Elasticsearch Open Inference API Now Supports Mistral AI Embeddings
Elastic (NYSE: ESTC) has announced that its Elasticsearch vector database now supports Mistral AI embeddings. This integration allows for native chunking via a single API call, streamlining the development process for RAG applications. The collaboration between Elastic and Mistral AI aims to simplify the storage and chunking of embeddings in Elasticsearch, making it easier for developers to build advanced search applications.
Key features of this integration include:
- Support for mistral-embed
- Native integrations with the Open Inference API
- Compatibility with the semantic_text field
This update aligns with Elastic's commitment to providing open-first, enterprise-grade GenAI tools and Mistral AI's focus on open-weights and accessibility in AI development.
Elastic (NYSE: ESTC) ha annunciato che il suo database vettoriale Elasticsearch supporta ora le embedding di Mistral AI. Questa integrazione consente il chunking nativo tramite una singola chiamata API, semplificando il processo di sviluppo per le applicazioni RAG. La collaborazione tra Elastic e Mistral AI si propone di rendere più semplice la memorizzazione e il chunking delle embedding in Elasticsearch, facilitando il lavoro degli sviluppatori nella creazione di applicazioni di ricerca avanzate.
Le caratteristiche principali di questa integrazione includono:
- Supporto per mistral-embed
- Integrazioni native con l'Open Inference API
- Compatibilità con il campo semantic_text
Questo aggiornamento si allinea con l'impegno di Elastic di fornire strumenti GenAI di livello enterprise e open-first, e con il focus di Mistral AI sull'apertura delle pesature e sull'accessibilità nello sviluppo AI.
Elastic (NYSE: ESTC) ha anunciado que su base de datos vectorial Elasticsearch ahora admite incorporaciones de Mistral AI. Esta integración permite chunking nativo a través de una sola llamada API, optimizando el proceso de desarrollo para aplicaciones RAG. La colaboración entre Elastic y Mistral AI tiene como objetivo simplificar el almacenamiento y el chunking de las incorporaciones en Elasticsearch, facilitando a los desarrolladores la creación de aplicaciones de búsqueda avanzadas.
Las características clave de esta integración incluyen:
- Soporte para mistral-embed
- Integraciones nativas con la Open Inference API
- Compatibilidad con el campo semantic_text
Esta actualización está alineada con el compromiso de Elastic de proporcionar herramientas GenAI de clase empresarial y abiertas, y el enfoque de Mistral AI en la apertura de pesos y la accesibilidad en el desarrollo de IA.
Elastic (NYSE: ESTC)는 Elasticsearch 벡터 데이터베이스가 이제 Mistral AI 임베딩을 지원한다고 발표했습니다. 이 통합은 단일 API 호출을 통한 네이티브 청킹을 가능하게 하여 RAG 애플리케이션 개발 프로세스를 간소화합니다. Elastic과 Mistral AI 간의 협력은 Elasticsearch에서 임베딩의 저장 및 청킹을 용이하게 하여 개발자가 고급 검색 애플리케이션을 더 쉽게 구축할 수 있도록 하는 것을 목표로 합니다.
이 통합의 주요 기능은 다음과 같습니다:
- mistral-embed 지원
- Open Inference API와의 네이티브 통합
- semantic_text 필드와의 호환성
이번 업데이트는 Elastic이 오픈 퍼스트, 기업급 GenAI 도구를 제공하겠다는 의지와 Mistral AI의 오픈 가중치 및 AI 개발의 접근성을 중시하는 목표와 일치합니다.
Elastic (NYSE: ESTC) a annoncé que sa base de données vectorielle Elasticsearch prend désormais en charge les embeddings Mistral AI. Cette intégration permet un chunking natif via un seul appel API, simplifiant ainsi le processus de développement pour les applications RAG. La collaboration entre Elastic et Mistral AI vise à faciliter le stockage et le chunking des embeddings dans Elasticsearch, permettant aux développeurs de créer plus facilement des applications de recherche avancées.
Les caractéristiques clés de cette intégration comprennent :
- Support pour mistral-embed
- Intégrations natives avec l'Open Inference API
- Compatibilité avec le champ semantic_text
Cette mise à jour est en phase avec l'engagement d'Elastic à fournir des outils GenAI de niveau entreprise et open-first, et avec l'accent de Mistral AI sur les poids ouverts et l'accessibilité dans le développement de l'IA.
Elastic (NYSE: ESTC) hat bekannt gegeben, dass seine Elasticsearch-Vektordatenbank jetzt Mistral AI-Embeddings unterstützt. Diese Integration ermöglicht natives Chunking über einen einzigen API-Aufruf, was den Entwicklungsprozess für RAG-Anwendungen vereinfacht. Die Zusammenarbeit zwischen Elastic und Mistral AI zielt darauf ab, die Speicherung und das Chunking von Embeddings in Elasticsearch zu vereinfachen und Entwicklern die Erstellung fortschrittlicher Suchanwendungen zu erleichtern.
Wichtige Funktionen dieser Integration umfassen:
- Unterstützung für mistral-embed
- Native Integrationen mit der Open Inference API
- Kompatibilität mit dem semantic_text-Feld
Dieses Update steht im Einklang mit Elastics Engagement, offene, unternehmensgerechte GenAI-Tools bereitzustellen, und mit Mistral AIs Fokus auf offene Gewichte und Zugänglichkeit in der KI-Entwicklung.
- Integration of Mistral AI embeddings into Elasticsearch vector database
- Simplified development process for RAG applications
- Native chunking via single API call reduces time to market
- Collaboration with Mistral AI enhances Elastic's GenAI tools offering
- None.
Mistral AI embeddings on Elasticsearch benefit from native chunking via a single API call
“We are invested in delivering open-first, enterprise-grade GenAI tools to help developers build next generation search applications,” said Shay Banon, founder and chief technology officer at Elastic. “Through our collaboration with the Mistral AI team, we’re simplifying the process of storing and chunking embeddings in Elasticsearch to a single API call.”
“Mistral AI has always been committed to open-weights and making AI accessible to all,” said Arthur Mensch, co-founder and CEO of Mistral AI. “Working with Elastic allows us to bring Mistral’s tools to more developers through the Elastic open inference API, and gives us the opportunity to work with a company that shares our value of accessibility. We’re excited to see what developers will create.”
Support for Mistral’s AI embedding model is available today, read the Elastic blog to get started.
About Elastic
Elastic (NYSE: ESTC), the Search AI Company, enables everyone to find the answers they need in real-time using all their data, at scale. Elastic’s solutions for search, observability and security are built on the Elastic Search AI Platform, the development platform used by thousands of companies, including more than
Elastic and associated marks are trademarks or registered trademarks of Elastic N.V. and its subsidiaries. All other company and product names may be trademarks of their respective owners.
View source version on businesswire.com: https://www.businesswire.com/news/home/20240801450338/en/
Elastic PR
PR-team@elastic.co
Source: Elastic N.V.
FAQ
What new feature has Elastic (ESTC) announced for its Elasticsearch vector database?
How does the Mistral AI integration benefit developers using Elasticsearch (ESTC)?
What specific Mistral AI product does Elasticsearch (ESTC) now support?
When did Elastic (ESTC) make the Mistral AI embeddings support available?
