Skip to main content

LangGraph Checkpoint MongoDB

Implementation of LangGraph CheckpointSaver that uses MongoDB.

Installation

pip install -U langgraph-checkpoint-mongodb

Usage

For more detailed usage examples and documentation, please refer to the MongoDB LangGraph documentation.

from langgraph.checkpoint.mongodb import MongoDBSaver

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

MONGODB_URI = "mongodb://localhost:27017"
DB_NAME = "checkpoint_example"

with MongoDBSaver.from_conn_string(MONGODB_URI, DB_NAME) as checkpointer:
    checkpoint = {
        "v": 1,
        "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
            }
        },
        "pending_sends": [],
    }

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

    # load checkpoint
    checkpointer.get(read_config)

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

Async

from langgraph.checkpoint.mongodb import MongoDBSaver

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

MONGODB_URI = "mongodb://localhost:27017"
DB_NAME = "checkpoint_example"

with MongoDBSaver.from_conn_string(MONGODB_URI, DB_NAME) as checkpointer:
    checkpoint = {
        "v": 1,
        "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
            }
        },
        "pending_sends": [],
    }

    # 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)]

Metadata

Release files for langgraph-checkpoint-mongodb 0.5.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for langgraph-checkpoint-mongodb 0.5.1
File Size Uploaded
langgraph_checkpoint_mongodb-0.5.1.tar.gz 201.5 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for langgraph-checkpoint-mongodb 0.5.1
File Interpreter ABI Platform
langgraph_checkpoint_mongodb-0.5.1-py3-none-any.whl Python 3 none any Details

Total release size: 210.4 kB

Release files / langgraph_checkpoint_mongodb-0.5.1.tar.gz

Download URL langgraph_checkpoint_mongodb-0.5.1.tar.gz
Size 201.5 kB
Tags Source
SHA-256 checksum
How to use checksums
16f047fe11fe9fd08bbf70a246ea9f17d61d89591f0434426c4ec522a5a8eefd
BLAKE2b-256 checksum
How to use checksums
23ec288003477574e932429445dcdbd4e4e9f3777175a378b34f6e60049a9ec1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Release files / langgraph_checkpoint_mongodb-0.5.1-py3-none-any.whl

Download URL langgraph_checkpoint_mongodb-0.5.1-py3-none-any.whl
Size 8.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
933fa3e7d60465d6af803ece6c0e462a336b74f89ee3a486a1196a3ca52028af
BLAKE2b-256 checksum
How to use checksums
ec35ed8c5759dab02a259f50c6356a38e2c2047295801988ad1f4183efbc3b00
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14
Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page