14 stories
Reachy Mini is an open-source robot from Pollen Robotics and Hugging Face, run by a Raspberry Pi with 4 GB of RAM. We wanted it to do what a good host does: greet you by name the second time you walk in, remember what you talked about, and tell you what it saw while you were gone.
A number in a financial report needs its row, column, and unit to mean anything. A chart needs its labels. When you build search over PDFs, that context is part of what you want to retrieve. Perplexity released pplx-embed-v2-late, two late interaction models that search document pages as images.
Classification is one of the oldest problems in machine learning. Unlike modern decoding transformers, most classification models were non-autoregressive by nature.
Google’s new EmbeddingGemma 2 can run on a phone. The model travels light. The vectors need their own suitcase. At 10 million documents, full-size float32 vectors alone take 30.7 GB of RAM.
Monitoring Managed Cloud with Prometheus and Grafana This tutorial will guide you through the process of setting up Prometheus and Grafana to monitor Qdrant databases running in Qdrant Managed Cloud.
As query traffic grows, so does the compute bill for embedding it. On a low-power device, a large model may not fit in memory. A smaller query model could reduce that cost, but switching usually means re-embedding the collection. Constella lets you make that switch.
Real world vector search workloads are increasingly large and complex. Enterprises are not using vector search to occasionally search through a couple of PDF files. They are indexing and searching billions of vectors at thousands of requests per second (RPS) and sub 50ms tail latency.
Your collection works. Queries return in a few milliseconds, results are mostly right, and product keeps forwarding you the ones that aren’t. You open the search API reference and get exact definitions for hnsw_ef, reciprocal rank fusion k, and quantization oversampling.
Every crawl, retried job, and embedding pipeline change writes points into a vector collection. The stored data keeps moving even when the query code never changes, and the top results move with it. At first, little looks wrong. Search returns results, and latency stays normal.
Adding a metadata filter to vector search can make good results disappear without making the query look broken. It still runs fast, returns something, and keeps the dashboards quiet, while some of the true nearest matches drop out.
Qdrant 1.19.0 is out! Let’s look at the main features for this version: TurboQuant Datatype: A new storage format that compresses vectors to four bits without keeping their original full-precision representation, reducing storage by up to nine times compared to TurboQuant quantization.
Relevance, filtering, personalization, merchandising, and recommendations usually arrive as five separate services, and the final ranking gets stitched across all of them. Each service ranks by its own rules, and none of them owns the order a shopper ends up seeing.
TL;DR Elastic recently published a benchmark claiming that their proprietary, disk-based index (dubbed “DiskBBQ”) delivers up to 7x higher throughput than Qdrant when deployed on nodes with network-attached storage.
Most code search is lexical. You grep a string or jump to a definition, and because it runs on your checkout, it always reflects the branch you have open.
Showing 14 of 14 stories
You're all caught up.
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts
