Spring shipped Spring AI 2.1.0-M1 on 2026-09-25. Headliners: OpenAI Responses API support (maps reasoning/function_call/image items to ReasoningPart/ToolCallPart/MediaPart while preserving item id/status for replay); ordered MessagePart lists on AbstractMessage so text, reasoning, tool calls, and media round-trip in model order; VectorStore.upsert for caller-supplied precomputed embeddings (wired for pgvector, Redis, Elasticsearch, Qdrant). Bumps Spring Boot to 4.2. First usable 2.1 milestone for teams adopting Responses and precomputed vector pipelines.

Key Takeaways

  • ✓Shipped: v2.1.0-M1 — spring-ai-bom:2.1.0-M1 on Maven Central / Spring milestone
  • ✓Responses API: reasoning/function_call/image → MessagePart types; only function_call becomes ToolCalls
  • ✓MessagePart: ordered multimodal list; legacy accessors remain views; Jackson 3 type discriminator
  • ✓VectorStore.upsert for precomputed embeddings; pgvector/Redis/ES/Qdrant replace-by-id
  • ✓See 2.1 upgrade notes; Boot 4.2 — try from milestone before GA
🔗

Project Links & Resources

Direct Access
Direct access to official project resources and documentation
🐙
GitHub Release Spring AI v2.1.0-M1
github.com/spring-projects/spring-ai/releases/tag/v2.1.0-M1
↗
📖
Spring AI 2.1 Upgrade Notes
docs.spring.io/spring-ai/reference/2.1/upgrade-notes.html
↗
📖
Spring AI 2.1 Getting Started
docs.spring.io/spring-ai/reference/2.1/getting-started.html
↗
📖
OpenAI Chat API reference (2.1)
docs.spring.io/spring-ai/reference/2.1/api/chat/openai-chat.html
↗
📖
Vector Databases reference (2.1)
docs.spring.io/spring-ai/reference/2.1/api/vectordbs.html
↗
🐙
PR #7006 OpenAI Responses API support
github.com/spring-projects/spring-ai/pull/7006
↗
🐙
PR #7002 VectorStore.upsert
github.com/spring-projects/spring-ai/pull/7002
↗
📝
Spring AI project page
spring.io/projects/spring-ai
↗
🐙
MessagePart
github.com/spring-projects/spring-ai/pull/6997
↗
🔬

In-Depth Technical Analysis

Core Background & Industry Pain Points

Enterprise Java stacks struggle to fold Responses-style reasoning signatures, tool calls, multimodal attachments, and offline precomputed embeddings into one Chat/RAG abstraction. Older Spring AI leaned on Chat Completions field bags—order gets lost—and VectorStore assumed on-the-fly EmbeddingModel calls, which blocks external feature pipelines. Responses also rejects unsigned reasoning replay without an opaque payload.

Architecture Highlights & Internals

v2.1.0-M1 ships three pieces. OpenAI Responses mapping turns items into ReasoningPart (OpaquePayload), TextPart, ToolCallPart, MediaPart, UnknownPart; only function_call becomes ToolCalls. MessagePart gives Assistant/User/ToolResponse an ordered shared list; legacy accessors remain views. VectorStore.upsert takes EmbeddedDocument pairs and replace-by-id on pgvector/Redis/Elasticsearch/Qdrant with UPSERT observation. BOM targets Spring Boot 4.2.

Authoritative Benchmarks & Measured Scores

No public cross-version latency or recall numbers in the notes. Validate Responses multi-turn replay (signed reasoning), MessagePart order vs provider items, and upsert round-trips. Do not extrapolate Completions latency to Responses.

Developer Hands-on Guide

Use spring-ai-bom:2.1.0-M1, read the 2.1 upgrade notes and getting started. Milestone APIs may still move—canary before GA.