The 'blurry' world of defence tech revenue
VCs report some founders are misrepresenting or not being transparent about defence revenue
Sifted AI8 min read
Qdrant
Stay updated with the latest developments in Artificial Intelligence
Reachy Remembers: Giving a Robot a Local Semantic Memory with Qdrant Edge
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.
Qdrant7 min readPerplexity's New Visual Retriever Has a Size Problem. We Fixed It.
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.
Qdrant4 min readSemantic Caching for RAG
Build a Semantic Cache for a RAG Pipeline Time: 30 min Level: Intermediate What’s a Semantic Cache Traditional caches operate on an exact match basis, while semantic caches search for the meaning of the key rather than an exact match.
Qdrant21 min readminiCOIL EN-ES: Sparse Neural Retrieval Across the Language Barrier
Sparse neural retrieval finally started getting more and more attention (SPARSEUP, MILCO, sparse encoders in Sentence Transformers…). Well, amazing, we like attention!
Qdrant17 min readJevjitsu: Or, How We Tried Generalized Classifiers on Everything
Classification is one of the oldest problems in machine learning. Unlike modern decoding transformers, most classification models were non-autoregressive by nature.
Qdrant10 min readHow Small Can Google's New EmbeddingGemma 2 Get?
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.
Qdrant3 min readManaged Cloud Prometheus Monitoring
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.
Qdrant4 min readConstella Preview: Swap Query Models Without Re-Embedding
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.
Qdrant6 min readOxidizing Cross-Encoders
We rewrote cross-encoder inference in Rust, benchmarked it against Python, and on a small reranking model it came out only 1.1x faster at the median. That is not a sign of a slow Rust implementation.
Qdrant7 min readSHIFTing Languages in Multilingual RAG
If you speak more than one language, you know the feeling when the mental switch in your head starts up with the rattling sound of a struggling engine, mixing every word you have to produce into some Denglish, Frenglish, or Spanglish.
Qdrant11 min readHyperbolic Embeddings in Qdrant
We choose embedding models, dimensions, and indexes. The geometry usually comes with the package. But why use a flat space, and what else could we choose? What Is a Manifold, and Where Do Our Vectors Live? A manifold is the space our embeddings live in.
Qdrant9 min readEnough with the Bad Benchmarks: Tools for Production-Grade Research
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.
Qdrant5 min readMemory Tiers in Qdrant: What to Use and When
Memory Tiers in Qdrant: What to Use and When A growing vector collection eventually outgrows the RAM it started with: Qdrant handles that by letting you assign dense vectors, the HNSW graph, quantized vectors, payloads, and payload indexes each to whichever memory tier that structure supports,…
Qdrant7 min readGPU-Accelerated HNSW Indexing
GPU-Accelerated HNSW Indexing in Qdrant Time: 45 min Level: Intermediate Output: GitHub Since Qdrant v1.13, Qdrant has supported GPU-accelerated Hierarchical Navigable Small World (HNSW) indexing on self-hosted instances.
Qdrant12 min readConfigure Qdrant's Optimizer for Predictable Search Latency
A bulk load finishes, and the collection looks ready: every point is in, and the upload call has returned. Then the first queries land, and search takes hundreds of milliseconds, sometimes several seconds at a stretch, while Qdrant’s indexing, merge, and vacuum optimizers work through the backlog…
Qdrant11 min readHybrid Search in Qdrant
Hybrid Search in Qdrant A search result can look plausible and still be wrong. Dense retrieval can return a document on the right topic but miss an exact identifier copied into the query. Sparse retrieval can miss a relevant document when the query describes it with terms the corpus doesn’t use.
Qdrant7 min readHow to Tune Vector Search Without Guessing
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.
Qdrant5 min readWhen Your Collection Outgrows RAM
When Your Collection Outgrows RAM Once a collection no longer fits in RAM, the kernel evicts vector pages, and the next query waits on a disk read to get them back. Quantization buys that memory back.
Qdrant11 min read
Showing 18 of 37 stories
Load more storiesAiByts Weekly Brief
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news from Qdrant
Join 15,000+ AI enthusiasts