[NOID] Fixes #4087: Add vector info procedures (#4142)

* Fixes #4087: Add vector info procedures

* changes review

* fix tests and added getInfoNotExistentCollection tests

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

@@ -7,6 +7,7 @@ note that the list and the signature procedures are consistent with the others,
 [opts=header, cols="1, 3"]
 |===
 | name | description
+| apoc.vectordb.chroma.info(hostOrKey, collection, $config) | Get information about the specified existing collection or throws an error 500 if it does not exist
 | apoc.vectordb.chroma.createCollection(hostOrKey, collection, similarity, size, $config) |
     Creates a collection, with the name specified in the 2nd parameter, and with the specified `similarity` and `size`.
     The default endpoint is `<hostOrKey param>/api/v1/collections`.
@@ -38,6 +39,19 @@ With hostOrKey=null, the default is 'http://localhost:8000'.
 
 === Examples
 
+.Get collection info (it leverages https://docs.trychroma.com/reference/py-client#get_collection[this API])
+[source,cypher]
+----
+CALL apoc.vectordb.chroma.info(hostOrKey, 'test_collection', {<optional config>})
+----
+
+.Example results
+[opts="header"]
+|===
+| value
+| {"name": "test_collection", "metadata": {"size": 4, "hnsw:space": "cosine"}, "database": "default_database", "id": "74ebe008-1ccb-4d3d-8c5d-cdd7cfa526c2", "tenant": "default_tenant"}
+|===
+
 .Create a collection (it leverages https://docs.trychroma.com/usage-guide#creating-inspecting-and-deleting-collections[this API])
 [source,cypher]
 ----

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

@@ -7,6 +7,7 @@ note that the list and the signature procedures are consistent with the others,
 [opts=header, cols="1, 3"]
 |===
 | name | description
+| apoc.vectordb.qdrant.info(hostOrKey, collection, $config) | Get information about the specified existing collection or throws a FileNotFoundException if it does not exist
 | apoc.vectordb.qdrant.createCollection(hostOrKey, collection, similarity, size, $config) |
     Creates a collection, with the name specified in the 2nd parameter, and with the specified `similarity` and `size`.
     The default endpoint is `<hostOrKey param>/collections/<collection param>`.
@@ -39,6 +40,29 @@ With hostOrKey=null, the default is 'http://localhost:6333'.
 
 === Examples
 
+.Get collection info (it leverages https://qdrant.github.io/qdrant/redoc/index.html#tag/collections/operation/get_collection[this API])
+[source,cypher]
+----
+CALL apoc.vectordb.qdrant.info(hostOrKey, 'test_collection', {<optional config>})
+----
+
+.Example results
+[opts="header"]
+|===
+| value
+| {"result": {"optimizer_status": "ok", "points_count": 2, "vectors_count": 2, "segments_count": 8, "indexed_vectors_count": 0,
+    "config": {"params": {"on_disk_payload": true, "vectors": {"size": 4, "distance": "Cosine"}, "shard_number": 1, "replication_factor": 1, "write_consistency_factor": 1},
+        "optimizer_config": {"max_optimization_threads": 1, "indexing_threshold": 20000, "deleted_threshold": 0.2, "flush_interval_sec": 5, "memmap_threshold": null, "default_segment_number": 0, "max_segment_size": null, "vacuum_min_vector_number": 1000}, "quantization_config": null,
+        "hnsw_config": {"max_indexing_threads": 0, "full_scan_threshold": 10000, "ef_construct": 100, "m": 16, "on_disk": false},
+        "wal_config": {"wal_segments_ahead": 0, "wal_capacity_mb": 32}
+        },
+        "status": green,
+        "payload_schema": {}
+    },
+    "time": 1.2725E-4, "status": ok
+}
+|===
+
 .Create a collection (it leverages https://qdrant.github.io/qdrant/redoc/index.html#tag/collections/operation/create_collection[this API])
 [source,cypher]
 ----

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

@@ -7,6 +7,7 @@ note that the list and the signature procedures are consistent with the others,
 [opts=header, cols="1, 3"]
 |===
 | name | description
+| apoc.vectordb.weaviate.info($host, $collectionName, $config) | Get information about the specified existing collection or throws a FileNotFoundException if it does not exist
 | apoc.vectordb.weaviate.createCollection(hostOrKey, collection, similarity, size, $config) |
     Creates a collection, with the name specified in the 2nd parameter, and with the specified `similarity` and `size`.
     The default endpoint is `<hostOrKey param>/schema`.
@@ -40,6 +41,33 @@ With hostOrKey=null, the default is 'http://localhost:8080/v1'.
 
 === Examples
 
+.Get collection info (it leverages https://weaviate.io/developers/weaviate/api/rest#tag/schema/get/schema/{className}[this API])
+[source, cypher]
+----
+CALL apoc.vectordb.weaviate.info($host, 'test_collection', {<optional config>})
+----
+
+.Example results
+[opts="header"]
+|===
+| value
+| {"vectorizer": "none",
+    "invertedIndexConfig": {"bm25": {"b": 0.75, "k1": 1.2}, "stopwords": {"additions": null, "removals": null, "preset": en}, "cleanupIntervalSeconds": 60},
+    "vectorIndexConfig": {"ef": -1, "dynamicEfMin": 100, "pq": {"centroids": 256, "trainingLimit": 100000, "encoder": {"type": "kmeans", "distribution": "log-normal"},
+    "enabled": false, "bitCompression": false, "segments": 0
+    },
+    "distance": cosine, "skip": false, "dynamicEfFactor": 8, "bq": {"enabled": false},
+    "vectorCacheMaxObjects": 1000000000000, "cleanupIntervalSeconds": 300, "dynamicEfMax": 500, "efConstruction": 128, "flatSearchCutoff": 40000, "maxConnections": 64},
+    "multiTenancyConfig": {"enabled": false},
+    "vectorIndexType": "hnsw", "replicationConfig": {"factor": 1},
+    "shardingConfig": {"desiredVirtualCount": 128, "desiredCount": 1, "actualCount": 1, "function": "murmur3", "virtualPerPhysical": 128, "strategy": "hash", "actualVirtualCount": 128, "key": "_id"},
+    "class": "TestCollection",
+    "properties": [{"name": "city", "description": "This property was generated by Weaviate's auto-schema feature on Wed Jul 10 12:50:18 2024", "indexFilterable": true, "tokenization": "word", "indexSearchable": true, "dataType": ["text"]},
+        {"name": "foo", "description": "This property was generated by Weaviate's auto-schema feature on Wed Jul 10 12:50:18 2024", "indexFilterable": true, "tokenization": word, "indexSearchable": true, "dataType": ["text"]}
+    ]
+}
+|===
+
 .Create a collection (it leverages https://weaviate.io/developers/weaviate/api/rest#tag/schema/post/schema[this API])
 [source,cypher]
 ----

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

@@ -1,5 +1,12 @@
 package apoc.full.it.vectordb;
 
+import java.util.List;
+import java.util.Map;
+import java.util.concurrent.atomic.AtomicReference;
+
+import static apoc.ml.Prompt.API_KEY_CONF;
+import static apoc.ml.RestAPIConfig.HEADERS_KEY;
+import static apoc.util.ExtendedTestUtil.assertFails;
 import static apoc.util.MapUtil.map;
 import static apoc.util.TestUtil.testCall;
 import static apoc.util.TestUtil.testResult;
@@ -8,6 +15,7 @@
 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;
@@ -42,6 +50,7 @@
 public class ChromaDbTest {
     private static final AtomicReference<String> COLL_ID = new AtomicReference<>();
     private static final ChromaDBContainer CHROMA_CONTAINER = new ChromaDBContainer("chromadb/chroma:0.4.25.dev137");
+    private static final String COLLECTION_NAME = "test_collection";
 
     private static String HOST;
 
@@ -101,6 +110,24 @@ public void before() {
         dropAndDeleteAll(db);
     }
 
+    @Test
+    public void getInfo() {
+        testResult(db, "CALL apoc.vectordb.chroma.info($host, $collection, $conf) ",
+                map("host", HOST, "collection", COLLECTION_NAME, "conf", map(ALL_RESULTS_KEY, true)),
+                r -> {
+                    Map<String, Object> row = (Map<String, Object>) r.next().get("value");
+                    assertEquals(COLLECTION_NAME, row.get("name"));
+                });
+    }
+
+    @Test
+    public void getInfoNotExistentCollection() {
+        assertFails(db, "CALL apoc.vectordb.chroma.info($host, 'wrong_collection', $conf) ",
+                map("host", HOST, "collection", COLLECTION_NAME, "conf", map(ALL_RESULTS_KEY, true)),
+                "Server returned HTTP response code: 500"
+        );
+    }
+
     @Test
     public void getVectors() {
         testResult(

full-it/src/test/java/apoc/full/it/vectordb/QdrantTest.java

@@ -1,6 +1,26 @@
 package apoc.full.it.vectordb;
 
+import apoc.ml.Prompt;
+import apoc.util.TestUtil;
+import apoc.util.Util;
+import org.junit.AfterClass;
+import org.junit.Assume;
+import org.junit.Before;
+import org.junit.BeforeClass;
+import org.junit.ClassRule;
+import org.junit.Test;
+import org.junit.rules.TemporaryFolder;
+import org.neo4j.dbms.api.DatabaseManagementService;
+import org.neo4j.graphdb.GraphDatabaseService;
+import org.neo4j.test.TestDatabaseManagementServiceBuilder;
+import org.testcontainers.qdrant.QdrantContainer;
+
+import java.util.List;
+import java.util.Map;
+
+import static apoc.ml.Prompt.API_KEY_CONF;
 import static apoc.ml.RestAPIConfig.HEADERS_KEY;
+import static apoc.util.ExtendedTestUtil.assertFails;
 import static apoc.util.MapUtil.map;
 import static apoc.util.TestUtil.testCall;
 import static apoc.util.TestUtil.testResult;
@@ -119,6 +139,29 @@ public void before() {
         dropAndDeleteAll(db);
     }
 
+    @Test
+    public void getInfo() {
+        testResult(
+                db,
+                "CALL apoc.vectordb.qdrant.info($host, 'test_collection', $conf)",
+                map("host", HOST, "conf", ADMIN_HEADER_CONF),
+                r -> {
+                    Map<String, Object> res = r.next();
+                    Map value = (Map) res.get("value");
+                    assertEquals("ok", value.get("status"));
+                });
+    }
+
+    @Test
+    public void getInfoNotExistentCollection() {
+        assertFails(
+                db,
+                "CALL apoc.vectordb.qdrant.info($host, 'wrong_collection', $conf)",
+                map("host", HOST, "conf", ADMIN_HEADER_CONF),
+                "java.io.FileNotFoundException"
+        );
+    }
+
     @Test
     public void getVectorsWithReadOnlyApiKey() {
         testResult(

full-it/src/test/java/apoc/full/it/vectordb/WeaviateTest.java

@@ -46,6 +46,7 @@ public class WeaviateTest {
     private static final List<String> FIELDS = List.of("city", "foo");
     private static final String ADMIN_KEY = "jane-secret-key";
     private static final String READONLY_KEY = "ian-secret-key";
+    private static final String COLLECTION_NAME = "TestCollection";
 
     private static final WeaviateContainer WEAVIATE_CONTAINER = new WeaviateContainer(
                     "semitechnologies/weaviate:1.24.5")
@@ -142,6 +143,27 @@ public void before() {
         dropAndDeleteAll(db);
     }
 
+    @Test
+    public void getInfo() {
+        testResult(db, "CALL apoc.vectordb.weaviate.info($host, $collectionName, $conf)",
+                map("host", HOST, "collectionName", COLLECTION_NAME, "conf", map(ALL_RESULTS_KEY, true, HEADERS_KEY, READONLY_AUTHORIZATION)),
+                r -> {
+                    Map<String, Object> row = r.next();
+                    Map value = (Map) row.get("value");
+                    assertEquals(COLLECTION_NAME, value.get("class"));
+                });
+    }
+
+    @Test
+    public void getInfoNotExistentCollection() {
+        assertFails(
+                db,
+                "CALL apoc.vectordb.weaviate.info($host, 'wrong_collection', $conf)",
+                map("host", HOST, "collectionName", COLLECTION_NAME, "conf", map(ALL_RESULTS_KEY, true, HEADERS_KEY, READONLY_AUTHORIZATION)),
+                "java.io.FileNotFoundException"
+        );
+    }
+
     @Test
     public void getVectorsWithReadOnlyApiKey() {
         testResult(

full/src/main/java/apoc/vectordb/VectorDbUtil.java

@@ -15,6 +15,21 @@
 import org.neo4j.graphdb.Node;
 import org.neo4j.graphdb.Relationship;
 
+import java.net.HttpURLConnection;
+import java.net.URL;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+
+import static apoc.ml.RestAPIConfig.BASE_URL_KEY;
+import static apoc.ml.RestAPIConfig.BODY_KEY;
+import static apoc.ml.RestAPIConfig.ENDPOINT_KEY;
+import static apoc.ml.RestAPIConfig.METHOD_KEY;
+import static apoc.util.SystemDbUtil.withSystemDb;
+import static apoc.vectordb.VectorEmbeddingConfig.MAPPING_KEY;
+import static apoc.vectordb.VectorMappingConfig.MODE_KEY;
+import static apoc.vectordb.VectorMappingConfig.MappingMode.READ_ONLY;
+
 public class VectorDbUtil {
 
     public static final String ERROR_READONLY_MAPPING =

full/src/main/resources/extended.txt

@@ -229,6 +229,8 @@ apoc.vectordb.weaviate.get
 apoc.vectordb.weaviate.getAndUpdate
 apoc.vectordb.weaviate.query
 apoc.vectordb.weaviate.queryAndUpdate
-apoc.vectordb.custom.get
+apoc.vectordb.weaviate.info
+apoc.vectordb.pinecone.info
+apoc.vectordb.milvus.info
 apoc.vectordb.custom
 apoc.vectordb.configure