Faiss
AI overview
Sign in and the AI will write an overview from our coverage.
Headlines · 3
- A Practical Guide to Storage Engines for AI Agent Memory
A chapter on AI agent long-term memory organizes the topic around where to store information, what to record, and when and how to use it. It reviews in-context storage, KV stores, vector databases, relational databases and graph databases, with examples including Redis, SQLite, Chroma, FAISS, PostgreSQL and Neo4j. It also includes a LlamaIndex VectorStoreIndex example using OpenAIEmbedding for semantic retrieval.
掘金 · 人工智能 · 🔥 0 - e-means speeds up large-scale k-means clustering
The authors introduced e-means, a mini-batch k-means algorithm based on exponential moving averages, with scaling laws that set decay rate and batch size across problem sizes and embedding datasets. They report that e-means reaches lower loss than Lloyd k-means in 1.2–3 epochs, with 10–45× GPU wall-clock reduction against Flash-KMeans and 8–15× CPU reduction against Faiss; the code is available in Faiss's contrib directory.
Hacker News 首页(100+ 分) · 🔥 0 - Paper Tests Text-Vector Integrity Attacks in Offline RAG
Georgios Feretzakis and Alexandros Papaspyridis examine a gap in offline retrieval-augmented generation: a signed knowledge pack authenticates its publisher but does not guarantee that its embedding vectors faithfully represent the included text. Their experiments on five corpora, two embedding models and a Raspberry Pi 5 showed exposure to vector tampering under several verification settings, while a proposed method that checks quantisation codes accepted all sampled honest vectors across three platforms; the authors also released code and data.
Hugging Face · Papers · 🔥 0
Experience and discussion from the community
Share my Faiss experienceAsk about Faiss
Nobody has shared their experience with Faiss yet.