1. M miniCOIL 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! O 10/08 15:00 ♡
2. W Why Hyperbolic Embeddings Matter for Hierarchical Data 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 W 09/08 08:00 ♡
3. P Predicting Weak Retrieval Without an LLM Most retrieval systems run one pipeline on every query, and it is the wrong default in both directions: a single pass under-serves the hard queries, while reranking or rewriting ev 06/24 05:00 ♡
4. R Reranking for Better Search Improve Semantic Search with Reranking using Qdrant In Retrieval-Augmented Generation (RAG) systems, irrelevant or missing information can throw off your model’s ability to p 11/28 02:27 ♡
6. How ColPali Models Work Module 2 How ColPali Models Work ColPali extends the late interaction paradigm from text to visual documents. It can process PDFs, images, and scanned documents, generating multi-v 01/01 08:00 ♡
7. H How vector search should be benchmarked? Benchmarking Vector Search At Qdrant, performance is the top-most priority. We always make sure that we use system resources efficiently so you get the fastest and most accurate re 01/01 08:00 ♡
8. Late Interaction Basics Module 1 Late Interaction Basics When building a search system, one fundamental question emerges: when should a query and document interact? The answer to this question may affect 01/01 08:00 ♡
9. Module Overview Module 0 Setting Up Dependencies Get started with Qdrant by setting up your environment and building your first vector search application. Today’s Path Qdrant Setup Implement 01/01 08:00 ♡
10. Module Overview Module 1 Let’s Understand Search Traditional search retrieves documents by matching the words in a query to the words in an index. It’s fast and still useful for precis 01/01 08:00 ♡
