Sarah Lea<p>LLMs don’t know your PDF.<br>They don’t know your company wiki either. Or your research papers.</p><p>What they can do with RAG is look through your documents in the background and answer using what they find.</p><p>But how does that actually work? Here’s the basic idea behind RAG:<br>:blobcoffee: Chunking: The document is split into small, overlapping parts so the LLM can handle them. This keeps structure and context.<br>: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.<br>:blobcoffee: Retriever + LLM: The top matches are sent to the LLM, which uses them to generate an answer based on that context.</p><p><a href="https://techhub.social/tags/llm" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>llm</span></a> <a href="https://techhub.social/tags/largelanguagemodel" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>largelanguagemodel</span></a> <a href="https://techhub.social/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ai</span></a> <a href="https://techhub.social/tags/ki" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ki</span></a> <a href="https://techhub.social/tags/rag" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>rag</span></a> <a href="https://techhub.social/tags/tech" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>tech</span></a> <a href="https://techhub.social/tags/technology" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>technology</span></a> <a href="https://techhub.social/tags/vector" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>vector</span></a> <a href="https://techhub.social/tags/datascience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>datascience</span></a> <a href="https://techhub.social/tags/vectorsearch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>vectorsearch</span></a> <a href="https://techhub.social/tags/vector" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>vector</span></a> <a href="https://techhub.social/tags/machinelearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>machinelearning</span></a></p>
veganism.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
Veganism Social is a welcoming space on the internet for vegans to connect and engage with the broader decentralized social media community.
Administered by:
Server stats:
293active users
veganism.social: About · Status · Profiles directory · Privacy policy
Mastodon: About · Get the app · Keyboard shortcuts · View source code · v4.4.0-alpha.5
#vectorsearch
0 posts · 0 participants · 0 posts today
Pragmatic Bookshelf 📚<p>In Berlin at <a href="https://techhub.social/tags/WWC25" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>WWC25</span></a> ? Catch our ✨ newest✨ Pragprog author - Ben Greenberg <span class="h-card" translate="no"><a href="https://fosstodon.org/@hummusonrails" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>hummusonrails</span></a></span><br>Learn how GenAI and Vector Search can help users find what they are looking for - even when they don't know!<br>Fri 2:20 pm - Stage 7 </p><p>Ben's Book - out in Beta this week!<br><a href="https://pragprog.com/titles/bgvector?utm_source=m" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">pragprog.com/titles/bgvector?u</span><span class="invisible">tm_source=m</span></a><br> <a href="https://techhub.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://techhub.social/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MachineLearning</span></a> <a href="https://techhub.social/tags/VectorSearch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>VectorSearch</span></a> <br>WeAreDevs</p>
The Linux Foundation<p>🚀 Scale vector search without breaking the bank! @OpenSearchProject introduces disk-based vector search, combining efficient quantization with secondary storage to reduce RAM usage while maintaining accuracy.</p><p>Read more: <a href="https://opensearch.org/blog/Reduce-Cost-with-Disk-based-Vector-Search/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">opensearch.org/blog/Reduce-Cos</span><span class="invisible">t-with-Disk-based-Vector-Search/</span></a><br><a href="https://social.lfx.dev/tags/OpenSearch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OpenSearch</span></a> <a href="https://social.lfx.dev/tags/VectorSearch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>VectorSearch</span></a> <a href="https://social.lfx.dev/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a></p>
VegansExploreLive 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