Hello from the Elastic DevRel team! In this edition of our newsletter blog, we cover the simplest and fastest way to get Elasticsearch and Kibana running locally, the Elastic AI Assistant with a private LLM, and the Vertex AI integration with Elasticsearch. Plus, our usual updates on interesting content and upcoming events.
What’s new?
Start local — it has never been easier to start Elasticsearch and Kibana locally: All you need to do is to have Docker running and run curl -fsSL https://elastic.co/start-local | sh in your shell. The command generates a Docker Compose setup with the latest images and a random password and starts it up. You can then access Kibana on http://localhost:5601 with the generated password. If you want to make any changes to the installation, take a look at the generated .env file for the available options like password and memory limits. You can control the installation through Docker Compose and there is also the uninstall.sh file that will remove everything the script has added.
If you want to inspect what you are running first, you can clone the start-local repository from GitHub, inspect its content, and then run the start-local.sh file.
Connect private LLMs with Elastic AI Assistant: By addressing concerns about data privacy when using public language models, you can now securely integrate private LLMs with the Elastic AI Assistant using the connector. This solution enhances data privacy and security by keeping sensitive information in house. By using the LM Studio connector, you also reduce latency and allow for quicker responses to security incidents. Beyond privacy and speed, the integration provides operational benefits, enabling retrieval augmented generation (RAG) and question and answer (QnA) on observability and security data. This approach helps secure your organization in the modern threat landscape all while maintaining control over your critical data.
Embedding generation and reranking with Google Vertex AI: Elasticsearch's vector database now natively supports generating text embeddings using any text embedding model available in Google Vertex AI. Additionally, it provides seamless support for reranking documents retrieved from Elasticsearch, ensuring you select the most relevant chunks for your RAG workflows.
Blogs, videos, and interesting links
Data set translation and insights: Jessica Garson walks you through how to translate a data set from one language to another and use Elastic's vector database capabilities to gain more insights.
RAG: Understand the big ideas behind retrieval augmented generation with Jessica Moszkowicz.
LangChain4j: David Pilato demonstrates how to use LangChain4j to simplify LLM integration into Java applications.
Data ingestion: Andre Luiz explains how to ingest data into Elasticsearch through Apache Camel with a practical example.
PII: Learn how to use NLP and pattern matching to detect, assess, and redact PII in logs with Stephen Brown.
Semantic search: Join Christine Komander as she applies semantic GenAI-powered search (RAG) to documents as part of the BSI IT Grundschutz using Elastic's new semantic_text field type and the Playground in Elastic.
Navigating an Elastic vector database: Justin Castilla breaks down the core concepts and components needed to navigate an Elastic vector database.
AI summaries: Enrich your search experience by adding an AI summary box along with the search results with Gustavo Llermaly.
Check out these videos:
Aparna Roy demonstrates how to use Amazon Bedrock with Elasticsearch and Langchain.
Jessica Garson explains how to update your Elasticsearch index with Node.js & an Azure Function App.
Annie Hansen and Stef Nestor explore how to monitor the health of and troubleshoot Index Lifecycle Management (ILM) on an Elastic Cloud deployment.
Start watching our new Elasticsearch 101 YouTube series presented by Iulia Feroli.
Featured blogs from the community:
Wallace Freitas showcases how to unlock the power of Elasticsearch, covering the top use cases for real-time search and analytics.
Ismayil Mahili demonstrates how to manage data with the ELK stack using Filebeat for Elasticsearch Cloud.
- Fabian Stadler shares his experience using the ELK stack to reduce downtime in device manufacturing.
Fabian Stadler shares his experience using the ELK stack to reduce downtime in device manufacturing.
Upcoming events
Americas
Virtual Meetup: Voxel51 & Elastic Vector Search Joint Meetup — October 10
Meetup in Silicon Valley: Accelerate Elasticsearch Data Access with Hasura’s GraphQL Connector + Stateless — October 10
Meetup in Minas Gerais: Elastic Meetup em Uberlândia — October 10
Meetup in Dallas: Making the Leap from Observability to Unified Security — October 15
Virtual Meetup in Brazil: 5º Meetup Virtual Elastic Brasil 2024 — October 16
Meetup in Lancaster: Monthly community meetup — October 16
Rio de Janeiro: Python Brazil 2024 — October 16–21
Meetup in Seattle: Effective User Email Search with Elasticsearch — October 17
Chicago: GOTO Chicago — October 21–22
Meetup in Rio de Janeiro: Elastic Meetup - Python Brazil — October 22
Meetup in Brasília: Elastic Meetup - Esquenta TDC AI Summit 2024 — October 22
Brasília: TDC AI Summit Brasília 2024 — October 23–24
Meetup in Denver: Scaling Kibana with Node Roles + Accelerating Elasticsearch Data with Hasura — October 24
Meetup in Montreal: Elastic Montreal October Meetup — October 24
Meetup in Santos, SP: Elastic + FCamara + NodeBR - Node.js além do básico — October 25
New York: BITS 2024 — October 25–26
Raleigh: All Things Open — October 27–29
Meetup in Chicago: It's time to use AI for SecOps — October 29
Meetup in São Paulo: Elastic & Red Hat em São Paulo — October 30
Virtual Meetup: Elastic & LM Studio — October 30
Meetup in Boston: Elastic & LangChain — November 4
Virtual Meetup: Harnessing Elastic for AI-Powered Research in International Development — November 6
Meetup in Minneapolis: Elastic User Group Meetup with GitLab — November 7
Recife: TDC AI Summit Recife 2024 — November 7–8
Austin: Generative AI World Summit — November 7–8
Meetup in Salt Lake City: Boost Developer Productivity - Streamlining Generative AI with Elastic and Azure — November 11
Meetup in New York: Elastic & Microsoft Meetup — November 12
Bogotá: DevOpsDays Bogotá 2024 — November 12
Europe, Middle East, and Africa
Antwerp: Devoxx Belgium — October 7–11
EMEA Virtual: All Day DevOps — October 10
Clermont-Ferrand: Volcamp 2024 — October 10–11
Paris: Forum PHP — October 10–11
Meetup in Berlin: October Edition - Zalando Meetup — October 15
Meetup in Amsterdam: Elastic & Trendyol — October 15
Poznań: JUGtoberfest — October 16
Nantes: DevFest Nantes — October 17–18
Meetup in Krakow: OpenTelemetry & Elasticsearch Query Language (ES|QL) — October 21
Krakow: GenAI buzzwords explained — October 22–23
London: Kubernetes Community Day UK — October 22–23
Meetup in Birmingham: Meetup Special with Apache Kafka Group — October 24
Paris: Meetup ElasticFR #93 at Canal+ — October 24
Birmingham: TechMids — October 25
London & Virtual: React Advanced — October 25 & 28
Meetup in Cologne: Elastic Meetup x Apache Kafka Cologne — October 29
Meetup in Dublin: ES|QL & SLOs across the Globe — October 29
Dublin: SRECon EMEA 2024 — October 29–31
Tel Aviv: DevOpsDays Tel Aviv — October 30–31
Warsaw: DevOpsDays Poland — November 5–6
Meetup in Amsterdam: Security Meetup — November 6
Toulouse: DevFest Toulouse — November 7
London: Halfstack London — November 13
Asia-Pacific
Meetup in Ahmedabad: GenAI and Search — October 12
Melbourne: KubeDay Australia 2024 — October 15
Meetup in Singapore: Elastic Security in Singapore with Mandy Andress — October 15
Meetup in Bengaluru: Security Meetup - The Hackers meetup x Elastic — October 19
Perth: AISA PerthSec Day — October 23
Meetup in Sydney: Elastic & Microsoft Meetup in Sydney — October 23
Changsha: 2024 Developer's Day — October 23–24
Singapore: STACK Conference — November 6–7
Sydney: GopherCon AU 2024 — November 7–8
Sydney: BSides Sydney 2024 — November 9
Join your local Elastic meetup group for the latest news on upcoming events. If you’re interested in presenting at a meetup, send an email to meetups@elastic.co.
The release and timing of any features or functionality described in this post remain at Elastic's sole discretion. Any features or functionality not currently available may not be delivered on time or at all.