<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Vector Databases on DATATWEETS</title><link>https://datatweets.com/courses/generative-ai/vector-databases/</link><description>Recent content in Vector Databases on DATATWEETS</description><generator>Hugo</generator><language>en</language><copyright>Copyright (c) 2025 Datatweets</copyright><lastBuildDate>Sat, 27 Jun 2026 09:00:00 +0200</lastBuildDate><atom:link href="https://datatweets.com/courses/generative-ai/vector-databases/index.xml" rel="self" type="application/rss+xml"/><item><title>Lesson 1 - Why Vector Databases</title><link>https://datatweets.com/courses/generative-ai/vector-databases/lesson-1-why-vector-databases/</link><pubDate>Fri, 14 Nov 2025 09:00:00 +0200</pubDate><guid>https://datatweets.com/courses/generative-ai/vector-databases/lesson-1-why-vector-databases/</guid><description>Comparing a query to every stored vector is fine for fifteen documents and hopeless for fifteen million. Learn what a vector database stores, why an index makes search fast, and the store-once-query-many pattern it enables.</description></item><item><title>Lesson 2 - Getting Started with Chroma</title><link>https://datatweets.com/courses/generative-ai/vector-databases/lesson-2-getting-started-with-chroma/</link><pubDate>Fri, 14 Nov 2025 09:00:00 +0200</pubDate><guid>https://datatweets.com/courses/generative-ai/vector-databases/lesson-2-getting-started-with-chroma/</guid><description>Chroma is an open-source vector database that runs locally and free. Create a client and collection, add documents that Chroma embeds automatically, count them, and query by meaning — reading the results and understanding Chroma&amp;rsquo;s distance scores.</description></item><item><title>Lesson 3 - Metadata and Filtering</title><link>https://datatweets.com/courses/generative-ai/vector-databases/lesson-3-metadata-and-filtering/</link><pubDate>Fri, 14 Nov 2025 09:00:00 +0200</pubDate><guid>https://datatweets.com/courses/generative-ai/vector-databases/lesson-3-metadata-and-filtering/</guid><description>Combine semantic similarity with structured filters: attach metadata, restrict queries with where clauses, filter on document text, and switch to a PersistentClient so your vector database is saved to disk and reused across runs.</description></item><item><title>Lesson 4 - Guided Project: Searchable Knowledge Base</title><link>https://datatweets.com/courses/generative-ai/vector-databases/lesson-4-guided-project-searchable-knowledge-base/</link><pubDate>Fri, 14 Nov 2025 09:00:00 +0200</pubDate><guid>https://datatweets.com/courses/generative-ai/vector-databases/lesson-4-guided-project-searchable-knowledge-base/</guid><description>Tie the module together into a real product: load a FAQ dataset, store it in a persistent Chroma collection that embeds once and survives restarts, and build a search function that returns the matched question, its answer, and the distance — with metadata filtering.</description></item></channel></rss>