CrateDB: Vector Store

langchain-ai · Oct 29, 2024 · 46750b6 · 46750b6
1 parent 447c0dd
commit 46750b6
Show file tree

Hide file tree

Showing 11 changed files with 1,365 additions and 2 deletions.
diff --git a/docs/docs/how_to/indexing.ipynb b/docs/docs/how_to/indexing.ipynb
@@ -60,7 +60,7 @@
     "   * document addition by id (`add_documents` method with `ids` argument)\n",
     "   * delete by id (`delete` method with `ids` argument)\n",
     "\n",
-    "Compatible Vectorstores: `Aerospike`, `AnalyticDB`, `AstraDB`, `AwaDB`, `AzureCosmosDBNoSqlVectorSearch`, `AzureCosmosDBVectorSearch`, `Bagel`, `Cassandra`, `Chroma`, `CouchbaseVectorStore`, `DashVector`, `DatabricksVectorSearch`, `DeepLake`, `Dingo`, `ElasticVectorSearch`, `ElasticsearchStore`, `FAISS`, `HanaDB`, `Milvus`, `MongoDBAtlasVectorSearch`, `MyScale`, `OpenSearchVectorSearch`, `PGVector`, `Pinecone`, `Qdrant`, `Redis`, `Rockset`, `ScaNN`, `SingleStoreDB`, `SupabaseVectorStore`, `SurrealDBStore`, `TimescaleVector`, `Vald`, `VDMS`, `Vearch`, `VespaStore`, `Weaviate`, `Yellowbrick`, `ZepVectorStore`, `TencentVectorDB`, `OpenSearchVectorSearch`.\n",
+    "Compatible Vectorstores: `Aerospike`, `AnalyticDB`, `AstraDB`, `AwaDB`, `AzureCosmosDBNoSqlVectorSearch`, `AzureCosmosDBVectorSearch`, `Bagel`, `Cassandra`, `Chroma`, `CouchbaseVectorStore`, `CrateDBVectorSearch`, `DashVector`, `DatabricksVectorSearch`, `DeepLake`, `Dingo`, `ElasticVectorSearch`, `ElasticsearchStore`, `FAISS`, `HanaDB`, `Milvus`, `MongoDBAtlasVectorSearch`, `MyScale`, `OpenSearchVectorSearch`, `PGVector`, `Pinecone`, `Qdrant`, `Redis`, `Rockset`, `ScaNN`, `SingleStoreDB`, `SupabaseVectorStore`, `SurrealDBStore`, `TimescaleVector`, `Vald`, `VDMS`, `Vearch`, `VespaStore`, `Weaviate`, `Yellowbrick`, `ZepVectorStore`, `TencentVectorDB`, `OpenSearchVectorSearch`.\n",
     "  \n",
     "## Caution\n",
     "\n",

diff --git a/libs/community/extended_testing_deps.txt b/libs/community/extended_testing_deps.txt
@@ -14,6 +14,7 @@ chardet>=5.1.0,<6
 cloudpathlib>=0.18,<0.19
 cloudpickle>=2.0.0
 cohere>=4,<6
+crate==1.0.0.dev1
 databricks-vectorsearch>=0.21,<0.22
 datasets>=2.15.0,<3
 dgml-utils>=0.3.0,<0.4
@@ -76,6 +77,7 @@ requests-toolbelt>=1.0.0,<2
 rspace_client>=2.5.0,<3
 scikit-learn>=1.2.2,<2
 simsimd>=5.0.0,<6
+sqlalchemy-cratedb>=0.40.0,<1
 sqlite-vss>=0.1.2,<0.2
 sqlite-vec>=0.1.0,<0.2
 sseclient-py>=1.8.0,<2

diff --git a/libs/community/langchain_community/vectorstores/__init__.py b/libs/community/langchain_community/vectorstores/__init__.py
@@ -92,6 +92,9 @@
     from langchain_community.vectorstores.couchbase import (
         CouchbaseVectorStore,
     )
+    from langchain_community.vectorstores.cratedb import (
+        CrateDBVectorSearch,
+    )
     from langchain_community.vectorstores.dashvector import (
         DashVector,
     )
@@ -334,6 +337,7 @@
     "Clickhouse",
     "ClickhouseSettings",
     "CouchbaseVectorStore",
+    "CrateDBVectorSearch",
     "DashVector",
     "DatabricksVectorSearch",
     "DeepLake",
@@ -438,6 +442,7 @@
     "Clickhouse": "langchain_community.vectorstores.clickhouse",
     "ClickhouseSettings": "langchain_community.vectorstores.clickhouse",
     "CouchbaseVectorStore": "langchain_community.vectorstores.couchbase",
+    "CrateDBVectorSearch": "langchain_community.vectorstores.cratedb",
     "DashVector": "langchain_community.vectorstores.dashvector",
     "DatabricksVectorSearch": "langchain_community.vectorstores.databricks_vector_search",  # noqa: E501
     "DeepLake": "langchain_community.vectorstores.deeplake",

diff --git a/libs/community/langchain_community/vectorstores/cratedb/__init__.py b/libs/community/langchain_community/vectorstores/cratedb/__init__.py
@@ -0,0 +1,7 @@
+from .base import CrateDBVectorSearch
+from .extended import CrateDBVectorSearchMultiCollection
+
+__all__ = [
+    "CrateDBVectorSearch",
+    "CrateDBVectorSearchMultiCollection",
+]