OpenSearch 3.8 introduces significant performance and functionality upgrades across search, AI, and observability workflows. Key enhancements include up to 4x faster vector ingestion via Base64 encoding, expanded Model Context Protocol (MCP) support for diverse agent architectures, and low-latency gRPC transport for ML predictions. Additionally, the release streamlines log analysis with a new visual PPL builder and expands LLM-as-a-Judge capabilities to include a wider range of model providers. Read more...