diff --git a/src/oss/python/integrations/providers/microsoft.mdx b/src/oss/python/integrations/providers/microsoft.mdx index 441a8fb18f..a13f1ef1ce 100644 --- a/src/oss/python/integrations/providers/microsoft.mdx +++ b/src/oss/python/integrations/providers/microsoft.mdx @@ -365,6 +365,37 @@ See a [usage example](/oss/integrations/document_loaders/url/#playwright-url-loa from langchain_community.document_loaders.onenote import OneNoteLoader ``` +## Memory + +### Azure Cosmos DB Chat Message History + +>[Azure Cosmos DB](https://learn.microsoft.com/azure/cosmos-db/) provides chat message history storage for conversational AI applications, enabling you to persist and retrieve conversation history with low latency and high availability. + + + ```bash pip + pip install langchain-azure-ai + ``` + + ```bash uv + uv add langchain-azure-ai + ``` + + +Configure your Azure Cosmos DB connection: + +```python +from langchain_azure_ai.chat_message_histories import CosmosDBChatMessageHistory + +history = CosmosDBChatMessageHistory( + cosmos_endpoint="https://.documents.azure.com:443/", + cosmos_database="", + cosmos_container="", + session_id="", + user_id="", + credential="" # or use connection_string +) +``` + ## Vector Stores ### Azure Cosmos DB @@ -382,15 +413,15 @@ Below are two available Azure Cosmos DB APIs that can provide vector store funct See [detailed configuration instructions](/oss/integrations/vectorstores/azure_cosmos_db_mongo_vcore). -We need to install `pymongo` python package. +We need to install `langchain-azure-ai` and `pymongo` python packages. ```bash pip - pip install pymongo + pip install langchain-azure-ai pymongo ``` ```bash uv - uv add pymongo + uv add langchain-azure-ai pymongo ``` @@ -405,7 +436,7 @@ With Cosmos DB for MongoDB vCore, developers can enjoy the benefits of native Az See a [usage example](/oss/integrations/vectorstores/azure_cosmos_db_mongo_vcore). ```python -from langchain_community.vectorstores import AzureCosmosDBVectorSearch +from langchain_azure_ai.vectorstores import AzureCosmosDBMongoVCoreVectorSearch ``` #### Azure Cosmos DB NoSQL @@ -421,15 +452,15 @@ efficiency of vector-based operations. See [detail configuration instructions](/oss/integrations/vectorstores/azure_cosmos_db_no_sql). -We need to install `azure-cosmos` python package. +We need to install `langchain-azure-ai` and `azure-cosmos` python packages. ```bash pip - pip install azure-cosmos + pip install langchain-azure-ai azure-cosmos ``` ```bash uv - uv add azure-cosmos + uv add langchain-azure-ai azure-cosmos ``` @@ -443,7 +474,7 @@ in every Azure region and can automatically replicate data closer to users. It h See a [usage example](/oss/integrations/vectorstores/azure_cosmos_db_no_sql). ```python -from langchain_community.vectorstores import AzureCosmosDBNoSQLVectorSearch +from langchain_azure_ai.vectorstores import AzureCosmosDBNoSqlVectorSearch ``` ### Azure Database for PostgreSQL