community[minor]: Add native async support to SQLChatMessageHistory

[pprados]

package community: Fix SQLChatMessageHistory

Description

Here is a rewrite of SQLChatMessageHistory to properly implement the asynchronous approach. The code circumvents issue 22021 by accepting a synchronous call to def add_messages() in an asynchronous scenario. This bypasses the bug.

For the same reasons as in PR 22 of langchain-postgres, we use a lazy strategy for table creation. Indeed, the promise of the constructor cannot be fulfilled without this. It is not possible to invoke a synchronous call in a constructor. We compensate for this by waiting for the next asynchronous method call to create the table.

The goal of the PostgresChatMessageHistory class (in langchain-postgres) is, among other things, to be able to recycle database connections. The implementation of the class is problematic, as we have demonstrated in issue 22021.

Our new implementation of SQLChatMessageHistory achieves this by using a singleton of type (Async)Engine for the database connection. The connection pool is managed by this singleton, and the code is then reentrant.

We also accept the type str (optionally complemented by async_mode. I know you don't like this much, but it's the only way to allow an asynchronous connection string).

In order to unify the different classes handling database connections, we have renamed connection_string to connection, and Session to session_maker.

Now, a single transaction is used to add a list of messages. Thus, a crash during this write operation will not leave the database in an unstable state with a partially added message list. This makes the code resilient.

We believe that the PostgresChatMessageHistory class is no longer necessary and can be replaced by:

PostgresChatMessageHistory = SQLChatMessageHistory

This also fixes the bug.

Issue

• issue 22021
  • Bug in _exit_history()
  • Bugs in PostgresChatMessageHistory and sync usage
  • Bugs in PostgresChatMessageHistory and async usage
• issue 36

Twitter handle:

pprados

Tests

• libs/community/tests/unit_tests/chat_message_histories/test_sql.py (add async test)

@baskaryan, @eyurtsev or @hwchase17 can you check this PR ?
And, I've been waiting a long time for validation from other PRs. Can you take a look?

• PR 32
• PR 15575
• PR 13200

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

1 Ignored Deployment

Name	Status	Preview	Comments	Updated (UTC)
langchain	⬜️ Ignored (Inspect)	Visit Preview		Jun 5, 2024 3:06pm

[eyurtsev]

Almost ready for merging.

Most important things to address:

1. Undo changes in core
2. Undo the code that calls async code from a sync function using a new event loop
3. Create a separate async session maker in chat history, so we can consolidate the asserts in just two places

[eyurtsev]

@pprados back from vacation -- this looks ready to merge, I'll take a final look tomorrow and resolve merge conflict

[eyurtsev]

(unrelated to this PR)

---

@pprados this pattern could be useful if you needed a transaction (e.g., as was the case in the indexing API if I recall correctly)

Allows passing a session maker as part of the init instead of initializing and then mutating a class attribute (the latter pattern is more likely to break in threaded scenarios)

[alew3]

Can you add in the documentation readme how to use async connections? Even with the PR, I'm getting errors.

[pprados]

Use:

history_engine = create_async_engine(url="postgresql+psycopg://user:password@localhost:5432)

def get_session_history(session_id: str) -> BaseChatMessageHistory:
    return SQLChatMessageHistory( 
        session_id=session_id,
        connection=history_engine,
        engine_args={"echo": False},
    )