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 #6523] feat: add batch_send utility function for map-reduce workflows #5093

New Issue
Closed
opened 2026-02-20 17:51:13 -05:00 by yindo · 0 comments
yindo commented 2026-02-20 17:51:13 -05:00
Owner
Copy Link
Copy Source

Original Pull Request: https://github.com/langchain-ai/langgraph/pull/6523

State: closed
Merged: No

📝 Summary

This PR introduces a new convenience function batch_send() to simplify map-reduce workflows in LangGraph. Instead of manually writing list comprehensions with Send objects for parallel node execution, developers can now use this cleaner helper function.

🔧 Changes Made

1. Added batch_send() function

File: libs/langgraph/langgraph/types.py

  • New utility function that creates multiple Send objects for the same node
  • Simplifies map-reduce patterns where one node needs to be invoked multiple times in parallel
  • Includes comprehensive docstring with usage example
  • Added to __all__ exports for public API

2. Added comprehensive unit tests

File: libs/langgraph/tests/test_utils.py

  • Test with simple arguments (integers)
  • Test with dictionary arguments (common in state graphs)
  • Test with empty lists
  • Test with single argument
  • Ensures correct Send object creation

3. Added repository architecture documentation

File: REPOSITORY_DIAGRAM.md

  • Comprehensive overview of LangGraph monorepo structure
  • Visual dependency graphs using Mermaid diagrams
  • Detailed explanation of each library (checkpoint, langgraph, prebuilt, CLI, SDKs)
  • Core concepts and workflow diagrams
  • Development guide and learning path

4. Cleared AGENTS.md

  • Removed previous content

💡 Motivation

The new batch_send() function improves code readability and reduces boilerplate for common map-reduce patterns:

Before (Manual List Comprehension):

def continue_to_jokes(state: OverallState):
    return [Send("generate_joke", {"subject": s}) for s in state["subjects"]]

After (Using batch_send):

from langgraph.types import batch_send

def continue_to_jokes(state: OverallState):
    return batch_send("generate_joke", [{"subject": s} for s in state["subjects"]])

This makes the intent clearer and is more maintainable.

✅ Checklist

  • Unit Tests added (4 comprehensive test cases)
  • Code follows existing patterns and style
  • Function properly exported in __all__
  • Comprehensive documentation added to function with examples
  • Repository documentation enhanced with visual diagrams
**Original Pull Request:** https://github.com/langchain-ai/langgraph/pull/6523 **State:** closed **Merged:** No --- ## 📝 Summary This PR introduces a new convenience function `batch_send()` to simplify map-reduce workflows in LangGraph. Instead of manually writing list comprehensions with `Send` objects for parallel node execution, developers can now use this cleaner helper function. ## 🔧 Changes Made ### 1. Added `batch_send()` function **File:** `libs/langgraph/langgraph/types.py` - New utility function that creates multiple `Send` objects for the same node - Simplifies map-reduce patterns where one node needs to be invoked multiple times in parallel - Includes comprehensive docstring with usage example - Added to `__all__` exports for public API ### 2. Added comprehensive unit tests **File:** `libs/langgraph/tests/test_utils.py` - Test with simple arguments (integers) - Test with dictionary arguments (common in state graphs) - Test with empty lists - Test with single argument - Ensures correct `Send` object creation ### 3. Added repository architecture documentation **File:** `REPOSITORY_DIAGRAM.md` - Comprehensive overview of LangGraph monorepo structure - Visual dependency graphs using Mermaid diagrams - Detailed explanation of each library (checkpoint, langgraph, prebuilt, CLI, SDKs) - Core concepts and workflow diagrams - Development guide and learning path ### 4. Cleared AGENTS.md - Removed previous content ## 💡 Motivation The new `batch_send()` function improves code readability and reduces boilerplate for common map-reduce patterns: **Before (Manual List Comprehension):** ```python def continue_to_jokes(state: OverallState): return [Send("generate_joke", {"subject": s}) for s in state["subjects"]] ``` **After (Using batch_send):** ```python from langgraph.types import batch_send def continue_to_jokes(state: OverallState): return batch_send("generate_joke", [{"subject": s} for s in state["subjects"]]) ``` This makes the intent clearer and is more maintainable. ## ✅ Checklist - [x] Unit Tests added (4 comprehensive test cases) - [x] Code follows existing patterns and style - [x] Function properly exported in `__all__` - [x] Comprehensive documentation added to function with examples - [x] Repository documentation enhanced with visual diagrams
yindo added the pull-request label 2026-02-20 17:51:13 -05:00
yindo closed this issue 2026-02-20 17:51:13 -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#5093
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?