Pre-Retrieval: * Consolidated naming and documentation
Retrieval: * Consolidated naming and documentation * Introduced DocumentJoiner sub-module and CompositionDocumentJoiner operator
Post-Retrieval: * Introduced main interfaces for sub-modules. Implementation waiting for missing features in Document APIs
Orchestration: * Introduced QueryRouter sub-module and AllDocumentRetrieversQueryRouter operator
Generation: * Consolidated naming and documentation
Advisor: * Introduced BaseAdvisor to reduce boilerplate when implementing Advisors * Extended RetrievalAugmentationAdvisor to include the new sub-modules
Relates to #gh-1603
Comment From: markpollack
I had to add
<dependency>
<groupId>io.micrometer</groupId>
<artifactId>context-propagation</artifactId>
<scope>test</scope>
</dependency>
to the spring-ai-integration-test
to avoid classdef not found . I would have thought it would come transitively.
Comment From: markpollack
This test didn't pass in the maven build in the terminal, but does in the IDE.
[ERROR] org.springframework.ai.integration.tests.client.advisor.RetrievalAugmentationAdvisorIT.ragWithTranslation -- Time elapsed: 2.402 s <<< FAILURE!
java.lang.AssertionError:
Expecting actual:
"Anacletus og Birbas eventyr finder sted i de skotske højland."
to contain:
"Highlands"
(ignoring case)
at org.springframework.ai.integration.tests.client.advisor.RetrievalAugmentationAdvisorIT.ragWithTranslation(RetrievalAugmentationAdvisorIT.java:131)
at java.base/java.lang.reflect.Method.invoke(Method.java:569)
at java.base/java.util.ArrayList.forEach(ArrayList.java:1511)
at java.base/java.util.ArrayList.forEach(ArrayList.java:1511)
seems like the model sometimes doesn't follow instructions?
Comment From: markpollack
merged in d759fb294bac1a811283d4a620fa0d15c66409d8 Will see how well the CI handles the test.