Awesome Search KG

Tag: company-blog

105 items with this tag.

Sep 05, 2026
GraphRAG: Unlocking LLM discovery on narrative private data
Sep 05, 2026
Measuring Hallucinations in RAG Systems
Sep 05, 2026
NVIDIA Research: RAG with Long Context LLMs
Sep 05, 2026
NeMo Guardrails: The Missing Manual
Aug 30, 2026
How Etsy Uses LLMs to Improve Search Relevance
Aug 28, 2026
Relational Reranking: Scoring Search Results with Structured Facts
Aug 28, 2026
Updating a Vector Database Is No Simple Thing
Aug 20, 2026
Automating Search Relevance Assessment at Scale with LLM-as-a-Judge
Jul 30, 2026
Improving Search Ranking with Few-Shot Prompting of LLMs
Jul 30, 2026
Improving Zero-Shot Ranking with Vespa Hybrid Search - part two
Jul 30, 2026
Improving Zero-Shot Ranking with Vespa Hybrid Search
Jun 29, 2026
Dense Retrieval at Vinted
Jun 29, 2026
Optimizing Vespa Latency with Match-Features at Vinted
Jun 28, 2026
Creating Judgement Lists with Quepid
Jun 27, 2026
How to Really Design Search for a Database
Jun 27, 2026
How to Really Do Autocomplete
Jun 27, 2026
Query Sampling for Relevancy Testing
Jun 27, 2026
Search Kōans
Jun 27, 2026
What is Elasticsearch and Why You Should Use It
Jun 27, 2026
What is OpenSearch and Why You Should Use It
Jun 19, 2026
ColPali & Elasticsearch: How to Search Complex Documents
May 31, 2026
Search Quality Assurance with AI as a Judge
May 31, 2026
This Is What Agentic Retrieval Looks Like
May 21, 2026
Exploring Hierarchical Navigable Small World
May 21, 2026
Late Interaction Models: How to Scale & Optimize in Elasticsearch
May 16, 2026
Adopting Vespa for Recommendation Retrieval at Vinted
May 16, 2026
Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
May 16, 2026
Building Smarter Search Products: 3 Steps for Evaluating Search Algorithms
May 16, 2026
ColBERT Comes to Apache Solr: Implementation and Tutorial of Late Interaction Model Reranking
May 16, 2026
ColBERT-Zero: To Pre-train Or Not To Pre-train ColBERT Models?
May 16, 2026
Common Pitfalls of Onsite Search Experimentation Part 2
May 16, 2026
Common Pitfalls of Onsite Search Experimentation
May 16, 2026
E-commerce Search and Recommendation with Vespa
May 16, 2026
Ecommerce Search Governance: Move Faster, Not Slower
May 16, 2026
Elasticsearch Personalized Search in Ecommerce: Improve Relevance
May 16, 2026
Evaluating the Best AB Testing Metrics for Search
May 16, 2026
Mutually Assured Distraction
May 16, 2026
My Journey Building Elasticsearch for Retail
May 16, 2026
Part 1: Learning to Rank for E-Commerce Search at Otto
May 16, 2026
Rethinking Spotify Search
May 16, 2026
Sparse Embeddings: Dense vs Sparse Vectors in Elasticsearch
May 16, 2026
TurboQuant in Qdrant
May 16, 2026
Using Approximate Nearest Neighbor Search to Find Similar Products
May 16, 2026
Using Cross-Encoders as Reranker in Multistage Vector Search
May 16, 2026
Using LLMs to Amplify Human Labeling and Improve Dash Search Relevance
May 16, 2026
Why Ecommerce Search Needs Governance & How It Improves Retrieval
May 15, 2026
13 Design Patterns for Autocomplete Suggestions (27% Get it Wrong)
May 15, 2026
Announcing the Vespa ColBERT Embedder
May 15, 2026
Announcing the Vespa ColBERT embedder
- clippings
- company-blog
May 15, 2026
Bayesian BM25 is Cool
May 15, 2026
Beyond Hybrid Search: Traversing Vector Spaces with Wormhole Vectors
May 15, 2026
Canva Search Pipeline Part I
May 15, 2026
Canva Search Pipeline Part II
May 15, 2026
Choosing Your Search Relevance Evaluation Metric
May 15, 2026
How to choose the best model for semantic search
- clippings
- company-blog
May 15, 2026
Chunking Strategies for LLM Applications
May 15, 2026
Demystifying nDCG and ERR
May 15, 2026
Ecommerce Search UX 2026: 8 Search "Query Types" UX Best Practices
May 15, 2026
Improving information retrieval in the Elastic Stack: Introducing Elastic Learned Sparse Encoder (ELSER)
- clippings
- company-blog
May 15, 2026
Improving Information Retrieval in the Elastic Stack: Introducing ELSER
May 15, 2026
Elasticsearch BBQ: Optimized Scalar Quantization vs. TurboQuant
May 15, 2026
Evaluating the Ideal Chunk Size for a RAG System using LlamaIndex
- clippings
- company-blog
May 15, 2026
Evaluating the Ideal Chunk Size for a RAG System using LlamaIndex
May 15, 2026
Food Discovery with Uber Eats: Building a Query Understanding Engine
May 15, 2026
From Zero to Semantic Search Embedding Model
May 15, 2026
How Etsy Uses Thermodynamics to Help You Search for 'Geeky'
May 15, 2026
How Netflix Content Engineering Makes a Federated Graph Searchable
May 15, 2026
How to Choose the Best Model for Semantic Search
May 15, 2026
How to Really Scale Autocomplete
May 15, 2026
Hypothetical Document Embeddings (HyDE)
- clippings
- company-blog
May 15, 2026
Hypothetical Document Embeddings (HyDE)
May 15, 2026
How to Implement a Normalized Discounted Cumulative Gain (NDCG) Ranking Quality Scorer in Quepid
- clippings
- company-blog
May 15, 2026
Improving Retrieval with LLM-as-a-Judge
May 15, 2026
Improving retrieval with LLM-as-a-judge
- clippings
- company-blog
May 15, 2026
Innovating Search Experience with Amazon OpenSearch and Amazon Bedrock
- clippings
- company-blog
May 15, 2026
Innovating Search Experience with Amazon OpenSearch and Amazon Bedrock
May 15, 2026
🪆 Introduction to Matryoshka Embedding Models
- clippings
- company-blog
May 15, 2026
Introduction to Matryoshka Embedding Models
May 15, 2026
Matryoshka Embeddings: Faster OpenAI Vector Search Using Adaptive Retrieval
May 15, 2026
Matryoshka embeddings: faster OpenAI vector search using Adaptive Retrieval
- clippings
- company-blog
May 15, 2026
Modeling Spelling Correction for Search at Etsy
May 15, 2026
Multilingual Embedding Model: Hybrid Search Reranking
May 15, 2026
Nearest Neighbor Indexes for Similarity Search
- clippings
- company-blog
May 15, 2026
Nearest Neighbor Indexes for Similarity Search
May 15, 2026
How to succeed with explicit relevance evaluation using Probability-Proportional-to-Size sampling
- clippings
- company-blog
May 15, 2026
Qwen3 Embedding Series
May 15, 2026
SPLADE: A Sparse Bi-Encoder BERT Model for First-Stage Ranking
May 15, 2026
SPLADE – a sparse bi-encoder BERT-based model achieves effective and efficient first-stage ranking
- clippings
- company-blog
May 15, 2026
SPLADE for Sparse Vector Search Explained
May 15, 2026
Search Query Expansion with Query Embeddings
May 15, 2026
Search at Slack
May 15, 2026
How to Succeed with Explicit Relevance Evaluation using PPS Sampling
May 15, 2026
Targeting Broad Queries in Search
May 15, 2026
The Day Our Own Queries DoS'ed Us: Inside Zalando Search
May 15, 2026
The Missing WHERE Clause in Vector Search
- clippings
- company-blog
May 15, 2026
The Missing WHERE Clause in Vector Search
May 15, 2026
Three Pillars of Search Quality Part 2: Discovery & Inspiration
May 15, 2026
Three Pillars of Search Quality in E-Commerce — Part 1: Findability
May 15, 2026
Stability and Scalability for Search
May 15, 2026
Understanding BERT and Search Relevance
May 15, 2026
What is ColBERT and Late Interaction and Why They Matter in Search?
May 15, 2026
What is ColBERT and Late Interaction and Why They Matter in Search?
- clippings
- company-blog
May 15, 2026
What is a 'Relevant' Search Result?
May 15, 2026
Wormhole Vectors: Beyond Hybrid Search in OpenSearch
May 15, 2026
You Say Search, I Say Recs: A Scalable Agentic Approach to Query Understanding and Exploratory Search at Spotify

Created with Quartz v4.5.2 © 2026

GitHub
Discord Community