github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2026-01-06 16:35:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

community: add SingleStoreDB semantic cache (#23218)

Browse Source 
This PR adds a `SingleStoreDBSemanticCache` class that implements a
cache based on SingleStoreDB vector store, integration tests, and a
notebook example.

Additionally, this PR contains minor changes to SingleStoreDB vector
store:
 - change add texts/documents methods to return a list of inserted ids
 - implement delete(ids) method to delete documents by list of ids
 - added drop() method to drop a correspondent database table
- updated integration tests to use and check functionality implemented
above


CC: @baskaryan, @hwchase17

---------

Co-authored-by: Volodymyr Tkachuk <vtkachuk-ua@singlestore.com>
This commit is contained in:
volodymyr-memsql
2024-07-05 16:26:06 +03:00
committed by GitHub
parent bb597b1286
commit a4eb6d0fb1
8 changed files with 423 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/docs/how_to/indexing.ipynb
View File

@@ -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`, `MyScale`, `OpenSearchVectorSearch`, `PGVector`, `Pinecone`, `Qdrant`, `Redis`, `Rockset`, `ScaNN`, `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`, `DashVector`, `DatabricksVectorSearch`, `DeepLake`, `Dingo`, `ElasticVectorSearch`, `ElasticsearchStore`, `FAISS`, `HanaDB`, `Milvus`, `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",

29
docs/docs/integrations/llm_caching.ipynb
View File

@@ -2147,6 +2147,32 @@
"llm(\"Tell me one joke\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## SingleStoreDB Semantic Cache\n",
"You can use [SingleStoreDB](https://python.langchain.com/docs/integrations/vectorstores/singlestoredb/) as a semantic cache to cache prompts and responses."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d82f1bdc",
"metadata": {},
"outputs": [],
"source": [
"from langchain_community.cache import SingleStoreDBSemanticCache\n",
"from langchain_openai import OpenAIEmbeddings\n",
"\n",
"set_llm_cache(\n",
" SingleStoreDBSemanticCache(\n",
" embedding=OpenAIEmbeddings(),\n",
" host=\"root:pass@localhost:3306/db\",\n",
" )\n",
")"
]
},
{
"cell_type": "markdown",
"id": "ae1f5e1c-085e-4998-9f2d-b5867d2c3d5b",
@@ -2178,7 +2204,7 @@
"source": [
"**Cache** classes are implemented by inheriting the [BaseCache](https://api.python.langchain.com/en/latest/caches/langchain_core.caches.BaseCache.html) class.\n",
"\n",
"This table lists all 20 derived classes with links to the API Reference.\n",
"This table lists all 21 derived classes with links to the API Reference.\n",
"\n",
"\n",
"| Namespace 🔻 | Class |\n",
@@ -2195,6 +2221,7 @@
"| langchain_community.cache | [MomentoCache](https://api.python.langchain.com/en/latest/cache/langchain_community.cache.MomentoCache.html) |\n",
"| langchain_community.cache | [OpenSearchSemanticCache](https://api.python.langchain.com/en/latest/cache/langchain_community.cache.OpenSearchSemanticCache.html) |\n",
"| langchain_community.cache | [RedisSemanticCache](https://api.python.langchain.com/en/latest/cache/langchain_community.cache.RedisSemanticCache.html) |\n",
"| langchain_community.cache | [SingleStoreDBSemanticCache](https://api.python.langchain.com/en/latest/cache/langchain_community.cache.SingleStoreDBSemanticCache.html) |\n",
"| langchain_community.cache | [SQLAlchemyCache](https://api.python.langchain.com/en/latest/cache/langchain_community.cache.SQLAlchemyCache.html) |\n",
"| langchain_community.cache | [SQLAlchemyMd5Cache](https://api.python.langchain.com/en/latest/cache/langchain_community.cache.SQLAlchemyMd5Cache.html) |\n",
"| langchain_community.cache | [UpstashRedisCache](https://api.python.langchain.com/en/latest/cache/langchain_community.cache.UpstashRedisCache.html) |\n",