langchain-ai/langgraph
1
0
Fork 0
mirror of https://github.com/langchain-ai/langgraph.git synced 2026-07-15 12:35:43 -04:00
Code Issues 314 Packages Projects Releases 17 Wiki Activity

[PR #5057] serialize/deserialize pandas with pickle fallback #4208

New Issue
Closed
opened 2026-02-20 17:49:50 -05:00 by yindo · 0 comments
yindo commented 2026-02-20 17:49:50 -05:00
Owner
Copy Link
Copy Source

Original Pull Request: https://github.com/langchain-ai/langgraph/pull/5057

State: closed
Merged: Yes

Writing custom ser/deser logic for pandas with msgpack (and potentially arrow) blows up quickly. For now, pickling as a fallback works quite well.

This is a great opportunity for open source contributors - will create a follow up issue!

In the meantime, can do something like:

from langgraph.graph import StateGraph, START
from langgraph.checkpoint.memory import MemorySaver
from typing_extensions import TypedDict
from langgraph.types import interrupt, Command
from langchain_core.runnables import RunnableConfig


class State(TypedDict):
    data: pd.DataFrame


def node(state: State) -> dict[str, pd.DataFrame]:
    value = interrupt("This is an interrupt")
    return {"data": pd.DataFrame({"a": [1, 2, 3], "b": ["x", "y", "z"]})}


graph = StateGraph(State)
graph.add_node("start", node)
graph.add_edge(START, "start")
compiled_graph = graph.compile(
    checkpointer=MemorySaver(serde=JsonPlusSerializer(pickle_fallback=True))
)

config: RunnableConfig = {"configurable": {"thread_id": 1}}
result = compiled_graph.invoke({}, config=config)

print(result)
state = compiled_graph.get_state(config=config)
print(state)
**Original Pull Request:** https://github.com/langchain-ai/langgraph/pull/5057 **State:** closed **Merged:** Yes --- Writing custom ser/deser logic for pandas with msgpack (and potentially arrow) blows up quickly. For now, pickling as a fallback works quite well. This is a great opportunity for open source contributors - will create a follow up issue! In the meantime, can do something like: ```py from langgraph.graph import StateGraph, START from langgraph.checkpoint.memory import MemorySaver from typing_extensions import TypedDict from langgraph.types import interrupt, Command from langchain_core.runnables import RunnableConfig class State(TypedDict): data: pd.DataFrame def node(state: State) -> dict[str, pd.DataFrame]: value = interrupt("This is an interrupt") return {"data": pd.DataFrame({"a": [1, 2, 3], "b": ["x", "y", "z"]})} graph = StateGraph(State) graph.add_node("start", node) graph.add_edge(START, "start") compiled_graph = graph.compile( checkpointer=MemorySaver(serde=JsonPlusSerializer(pickle_fallback=True)) ) config: RunnableConfig = {"configurable": {"thread_id": 1}} result = compiled_graph.invoke({}, config=config) print(result) state = compiled_graph.get_state(config=config) print(state) ```
yindo added the pull-request label 2026-02-20 17:49:50 -05:00
yindo closed this issue 2026-02-20 17:49:50 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
agents
awaiting author revision
bug
change
chat models
checkpointer
ci
code quality
code quality
dependencies
documentation
drawing
duplicate
enhancement
good first issue
help wanted
invalid
maintainer
meta
missing information
not maintained by langchain
open-swe-auto
open-swe-max
open-swe-max-auto
pending
performance
pull-request
Mirrored from GitHub Pull Request
 question
requires design
sdk
server
stale
studio
tests
type checking
usage question
v0.5
v1.1
No Label pull-request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/langgraph#4208
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?