# 🎉 What’s new in Elastic 8.15
**URL:** https://discuss.elastic.co/t/what-s-new-in-elastic-8-15/364628
**Category:** Announcements
**Created:** [August 8, 2024, 7:58pm UTC](https://discuss.elastic.co/t/what-s-new-in-elastic-8-15/364628 "2024-08-08T19:58:07Z")
**Posts on this page:** 1
**Page:** 1
### Author:  [@dadoonet](https://discuss.elastic.co/u/dadoonet)
#### Post date: [August 8, 2024, 7:58pm UTC](https://discuss.elastic.co/t/what-s-new-in-elastic-8-15/364628/1 "2024-08-08T19:58:07Z")
Learn about Elastic 8.15 which includes better semantic search, new OTel distribution, SIEM data import, and more.
The [8.15 release](https://www.elastic.co/blog/whats-new-elastic-8-15-0) includes:
- [`semantic_text`](https://www.elastic.co/blog/whats-new-elasticsearch-platform-8-15-0/#semantic_text:-the-solution-to-chunking-in-rag-applications): making RAG development much easier with simplified mapping, type and automatic chunking. With this, you basically switch from this 8.14 index/query:
```auto
POST semantic-starwars/_doc
{
"quote": "These are not the droids you are looking for.",
"quote_e5": [0.5, 10, 6, ...]
}
GET semantic-starwars/_search
{
"query": {
"knn": {
"field": "quote_e5"
"k" : 10,
"num_candidates": 100,
"query_vector_builder": {
"text_embedding": {
"model_id": "e5-small-multilingual",
"model_text": "search for an android"
}}}}}
```
To this 8.15 version:
```auto
POST semantic-starwars/_doc
{
"quote": "These are not the droids you are looking for."
}
GET semantic-starwars/_search
{
"query": {
"semantic": {
"field": "quote_e5"
"query" : "search for an android"
}}}
```
Easier, right?
- Lot of other enhancements in the vector search space like [hamming distance and bit vectors](https://www.elastic.co/blog/whats-new-elasticsearch-platform-8-15-0/#hamming-distance-and-bit-vectors), [int4 automatic quantization](https://www.elastic.co/blog/whats-new-elasticsearch-platform-8-15-0/#automatic-quantization-journey:-int4-brings-8x-memory-savings) which brings 8x memory savings, the `k` parameter is now [optional in kNN query](https://www.elastic.co/blog/whats-new-elasticsearch-platform-8-15-0/#optional-k-parameter-in-knn-query), [SIMD optimization at query time](https://www.elastic.co/blog/whats-new-elasticsearch-platform-8-15-0/#ludicrous-speed:-optimizing-cpu-instructions-for-vector-search) on both x64 and ARM architectures
- We want to remain the best platform for logs so we are introducing [LogsDB index mode](https://www.elastic.co/blog/whats-new-elasticsearch-platform-8-15-0/#introducing-logsdb-index-mode:-you-know,-for-logs): You know, for logs. As we did for metrics with the `time_series` index mode, we are adding the `logs` mode which applies default sort settings on the `host.name` and `@timestamp` fields and uses `synthetic _source` to save a lot of storage space.
- [The Elastic Distribution for OpenTelemetry Collector](http://www.elastic.co/blog/whats-new-elastic-observability-8-15-0#introducing-the-elastic-distro-for-opentelemetry-collector) which enables users, in 3 clicks, to gather log data from various sources and ship it directly to Elastic where it can be analyzed in Kibana Discover. It also helps to assess host health by leveraging the OpenTelemetry host metrics receiver to monitor and evaluate the performance of the hosts.
- After donating our profiling agent to the OpenTelemetry project, we now [support the OpenTelemetry Protocol (OTLP) Universal Profiling in Elastic Cloud](http://www.elastic.co/blog/whats-new-elastic-observability-8-15-0#elastic-cloud-now-accepts-universal-profiling-data-in-otlp-format).
- [New connectors](https://www.elastic.co/blog/whats-new-elastic-search-8-15-0#more-model-flexibility-with-additional-third-party-providers) for the [inference API](https://www.elastic.co/guide/en/elasticsearch/reference/8.15/put-inference-api.html#put-inference-api-desc): Google AI Studio (embeddings and completions), Vertex AI (embeddings and reranking), Mistral (embeddings), Amazon Bedrock (embeddings and completions) and Anthropic (completions)
- Lot of enhancements in ES|QL like the support of [Geospatial search](https://www.elastic.co/blog/whats-new-elasticsearch-platform-8-15-0/#geospatial-search-with-es%7Cql), [named variables](https://www.elastic.co/blog/whats-new-elasticsearch-platform-8-15-0/#inject-named-variables-into-your-es%7Cql-query) in queries, new [functions and aggregations](https://www.elastic.co/blog/whats-new-elasticsearch-platform-8-15-0/#even-more-functions-and-aggregations-in-es%7Cql): [`MV_APPEND`](https://www.elastic.co/guide/en/elasticsearch/reference/8.15/esql-functions-operators.html#esql-mv_append), [`REPEAT`](https://www.elastic.co/guide/en/elasticsearch/reference/8.15/esql-functions-operators.html#esql-repeat), [`IP_PREFIX`](https://www.elastic.co/guide/en/elasticsearch/reference/8.15/esql-functions-operators.html#esql-ip_prefix), [`CBRT`](https://www.elastic.co/guide/en/elasticsearch/reference/8.15/esql-functions-operators.html#esql-cbrt), [`TOP` agg](https://www.elastic.co/guide/en/elasticsearch/reference/8.15/esql-functions-operators.html#esql-top), [`WEIGHTED_AVG` agg](https://www.elastic.co/guide/en/elasticsearch/reference/8.15/esql-functions-operators.html#esql-agg-weighted-avg),
[field statistics in Kibana](https://www.elastic.co/blog/whats-new-elasticsearch-platform-8-15-0/#field-statistics-in-es%7Cql) and many more
- Cross-cluster search enhancements: [users can see partial results](https://www.elastic.co/blog/whats-new-elasticsearch-platform-8-15-0/#users-can-see-partial-results-with-cross-cluster-search-even-if-one-of-the-clusters-doesn%E2%80%99t-respond-) even if one of the clusters doesn’t respond, [CCS skips unavailable clusters by default](https://www.elastic.co/blog/whats-new-elasticsearch-platform-8-15-0/#cross-cluster-searches-will-now-skip-unavailable-clusters-by-default), [remote cluster status in stack management](https://www.elastic.co/blog/whats-new-elasticsearch-platform-8-15-0/#remote-cluster-status-in-stack-management-is-more-accurate) is more accurate
- a new [field statistic visualization](https://www.elastic.co/blog/whats-new-elasticsearch-platform-8-15-0/#field-statistic-in-dashboards) could be added in your Kibana dashboards
- The GA of the [Logstash Elastic Agent-based monitoring](https://www.elastic.co/blog/whats-new-elasticsearch-platform-8-15-0/#logstash-elastic-agent-based-monitoring-is-ga) with new dashboards to understand how Logstash is functioning on an individual pipeline or plugin basis, with also advanced metrics like throughput and worker utilization.
# Release blogs
Learn more with our release blog posts:
> **[Elastic 8.15: Enhanced semantic search and new SIEM data import](https://www.elastic.co/blog/whats-new-elastic-8-15-0)**
>
> Elastic 8.15 includes enhancements in semantic search, new OTel collector distribution, AI-driven SIEM data onboarding, LLM integrations, additions to cross-cluster search (CCS), and more functionalit...
> **[Elastic Platform 8.15: Leverage vector search optimizations and semantic text](https://www.elastic.co/blog/whats-new-elasticsearch-platform-8-15-0)**
>
> Elasticsearch native vector database now supports bit vectors, SIMD acceleration, and int4 quantization. The new semantic\_text field type makes generating embeddings simple. ES|QL has new query capabi...
> **[Elastic Search 8.15: Accessible semantic search with semantic text and reranking](https://www.elastic.co/blog/whats-new-elastic-search-8-15-0)**
>
> Elastic Search 8.15 introduces the semantic\_text field and semantic reranking. The Elastic open inference API enables more third-party model providers. Learning to rank and query rules are now GA....
> **[Elastic 8.15: Automatic Import, Gemini LLMs, AI Assistant APIs, and context...](https://www.elastic.co/blog/whats-new-elastic-security-8-15-0)**
>
> Elastic Security 8.15 introduces Automatic Import, support for Gemini 1.5 Pro/Flash Models, on-demand scanning for the Elastic Defend integration, a full set of APIs for the Elastic AI Assistant, and ...
> **[Elastic Observability 8.15: AI Assistant, OTel, and log quality enhancements](https://www.elastic.co/blog/whats-new-elastic-observability-8-15-0)**
>
> Introducing Elastic Observability 8.15: Elastic Distribution for OTel Collector, native OTLP profiling, AI Assistant support for Google Vertex (Gemini 1.5 Pro model), LLM observability for Azure OpenA...