Fixes #4090: The apoc.vectordb.* procedures should search for nodes/r…

…elationships with mapping config

build.gradle

@@ -131,7 +131,7 @@ subprojects {
 
 ext {
  // NB: due to version.json generation by parsing this file, the next line must not have any if/then/else logic
- neo4jVersion = "5.21.0"
+ neo4jVersion = "5.19.0"
  // instead we apply the override logic here
  neo4jVersionEffective = project.hasProperty("neo4jVersionOverride") ? project.getProperty("neo4jVersionOverride") : neo4jVersion
  testContainersVersion = '1.18.3'

docs/asciidoc/modules/ROOT/pages/database-integration/vectordb/chroma.adoc

@@ -119,17 +119,6 @@ CALL apoc.vectordb.chroma.queryAndUpdate($host,
 | ...
 |===
 
-[NOTE]
-====
-We can use mapping with `apoc.vectordb.chroma.getAndUpdate` procedure as well
-====
-
-[NOTE]
-====
-To optimize performances, we can choose what to `YIELD` with the apoc.vectordb.chroma.query and the `apoc.vectordb.chroma.get` procedures.
-For example, by executing a `CALL apoc.vectordb.chroma.query(...) YIELD metadata, score, id`, the RestAPI request will have an {"include": ["metadatas", "documents", "distances"]},
-so that we do not return the other values that we do not need.
-====
 
 
 In the same way as other procedures, we can define a mapping, to fetch the associated nodes and relationships and optionally create them,
@@ -151,7 +140,35 @@ CALL apoc.vectordb.chroma.query($host, '<collection_id>',
  })
 ----
 
+We can also use mapping for `apoc.vectordb.chroma.query` procedure, to search for nodes/rels fitting label/type and metadataKey, without making updates.
+For example, with the previous relationships, we can execute the following procedure, which just return the relationships in the column `rel`:
 
+[source,cypher]
+----
+CALL apoc.vectordb.chroma.query($host, '<collection_id>',
+ [0.2, 0.1, 0.9, 0.7],
+ {},
+ 5, 
+ { mapping: {
+ embeddingKey: "vect", 
+ nodeLabel: "Test", 
+ entityKey: "myId", 
+ metadataKey: "foo" 
+ }
+ })
+----
+
+[NOTE]
+====
+We can use mapping with `apoc.vectordb.chroma.get*` procedures as well
+====
+
+[NOTE]
+====
+To optimize performances, we can choose what to `YIELD` with the apoc.vectordb.chroma.query and the `apoc.vectordb.chroma.get` procedures.
+For example, by executing a `CALL apoc.vectordb.chroma.query(...) YIELD metadata, score, id`, the RestAPI request will have an {"include": ["metadatas", "documents", "distances"]},
+so that we do not return the other values that we do not need.
+====
 
 .Delete vectors (it leverages https://docs.trychroma.com/usage-guide#deleting-data-from-a-collection[this API])
 [source,cypher]

docs/asciidoc/modules/ROOT/pages/database-integration/vectordb/milvus.adoc

@@ -189,9 +189,28 @@ which populates the two relationships as: `()-[:TEST {myId: 'one', city: 'Berlin
 and `()-[:TEST {myId: 'two', city: 'London', vect: [vector2]}]-()`,
 which will be returned in the `entity` column result.
 
+
+We can also use mapping for `apoc.vectordb.milvus.query` procedure, to search for nodes/rels fitting label/type and metadataKey, without making updates.
+For example, with the previous relationships, we can execute the following procedure, which just return the relationships in the column `rel`:
+
+[source,cypher]
+----
+CALL apoc.vectordb.milvus.query('http://localhost:19531', 'test_collection',
+ [0.2, 0.1, 0.9, 0.7],
+ {},
+ 5, 
+ { mapping: {
+ embeddingKey: "vect", 
+ relType: "TEST", 
+ entityKey: "myId", 
+ metadataKey: "foo" 
+ }
+ })
+----
+
 [NOTE]
 ====
-We can use mapping with `apoc.vectordb.milvus.getAndUpdate` procedure as well
+We can use mapping with `apoc.vectordb.milvus.get*` procedures as well
 ====
 
 [NOTE]

docs/asciidoc/modules/ROOT/pages/database-integration/vectordb/pinecone.adoc

@@ -203,9 +203,28 @@ which populates the two relationships as: `()-[:TEST {myId: 'one', city: 'Berlin
 and `()-[:TEST {myId: 'two', city: 'London', vect: [vector2]}]-()`,
 which will be returned in the `entity` column result.
 
+
+We can also use mapping for `apoc.vectordb.pinecone.query` procedure, to search for nodes/rels fitting label/type and metadataKey, without making updates.
+For example, with the previous relationships, we can execute the following procedure, which just return the relationships in the column `rel`:
+
+[source,cypher]
+----
+CALL apoc.vectordb.pinecone.query($host, 'test-index',
+ [0.2, 0.1, 0.9, 0.7],
+ {},
+ 5, 
+ { mapping: {
+ embeddingKey: "vect", 
+ relType: "TEST", 
+ entityKey: "myId", 
+ metadataKey: "foo" 
+ }
+ })
+----
+
 [NOTE]
 ====
-We can use mapping with `apoc.vectordb.pinecone.getAndUpdate` procedure as well
+We can use mapping with `apoc.vectordb.pinecone.get*` procedures as well
 ====
 
 [NOTE]

docs/asciidoc/modules/ROOT/pages/database-integration/vectordb/qdrant.adoc

@@ -191,9 +191,27 @@ which populates the two relationships as: `()-[:TEST {myId: 'one', city: 'Berlin
 and `()-[:TEST {myId: 'two', city: 'London', vect: [vector2]}]-()`,
 which will be returned in the `entity` column result.
 
+
+We can also use mapping for `apoc.vectordb.qdrant.query` procedure, to search for nodes/rels fitting label/type and metadataKey, without making updates.
+For example, with the previous relationships, we can execute the following procedure, which just return the relationships in the column `rel`:
+
+[source,cypher]
+----
+CALL apoc.vectordb.qdrant.queryAndUpdate($hostOrKey, 'test_collection',
+ [0.2, 0.1, 0.9, 0.7],
+ {},
+ 5, 
+ { mapping: {
+ relType: "TEST", 
+ entityKey: "myId", 
+ metadataKey: "foo" 
+ }
+ })
+----
+
 [NOTE]
 ====
-We can use mapping with `apoc.vectordb.qdrant.getAndUpdate` procedure as well
+We can use mapping with `apoc.vectordb.qdrant.get*` procedures as well
 ====
 
 [NOTE]

docs/asciidoc/modules/ROOT/pages/database-integration/vectordb/weaviate.adoc

@@ -205,9 +205,29 @@ and `()-[:TEST {myId: 'two', city: 'London', vect: [vector2]}]-()`,
 which will be returned in the `entity` column result.
 
 
+We can also use mapping for `apoc.vectordb.weaviate.query` procedure, to search for nodes/rels fitting label/type and metadataKey, without making updates.
+For example, with the previous relationships, we can execute the following procedure, which just return the relationships in the column `rel`:
+
+[source,cypher]
+----
+CALL apoc.vectordb.weaviate.query($host, 'test_collection',
+ [0.2, 0.1, 0.9, 0.7],
+ {},
+ 5, 
+ { fields: ["city", "foo"],
+ mapping: {
+ relType: "TEST", 
+ entityKey: "myId", 
+ metadataKey: "foo" 
+ }
+ })
+----
+
+
+
 [NOTE]
 ====
-We can use mapping with `apoc.vectordb.weaviate.getAndUpdate` procedure as well
+We can use mapping with `apoc.vectordb.weaviate.get*` procedures as well
 ====
 
 [NOTE]

extended-it/src/test/java/apoc/vectordb/ChromaDbTest.java

@@ -18,13 +18,15 @@
 import java.util.Map;
 import java.util.concurrent.atomic.AtomicReference;
 
+import static apoc.ml.RestAPIConfig.HEADERS_KEY;
 import static apoc.util.MapUtil.map;
 import static apoc.util.TestUtil.testCall;
 import static apoc.util.TestUtil.testResult;
 import static apoc.vectordb.VectorDbHandler.Type.CHROMA;
 import static apoc.vectordb.VectorDbTestUtil.assertBerlinResult;
 import static apoc.vectordb.VectorDbTestUtil.assertLondonResult;
 import static apoc.vectordb.VectorDbTestUtil.assertNodesCreated;
+import static apoc.vectordb.VectorDbTestUtil.assertReadOnlyProcWithMappingResults;
 import static apoc.vectordb.VectorDbTestUtil.assertRelsCreated;
 import static apoc.vectordb.VectorDbTestUtil.dropAndDeleteAll;
 import static apoc.vectordb.VectorDbTestUtil.EntityType.*;
@@ -294,19 +296,22 @@ MAPPING_KEY, map(EMBEDDING_KEY, "vect",
  assertNodesCreated(db);
  }
 
+
  @Test
  public void getReadOnlyVectorsWithMapping() {
+ db.executeTransactionally("CREATE (:Test {readID: 'one'}), (:Test {readID: 'two'})");
+
  Map<String, Object> conf = map(ALL_RESULTS_KEY, true,
- MAPPING_KEY, map(EMBEDDING_KEY, "vect"));
-
- try {
-  testCall(db, "CALL apoc.vectordb.chroma.get($host, $collection, [1, 2], $conf)",
- map("host", HOST, "collection", COLL_ID.get(), "conf", conf),
-  r -> fail()
- );
- } catch (RuntimeException e) {
- Assertions.assertThat(e.getMessage()).contains(ERROR_READONLY_MAPPING);
- }
+ MAPPING_KEY, map(NODE_LABEL, "Test",
+ ENTITY_KEY, "readID",
+  METADATA_KEY, "foo")
+ );
+
+ testResult(db, "CALL apoc.vectordb.chroma.get($host, $collection, ['1', '2'], $conf) " +
+  "YIELD vector, id, metadata, node RETURN * ORDER BY id",
+  map("host", HOST, "collection", COLL_ID.get(), "conf", conf),
+  r -> assertReadOnlyProcWithMappingResults(r, "node")
+ );
  }
 
  @Test
@@ -338,17 +343,19 @@ MAPPING_KEY, map(EMBEDDING_KEY, "vect",
 
  @Test
  public void queryReadOnlyVectorsWithMapping() {
+ db.executeTransactionally("CREATE (:Start)-[:TEST {readID: 'one'}]->(:End), (:Start)-[:TEST {readID: 'two'}]->(:End)");
+
  Map<String, Object> conf = map(ALL_RESULTS_KEY, true,
- MAPPING_KEY, map(EMBEDDING_KEY, "vect"));
-
- try {
- testCall(db, "CALL apoc.vectordb.chroma.query($host, $collection, [0.2, 0.1, 0.9, 0.7], {}, 5, $conf)",
-  map("host", HOST, "collection", COLL_ID.get(), "conf", conf),
- r -> fail()
-  );
- } catch (RuntimeException e) {
- Assertions.assertThat(e.getMessage()).contains(ERROR_READONLY_MAPPING);
- }
+ MAPPING_KEY, map(
+  REL_TYPE, "TEST",
+  ENTITY_KEY, "readID",
+  METADATA_KEY, "foo")
+ );
+
+ testResult(db, "CALL apoc.vectordb.chroma.query($host, $collection, [0.2, 0.1, 0.9, 0.7], {}, 5, $conf)",
+  map("host", HOST, "collection", COLL_ID.get(), "conf", conf),
+  r -> assertReadOnlyProcWithMappingResults(r, "rel")
+ );
  }
 
  @Test

extended-it/src/test/java/apoc/vectordb/MilvusTest.java

@@ -2,7 +2,6 @@
 
 import apoc.util.TestUtil;
 import apoc.util.Util;
-import org.assertj.core.api.Assertions;
 import org.junit.AfterClass;
 import org.junit.Before;
 import org.junit.BeforeClass;
@@ -27,9 +26,9 @@
 import static apoc.vectordb.VectorDbTestUtil.assertBerlinResult;
 import static apoc.vectordb.VectorDbTestUtil.assertLondonResult;
 import static apoc.vectordb.VectorDbTestUtil.assertNodesCreated;
+import static apoc.vectordb.VectorDbTestUtil.assertReadOnlyProcWithMappingResults;
 import static apoc.vectordb.VectorDbTestUtil.assertRelsCreated;
 import static apoc.vectordb.VectorDbTestUtil.dropAndDeleteAll;
-import static apoc.vectordb.VectorDbUtil.ERROR_READONLY_MAPPING;
 import static apoc.vectordb.VectorEmbeddingConfig.ALL_RESULTS_KEY;
 import static apoc.vectordb.VectorEmbeddingConfig.FIELDS_KEY;
 import static apoc.vectordb.VectorEmbeddingConfig.MAPPING_KEY;
@@ -297,6 +296,24 @@ MAPPING_KEY, map(EMBEDDING_KEY, "vect",
  assertNodesCreated(db);
  }
 
+ @Test
+ public void getReadOnlyVectorsWithMapping() {
+ db.executeTransactionally("CREATE (:Test {readID: 'one'}), (:Test {readID: 'two'})");
+
+ Map<String, Object> conf = map(ALL_RESULTS_KEY, true,
+ FIELDS_KEY, FIELDS,
+ MAPPING_KEY, map(EMBEDDING_KEY, "vect",
+ NODE_LABEL, "Test",
+ ENTITY_KEY, "readID",
+ METADATA_KEY, "foo"));
+
+ testResult(db, "CALL apoc.vectordb.milvus.get($host, 'test_collection', [1, 2], $conf) " +
+ "YIELD vector, id, metadata, node RETURN * ORDER BY id",
+ map("host", HOST, "conf", conf),
+ r -> assertReadOnlyProcWithMappingResults(r, "node")
+ );
+ }
+
  @Test
  public void queryVectorsWithCreateNodeUsingExistingNode() {
 
@@ -336,7 +353,8 @@ public void queryVectorsWithCreateRel() {
  MAPPING_KEY, map(EMBEDDING_KEY, "vect",
  REL_TYPE, "TEST",
  ENTITY_KEY, "myId",
- METADATA_KEY, "foo"));
+ METADATA_KEY, "foo")
+ );
  testResult(db, "CALL apoc.vectordb.milvus.queryAndUpdate($host, 'test_collection', [0.2, 0.1, 0.9, 0.7], null, 5, $conf)",
  map("host", HOST, "conf", conf),
  r -> {
@@ -356,17 +374,20 @@ MAPPING_KEY, map(EMBEDDING_KEY, "vect",
 
  @Test
  public void queryReadOnlyVectorsWithMapping() {
+ db.executeTransactionally("CREATE (:Start)-[:TEST {readID: 'one'}]->(:End), (:Start)-[:TEST {readID: 'two'}]->(:End)");
+
  Map<String, Object> conf = map(ALL_RESULTS_KEY, true,
- MAPPING_KEY, map(EMBEDDING_KEY, "vect"));
-
- try {
- testCall(db, "CALL apoc.vectordb.milvus.query($host, 'test_collection', [0.2, 0.1, 0.9, 0.7], {}, 5, $conf)",
- map("host", HOST, "conf", conf),
- r -> fail()
- );
- } catch (RuntimeException e) {
- Assertions.assertThat(e.getMessage()).contains(ERROR_READONLY_MAPPING);
- }
+ FIELDS_KEY, FIELDS,
+ MAPPING_KEY, map(
+ REL_TYPE, "TEST",
+ ENTITY_KEY, "readID",
+ METADATA_KEY, "foo")
+ );
+
+ testResult(db, "CALL apoc.vectordb.milvus.query($host, 'test_collection', [0.2, 0.1, 0.9, 0.7], null, 5, $conf)",
+ map("host", HOST, "conf", conf),
+ r -> assertReadOnlyProcWithMappingResults(r, "rel")
+ );
  }
 
  @Test