spring-ai

spring-ai copied to clipboard

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

7

* Add semantic caching for chat responses: - SemanticCache interface and Redis implementation using vector similarity - SemanticCacheAdvisor for intercepting and caching chat responses - Uses vector search to cache...

bsbodden

Docs don't show these as bullets because they are in a note block.

3

Was going through the notes and noticed this.

jrgleason

See most notable changes here - https://tika.apache.org/3.1.0/index.html

dafriz

Fix: Prevent exceptions when disabling MCP Server

1

- Prevent projects depending on `mcp-server-webmvc` or `mcp-server-webflux` from exceptions when `spring.ai.mcp.server.enabled` is set to `false`. - Add unit tests to verify. When the project depends on the `spring-ai-starter-mcp-server-webmvc` package...

YunKuiLu

fix null systemText in PromptChatMemoryAdvisor

1

I started having `null` word in LLM prompts while using PromptChatMemoryAdvisor. Since `systemText` is `@Nullable`, as a fix I added check for it. 

MilosHavranek

Make ChatClient and Advisor APIs more robust, consistent, and flexible

3

### Advisor API The Advisor API went through some changes over time. Initially, there was a concept of "advisor type", with separate interfaces for "before", "after", and "around" advisors. Currently,...

ThomasVitale

Fixes: #2518 Issue: https://github.com/spring-projects/spring-ai/issues/2518 This commit removes the deprecated requestOptions field from ChatModelObservationContext and EmbeddingModelObservationContext classes. Instead of passing options separately, the code now retrieves them directly from the request...

sobychacko

Cassandra Chat Memory: Fixed message order

2

Fixes issue #2815 This PR solves problem with message ordering: CassandraChatMemory fetches rows in DESC order (by message_timestamp), and MessageChatMemoryAdvisor get and add all messages in that order - from...

linarkou

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

6

Please do a quick search on GitHub issues first, there might be already a duplicate issue for the one you are about to create. If the bug is trivial, just...

jorge-trujillo

I don't see any document references to it and there are no tests so I'm not 100% but looking at LastMaxTokenSizeContentPurger it appears to return all content that will not...

jasonparallel