Spring/spring-ai
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Update usage of Document::getContent to getText

Browse Source
This commit is contained in:
Mark Pollack
2024-12-12 14:43:51 -05:00
parent f252b2417a
commit 5b11501cbe
8 changed files with 12 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
document-readers/markdown-reader/src/test/java/org/springframework/ai/reader/markdown/MarkdownDocumentReaderTest.java
View File

@@ -39,7 +39,7 @@ class MarkdownDocumentReaderTest {
List<Document> documents = reader.get();
assertThat(documents).hasSize(4)
.extracting(Document::getMetadata, Document::getContent)
.extracting(Document::getMetadata, Document::getText)
.containsOnly(tuple(Map.of("category", "header_1", "title", "Header 1a"),
"Lorem ipsum dolor sit amet, consectetur adipiscing elit. Curabitur diam eros, laoreet sit amet cursus vitae, varius sed nisi. Cras sit amet quam quis velit commodo porta consectetur id nisi. Phasellus tincidunt pulvinar augue."),
tuple(Map.of("category", "header_1", "title", "Header 1b"),
@@ -57,7 +57,7 @@ class MarkdownDocumentReaderTest {
List<Document> documents = reader.get();
assertThat(documents).hasSize(2)
.extracting(Document::getMetadata, Document::getContent)
.extracting(Document::getMetadata, Document::getText)
.containsOnly(tuple(Map.of("category", "header_1", "title", "This is a fancy header name"),
"Lorem ipsum dolor sit amet, consectetur adipiscing elit. Donec tincidunt velit non bibendum gravida. Cras accumsan tincidunt ornare. Donec hendrerit consequat tellus blandit accumsan. Aenean aliquam metus at arcu elementum dignissim."),
tuple(Map.of("category", "header_3", "title", "Header 3"),
@@ -75,7 +75,7 @@ class MarkdownDocumentReaderTest {
List<Document> documents = reader.get();
assertThat(documents).hasSize(7)
.extracting(Document::getMetadata, Document::getContent)
.extracting(Document::getMetadata, Document::getText)
.containsOnly(tuple(Map.of(),
"Lorem ipsum dolor sit amet, consectetur adipiscing elit. Donec tincidunt velit non bibendum gravida."),
tuple(Map.of(),
@@ -187,7 +187,7 @@ class MarkdownDocumentReaderTest {
List<Document> documents = reader.get();
assertThat(documents).hasSize(2)
.extracting(Document::getMetadata, Document::getContent)
.extracting(Document::getMetadata, Document::getText)
.containsOnly(tuple(Map.of(),
"Lorem ipsum dolor sit amet, consectetur adipiscing elit. Curabitur diam eros, laoreet sit amet cursus vitae, varius sed nisi. Cras sit amet quam quis velit commodo porta consectetur id nisi. Phasellus tincidunt pulvinar augue."),
tuple(Map.of("category", "blockquote"),
@@ -219,7 +219,7 @@ class MarkdownDocumentReaderTest {
List<Document> documents = reader.get();
assertThat(documents).hasSize(2)
.extracting(Document::getMetadata, Document::getContent)
.extracting(Document::getMetadata, Document::getText)
.containsOnly(tuple(Map.of("category", "header_2", "title", "Ordered list"),
"Lorem ipsum dolor sit amet, consectetur adipiscing elit. Curabitur diam eros, laoreet sit amet cursus vitae, varius sed nisi. Cras sit amet quam quis velit commodo porta consectetur id nisi. Phasellus tincidunt pulvinar augue. Proin vel laoreet leo, sed luctus augue. Sed et ligula commodo, commodo lacus at, consequat turpis. Maecenas eget sapien odio. Pellentesque auctor pharetra eros, viverra sodales lorem aliquet id. Curabitur semper nisi vel sem interdum suscipit. Maecenas urna lectus, pellentesque in accumsan aliquam, congue eu libero. Ut rhoncus nec justo a porttitor."),
tuple(Map.of("category", "header_2", "title", "Unordered list"),

2
document-readers/pdf-reader/src/test/java/org/springframework/ai/reader/pdf/PagePdfDocumentReaderTests.java
View File

@@ -52,7 +52,7 @@ class PagePdfDocumentReaderTests {
assertThat(docs).hasSize(4);
String allText = docs.stream().map(Document::getContent).collect(Collectors.joining(System.lineSeparator()));
String allText = docs.stream().map(Document::getText).collect(Collectors.joining(System.lineSeparator()));
assertThat(allText).doesNotContain(
List.of("Page 1 of 4", "Page 2 of 4", "Page 3 of 4", "Page 4 of 4", "PDF Bookmark Sample"));

1
spring-ai-core/src/main/java/org/springframework/ai/chat/client/advisor/QuestionAnswerAdvisor.java
View File

@@ -35,7 +35,6 @@ import org.springframework.ai.chat.client.advisor.api.StreamAroundAdvisorChain;
import org.springframework.ai.chat.model.ChatResponse;
import org.springframework.ai.chat.prompt.PromptTemplate;
import org.springframework.ai.document.Document;
import org.springframework.ai.model.Content;
import org.springframework.ai.vectorstore.SearchRequest;
import org.springframework.ai.vectorstore.VectorStore;
import org.springframework.ai.vectorstore.filter.Filter;

2
spring-ai-core/src/main/java/org/springframework/ai/embedding/EmbeddingModel.java
View File

@@ -86,7 +86,7 @@ public interface EmbeddingModel extends Model<EmbeddingRequest, EmbeddingRespons
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();
List<String> texts = subBatch.stream().map(Document::getText).toList();
EmbeddingRequest request = new EmbeddingRequest(texts, options);
EmbeddingResponse response = this.call(request);
for (int i = 0; i < subBatch.size(); i++) {

2
spring-ai-core/src/main/java/org/springframework/ai/vectorstore/observation/VectorStoreObservationContentProcessor.java
View File

@@ -36,7 +36,7 @@ public final class VectorStoreObservationContentProcessor {
return List.of();
}
return context.getQueryResponse().stream().map(Document::getContent).toList();
return context.getQueryResponse().stream().map(Document::getText).toList();
}
}

4
spring-ai-core/src/test/java/org/springframework/ai/rag/retrieval/join/ConcatenationDocumentJoinerTests.java
View File

@@ -89,8 +89,8 @@ class ConcatenationDocumentJoinerTests {
assertThat(result).hasSize(4);
assertThat(result).extracting(Document::getId).containsExactlyInAnyOrder("1", "2", "3", "4");
assertThat(result).extracting(Document::getContent).contains("Content 2");
assertThat(result).extracting(Document::getContent).doesNotContain("Content 2 Duplicate");
assertThat(result).extracting(Document::getText).contains("Content 2");
assertThat(result).extracting(Document::getText).doesNotContain("Content 2 Duplicate");
}
}

2
spring-ai-docs/src/main/antora/modules/ROOT/pages/api/vectordbs/hana.adoc
View File

@@ -298,7 +298,7 @@ public class CricketWorldCupHanaController {
@GetMapping("/ai/hana-vector-store/cricket-world-cup")
public Map<String, String> hanaVectorStoreSearch(@RequestParam(value = "message") String message) {
var documents = this.hanaCloudVectorStore.similaritySearch(message);
var inlined = documents.stream().map(Document::getContent).collect(Collectors.joining(System.lineSeparator()));
var inlined = documents.stream().map(Document::getText).collect(Collectors.joining(System.lineSeparator()));
var similarDocsMessage = new SystemPromptTemplate("Based on the following: {documents}")
.createMessage(Map.of("documents", inlined));

2
vector-stores/spring-ai-hanadb-store/src/test/java/org/springframework/ai/vectorstore/CricketWorldCupHanaController.java
View File

@@ -84,7 +84,7 @@ public class CricketWorldCupHanaController {
@GetMapping("/ai/hana-vector-store/cricket-world-cup")
public Map<String, String> hanaVectorStoreSearch(@RequestParam("message") String message) {
var documents = this.hanaCloudVectorStore.similaritySearch(message);
var inlined = documents.stream().map(Document::getContent).collect(Collectors.joining(System.lineSeparator()));
var inlined = documents.stream().map(Document::getText).collect(Collectors.joining(System.lineSeparator()));
var similarDocsMessage = new SystemPromptTemplate("Based on the following: {documents}")
.createMessage(Map.of("documents", inlined));