InTowards AIby“The AI Engineer”·2d agoWhy Your Embeddings Model Upgrade Silently Broke RetrievalThe worst retrieval bug I know of throws no error. Latency stays flat. The error rate sits at zero. The index reports healthy, and every…A response icon1A response icon1
Rui Huang·2d agoThe Average Customer: Why One Vector per User Dilutes the Signal That MattersThree generations of a long-term customer embedding — pooled, clustered, then searched — and what each one taught us about where the…
Anirudh·3d agoRAG Explained: From Embeddings to Building Your First Retrieval SystemUnderstanding how LLMs retrieve information, why vector databases matter, and what it actually takes to build a reliable RAG system.
Abhishek·5d agoUnderstanding RAG from the Ground UpFrom text vectorization and embeddings to semantic retrieval
InData Science CollectivebyBenjamin Etienne·6d agoBuilding an offline & private Personal Markdown Search Engine100% local, 100% privateA response icon1A response icon1
InTowards AIbyMontasir Mahmud·Oct 28[Day 35/100] Embeddings for AI Agent Memory: What Similarity Search Gets WrongHow vector search finds “I’m vegetarian” from “suggest dinner,” why it can’t tell a fact from its contradiction, and how to wire it into a…A response icon1A response icon1
shaik umme kulsum·Oct 28The Blindfolded Genius Inside Your AIIt’s never seen a sunset, heard a song, or read a book. Here is what it’s actually looking at.
David Montero Crespo·Oct 28All of Hacker News in 5.3 GB, searchable on a laptopThis article describes hnz, a Rust library with a Python API that stores every Hacker News item in a single 5.34 GB file and searches it…A response icon1A response icon1
Sara Hamouda·Oct 27FAISS detailed..Semantic Textual Similarity, Sentence Transformers, embeddings, FAISS et clustering : comment construire un moteur de recherche sémantique…
TechWealthBuzz·Oct 27Cutting the Pie Right: Chunking and Embedding Your Documents with LangChainWhy the way you slice your documents matters more than the model you pick, and how to get it right with LangChain.
![[Day 35/100] Embeddings for AI Agent Memory: What Similarity Search Gets Wrong](https://webproxy.poorya-velaei-d67.workers.dev/https://miro.medium.com/v2/resize:fill:160:106/1*iXAdpDICQeWXzmGzad8ECA.png)
![[Day 35/100] Embeddings for AI Agent Memory: What Similarity Search Gets Wrong](https://webproxy.poorya-velaei-d67.workers.dev/https://miro.medium.com/v2/resize:fill:320:214/1*iXAdpDICQeWXzmGzad8ECA.png)
