Learn about the improvements we've made to the inference performance of ELSER v2, achieving a 60% to 120% speed increase over ELSER v1.

Improved relevance for BEIR with ELSER v2

Quantization in ELSER v2

Block layout of linear layers in ELSER v2

Conclusion

ElSER v2: Improved information retrieval & inference performance

Improving information retrieval in the Elastic Stack: Improved inference performance with ELSER v2

Learn how we are reducing the retrieval costs of the Learned Sparse EncodeR (ELSER) v2.

Retrieval cost aware training

Optimizing ELSER queries

Implementing with an Elasticsearch query

ELSER: Optimizing retrieval with ELSER v2

Improving information retrieval in the Elastic Stack: Optimizing retrieval with ELSER v2

With LocalAI, you can compute text embeddings in air-gapped systems. GPU support is available. Here's how to set up LocalAI to compute embeddings for your data.

Introduction

How to set up LocalAI to compute embeddings for your data

Step 1: Set up LocalAI with docker-compose

Step 2: Configure LocalAI to use Sentence Transformers models

Step 3: Start the LocalAI server

Step 4: Create Elasticsearch `_inference` service

LocalAI is a free and open-source inference server compatible with the OpenAI API. It supports model inference using multiple backends, including Sentence Transformers for embedding and llama.cpp for text generation. LocalAI also supports GPU acceleration, so you can compute embeddings faster.

What is LocalAI?

LocalAI for GPU-powered text embeddings in air-gapped systems

How to set up LocalAI for GPU-powered text embeddings in air-gapped environments

Author

Valeriy Khakhutskyy

Articles

Improving information retrieval in the Elastic Stack: Improved inference performance with ELSER v2

Improving information retrieval in the Elastic Stack: Optimizing retrieval with ELSER v2

How to set up LocalAI for GPU-powered text embeddings in air-gapped environments