#vectordatabases — Public Fediverse posts

If you are running a #RAG pipeline on embeddings alone, you are leaving retrieval quality on the table.

To maximize accuracy, you need to:
➤ Add BM25
➤ Fuse with Reciprocal Rank Fusion (RRF)
➤ Consider a cross-encoder re-ranking stage

📰 Read the #InfoQ article by Aaditya Chauhan for more information: https://bit.ly/4o8GnoZ

#AI #GenerativeAI #LLMs #VectorDatabases

🤔
The paper studies what happens when embedding based systems replace many memories, vectors, or retrieved passages with only a few representatives. The central claim: the same spectral structure that governs forgetting under retrieval noise also governs consolidation under compression: efficiency is increasingly becoming a question of representation geometry rather than brute force scaling alone.

https://github.com/niashwin/geometry-of-consolidation/blob/main/paper/arxiv/main.pdf
#AIInfrastructure #RAG #LLM #ArtificialIntelligence #VectorDatabases

#DoorDash launched a multimodal #ML system aligning images, text, and user queries in a shared embedding space.

• Trained on 32M query–product pairs
• Uses contrastive learning
• Improves semantic search, ranking, and advertising relevance

More details here ⇨ https://bit.ly/41fhrl3

#SoftwareArchitecture #AI #Rankings #Search #VectorDatabases #EmbeddedDatabases #InfoQ

Database Systems and Comparisons in 2025: The Ultimate Guide to Choosing Your Data Home

https://techlife.blog/posts/database-systems-2025/ #databases

#SQL #NoSQL #PostgreSQL #MongoDB #Oracle #MySQL #VectorDatabases #CloudDatabases

Amazon S3 Vectors is now GA!

AWS introduces a “Storage-First” architecture that decouples compute from storage, cutting TCO by up to 90% for large-scale RAG workloads.

With this GA release, S3 Vectors:
• Boosts per-index capacity 40× to 2 billion vectors
• Delivers sub-100ms query latencies

More on #InfoQ 👉 https://bit.ly/4ppNAQD

#CloudComputing #AI #VectorDatabases #RAG #AWS #S3

Swiggy launches Hermes V3 – a GenAI-powered text-to-SQL assistant.

Built to operate within #Slack, it uses vector retrieval, session memory, agentic orchestration & an explanation layer to generate accurate SQL queries.

🔗 https://bit.ly/49rSM0C

#AI #LLMs #Chatbots #VectorDatabases #SoftwareArchitecture #InfoQ

via @dotnet : Generative AI with Large Language Models in C# in 2026

https://ift.tt/ikxf7Ej
#GenerativeAI #LargeLanguageModels #CSharp #AI2026 #OpenAI #Microsoft #Azure #SemanticKernel #MachineLearning #AIExtensions #VectorDatabases #DotNet #AIInnovation #ChatGP…

Oh, you wanna play newspaper tycoon with your own lil' RAG? 🤓 How quaint! Here's a riveting tale of nerds turning Skald into a privacy utopia because nothing screams fun like vector databases and #LLMs. 🙄 Spoiler alert: proprietary APIs are faster, but who needs speed when you have open-source purity, right? 🚀
https://blog.yakkomajuri.com/blog/local-rag #newspaperTycoon #privacyUtopia #vectorDatabases #openSource #HackerNews #ngated

Replicate joins Cloudflare in a massive bet on the future of developer friendly AI

https://web.brid.gy/r/https://nerds.xyz/2025/11/replicate-joins-cloudflare/

Explore how #RetrievalAugmentedGeneration & #SemanticCaching can reduce #FalsePositives in AI-powered apps.

Insights come from a production-grade #CaseStudy testing 1,000 queries across 7 bi-encoder models.

📰 Read now: https://bit.ly/4nTPmso

#AI #LLMs #RAG #VectorDatabases #Infrastructure

🔍 Optimiertes Retrieval = bessere Antworten!

Auf der #BaselOne25 zeigt Ursula Deriu, wie man RAG-Systeme mit hybrider Suche, Reranking, Anfrageerweiterung & Vektor-Datenbanken optimiert 🚀 Erwartet Best Practices, Stolperfallen & praxisnahe Strategien.

📅 16. Okt | Markthalle Basel
🎟️ Tickets: https://eventfrog.ch/BaselOne2025
📌 Programm mit @kevindubois, @ixchelruiz & @aalmiray: https://baselone.org/#programm

👉 Sichere Dir Dein Ticket & sei live dabei!

#BaselOne25 #AI #RAG #VectorDatabases

🚀 NEW on We ❤️ Open Source 🚀

Jessica Garson shares how vector databases go beyond keywords to power semantic search, embeddings & smarter AI workflows. A practical intro to RAG & context-aware apps.

Read the article: https://allthingsopen.org/articles/vector-databases-semantic-search-ai

#WeLoveOpenSource #VectorDatabases #AI #SemanticSearch #MachineLearning #OpenSource

Amazon S3 #vectors are coming for your precious vector databases, like a bear in a honey warehouse 🐻🍯. But don't worry, #Zilliz is here to reassure you with a deluge of buzzwords and a pricing calculator that even your cat could use 🐱🧮. Grab a coffee, folks, this one's a real nail-biter! ☕️💤
https://zilliz.com/blog/will-amazon-s3-vectors-kill-vector-databases-or-save-them #AmazonS3 #VectorDatabases #TechBuzzwords #CloudComputing #HackerNews #ngated

Will Amazon S3 Vectors Kill Vector Databases–Or Save Them?

https://zilliz.com/blog/will-amazon-s3-vectors-kill-vector-databases-or-save-them

#HackerNews #AmazonS3 #Vectors #VectorDatabases #CloudComputing #DataStorage #TechNews

🚀 From $26K to $9K/month.
⚡ 3x faster search.
🔓 100% control over your AI memory.

Discover why Qdrant is quietly taking over Pinecone in the biggest shift in AI infra you haven’t heard of... yet.

💡 Engineers, founders, DevOps—this one’s for you.

👉 Read the full story:
https://medium.com/@rogt.x1997/qdrant-vs-pinecone-the-open-source-rebellion-thats-reshaping-ai-infrastructure-3c0f13a98135

#Qdrant #VectorDatabases #AIInfrastructure #OpenSource
https://medium.com/@rogt.x1997/qdrant-vs-pinecone-the-open-source-rebellion-thats-reshaping-ai-infrastructure-3c0f13a98135

🤔 Ah yes, because what we all desperately needed was another way to complicate our Linux filesystems by transforming them into "vector databases" using ✨magic✨ Python packages. 🤯 Just what we've been missing: a filesystem that doubles as an impenetrable, semantic labyrinth—clearly the future of user-friendly computing! 🧩🔍
https://vectorvfs.readthedocs.io/en/latest/ #LinuxFilesystems #VectorDatabases #PythonMagic #UserFriendlyComputing #SemanticLabyrinth #HackerNews #ngated

Are you passionate about the latest in #AI? Here's your chance to shine!

✍️ Join the #InfoQ Annual Article Writing Competition!

🏆 Win a #FreeTicket to #QCon or #InfoQDevSummit!

🔗 Submit by March 30, 2025: https://bit.ly/417KPtk

Which AI topic are you most excited to explore?

Explore topics like #LLMs, #SLMs, #vLLMs, #GenAI, #VectorDatabases, #ExplainableAI, #RAG, and more!

Wasn’t this…obvious? 🤔

“Vector Databases Are The Wrong Abstraction”, Timescale (https://www.timescale.com/blog/vector-databases-are-the-wrong-abstraction/).

Via HN: https://news.ycombinator.com/item?id=41985176

#MachineLearning #Databases #Embeddings #VectorDB #DB #ML #AI #ArtificialIntelligence #VectorDatabases

🎙️ Listen to the #InfoQ #podcast with Edo Liberty as he explores the importance of #VectorDatabases in the successful adoption of Generative AI and LLM-based applications.

Discover the difference between vector databases and traditional data stores: https://bit.ly/4bI0p2I

#GenerativeAI #LLMs #AI

🔥⏲️ Fudge Sunday #newsletter "Mind Mapping and A.I." A look at what's on my mind as a map with A.I.

#knowledgegraphs
#aiagents
#aiassistants
#vectordatabases
#mindmapping
#obsidian
#zettelkasten

https://fudge.org/archive/mind-mapping-and-ai/

Everyone and their dog 🐶 is using #LLMs, #RAG and #vectordatabases now. What is your favorite vector database?

🔻 @singlestoredb #llm #ai Did you miss our "Building Applications with Vector Databases" webinar? No problem unlock the potential of vector databases in app development by watching it now on demand: http://bit.ly/4a00P3e

#VectorDatabases #TechWebinar #SingleStore

[ Vector databases: Shiny object syndrome and the case of a missing unicorn | VentureBeat ]
https://venturebeat.com/ai/vector-databases-shiny-object-syndrome-and-the-case-of-a-missing-unicorn/ #VectorDatabases #ShinyObject

Guest @FranckPachot from #yugabyte joins our very own @noctarius2k in this episode of the weekly, 20 min #CloudCommute #podcast, talking about #distributedsql, #postgresql , #vectordatabases, and more. Tune in!

The 🎙️ is available on Spotify, iTunes, Pandora, Amazon Music, and more.

🎥👉 https://youtu.be/1EAKqwcP2SY

#vectordatabase #vectorsearch #vectordb #database #databases #postgres #postgressql

#vectordatabases are amazing. Created an Q&A #ai running completely local. And it is shockingly good whilst being shockingly easy to implement...

I just dump a folder of PDFs into #apache #tika. Concat them, split them by /n/n to get paragraphs. Yoink them into #chromadb. Done

Now I can pose a question that will query chroma to return 20 semantically similar documents. Those documents are dumped into a mixtral-instruct in combination with the original question.
The results are nearly perfect!

"Developers are moving fast to adopt new technologies that make their applications more powerful, their businesses more intelligent and their jobs easier. But AI systems that rely on #vectordatabases are introducing risks faster than the defenders can keep up."

#datasecurity #dataprivacy #infosec #ai #aidata

https://www.forbes.com/sites/forbestechcouncil/2023/11/02/ai-systems-and-vector-databases-are-generating-new-privacy-risks/?sh=65c8b4b3631e