MongoDB.local NYC 2025: Definition der idealen Datenbank für das KI-Zeitalter

Summary

MongoDB unveiled several core database updates aimed at supporting artificial intelligence workloads during MongoDB.local NYC 2025. The release of MongoDB 8.2 introduces performance enhancements alongside Voyage AI embedding models and rerankers for AI applications. Furthermore, Search and Vector Search are now available in public preview for both MongoDB Community Edition and MongoDB Enterprise Server. To address the costs and operational friction of legacy systems, MongoDB launched the Application Modernization Platform (AMP), which combines AI-powered tools with specialized talent to accelerate database migrations. These capabilities position the JSON-based document model to supply the persistent state, memory, and retrieval mechanisms required by emerging agentic AI architectures.

Context

Legacy relational systems struggle with the scaling demands and complexity of modern artificial intelligence workloads, while organizations face high costs and operational risks when attempting to modernize critical business infrastructure. Additionally, agentic AI systems require persistent context, memory, and state that large language models cannot provide alone.

Approach / What changed

MongoDB introduced version 8.2 alongside Voyage AI embedding models and rerankers, while releasing Search and Vector Search into public preview for both Community Edition and Enterprise Server. The company also launched the Application Modernization Platform (AMP), an end-to-end platform integrating AI-driven tools, established methodologies, and specialized talent to accelerate legacy system migrations.

Takeaways

• Search and Vector Search capabilities have entered public preview for both MongoDB Community Edition and MongoDB Enterprise Server, enabling local retrieval deployments across customer environments.
• The MongoDB Application Modernization Platform (AMP) utilizes AI-assisted tooling and specialist support to accelerate legacy migrations two to three times faster than conventional methods.
• MongoDB 8.2 integrates Voyage AI embedding models and reranking to support agentic AI workloads that depend on structured memory, state tracking, and intent-based querying.

Related reading