57 Pull requests merged by 27 people

• Fix McpServerAutoConfigurationIT

  #3792 merged Jul 11, 2025

• Upgrade io.modelcontextprotocol 0.10.0 -> 0.11.0-SNAPSHOT

  #3781 merged Jul 10, 2025

• Improve the MCP document to stop referring to outdated DefaultMcpSession

  #3760 merged Jul 8, 2025

• Fix NPE in AnthropicApi StreamHelper

  #3755 merged Jul 7, 2025

• Fix the judge bug

  #3733 merged Jul 3, 2025

• Update anthropic-chat.adoc

  #2723 merged Jul 2, 2025

• Fix typos in chat client module

  #3013 merged Jul 2, 2025

• docs: replace CLA section with DCO (#3094)

  #3228 merged Jul 2, 2025

• Use diamond operator where possible

  #3458 merged Jul 2, 2025

• Fix annotation package

  #3716 merged Jul 2, 2025

• improve schema initialization logic and update deprecated code for Milvus vectorstore

  #3705 merged Jul 2, 2025

• Refactor: Add null check, optimize string joining, and add JavaDocs

  #3663 merged Jul 2, 2025

• Fix typo in token configuration documentation

  #3677 merged Jul 2, 2025

• fix: GH-3713 Fixed outdated code examples in the documentation.

  #3717 merged Jul 2, 2025

• docs: correct property name from is-auto-id to auto-id in milvus.adoc

  #3704 merged Jul 1, 2025

• Fix typos

  #3695 merged Jul 1, 2025

• doc: Remove duplicated dependency instructions in opensearch.adoc

  #3712 merged Jul 1, 2025

• Validate documents for text/media check when adding to vector store

  #3687 merged Jun 27, 2025

• doc: fix incorrect default embedding model reference in ollama-embeddings.adoc

  #3686 merged Jun 27, 2025

• Convert Qdrant vector store IT use OpenAI embedding model

  #3671 merged Jun 27, 2025

• Add Elasticsearch to the README

  #3688 merged Jun 27, 2025

• chore: fix SimpleApiKey assert message

  #3656 merged Jun 27, 2025

• Add link to javadoc on Content class

  #3672 merged Jun 26, 2025

• fix: Fixed some typo in the documentation and comments.

  #3678 merged Jun 26, 2025

• fix: remove unused options from ZhiPu model

  #3669 merged Jun 26, 2025

• fix: ZhiPuAiEmbedding supports custom dimensions

  #3668 merged Jun 26, 2025

• Remove @Nullable from VectorStore similaritySearch

  #3613 merged Jun 25, 2025

• Make the meta field prefix configurable in Weaviate vector store properties

  #3585 merged Jun 25, 2025

• Use OkHttpClient for AzureOpenAiAudioTranscriptionModelIT

  #3665 merged Jun 25, 2025

• Cleanup: Cleaned up redundant assignments in TextReader.

  #3627 merged Jun 25, 2025

• Fix incorrect ollama autoconfiguration changes

  #3645 merged Jun 25, 2025

• fix: Correct naming inconsistencies in Mistral package

  #3652 merged Jun 25, 2025

• [Refactor] Remove redundant null check in OpenAiApi.Builder#apiKey(String)

  #3654 merged Jun 25, 2025

• fix: Added a license header for FileDocumentWriterTest

  #3651 merged Jun 24, 2025

• migrate junit4 to junit5 in JdbcChatMemoryRepositoryHsqldbAutoConfigIT

  #3633 merged Jun 23, 2025

• docs: correct SimpleLoggerAdvisor documentation

  #3638 merged Jun 23, 2025

• chore: Remove useless proerties tags

  #3634 merged Jun 23, 2025

• Update tools.adoc

  #3624 merged Jun 20, 2025

• Remove hardcoded topK in BedrockConverseProxyChatProperties

  #3621 merged Jun 20, 2025

• chore: Remove unnecessary environment variable validation in QdrantVectorStoreIT

  #3615 merged Jun 19, 2025

• fix(elevenlabs): correct autoconfiguration class name and add ElevenLabs speech doc link

  #3610 merged Jun 19, 2025

• Refactor: Replace System.err.println with log output

  #3600 merged Jun 19, 2025

• Cleanup: Cleaned up some unused imports.

  #3599 merged Jun 19, 2025

• Update tools.adoc About toolDefinition parameter transfer error

  #3468 merged Jun 18, 2025

• Remove unused messageHistory

  #3574 merged Jun 18, 2025

• chore: Fix order of getter and setter methods in WeaviateVectorStoreProperties

  #3582 merged Jun 18, 2025

• docs: fix broken link to ChatModel

  #3583 merged Jun 18, 2025

• Fix Test Failure in ChromaVectorStoreAutoConfigurationIT

  #3581 merged Jun 18, 2025

• Fix exception in OpenAiAudioTranscriptionResponseMetadata.toString

  #3575 merged Jun 17, 2025

• fix: failed to generate spring.ai.tools.observations config metadata

  #3539 merged Jun 16, 2025

• Update advisors.adoc

  #3552 merged Jun 16, 2025

• Improved the documentation in the MCP Server Boot Starter regarding Starter selection

  #3511 merged Jun 13, 2025

• docs: update OpenAI page Vision section

  #3490 merged Jun 13, 2025

• Update zhipuai-chat.adoc

  #3531 merged Jun 13, 2025

• docs: fix incorrect usage of tools and defaultTools

  #3533 merged Jun 13, 2025

• docs(web): fix broken links to ChatOptions and ChatOptions#builder()

  #3447 merged Jun 13, 2025

• feat: Add new Mistral AI chat models

  #3523 merged Jun 12, 2025

35 Pull requests opened by 28 people

• fix(MessageChatMemoryAdvisor): Fix incorrect prompt position for system messages

  #3520 opened Jun 12, 2025

• fix(streaming): Remove retry wrapper from chat model stream methods

  #3524 opened Jun 12, 2025

• fix(memory): Replace the outdated manual way of creating the ChatMemoryRepository

  #3532 opened Jun 13, 2025

• Add docker/mcp-gateway docker compose service connection

  #3536 opened Jun 13, 2025

• GH-3540: Allow user-provided embeddings in VectorStore

  #3541 opened Jun 14, 2025

• fixed #3559 Modify the DefaultToolCallResultConverter.convert method …

  #3568 opened Jun 17, 2025

• Add a method to delete all chat memories in ChatMemory

  #3590 opened Jun 18, 2025

• Oracle: add OracleChatMemory support

  #3601 opened Jun 19, 2025

• refactor(ai-client-chat): optimize conversation memory handling in PromptChatMemoryAdvisor

  #3605 opened Jun 19, 2025

• Fixed GH-3604, Add `STErrorListener` to `StTemplateRenderer`.

  #3606 opened Jun 19, 2025

• Provide a way for developers to set a custom StreamFunctionCallingHelper

  #3607 opened Jun 19, 2025

• chore: removed unused class file in openai moulde.

  #3636 opened Jun 22, 2025

• [REVIEW-ONLY-DO-NOT-MERGE] Initial sketch for unified hybrid search API

  #3658 opened Jun 25, 2025

• Support any nullable annotation for mark argument or field as nullable

  #3666 opened Jun 25, 2025

• fix: GH-3682 misspelling in documentation

  #3683 opened Jun 26, 2025

• Checkstyle fixes

  #3701 opened Jun 27, 2025

• enhanced-deepseek cot

  #3703 opened Jun 28, 2025

• Add `ISNULL`, `ISNOTNULL` Filter Expression

  #3706 opened Jun 28, 2025

• feat(template-st): log StringTemplate compile/runtime errors via SLF4J

  #3708 opened Jun 29, 2025

• [GH-3723] Vertex AI Gemini logprobs support

  #3724 opened Jul 2, 2025

• feat: support the chat_template_kwargs, with OpenAI-Compatible Server…

  #3744 opened Jul 4, 2025

• docs(mcp): add dynamic MCP client selection example

  #3751 opened Jul 6, 2025

• Fix string return conversion in DefaultToolCallResultConverter

  #3756 opened Jul 7, 2025

• feat(SimpleLoggerAdvisor): Add log level configuration function

  #3764 opened Jul 8, 2025

• Support responseSchema in VertexAiGeminiChatOptions

  #3765 opened Jul 8, 2025

• refactor: GH-3620 Add `BedrockChatOptions` to Bedrock

  #3770 opened Jul 9, 2025

• refactor: Simplifies VectorStoreChatMemoryAdvisor code

  #3773 opened Jul 9, 2025

• fix: update default sse-message-endpoint from /mcp/message to /mcp/messages

  #3779 opened Jul 10, 2025

• Feature (TokenTextCplitter): Add overlapping function for text segmentation #2123

  #3780 opened Jul 10, 2025

• fix: Handling default implementation of ToolCallback#call(String,ToolContext)

  #3784 opened Jul 10, 2025

• fix: Fixed the issue where the returnDirect attribute was not effective on the MCP server side.

  #3787 opened Jul 11, 2025

• Feat(rerank): Add Cohere Reranker with topN filtering and fallback support

  #3791 opened Jul 11, 2025

• McpSyncServer: set immediate execution when in a servlet context

  #3794 opened Jul 11, 2025

• GH-3690: Support customization of RedisVectorStore via builder customizer

  #3795 opened Jul 11, 2025

• feat(zhipuai): Support glm-4.1v-thinking-flash model

  #3796 opened Jul 11, 2025

125 Issues closed by 22 people

• could not found io.modelcontextprotocol.sdk:mcp:jar:0.11.0-SNAPSHOT in repo

  #3789 closed Jul 11, 2025

• When I use Gemini, if I am not configured in the configuration file, I cannot start how to close it, because I want to create it through the application.

  #3774 closed Jul 10, 2025

• Support for OpenAI /v1/responses

  #3766 closed Jul 9, 2025

• Support for Azure OpenAI Assistants API

  #3772 closed Jul 9, 2025

• Will `returnDirect = true` effect in mcp server?

  #3400 closed Jul 9, 2025

• Git clone with error: Filename too long

  #3125 closed Jul 9, 2025

• How to dynamically add McpSyncServer in a project and add sseendpoint as needed, such as /sse1, /sse2, /sse3....

  #3771 closed Jul 9, 2025

• Feature Request: Java Stream HTTP Support for MCP SDK

  #3752 closed Jul 9, 2025

• mcp-client-stdio-test bug

  #3598 closed Jul 8, 2025

• Support Foundry local https://github.com/microsoft/Foundry-Local

  #3628 closed Jul 8, 2025

• EsVectorStore Search NoSuchMethodError

  #3632 closed Jul 8, 2025

• When version 1.0.0-M5 uses elastic as vectorstore, the query will report that the method cannot be found

  #2220 closed Jul 8, 2025

• Docs: spring docs retrieval wrong method name

  #2296 closed Jul 8, 2025

• Improve the MCP document to stop referring to outdated DefaultMcpSession

  #3762 closed Jul 8, 2025

• Problems with the use of the chat memory function

  #3759 closed Jul 8, 2025

• AnthropicChatModel#stream produces too much output when calling tools

  #3650 closed Jul 7, 2025

• Please help improve the response speed of the model when using tools.

  #3676 closed Jul 7, 2025

• How to make tools/list return specific tool sets according to different business areas

  #3719 closed Jul 7, 2025

• Chat memory questions during use！

  #3754 closed Jul 7, 2025

• SystemPromptTemplate removes double curly braces {{...}} when rendering prompts

  #3721 closed Jul 7, 2025

• Anthropic Error Responses Can Cause NPE In StreamHelper

  #3757 closed Jul 7, 2025

• Anthropic Error Responses Can Cause NPE In StreamHelper

  #3740 closed Jul 7, 2025

• Invalid message type created when using SystemPromptTemplate builder

  #3745 closed Jul 4, 2025

• Invalid message type created when using SystemPromptTemplate builder

  #3526 closed Jul 4, 2025

• Incorrect use of ClassUtils.isAssignable

  #3741 closed Jul 3, 2025

• The isFunctionalType method of MethodToolVNet Provider is incorrect, resulting in some cases where the tool cannot be registered

  #3355 closed Jul 3, 2025

• Incorrect use of ClassUtils.isAssignable

  #3729 closed Jul 3, 2025

• Spring project startup error Failed to instantiate [org.springframework.ai.tool.ToolCallbackProvider]

  #2783 closed Jul 3, 2025

• Multiple SSE connections issue and SYNC mode startup failure in McpClientAutoConfiguration

  #2486 closed Jul 3, 2025

• Caused by: com.fasterxml.jackson.databind.exc.UnrecognizedPropertyException: Unrecognized field "tools"

  #2481 closed Jul 3, 2025

• Update anthropic-chat.adoc

  #3736 closed Jul 2, 2025

• Fix typos in chat client module

  #3735 closed Jul 2, 2025

• Remove CLA link from PR Template

  #3094 closed Jul 2, 2025

• Use diamond operator where possible

  #3734 closed Jul 2, 2025

• Fix annotation package

  #3732 closed Jul 2, 2025

• improve schema initialization logic and update deprecated code for Milvus vectorstore

  #3731 closed Jul 2, 2025

• Refactor: Add null check, optimize string joining, and add JavaDocs

  #3728 closed Jul 2, 2025

• Fix typo in token configuration documentation

  #3727 closed Jul 2, 2025

• Outdated new PromptTemplate(...) calls in Documentation

  #3720 closed Jul 2, 2025

• Outdated new PromptTemplate(...) calls in Documentation

  #3713 closed Jul 2, 2025

• spring ai doc is wrong

  #3715 closed Jul 1, 2025

• spring ai doc is wrong

  #3702 closed Jul 1, 2025

• doc: Remove duplicated dependency instructions in opensearch.adoc

  #3714 closed Jul 1, 2025

• when process toolcall and 'Map<String, Object> toolArguments = extractToolArguments(toolInput);' throws error

  #3709 closed Jul 1, 2025

• QdrantVectorStore throws NPE when Document contains only media

  #3700 closed Jun 27, 2025

• Transcription API File Extension Issue

  #3699 closed Jun 27, 2025

• doc: fix incorrect default embedding model reference in ollama-embeddings.adoc

  #3698 closed Jun 27, 2025

• Transcription API File Extension Issue

  #3557 closed Jun 27, 2025

• QdrantVectorStore throws NPE when Document contains only media

  #3609 closed Jun 27, 2025

• Convert Qdrant vector store IT use OpenAI embedding model

  #3697 closed Jun 27, 2025

• Observation can distinguish between different ChatModel or ChatClient instances

  #3473 closed Jun 27, 2025

• Add Elasticsearch to the README

  #3696 closed Jun 27, 2025

• chore: fix `SimpleApiKey` assert message

  #3692 closed Jun 27, 2025

• Adding multiple mcp server-configuration in a claude desktop json format doesn't work.

  #3685 closed Jun 27, 2025

• Spring AI M4 Observability Issue

  #2052 closed Jun 26, 2025

• fix(anthropic): prevent streaming tool calling responses when internal execution is enabled

  #3684 closed Jun 26, 2025

• AnthropicApi does not invoke nullary function tools when using streaming

  #2735 closed Jun 26, 2025

• Add link to javadoc on Content class

  #3681 closed Jun 26, 2025

• fix: Fixed some typo in the documentation and comments.

  #3680 closed Jun 26, 2025

• fix: remove unused options from ZhiPu model

  #3675 closed Jun 26, 2025

• fix: ZhiPuAiEmbedding supports custom dimensions

  #3674 closed Jun 26, 2025

• Remove `@Nullable` from VectorStore similaritySearch

  #3670 closed Jun 25, 2025

• Use OkHttpClient for AzureOpenAiAudioTranscriptionModelIT

  #3667 closed Jun 25, 2025

• ParagraphPdfDocumentReader throws java.lang.IndexOutOfBoundsException

  #3664 closed Jun 25, 2025

• ParagraphPdfDocumentReader throws java.lang.IndexOutOfBoundsException

  #3421 closed Jun 25, 2025

• Cleanup: Cleaned up redundant assignments in TextReader.

  #3662 closed Jun 25, 2025

• Fix incorrect ollama autoconfiguration changes

  #3661 closed Jun 25, 2025

• fix: Correct naming inconsistencies in Mistral package

  #3660 closed Jun 25, 2025

• [Refactor] Remove redundant null check in OpenAiApi.Builder#apiKey(String)

  #3659 closed Jun 25, 2025

• SafeGuardAdvisor lacks logs

  #3586 closed Jun 24, 2025

• fix: Added a license header for `FileDocumentWriterTest`

  #3655 closed Jun 24, 2025

• Add Missing Tests for FileDocumentWriter

  #3649 closed Jun 23, 2025

• Integrate ElevenLabs Text-to-Speech (TTS) as a supported provider within Spring AI.

  #2371 closed Jun 23, 2025

• migrate junit4 to junit5 in `JdbcChatMemoryRepositoryHsqldbAutoConfigIT`

  #3643 closed Jun 23, 2025

• docs: correct `SimpleLoggerAdvisor` documentation

  #3642 closed Jun 23, 2025

• chore: Remove useless proerties tags

  #3641 closed Jun 23, 2025

• NullPointerException org.springframework.ai.ollama.OllamaChatModel.from(OllamaChatModel.java:174)

  #3631 closed Jun 21, 2025

• Update tools.adoc

  #3626 closed Jun 20, 2025

• Remove hardcoded topK in BedrockConverseProxyChatProperties

  #3625 closed Jun 20, 2025

• Bedrock/Converse Chat Model Does not Properly Stream Tools When Using Suppliers vs Functions

  #3619 closed Jun 19, 2025

• Bedrock/Converse Chat Model Does not Properly Stream Tools When Using Suppliers vs Functions

  #1878 closed Jun 19, 2025

• chore: Remove unnecessary environment variable validation in `QdrantVectorStoreIT`

  #3617 closed Jun 19, 2025

• Streaming mode AssistantMessage does not retain toolCalls, causing issues with tool confirmation workflows

  #3616 closed Jun 19, 2025

• Streaming mode AssistantMessage does not retain toolCalls, causing issues with tool confirmation workflows

  #3366 closed Jun 19, 2025

• ToolCalling fail on vLLM server 0.9.1

  #3611 closed Jun 19, 2025

• ToolCalling fail on vLLM server 0.9.1

  #3534 closed Jun 19, 2025

• Refactor: Replace `System.err.println` with log output

  #3603 closed Jun 19, 2025

• Allow specifying credentials to vertexai embeddings model

  #1387 closed Jun 18, 2025

• Can't get vectorStoreTest with MongoDBAtlasVectorStore to work locally

  #1573 closed Jun 18, 2025

• Add support for Voyage embedding model

  #1513 closed Jun 18, 2025

• How can I implement the ChatMemory in an agentic workflow?

  #1408 closed Jun 18, 2025

• AWS Bedrock: Increase read timeout for chatModel

  #441 closed Jun 18, 2025

• Add Watson AI chat model support

  #2843 closed Jun 18, 2025

• When will Spring AI be released?

  #2587 closed Jun 18, 2025

• Update OpenAiChatModel.java

  #3594 closed Jun 18, 2025

• feat: `ChatClient#mutate` adds copies of `advisors` and `advisorParams`.

  #3593 closed Jun 18, 2025

• Update tools.adoc About toolDefinition parameter transfer error

  #3592 closed Jun 18, 2025

• Remove unused `messageHistory`

  #3591 closed Jun 18, 2025

• docs: fix broken link to `ChatModel`

  #3588 closed Jun 18, 2025

• 调用阿里百炼大模型的时候，调用工具流式输出会报错：Cannot invoke "String.equals(Object)" because "toolName" is null

  #3551 closed Jun 18, 2025

• The maven dependency `spring-ai-mcp-server-spring-boot-starter` for studio MCP server is missing in org.springframework.ai BOM v1.0.0

  #3563 closed Jun 18, 2025

• Fix Test Failure in ChromaVectorStoreAutoConfigurationIT

  #3584 closed Jun 18, 2025

• org.springframework.web.client.ResourceAccessException: I/O error on POST request for "https://api.siliconflow.cn/v1/chat/completions": Timeout on blocking read for 5000000000 NANOSECONDS

  #3480 closed Jun 18, 2025

• WebClientResponseException$UnprocessableEntity: 422 Unprocessable Entity

  #3567 closed Jun 18, 2025

• Fix exception in `OpenAiAudioTranscriptionResponseMetadata.toString`

  #3579 closed Jun 17, 2025

• Fix infinite recursion in `getMimeType(Path)` method

  #3578 closed Jun 17, 2025

• Enable custom configuration of more properties for weaviate vector store

  #3535 closed Jun 17, 2025

• When calling the Ollama chat model, Ollama responds slowly, causing a read timeout error

  #3573 closed Jun 17, 2025

• When calling the Ollama chat model, Ollama responds slowly, causing a read timeout error.

  #3572 closed Jun 17, 2025

• Chroma DB default tenant and database : should be able to ovverride through application properties

  #3571 closed Jun 17, 2025

• Chroma DB default tenant and database : should be able to ovverride through application properties

  #3542 closed Jun 17, 2025

• fix: Incorrect outputModalities judgment in stream mode

  #3570 closed Jun 17, 2025

• Reuse DocumentRowMapper instance to reduce redundant object creation

  #3569 closed Jun 17, 2025

• spring ai mcp server multi-instance solution

  #3515 closed Jun 17, 2025

• spring.ai.chat.client.enable=false not working

  #3561 closed Jun 17, 2025

• Improved the documentation in the MCP Server Boot Starter regarding Starter selection

  #3556 closed Jun 16, 2025

• `spring.ai.tools.observations.include-content` can not be resolved by IDEA

  #3550 closed Jun 16, 2025

• Features that Springai must support

  #2882 closed Jun 16, 2025

• 调用工具流式输出会报空指针异常： Cannot invoke "java.time.Duration.plus(java.time.Duration)" because "evalDuration" is null

  #3549 closed Jun 16, 2025

• Adding custom CardinalityKeyValue did not work

  #3393 closed Jun 13, 2025

• Using `spring.ai.azure.openai.chat.options.response-format=json` won't allow Arrays

  #3508 closed Jun 13, 2025

• LLM native returns

  #3174 closed Jun 13, 2025

• The FilterExpressionTextParser cannot parse Long type values

  #3509 closed Jun 13, 2025

• The Ollama model does not support retries, unlike most other models.

  #2372 closed Jun 12, 2025

• ToolContext没有被传递

  #3510 closed Jun 12, 2025

61 Issues opened by 58 people

• StTemplateRenderer delimiter token allows multiple characters

  #3800 opened Jul 12, 2025

• Doc: Wrong dependency info in the RAG doc

  #3798 opened Jul 11, 2025

• Feature Request: Allow configuration of payload content key for QdrantVectorStore

  #3797 opened Jul 11, 2025

• open ai + vllm 工具调用模型死循环不返回

  #3793 opened Jul 11, 2025

• Add ChatClient getChatModel() method

  #3790 opened Jul 11, 2025

• response.getEvalDuration(); threw a NullPointerException.

  #3788 opened Jul 11, 2025

• Add Support for OpenAI based64 format embedding responses

  #3786 opened Jul 11, 2025

• Unable to start app after setting up opensearch vector store

  #3785 opened Jul 10, 2025

• Official Claude 4 Support

  #3783 opened Jul 10, 2025

• Add MCP Client Streamable HTTP transport auto-configuration

  #3782 opened Jul 10, 2025

• Does it support video inference

  #3777 opened Jul 10, 2025

• Question about Tool Call Information in Multi-Turn Conversations

  #3776 opened Jul 10, 2025

• Please confirm if it is a bug,Springai encountered an error while calling VLLM

  #3775 opened Jul 10, 2025

• mcp illegal jsonrpc

  #3769 opened Jul 9, 2025

• Streaming with tools not working with Anthropic ChatClient

  #3767 opened Jul 8, 2025

• A few minutes after the mcp client connects, the server will be disconnected

  #3763 opened Jul 8, 2025

• TransformersEmbeddingModel and configuration of Threads

  #3761 opened Jul 8, 2025

• Make the setting spring.ai.openai.api-key optional

  #3753 opened Jul 7, 2025

• Can this Spring AI compete official Typescript AI SDKs?

  #3750 opened Jul 5, 2025

• run license:update-file-header faild

  #3749 opened Jul 4, 2025

• com.fasterxml.jackson.databind.JsonMappingException: Unexpected end-of-input: was expecting closing quote for a string value at [Source: REDACTED (`StreamReadFeature.INCLUDE_SOURCE_IN_LOCATION` disabled); line: 43, column: 43]

  #3748 opened Jul 4, 2025

• sse client doesn't support like reconnect

  #3742 opened Jul 4, 2025

• VectorStore filter improve

  #3739 opened Jul 3, 2025

• Hope to provide support for Ollama's thinking mode

  #3738 opened Jul 3, 2025

• AssistantMessage doesn't support 'name' property

  #3737 opened Jul 3, 2025

• Reasoning options documented in docs

  #3725 opened Jul 2, 2025

• Vertex AI Gemini logprobs support

  #3723 opened Jul 2, 2025

• Spring AI Kotlin Coroutines

  #3718 opened Jul 2, 2025

• Cannot Set Image detail Option (e.g., "low") When Using Multimodal Input in Spring AI

  #3710 opened Jun 30, 2025

• FilterExpressionTextParser does not support 'null' values

  #3694 opened Jun 27, 2025

• [EPIC] - Support latest Google Unifed SDK to access Google AI Models

  #3693 opened Jun 27, 2025

• spring ai supports tool chaining

  #3691 opened Jun 27, 2025

• RedisVectorStore auto-configuration does not support metadataFields, causing chat memory retrieval failure

  #3690 opened Jun 27, 2025

• Misspelling in Documentation

  #3682 opened Jun 26, 2025

• Question about sglang + deepseek

  #3657 opened Jun 24, 2025

• mcp server header data deliver to tools

  #3647 opened Jun 23, 2025

• Feature Request: Add public getters for configuration fields in TokenTextSplitter

  #3644 opened Jun 23, 2025

• How can I obtain the information before and after the tool call using the streaming call tool?

  #3639 opened Jun 23, 2025

• question: About the purpose of class file `ImageResponseMetadata`

  #3635 opened Jun 22, 2025

• Is the `embeddingDistance` Method in `PgVectorStore` Necessary?

  #3630 opened Jun 21, 2025

• spring ai bedrock converse properties auto completion doesn't auto complete

  #3620 opened Jun 19, 2025

• PromptTemplate should configure error reporting in String Template

  #3604 opened Jun 19, 2025

• I need a solution to instable tool calling behavior in deepseek

  #3602 opened Jun 19, 2025

• JdbcChatMemoryRepository do not persist Media in UserMessage

  #3597 opened Jun 18, 2025

• Search failed in RagFlow's ElasticSearch, returned 400

  #3596 opened Jun 18, 2025

• Most of classes implementing BaseAdvisor lacks logs

  #3587 opened Jun 18, 2025

• PgVectorStore does not handle ANDs and ORs together properly when using the FilterExpressionBuilder

  #3577 opened Jun 17, 2025

• Feature Request: Add a Property to Disable All AI Models at Once

  #3566 opened Jun 17, 2025

• Automatically generate conversionId and return suggestions in the message body

  #3565 opened Jun 17, 2025

• I hope the next version can provide the functionality of openai request and response formats

  #3560 opened Jun 17, 2025

• Modify the DefaultToolCallResultConverter.convert method and add filtering code

  #3559 opened Jun 17, 2025

• Should allow to override the column name 'content' for pgvector, weaviate

  #3547 opened Jun 16, 2025

• Ollama thinking mode

  #3543 opened Jun 15, 2025

• Support Custom User-Provided Embeddings in VectorStore add(...) Method

  #3540 opened Jun 14, 2025

• Bug: DefaultAroundAdvisorChain fails to maintain immutability across multiple calls

  #3537 opened Jun 14, 2025

• feat support ChatResponse revert to ChatCompletion

  #3530 opened Jun 13, 2025

• OpenAI API returns body as empty

  #3528 opened Jun 13, 2025

• We need the Spring AI framework to support java8 我们需要spring ai框架支持java8

  #3527 opened Jun 13, 2025

• Getting Error: getting embedding channel not registered to an event loop when calling model.embed (azure open ai)

  #3522 opened Jun 12, 2025

• I want to have a function that I can define as a tool for tool invocation. The parameter of the function is an object type, such as public String test(User user). How should I define this tool?

  #3519 opened Jun 12, 2025

• Auto-Configuration for Multiple Beans of the Same Type

  #3518 opened Jun 12, 2025

107 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• ToolCallingChatOptions support internalToolExecutionMaxIterations, to limit the maximum number of tool calls and prevent infinite recursive calls to LLM in special cases

  #3380 commented on Jul 8, 2025 • 9 new comments

• Added support for the "think" for Ollama

  #3386 commented on Jun 24, 2025 • 4 new comments

• Ollama: Support custom Ollama API paths

  #3470 commented on Jul 8, 2025 • 1 new comment

• Fixed GH-3509 Added support for Long type in FilterExpressionTextParser.

  #3516 commented on Jun 13, 2025 • 0 new comments

• Added new VertexAI Anthropic's model module

  #1213 commented on Jul 11, 2025 • 0 new comments

• feat: add hugging face text to image integration

  #1162 commented on Jul 11, 2025 • 0 new comments

• Bedrock API: Add option to configure API endpoint (#1018)

  #1063 commented on Jun 23, 2025 • 0 new comments

• Add self-query advisor

  #1019 commented on Jul 11, 2025 • 0 new comments

• After the mcp server restarts, the client will return 404.

  #3337 commented on Jul 11, 2025 • 0 new comments

• Request to Make ChatOptions Runtime-Validated Instead of Required at Startup

  #3404 commented on Jul 11, 2025 • 0 new comments

• VectorStore interface should be split, with readonly operations becoming a super interface

  #1290 commented on Jul 11, 2025 • 0 new comments

• Support A2A Protocol

  #2911 commented on Jul 11, 2025 • 0 new comments

• Spring AI MCP Streamable HTTP

  #3145 commented on Jul 11, 2025 • 0 new comments

• com.google.api.gax.rpc.UnknownException: java.net.SocketTimeoutException: Read timed out

  #1577 commented on Jul 11, 2025 • 0 new comments

• block()/blockFirst()/blockLast() are blocking, which is not supported in thread reactor-http-nio-3

  #2533 commented on Jul 11, 2025 • 0 new comments

• openai options support extra params

  #3409 commented on Jul 11, 2025 • 0 new comments

• ToolCallback fails if tool context is provided

  #3389 commented on Jul 10, 2025 • 0 new comments

• After migrating from milestones to stable, Observability stopped exposing input/output (null)

  #3401 commented on Jul 10, 2025 • 0 new comments

• Support for Text Chunking with Overlap in TokenTextSplitter

  #2123 commented on Jul 10, 2025 • 0 new comments

• @Tool returnDirect Attribute Ignored

  #3481 commented on Jul 10, 2025 • 0 new comments

• Can multiple MCP servers with different endpoints be published in one service?

  #3299 commented on Jul 10, 2025 • 0 new comments

• Support image moderation in OpenAI

  #2832 commented on Jul 9, 2025 • 0 new comments

• Vertex AI Streaming not working

  #3313 commented on Jul 9, 2025 • 0 new comments

• "Request was interrupted: null" error when VectorStore.save is called with a List<Document> whose size is large

  #3370 commented on Jul 9, 2025 • 0 new comments

• Is it considered to support AG-UI Protocol?

  #3260 commented on Jul 8, 2025 • 0 new comments

• Support Vector Databases Multiple indexes or collections

  #468 commented on Jul 8, 2025 • 0 new comments

• Consider caching JSON schema generation in function calling

  #3403 commented on Jul 7, 2025 • 0 new comments

• MCP server: Authentication lost in tool execution

  #2506 commented on Jul 5, 2025 • 0 new comments

• Support asynchronous/reactive function calling

  #1778 commented on Jun 25, 2025 • 0 new comments

• Add support for OpenAI's Create Image Edit API

  #3484 commented on Jun 24, 2025 • 0 new comments

• fix: Incorrect order when Advisors have the same order

  #3461 commented on Jun 24, 2025 • 0 new comments

• ChatClientAutoConfiguration should back off if there are multiple ChatModels

  #3429 commented on Jun 18, 2025 • 0 new comments

• An implementation of ChatMemory based on token size control

  #3424 commented on Jul 10, 2025 • 0 new comments

• Create new ToolChatOptions if input request has tool configuration without options

  #3397 commented on Jun 24, 2025 • 0 new comments

• fix(ai-rag): Fix query expansion result handling logic, same as #3345

  #3347 commented on Jun 24, 2025 • 0 new comments

• fix: omit temperature for search models and add tests

  #3315 commented on Jun 21, 2025 • 0 new comments

• Fix PropmptTemplate typo in structured-output-api.jpg

  #3304 commented on Jul 11, 2025 • 0 new comments

• Add Spring SpEL implementation of TemplateRenderer

  #3262 commented on Jul 11, 2025 • 0 new comments

• Provides a Jinja2 implementation for TemplateRenderer

  #3259 commented on Jul 11, 2025 • 0 new comments

• Make `BedrockAwsConnectionProperties#region` empty by default

  #3225 commented on Jun 23, 2025 • 0 new comments

• add aws bedrock prompt-caching support

  #3213 commented on Jul 11, 2025 • 0 new comments

• feat(memory): First commit of file-based memory repository

  #3210 commented on Jul 11, 2025 • 0 new comments

• fix(redis): Implement ChatMemoryRepository interface and fix test connectivity

  #2991 commented on Jun 12, 2025 • 0 new comments

• fix method tool call throws same method name

  #2774 commented on Jul 3, 2025 • 0 new comments

• Add filter query support for GemFireVectorStore

  #2753 commented on Jul 8, 2025 • 0 new comments

• Create MongoDB chat memory implementation

  #2679 commented on Jul 11, 2025 • 0 new comments

• feat: add OpenAI transcribe and TTS models

  #2540 commented on Jun 23, 2025 • 0 new comments

• feat: Add Mistral AI OCR API integration

  #2404 commented on Jul 11, 2025 • 0 new comments

• feat(redis): Add Redis-based semantic caching and chat memory implementations

  #2295 commented on Jul 11, 2025 • 0 new comments

• Adding Vertex AI Imagen models support

  #2144 commented on Jun 17, 2025 • 0 new comments

• feat(spring-ai-bedrock-converse): Introduce BedrockProxyChatOptions

  #1760 commented on Jun 23, 2025 • 0 new comments

• feature: Add common TranscriptionModel interface for audio transcription

  #1484 commented on Jul 11, 2025 • 0 new comments

• Support StabilityAi Image Edit Api

  #1344 commented on Jul 11, 2025 • 0 new comments

• Enhanced Vector Store Capabilities with Full-Text/Hybrid Search and Reranking

  #1227 commented on Jul 1, 2025 • 0 new comments

• How can the MCP Client dynamically set the Header?

  #2658 commented on Jun 24, 2025 • 0 new comments

• server.servlet.context-path not properly factoring into SSE MCP server path

  #2512 commented on Jun 24, 2025 • 0 new comments

• SpringAI does not follow the AWS SDK's default region resolution rules

  #823 commented on Jun 23, 2025 • 0 new comments

• Change the BedrockAwsConnectionProperties region property to be empty by default

  #3223 commented on Jun 23, 2025 • 0 new comments

• ToolContext is not supported by the MCP tools

  #3505 commented on Jun 23, 2025 • 0 new comments

• Add advanced RAG (Hybrid Search and Semantic Hybrid Search) with Azure AI Search

  #517 commented on Jun 21, 2025 • 0 new comments

• Add Support for Customization to McpClientTransport

  #2917 commented on Jun 21, 2025 • 0 new comments

• MPC Client fails application startup when server is unavailable - need graceful degradation option

  #3232 commented on Jun 21, 2025 • 0 new comments

• Model incompatible request argument supplied: temperature

  #3253 commented on Jun 21, 2025 • 0 new comments

• EPIC - Structured Output Improvements

  #2787 commented on Jun 19, 2025 • 0 new comments

• Generate complex Json schemas with BeanOutputConverter

  #794 commented on Jun 19, 2025 • 0 new comments

• Unable to use spring ai with LMStudio using spring-ai openai module

  #2441 commented on Jun 18, 2025 • 0 new comments

• Implement support for Cloudflare Workers AI

  #1436 commented on Jun 18, 2025 • 0 new comments

• Add batching strategy for all vector store implementations

  #1261 commented on Jun 18, 2025 • 0 new comments

• Add docs and examples for spring-ai-test

  #88 commented on Jun 18, 2025 • 0 new comments

• Add support for Mistral OCR

  #2582 commented on Jun 18, 2025 • 0 new comments

• openai chat error

  #2653 commented on Jun 18, 2025 • 0 new comments

• Add Headers (Authorization) to ToolContext to be used by tool call back method

  #3476 commented on Jun 17, 2025 • 0 new comments

• Unable to use Tools - No @Tool annotated methods found

  #3485 commented on Jun 17, 2025 • 0 new comments

• Support for the @PreAuthorize annotation in @Tool Components

  #3272 commented on Jun 16, 2025 • 0 new comments

• Documentation: The example code for Vision in the OpenAI reference documentation is incorrect.

  #3486 commented on Jun 16, 2025 • 0 new comments

• Feature Request: Support for Invoking HTTP-based APIs via OpenAPI Spec

  #806 commented on Jun 15, 2025 • 0 new comments

• The specifications for mcp 2025-03-26 support.

  #3301 commented on Jun 15, 2025 • 0 new comments

• RedisVectorStore search incorrect

  #2514 commented on Jun 13, 2025 • 0 new comments

• when use deepseek-r1 mode in mcp call return the error of 400 Bad Request

  #3437 commented on Jun 13, 2025 • 0 new comments

• Wrong implementation of MethodToolCallback.validateToolContextSupport

  #3466 commented on Jun 12, 2025 • 0 new comments

• Supporting multiple LLMs in auto-config

  #2610 commented on Jul 5, 2025 • 0 new comments

• MistralAiChatModel returns an error if MessageChatMemoryAdvisor is used

  #2380 commented on Jul 4, 2025 • 0 new comments

• How does zhipu ai embeddings model support dimensions parameters

  #1857 commented on Jul 4, 2025 • 0 new comments

• Support for OpenAI Responses API

  #2962 commented on Jul 4, 2025 • 0 new comments

• MCP Context Propagation

  #2967 commented on Jul 4, 2025 • 0 new comments

• Support for Re-ranking Retrieval Optimization in Advanced RAG

  #1366 commented on Jul 4, 2025 • 0 new comments

• JsonParser is using a self instantiated ObjectMapper, allow usage of a custom ObjectMapper instance

  #2494 commented on Jul 3, 2025 • 0 new comments

• Spring AI vector store operations not reactive-friendly

  #3255 commented on Jul 3, 2025 • 0 new comments

• MCP Server how to refresh resources and sendNotification to client

  #2777 commented on Jul 3, 2025 • 0 new comments

• MCP Server @Tool throws "Multiple tools with the same name"

  #2771 commented on Jul 3, 2025 • 0 new comments

• SSE方式接入高德MCP报错

  #2758 commented on Jul 3, 2025 • 0 new comments

• After restarting the mcp server, the previous client will not automatically reconnect

  #2740 commented on Jul 3, 2025 • 0 new comments

• When I chat robot configuration MCP client for https://openrouter.ai/api/, the corresponding model is deepseek/deepseek - chat - v3-0324: when free Returns an error

  #2675 commented on Jul 3, 2025 • 0 new comments

• Tools MethodToolCallback， parameter name cannot be matched

  #2947 commented on Jul 3, 2025 • 0 new comments

• Unstable MCP implementation for reactive webflux client (IntelliJ MCP not working)

  #3116 commented on Jul 3, 2025 • 0 new comments

• Connect to the n8n MCP server using SSE.

  #3178 commented on Jul 3, 2025 • 0 new comments

• The overload `tools` or `defaultTools` method in `ChatClientBuilder` causes FunctionToolCallback not taking effect.

  #2495 commented on Jul 3, 2025 • 0 new comments

• Bug: Document class causes assertion failure when 'content' is missing in JSON

  #2279 commented on Jul 2, 2025 • 0 new comments

• Jackson 2.18.4 version: java.lang.AbstractMethodError

  #3474 commented on Jul 2, 2025 • 0 new comments

• Why does MCP sse client do not have heartbeat detection

  #2795 commented on Jul 1, 2025 • 0 new comments

• Add support for Models that are accessed via the new google java-genapi

  #2272 commented on Jul 1, 2025 • 0 new comments

• Allow using OpenAI tools like 'web_search_preview'

  #3022 commented on Jun 30, 2025 • 0 new comments

• Support accessing HTTP headers in ToolContext when using WebFlux

  #2757 commented on Jun 30, 2025 • 0 new comments

• Unable to start application : VertexAiEmbeddingConnectionAutoConfiguration.class: Failed to instantiate | ClassNotFoundException: com.google.auth.oauth2.SecureSessionAgent

  #3453 commented on Jun 26, 2025 • 0 new comments

• How to add multi-model support via Spring AI 1.0.0 custom configurations for Azure OpenAI?

  #3475 commented on Jun 26, 2025 • 0 new comments

• Ollama inference thread not terminating after HTTP request is interrupted, causing GPU resource leak

  #2944 commented on Jun 26, 2025 • 0 new comments

• Incorrect Error handling when calling MCP tools

  #2857 commented on Jun 26, 2025 • 0 new comments