Skip to content

Fix PgVectorStore overwriting a document's own distance metadata #6983

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ss-bhatt wants to merge 1 commit into
base: main
Choose a base branch
from
+65 −1
Open

Fix PgVectorStore overwriting a document's own distance metadata #6983

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 7 additions & 1 deletion ...vector-store/src/main/java/org/springframework/ai/vectorstore/pgvector/PgVectorStore.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -635,7 +635,13 @@ public Document mapRow(ResultSet rs, int rowNum) throws SQLException {
Float distance = rs.getFloat(COLUMN_DISTANCE);

Map<String, Object> metadata = toMap(pgMetadata);
metadata.put(DocumentMetadata.DISTANCE.value(), distance);
if (metadata.containsKey(DocumentMetadata.DISTANCE.value())) {
logger.warn("Skipping computed similarity distance for document " + id
+ " because its metadata already contains a '" + DocumentMetadata.DISTANCE.value() + "' key");
}
else {
metadata.put(DocumentMetadata.DISTANCE.value(), distance);
}

// @formatter:off
return Document.builder()
Expand Down
58 changes: 58 additions & 0 deletions ...r-store/src/test/java/org/springframework/ai/vectorstore/pgvector/PgVectorStoreTests.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,7 @@

package org.springframework.ai.vectorstore.pgvector;

import java.sql.ResultSet;
import java.util.Collections;
import java.util.List;

Expand All @@ -24,8 +25,10 @@
import org.junit.jupiter.params.provider.CsvSource;
import org.mockito.ArgumentCaptor;
import org.mockito.ArgumentMatchers;
import org.postgresql.util.PGobject;

import org.springframework.ai.document.Document;
import org.springframework.ai.document.DocumentMetadata;
import org.springframework.ai.embedding.EmbeddingModel;
import org.springframework.ai.vectorstore.SearchRequest;
import org.springframework.ai.vectorstore.filter.Filter;
Expand Down Expand Up @@ -206,4 +209,59 @@ void similaritySearchDoublesSingleQuotesInsideJsonPathSqlLiteral() {
assertThat(sqlCaptor.getValue()).contains("O''Brien");
}

@Test
@SuppressWarnings("unchecked")
void rowMapperSkipsDistanceMetadataWhenUserAlreadyUsesThatKey() throws Exception {
var jdbcTemplate = mock(JdbcTemplate.class);
var embeddingModel = mock(EmbeddingModel.class);
ArgumentCaptor<RowMapper<Document>> rowMapperCaptor = ArgumentCaptor.forClass(RowMapper.class);
when(jdbcTemplate.query(anyString(), rowMapperCaptor.capture(), any(), any(), any(), any()))
.thenReturn(List.of());

var store = PgVectorStore.builder(jdbcTemplate, embeddingModel).build();
store.doSimilaritySearch(SearchRequest.builder().query("hello").topK(5).similarityThresholdAll().build());

var pgMetadata = new PGobject();
pgMetadata.setType("json");
pgMetadata.setValue("{\"distance\": \"12.5 miles from depot\"}");

var resultSet = mock(ResultSet.class);
when(resultSet.getString("id")).thenReturn("doc-1");
when(resultSet.getString("content")).thenReturn("hello world");
when(resultSet.getObject("metadata", PGobject.class)).thenReturn(pgMetadata);
when(resultSet.getFloat("distance")).thenReturn(0.42f);

Document document = rowMapperCaptor.getValue().mapRow(resultSet, 0);

assertThat(document.getMetadata()).containsEntry(DocumentMetadata.DISTANCE.value(), "12.5 miles from depot");
assertThat(document.getScore()).isEqualTo(1.0 - 0.42f);
}

@Test
@SuppressWarnings("unchecked")
void rowMapperAddsDistanceMetadataWhenAbsent() throws Exception {
var jdbcTemplate = mock(JdbcTemplate.class);
var embeddingModel = mock(EmbeddingModel.class);
ArgumentCaptor<RowMapper<Document>> rowMapperCaptor = ArgumentCaptor.forClass(RowMapper.class);
when(jdbcTemplate.query(anyString(), rowMapperCaptor.capture(), any(), any(), any(), any()))
.thenReturn(List.of());

var store = PgVectorStore.builder(jdbcTemplate, embeddingModel).build();
store.doSimilaritySearch(SearchRequest.builder().query("hello").topK(5).similarityThresholdAll().build());

var pgMetadata = new PGobject();
pgMetadata.setType("json");
pgMetadata.setValue("{\"author\": \"jane\"}");

var resultSet = mock(ResultSet.class);
when(resultSet.getString("id")).thenReturn("doc-1");
when(resultSet.getString("content")).thenReturn("hello world");
when(resultSet.getObject("metadata", PGobject.class)).thenReturn(pgMetadata);
when(resultSet.getFloat("distance")).thenReturn(0.42f);

Document document = rowMapperCaptor.getValue().mapRow(resultSet, 0);

assertThat(document.getMetadata()).containsEntry(DocumentMetadata.DISTANCE.value(), 0.42f);
}

}