nofollow noopener" target="_blank">https://medium.com/the-ai-forum/multi-document-agentic-rag-using-llama-index-and-mistral-b334fa45d3ee</a> <a href="https://misskey.social/tags/RAG" rel="nofollow noopener" target="_blank">#RAG</a> <a href="https://misskey.social/tags/Agent" rel="nofollow noopener" target="_blank">#Agent</a> <a href="https://misskey.social/tags/LlamaIndex" rel="nofollow noopener" target="_blank">#LlamaIndex</a> <a href="https://misskey.social/tags/Mistral" rel="nofollow noopener" target="_blank">#Mistral</a></p>
Ferdinando Simonetti <p><span>[ cookbook/llamaindex_agentic_rag.ipynb at main · mistralai/cookbook · GitHub ]<br></span><a href="https://github.com/mistralai/cookbook/blob/main/llamaindex_agentic_rag.ipynb" rel="nofollow noopener" target="_blank">https://github.com/mistralai/cookbook/blob/main/llamaindex_agentic_rag.ipynb</a> <a href="https://misskey.social/tags/MistralAI" rel="nofollow noopener" target="_blank">#MistralAI</a> <a href="https://misskey.social/tags/LlamaIndex" rel="nofollow noopener" target="_blank">#LlamaIndex</a></p>
Sharon Machlis<p>If you use LlamaIndex in your generative AI applications, there are some breaking changes in version 0.10 (as I discovered this weekend)</p><p>Project blog post: <a href="https://blog.llamaindex.ai/llamaindex-v0-10-838e735948f8" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">blog.llamaindex.ai/llamaindex-</span><span class="invisible">v0-10-838e735948f8</span></a><br>Jerry Liu video <a href="https://youtu.be/swJsw9Jvgoc?si=qKXkGRdqt-dIi2o7" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">youtu.be/swJsw9Jvgoc?si=qKXkGR</span><span class="invisible">dqt-dIi2o7</span></a></p><p><a href="https://masto.machlis.com/tags/LlamaIndex" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LlamaIndex</span></a> <a href="https://masto.machlis.com/tags/GenAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GenAI</span></a> <a href="https://masto.machlis.com/tags/GenerativeAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GenerativeAI</span></a> <a href="https://masto.machlis.com/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RAG</span></a> <a href="https://masto.machlis.com/tags/Python" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Python</span></a></p>
Kaveinthran<p><span class="h-card" translate="no"><a href="https://mastodon.social/@chikim" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>chikim</span></a></span> good for those who are hacking with <a href="https://disabled.social/tags/llamaIndex" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>llamaIndex</span></a>, there is more in the <a href="https://disabled.social/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RAG</span></a> survey paper.<br><a href="https://arxiv.org/abs/2312.10997" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">arxiv.org/abs/2312.10997</span><span class="invisible"></span></a> <br><a href="https://disabled.social/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ai</span></a> <a href="https://disabled.social/tags/openSource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>openSource</span></a> <a href="https://disabled.social/tags/machinelearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>machinelearning</span></a></p>
Sharon Machlis<p>From <a href="https://masto.machlis.com/tags/LlamaIndex" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LlamaIndex</span></a>: <br>The new docs from Mistral AI are out! Check out the links from Sophia Yang, Ph.D. or get started with RAG with LlamaIndex in 10 lines of code: <a href="https://docs.mistral.ai/guides/basic-RAG/#rag-with-llamaindex" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">docs.mistral.ai/guides/basic-R</span><span class="invisible">AG/#rag-with-llamaindex</span></a></p><p>Sophia's links: <a href="https://lnkd.in/gh7iBGeQ" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">lnkd.in/gh7iBGeQ</span><span class="invisible"></span></a></p><p>You can also check out our own docs to see how to use Mistral-medium, streaming, async and more: <a href="https://docs.llamaindex.ai/en/stable/examples/llm/mistralai.html" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">docs.llamaindex.ai/en/stable/e</span><span class="invisible">xamples/llm/mistralai.html</span></a></p><p>And check out our entry in their brand-new cookbook where we show you how to build agentic RAG with Mistral: <a href="https://github.com/mistralai/cookbook/blob/main/llamaindex_agentic_rag.ipynb" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/mistralai/cookbook/</span><span class="invisible">blob/main/llamaindex_agentic_rag.ipynb</span></a></p><p><a href="https://masto.machlis.com/tags/GenAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GenAI</span></a> <a href="https://masto.machlis.com/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RAG</span></a></p>
Alros<p><span class="h-card" translate="no"><a href="https://mstdn.social/@Powerfromspace1" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>Powerfromspace1</span></a></span> you can build an impressive RAG application running 100% locally in just an hour with <a href="https://hachyderm.io/tags/LlamaIndex" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LlamaIndex</span></a>. The real challenge is to go from tutorial/POC level to production-ready 😅</p>
Anders Thoresson<p>So, I got <a href="https://thoresson.social/tags/Python" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Python</span></a> and <a href="https://thoresson.social/tags/Llamaindex" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Llamaindex</span></a> running and my first vector database created from 600+ Markdown-files on my harddrive. Can now query and get responses back.</p><p>But I can't figure out how to also output the filenames for the nodes that VectorIndexRetriever returns.</p>
TrendingLive feeds
Mastodon is the best way to keep up with what's happening.
Follow anyone across the fediverse and see it all in chronological order. No algorithms, ads, or clickbait in sight.
Create accountLoginDrag & drop to upload