HDDS-14816. Add Recon AI Assistant backend foundation with Multi LLM integration #9915
There are no files selected for viewing
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -62,6 +62,18 @@ | |
| <groupId>commons-io</groupId> | ||
| <artifactId>commons-io</artifactId> | ||
| </dependency> | ||
| <dependency> | ||
| <groupId>dev.langchain4j</groupId> | ||
| <artifactId>langchain4j-anthropic</artifactId> | ||
|
Contributor
There was a problem hiding this comment. If you run
Contributor
Author
There was a problem hiding this comment. Thanks for pointing out the OkHttp dependency tree. I dug into this, and because Because they are technically different artifacts, adding an At runtime, both JARs will be present on the classpath. Fortunately, this won't cause a problem because OkHttp 5.x is highly backward-compatible with 4.x. The JVM will simply load the If we ever want to strictly enforce a single OkHttp version across the entire project to avoid classpath pollution, the safest way would be to manage both cc: @devmadhuu |
||
| </dependency> | ||
| <dependency> | ||
| <groupId>dev.langchain4j</groupId> | ||
| <artifactId>langchain4j-core</artifactId> | ||
| </dependency> | ||
|
Comment on lines
+69
to
+72
Contributor
There was a problem hiding this comment. https://github.com/ArafatKhan2198/ozone/actions/runs/26503992485/job/78053259617#step:13:18
Contributor
Author
There was a problem hiding this comment. Done. I've updated both jar-report.txt and LICENSE.txt to include the new transitive dependencies introduced by LangChain4j (such as jtokkit, okhttp, retrofit, and kotlin-stdlib). |
||
| <dependency> | ||
| <groupId>dev.langchain4j</groupId> | ||
| <artifactId>langchain4j-open-ai</artifactId> | ||
| </dependency> | ||
| <dependency> | ||
| <groupId>info.picocli</groupId> | ||
| <artifactId>picocli</artifactId> | ||
|
|
||
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Why was this changed? We use a small value to reduce chances of disk out of space error in acceptance tests.