Elastic

@elastic

Where developers learn, build, and share. Your source for hands-on demos, cheat sheets, explainers and more.

Global

Joined October 2009

Elastic
@elastic
1h
Relevance Please: Ep 5 - Build Agents That Ask Before They Act
REPLAY
Elastic
@elastic
Relevance Please: Ep 5 - Build Agents That Ask Before They Act
Elastic
@elastic
Aug 12
We batched shard queries per data node. Each data node handles partial reductions locally. Lower latency, better work distribution across the cluster.
Article
How Elasticsearch's batched query phase improves search performance at scale
The batched query phase, which is live in Elasticsearch Serverless and released in Elasticsearch 9.5.0, changes how search is coordinated across the cluster. The coordinating node now batches all...
Elastic
@elastic
Aug 11
How can a text embedding model map audio and image vectors? After being transformed via a projector (translator), a foreign modality vector must announce itself before entering an embedding model for an unrelated modality. Think of HTML. <p> These tags let the document know
Elastic
@elastic
Aug 10
Before EIS: CPU nodes, self-managed, one per model. After EIS: 1 GPU-accelerated fleet, managed by Elastic. Vector search and semantic reranking each ran on CPU nodes you provisioned yourself. More models meant more infrastructure to operate. The Elastic Inference Service (EIS)
Elastic
@elastic
Aug 7
Retraining a model is an expensive process. LoRA adapters allow you to fine-tune an existing model without retraining. For jina-embeddings-v5-omni, we use a LoRA adapter to tweak the final output to be optimized for 4 distinct tasks.