GH-1826 Fix EmbeddingModel's usage on Document#embedding

- Since the Document object's reference to the `embedding` is deprecated and will be removed, the VectorStore implementations require a way to store the embedding of the corresponding Document objects

     - One way to fix this is, to have the EmbeddingModel#embed to return the embeddings in the same order as that of the Documents passed to it.

       - Since both the Document and embedding collections use the List object, their iteration operation will make sure to keep them in line with the same order.

       - A fix is required to preserve the order when batching strategy is applied.
	  - Updated the Javadoc for BatchingStrategy
          - Fixed the Document List order in TokenCountBatchingStrategy

    - Refactored the vector store implementations to update this change

Resolves #GH-1826

spring-ai-core/src/main/java/org/springframework/ai/embedding/BatchingStrategy.java

@@ -31,7 +31,9 @@ public interface BatchingStrategy {
 
 	/**
 	 * {@link EmbeddingModel} implementations can call this method to optimize embedding
-	 * tokens. The incoming collection of {@link Document}s are split into su-batches.
+	 * tokens. The incoming collection of {@link Document}s are split into sub-batches. It
+	 * is important to preserve the order of the list of {@link Document}s when batching
+	 * as they are mapped to their corresponding embeddings by their order.
 	 * @param documents to batch
 	 * @return a list of sub-batches that contain {@link Document}s.
 	 */

spring-ai-core/src/main/java/org/springframework/ai/embedding/EmbeddingModel.java

@@ -78,25 +78,23 @@ public interface EmbeddingModel extends Model<EmbeddingRequest, EmbeddingRespons
 	 * @param options {@link EmbeddingOptions}.
 	 * @param batchingStrategy {@link BatchingStrategy}.
 	 * @return a list of float[] that represents the vectors for the incoming
-	 * {@link Document}s.
+	 * {@link Document}s. The returned list is expected to be in the same order of the
+	 * {@link Document} list.
 	 */
 	default List<float[]> embed(List<Document> documents, EmbeddingOptions options, BatchingStrategy batchingStrategy) {
 		Assert.notNull(documents, "Documents must not be null");
-		List<float[]> embeddings = new ArrayList<>();
-
+		List<float[]> embeddings = new ArrayList<>(documents.size());
 		List<List<Document>> batch = batchingStrategy.batch(documents);
-
 		for (List<Document> subBatch : batch) {
 			List<String> texts = subBatch.stream().map(Document::getContent).toList();
 			EmbeddingRequest request = new EmbeddingRequest(texts, options);
 			EmbeddingResponse response = this.call(request);
 			for (int i = 0; i < subBatch.size(); i++) {
-				Document document = subBatch.get(i);
-				float[] output = response.getResults().get(i).getOutput();
-				embeddings.add(output);
-				document.setEmbedding(output);
+				embeddings.add(response.getResults().get(i).getOutput());
 			}
 		}
+		Assert.isTrue(embeddings.size() == documents.size(),
+				"Embeddings must have the same number as that of the documents");
 		return embeddings;
 	}
 

spring-ai-core/src/main/java/org/springframework/ai/embedding/TokenCountBatchingStrategy.java

@@ -17,7 +17,7 @@
 package org.springframework.ai.embedding;
 
 import java.util.ArrayList;
-import java.util.HashMap;
+import java.util.LinkedHashMap;
 import java.util.List;
 import java.util.Map;
 
@@ -139,7 +139,9 @@ public class TokenCountBatchingStrategy implements BatchingStrategy {
 		List<List<Document>> batches = new ArrayList<>();
 		int currentSize = 0;
 		List<Document> currentBatch = new ArrayList<>();
-		Map<Document, Integer> documentTokens = new HashMap<>();
+		// Make sure the documentTokens' entry order is preserved by making it a
+		// LinkedHashMap.
+		Map<Document, Integer> documentTokens = new LinkedHashMap<>();
 
 		for (Document document : documents) {
 			int tokenCount = this.tokenCountEstimator