spring-ai
spring-ai copied to clipboard
An Application Framework for AI Engineering
I'am trying to use AzureOpenAiChatClient. When I'am using the stream() method, I can not get info about input and output tokens. It seems all is 0. But i can get...
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...
I am writing some blog post on Ollama et Spring AI and I wonder if it's a bug or a bad configuration on my end but when I do a...
java.lang.NullPointerException: Cannot invoke "java.util.List.stream()" because the return value of "org.springframework.ai.openai.api.OpenAiApi$ChatCompletion.choices()" is null at org.springframework.ai.openai.OpenAiChatClient.lambda$call$1(OpenAiChatClient.java:153) at org.springframework.retry.support.RetryTemplate.doExecute(RetryTemplate.java:335) at org.springframework.retry.support.RetryTemplate.execute(RetryTemplate.java:211) at org.springframework.ai.openai.OpenAiChatClient.call(OpenAiChatClient.java:141) org.springframework.ai spring-ai-openai-spring-boot-starter 1.0.0-SNAPSHOT
Instead of manually setting the url use containers OOTB URL
basically, spring boot can automatically during development create a connetion to a running docker image or to a testcontainer, allowing the user to avoid having to specify all this in...
This PR provides a more performant search function for the Elasticsearch vector store and removes the bean autoconfiguration. ## In depth ### Autoconfiguration The current implementation of `afterPropertiesSet()` automatically creates...
## Background Hey there, while developing with Spring Boot, I encountered issues with Jackson deserialization when storing historical messages into the Redis client. After troubleshooting using the control variable method,...
**Expected Behavior** I would like to be able to extract SafetyRatings from ChatResponse returned by VertexAiGeminiChatClient.call(Prompt prompt). GenerateContentResponse contains list of SafetyRatings on each Candidate, so the data is already...
at the moment there is initialization done on every run of `PgVectorStore`, which delays the startup time significantly. (more than double my normal startup time) It would be good to:...