`langchain_community.chat_message_histories.cosmos_db`.CosmosDBChatMessageHistory¶

class langchain_community.chat_message_histories.cosmos_db.CosmosDBChatMessageHistory(cosmos_endpoint: str, cosmos_database: str, cosmos_container: str, session_id: str, user_id: str, credential: Optional[Any] = None, connection_string: Optional[str] = None, ttl: Optional[int] = None, cosmos_client_kwargs: Optional[dict] = None)[source]¶

Chat message history backed by Azure CosmosDB.

Initializes a new instance of the CosmosDBChatMessageHistory class.

Make sure to call prepare_cosmos or use the context manager to make sure your database is ready.

Either a credential or a connection string must be provided.

Parameters

cosmos_endpoint (str) – The connection endpoint for the Azure Cosmos DB account.
cosmos_database (str) – The name of the database to use.
cosmos_container (str) – The name of the container to use.
session_id (str) – The session ID to use, can be overwritten while loading.
user_id (str) – The user ID to use, can be overwritten while loading.
credential (Any) – The credential to use to authenticate to Azure Cosmos DB.
connection_string (Optional[str]) – The connection string to use to authenticate.
ttl (Optional[int]) – The time to live (in seconds) to use for documents in the container.
cosmos_client_kwargs (Optional[dict]) – Additional kwargs to pass to the CosmosClient.

Attributes

messages

A property or attribute that returns a list of messages.

Methods

`__init__`(cosmos_endpoint, cosmos_database, ...)	Initializes a new instance of the CosmosDBChatMessageHistory class.
`aadd_messages`(messages)	Add a list of messages.
`aclear`()	Remove all messages from the store
`add_ai_message`(message)	Convenience method for adding an AI message string to the store.
`add_message`(message)	Add a self-created message to the store
`add_messages`(messages)	Add a list of messages.
`add_user_message`(message)	Convenience method for adding a human message string to the store.
`aget_messages`()	Async version of getting messages.
`clear`()	Clear session memory from this memory and cosmos.
`load_messages`()	Retrieve the messages from Cosmos
`prepare_cosmos`()	Prepare the CosmosDB client.
`upsert_messages`()	Update the cosmosdb item.

__init__(cosmos_endpoint: str, cosmos_database: str, cosmos_container: str, session_id: str, user_id: str, credential: Optional[Any] = None, connection_string: Optional[str] = None, ttl: Optional[int] = None, cosmos_client_kwargs: Optional[dict] = None)[source]¶

Initializes a new instance of the CosmosDBChatMessageHistory class.

Make sure to call prepare_cosmos or use the context manager to make sure your database is ready.

Either a credential or a connection string must be provided.

Parameters

cosmos_endpoint (str) – The connection endpoint for the Azure Cosmos DB account.
cosmos_database (str) – The name of the database to use.
cosmos_container (str) – The name of the container to use.
session_id (str) – The session ID to use, can be overwritten while loading.
user_id (str) – The user ID to use, can be overwritten while loading.
credential (Optional[Any]) – The credential to use to authenticate to Azure Cosmos DB.
connection_string (Optional[str]) – The connection string to use to authenticate.
ttl (Optional[int]) – The time to live (in seconds) to use for documents in the container.
cosmos_client_kwargs (Optional[dict]) – Additional kwargs to pass to the CosmosClient.

async aadd_messages(messages: Sequence[BaseMessage]) → None¶

Add a list of messages.

Parameters: messages (Sequence[BaseMessage]) – A list of BaseMessage objects to store.
Return type: None

async aclear() → None¶

Remove all messages from the store

Return type: None

add_ai_message(message: Union[AIMessage, str]) → None¶

Convenience method for adding an AI message string to the store.

Please note that this is a convenience method. Code should favor the bulk add_messages interface instead to save on round-trips to the underlying persistence layer.

This method may be deprecated in a future release.

Parameters: message (Union[AIMessage, str]) – The AI message to add.
Return type: None

add_message(message: BaseMessage) → None[source]¶

Add a self-created message to the store

Parameters: message (BaseMessage) –
Return type: None

add_messages(messages: Sequence[BaseMessage]) → None¶

Add a list of messages.

Implementations should over-ride this method to handle bulk addition of messages in an efficient manner to avoid unnecessary round-trips to the underlying store.

Parameters: messages (Sequence[BaseMessage]) – A list of BaseMessage objects to store.
Return type: None

add_user_message(message: Union[HumanMessage, str]) → None¶

Convenience method for adding a human message string to the store.

Please note that this is a convenience method. Code should favor the bulk add_messages interface instead to save on round-trips to the underlying persistence layer.

This method may be deprecated in a future release.

Parameters: message (Union[HumanMessage, str]) – The human message to add
Return type: None

async aget_messages() → List[BaseMessage]¶

Async version of getting messages.

Can over-ride this method to provide an efficient async implementation.

In general, fetching messages may involve IO to the underlying persistence layer.

Return type: List[BaseMessage]

clear() → None[source]¶

Clear session memory from this memory and cosmos.

Return type: None

load_messages() → None[source]¶

Retrieve the messages from Cosmos

Return type: None

prepare_cosmos() → None[source]¶

Prepare the CosmosDB client.

Use this function or the context manager to make sure your database is ready.

Return type: None

upsert_messages() → None[source]¶

Update the cosmosdb item.

Return type: None

langchain_community.chat_message_histories.cosmos_db.CosmosDBChatMessageHistory¶

`langchain_community.chat_message_histories.cosmos_db`.CosmosDBChatMessageHistory¶