How to beginner · 3 min read

How to use RunnablePassthrough in LangChain

Q: How to use RunnablePassthrough in LangChain

Use RunnablePassthrough in LangChain to create a chain component that returns its input unchanged, useful for debugging or chaining without transformation. Instantiate it and call invoke or use it in a RunnableSequence to pass data through unchanged.

Quick answer

Use RunnablePassthrough in LangChain to create a chain component that returns its input unchanged, useful for debugging or chaining without transformation. Instantiate it and call invoke or use it in a RunnableSequence to pass data through unchanged.

PREREQUISITES

Python 3.8+
pip install langchain>=0.2
Basic knowledge of LangChain runnables

Setup

Install LangChain if you haven't already and import RunnablePassthrough from langchain.schema.runnable. Ensure your environment uses Python 3.8 or higher.

bash

pip install langchain>=0.2

Step by step

This example shows how to instantiate RunnablePassthrough and use it to pass input through unchanged. It also demonstrates chaining it with another runnable.

python

from langchain.schema.runnable import RunnablePassthrough

# Create a passthrough runnable
passthrough = RunnablePassthrough()

# Input data
input_data = "Hello, LangChain!"

# Invoke passthrough to get the same input back
output = passthrough.invoke(input_data)
print("Output:", output)

# Example chaining with RunnableSequence
from langchain.schema.runnable import RunnableSequence

# Define a simple runnable that uppercases text
class RunnableUppercase(RunnablePassthrough):
    def invoke(self, input):
        return input.upper()

uppercase = RunnableUppercase()

# Chain passthrough and uppercase
chain = RunnableSequence([passthrough, uppercase])

result = chain.invoke("chain me")
print("Chained output:", result)

output

Output: Hello, LangChain!
Chained output: CHAIN ME

Common variations

Use RunnablePassthrough in async contexts with ainvoke.
Combine with other runnables like RunnableMap or RunnableSequence for complex pipelines.
Use with LangChain's Runnable interface to integrate with LLMs or other tools.

python

import asyncio

async def async_example():
    passthrough = RunnablePassthrough()
    result = await passthrough.ainvoke("async input")
    print("Async output:", result)

asyncio.run(async_example())

output

Async output: async input

Troubleshooting

If RunnablePassthrough does not return input, verify you are calling invoke or ainvoke correctly.
Ensure LangChain version is 0.2 or higher to have RunnablePassthrough.
Check that input types are compatible; RunnablePassthrough returns exactly what it receives.

✅

Key Takeaways

Use RunnablePassthrough to pass inputs unchanged in LangChain pipelines.
Combine RunnablePassthrough with other runnables for flexible chaining.
Invoke invoke or ainvoke methods to run the passthrough synchronously or asynchronously.

Verified 2026-04

Verify ↗