MLE-26953 Chunks now capture model name

[rjrudin]

This is using embeddingModel.getModelName() in the LangChain4j API, and it will allow for Nuclia integration to easily add the model name found in each chunk response.

[github-actions]

Copyright Validation Results
Total: 14 | Passed: 14 | Failed: 0 | Skipped: 0 | at: 2026-02-03 17:38:14 UTC | commit: 293d991

✅ Valid Files

• marklogic-spark-connector/src/main/java/com/marklogic/langchain4j/embedding/EmbeddingGenerator.java
• marklogic-spark-connector/src/main/java/com/marklogic/spark/core/ChunkInputs.java
• marklogic-spark-connector/src/main/java/com/marklogic/spark/core/DocumentInputs.java
• marklogic-spark-connector/src/main/java/com/marklogic/spark/core/DocumentPipeline.java
• marklogic-spark-connector/src/main/java/com/marklogic/spark/core/embedding/Chunk.java
• marklogic-spark-connector/src/main/java/com/marklogic/spark/core/embedding/DOMChunk.java
• marklogic-spark-connector/src/main/java/com/marklogic/spark/core/embedding/JsonChunk.java
• marklogic-spark-connector/src/main/java/com/marklogic/spark/core/splitter/JsonChunkDocumentProducer.java
• marklogic-spark-connector/src/main/java/com/marklogic/spark/core/splitter/XmlChunkDocumentProducer.java
• marklogic-spark-connector/src/test/java/com/marklogic/spark/writer/embedding/AbstractEmbeddingTest.java
• marklogic-spark-connector/src/test/java/com/marklogic/spark/writer/embedding/AddEmbeddingsFromTextTest.java
• marklogic-spark-connector/src/test/java/com/marklogic/spark/writer/embedding/AddEmbeddingsToJsonTest.java
• marklogic-spark-connector/src/test/java/com/marklogic/spark/writer/embedding/AddEmbeddingsToXmlTest.java
• marklogic-spark-connector/src/test/java/com/marklogic/spark/writer/embedding/TestEmbeddingModel.java

✅ All files have valid copyright headers!

[Copilot]

Pull request overview

This PR adds support for capturing and storing the model name in chunks when generating embeddings. The change leverages the LangChain4j API's getModelName() method to retrieve the model name from the embedding model and stores it alongside the embedding vector in both JSON and XML chunk documents.

Changes:

• Modified the Chunk interface and its implementations to accept a modelName parameter in the addEmbedding method
• Updated EmbeddingGenerator to retrieve and pass the model name when adding embeddings to chunks
• Added comprehensive test coverage to verify model name storage across different document formats and configurations

Reviewed changes

Copilot reviewed 14 out of 14 changed files in this pull request and generated 1 comment.

Show a summary per file

File	Description
Chunk.java	Updated interface signature to include modelName parameter
DOMChunk.java	Added XML element creation for model-name in the embedding namespace
JsonChunk.java	Added model-name field to JSON chunk objects
ChunkInputs.java	Added modelName field with getter/setter methods
DocumentInputs.java	Updated to pass modelName when setting embeddings on chunks
DocumentPipeline.java	Updated wrapper to forward modelName parameter
EmbeddingGenerator.java	Captures model name from embedding model and passes it to chunks
XmlChunkDocumentProducer.java	Updated method calls to include modelName parameter
JsonChunkDocumentProducer.java	Updated method calls to include modelName parameter
AbstractEmbeddingTest.java	New test base class with shared test constants including expected model name
AddEmbeddingsToXmlTest.java	Extended test coverage to verify model name storage in XML documents
AddEmbeddingsToJsonTest.java	Extended test coverage to verify model name storage in JSON documents
AddEmbeddingsFromTextTest.java	Extended test coverage to verify model name storage in text-based embeddings
TestEmbeddingModel.java	Updated test implementation to match new interface signature

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

The parameter documentation is incomplete. Add descriptions explaining what each parameter represents. For example: '@param embedding the vector embedding data as a float array' and '@param modelName the name of the model used to generate the embedding'.

Suggested change

	* @param embedding
	* @param modelName
	* @param embedding the vector embedding data associated with this chunk
	* @param modelName the name of the model used to generate the embedding