spring-projects /spring-ai
An Application Framework for AI Engineering
★ 9,651⑂ 3,055👁 111⑃ 4,082● 2,979▤ 39
More from this author
+3
Daily
+34
Weekly
+119
Monthly
9,651
stars
3,055
forks
111
watchers
4,082
prs
2,979
issues
39
releases
README
Spring AI The Spring AI project provides a Spring-friendly API and abstractions for developing AI applications. Its goal is to apply Spring ecosystem design principles, such as portability and modular design, to the AI domain and promote using strongly-typed data structures and APIs as the building blocks of an application. !spring-ai-integration-diagram-3 At its core, Spring AI addresses the fundamental challenge of AI integration: connecting your enterprise __Data__ and __APIs__ with the __AI Models__. Getting Started The reference documentation includes a Getting Started guide. Spring Boot Version Compatibility: Spring AI 2.x.x (main branch) - Spring Boot 4.x Spring AI 1.1.x (1.1.x branch) - Spring Boot 3.5.x Project Resources Reference documentation Javadoc Upgrade notes Awesome Spring AI - A curated list of awesome resources, tools, tutorials, and projects for building generative AI applications using Spring AI Spring AI Examples - Contains example projects that explain specific features in more detail. Spring AI Community - A community-driven organization for building Spring-based integrations with AI models, agents, vector databases, and more. Contributing We welcome contributions of all kinds! Please read our contribution guidelines before submitting a pull request or an issue. Features This is a high level feature overview. Support for all major AI Model providers such as Anthropic, OpenAI, Amazon Bedrock, Google, Ollama, Mistral AI, DeepSeek, and more. Supported model types include: - Chat - Embedding - Text to Image - Audio Transcription - Text to Speech - Moderation Portable API support across AI providers for both synchronous and streaming options. Access to model-specific features is also available. Structured Outputs - Mapping of AI Model output to POJOs. Support for all major Vector Store providers such as Amazon Bedrock Knowledge Base, Amazon S3, Apache Cassandra, Azure Vector Search, Chroma, Couchbase, Elasticsearch, GemFire, MariaDB, Milvus, MongoDB Atlas, Neo4j, OpenSearch, Oracle, PostgreSQL/PGVector, Pinecone, Qdrant, Redis, Typesense, and Weaviate. Portable API across Vector Store providers, including a novel SQL-like metadata filter API. Tool Calling - Permits the model to request the execution of client-side tools and functions, thereby accessing necessary real-time information as required. Observability - Provides insights into AI-related operations. Document injection ETL framework for Data Engineering. AI Model Evaluation - Utilities to help evaluate generated content and protect against hallucinated response. ChatClient API - Fluent API for communicating with AI Chat Models, idiomatically similar to the WebClient and RestClient APIs. Advisors API - Encapsulates recurring Generative AI patterns, transforms data sent to and from Language Models (LLMs), and provides portability across various models and use cases. MCP (Model Context Protocol) - First-class support v
Top issues
#5334Ecosystem CI Health Dashboard418 comments · 2026-01-26#2758SSE方式接入高德MCP报错34 comments · 2025-04-16#2740After restarting the mcp server, the previous client will not automatically reconnect30 comments · 2025-04-15#2818当需要调用MCP Server的多个tool时,MCP Client在调用第二个tool时出现反序列化错误(When multiple tools of the MCP Server need to be called, the MCP Client encounters a deserialization error when calling the second tool.)26 comments · 2025-04-21#3299Can multiple MCP servers with different endpoints be published in one service?22 comments · 2025-05-23#4170Chat memory advisor causes message ordering problem with default system message prompt20 comments · 2025-08-16#4790[Bug] Streaming tool_calls with Qwen models cause toolName cannot be null or empty in Spring AI 1.0.318 comments · 2025-11-03#4097400 Bad Request when using model 'gpt-5' with OpenAI ChatClient (works with gpt-4.1 and Anthropic models)18 comments · 2025-08-09
Discussions
#7324Question about the Transcription API example2 comments · 2026-11-04#7289MCP Schema and Kotlin Nullability Fixes for Spring Boot 3.51 comments · 2026-10-31#7287Token Allowance: per-user token and cost budgets for ChatClient, as a Boot starter1 comments · 2026-10-31#7286Show and tell: testing caller isolation and concurrent chat turns in a Spring AI example0 comments · 2026-10-31#7224Show and tell: SentinelPay — fail-safe Spring AI fraud analysis in an event-driven payment pipeline1 comments · 2026-10-24#7099A hard dollar limit per request flow or job with OpenAiChatModel (per-call customHeaders)0 comments · 2026-10-03#7074An independent Tool Runtime for dynamic and secure Tool management in Spring AI0 comments · 2026-09-29#6939Infinispan Vector Store1 comments · 2026-09-08
Latest release
v2.0.2 v2.0.2 2026-10-23For upgrading from 2.0.1 to 2.0.2, please refer to the upgrade notes here. :star: New Features - Upgrade the Anthropic Java SDK to 2.72.0 7164 - Add observability support for TextToSpeechModel, TranscriptionModel and StabilityAiImageModel 7141 - Configure Redis vector store metadata fields 6870 - Add customizers for stateless MCP servers 6539 :lady_beetle: Bug Fixes - Fix numeric filters in Cassandra vector store 7117 - Fix StructuredOutputValidationAdvisor repeating tool call requests 7100 - Handle Ollama responses without a message 7066 - Return final answer first in Anth