Blogs
Entwickler-Einblicke und praktische Anleitungen von unseren Experten, um Ihr Sucherlebnis zu inspirieren und zu verbessern
Mapping embeddings to Elasticsearch field types: semantic_text, dense_vector, sparse_vector
Discussing how and when to use semantic_text, dense_vector, or sparse_vector, and how they relate to embedding generation.
Excluding Elasticsearch fields from indexing
Learn how to configure Elasticsearch to exclude fields, the main reasons for excluding fields from indexing, and best practices to follow.
Deleting a field from a document in Elasticsearch
Learn how to delete fields from Elasticsearch documents using the Update API, scripts, or reindexing for single and bulk removals.
Unstructured data processing with NVIDIA NeMo Retriever, Unstructured, and Elasticsearch
Learn how to build a scalable data pipeline for unstructured documents using NeMo Retriever, Unstructured Platform, and Elasticsearch for RAG applications.
How to join two indices in Elasticsearch
Explaining how to use the terms query, Logstash elasticsearch filter, the enrich processor and ES|QL for joining two indices in Elasticsearch.
Built with Elastic: Hybrid search for Cypris – the world’s largest innovation database
Discover how Cypris optimized hybrid search in Elasticsearch to handle 500M vectors, cutting query times from 60 seconds down to 5–10 seconds using binary quantization and segment tuning.
Understanding Elasticsearch scoring and the Explain API
Learn about Elasticsearch scoring mechanisms and the practical scoring function to audit search relevance and improve document ranking with the Explain API.
Index templating in Elasticsearch: How to use composable templates
Explore how to create composable and component index templates in Elasticsearch to ensure consistent mappings and automate index configuration.
RAG and the value of grounding in Elasticsearch
Learn about RAG, grounding, and how to reduce hallucinations by connecting an LLM to your documents.
Elasticsearch search by two fields
Explore techniques for searching by two fields, including multi-match queries, bool queries, and query-time field boosting.
RAG without “AG”?
Learn how to leverage semantic search and ELSER to build a visually appealing Q&A experience, without using LLMs.
Building a RAG workflow using LangGraph and Elasticsearch
Learn how to configure and customize a LangGraph Retrieval Agent Template with Elasticsearch to build a RAG workflow for efficient data retrieval and AI-driven responses.