Skip to main content

Library with a MySQL implementation of LangGraph checkpoint saver.

Project description

LangGraph Checkpoint MySQL

Implementation of LangGraph CheckpointSaver that uses MySQL.

[!TIP] The code in this repository tries to mimic the code in langgraph-checkpoint-postgres as much as possible to enable keeping in sync with the official checkpointer implementation.

[!NOTE] In order to keep the queries close to the Postgres queries, we use features that require MySQL >= 8.0.19 or MariaDB >= 10.7.1.

Dependencies

  • To use synchronous PyMySQLSaver, install langgraph-checkpoint-mysql[pymysql].
  • To use asynchronous AIOMySQLSaver, install langgraph-checkpoint-mysql[aiomysql].
  • To use asynchronous AsyncMySaver, install langgraph-checkpoint-mysql[asyncmy].

There is currently no support for other drivers.

Usage

[!IMPORTANT] When using MySQL checkpointers for the first time, make sure to call .setup() method on them to create required tables. See example below.

[!IMPORTANT] When manually creating MySQL connections and passing them to PyMySQLSaver or AIOMySQLSaver, make sure to include autocommit=True.

Why this parameter is required:

  • autocommit=True: Required for the .setup() method to properly commit the checkpoint tables to the database. Without this, table creation may not be persisted.
from langgraph.checkpoint.mysql.pymysql import PyMySQLSaver

write_config = {"configurable": {"thread_id": "1", "checkpoint_ns": ""}}
read_config = {"configurable": {"thread_id": "1"}}

DB_URI = "mysql://mysql:mysql@localhost:3306/mysql"
with PyMySQLSaver.from_conn_string(DB_URI) as checkpointer:
    # call .setup() the first time you're using the checkpointer
    checkpointer.setup()
    checkpoint = {
        "v": 4,
        "ts": "2024-07-31T20:14:19.804150+00:00",
        "id": "1ef4f797-8335-6428-8001-8a1503f9b875",
        "channel_values": {
            "my_key": "meow",
            "node": "node"
        },
        "channel_versions": {
            "__start__": 2,
            "my_key": 3,
            "start:node": 3,
            "node": 3
        },
        "versions_seen": {
            "__input__": {},
            "__start__": {
            "__start__": 1
            },
            "node": {
            "start:node": 2
            }
        },
    }

    # store checkpoint
    checkpointer.put(write_config, checkpoint, {}, {})

    # load checkpoint
    checkpointer.get(read_config)

    # list checkpoints
    list(checkpointer.list(read_config))

Async

from langgraph.checkpoint.mysql.aio import AIOMySQLSaver

async with AIOMySQLSaver.from_conn_string(DB_URI) as checkpointer:
    checkpoint = {
        "v": 4,
        "ts": "2024-07-31T20:14:19.804150+00:00",
        "id": "1ef4f797-8335-6428-8001-8a1503f9b875",
        "channel_values": {
            "my_key": "meow",
            "node": "node"
        },
        "channel_versions": {
            "__start__": 2,
            "my_key": 3,
            "start:node": 3,
            "node": 3
        },
        "versions_seen": {
            "__input__": {},
            "__start__": {
            "__start__": 1
            },
            "node": {
            "start:node": 2
            }
        },
    }

    # store checkpoint
    await checkpointer.aput(write_config, checkpoint, {}, {})

    # load checkpoint
    await checkpointer.aget(read_config)

    # list checkpoints
    [c async for c in checkpointer.alist(read_config)]

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

langgraph_checkpoint_mysql-2.0.17.tar.gz (219.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

langgraph_checkpoint_mysql-2.0.17-py3-none-any.whl (38.3 kB view details)

Uploaded Python 3

File details

Details for the file langgraph_checkpoint_mysql-2.0.17.tar.gz.

File metadata

File hashes

Hashes for langgraph_checkpoint_mysql-2.0.17.tar.gz
Algorithm Hash digest
SHA256 e6afc559c4a4ac7fc68afb8bee6dd91a3e53761e2bcaf6d837b126b766205d1e
MD5 7d13accf570b361feb2d06b6a770f71c
BLAKE2b-256 4a5bee58fdc0ca5d88ca17499fee39be863a20d221681700d14b58f63c6dc257

See more details on using hashes here.

File details

Details for the file langgraph_checkpoint_mysql-2.0.17-py3-none-any.whl.

File metadata

File hashes

Hashes for langgraph_checkpoint_mysql-2.0.17-py3-none-any.whl
Algorithm Hash digest
SHA256 a7e2b35344f947f778d82ba5ce3fe60c58fe2dd0eb8b9c35ad381ea5f20607b3
MD5 bdb8acde5ebbfaeef9345c4d06e42904
BLAKE2b-256 e1c342c3ed598b11b07d81678747085d383ac39ed7ed9249446cdfa0e77b3bc8

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page