LangChain Integration

There are two main ways in which you can use NeMo Guardrails with LangChain:

Add guardrails to a LangChain chain (or Runnable).
Use a LangChain chain (or Runnable) inside a guardrails configuration.

Add Guardrails to a Chain

You can easily add guardrails to a chain using the RunnableRails class:

from nemoguardrails import RailsConfig
from nemoguardrails.integrations.langchain.runnable_rails import RunnableRails

# ... initialize `some_chain`

config = RailsConfig.from_path("path/to/config")

# Using LCEL, you first create a RunnableRails instance, and "apply" it using the "|" operator
guardrails = RunnableRails(config)
chain_with_guardrails = guardrails | some_chain

# Alternatively, you can specify the Runnable to wrap
# when creating the RunnableRails instance.
chain_with_guardrails = RunnableRails(config, runnable=some_chain)

For more details, check out the RunnableRails Guide and the Chain with Guardrails Guide.

Using a Chain inside Guardrails

To use a chain (or Runnable) inside a guardrails configuration, you can register it as an action.

from nemoguardrails import RailsConfig, LLMRails

config = RailsConfig.from_path("path/to/config")
rails = LLMRails(config)

rails.register_action(SampleChainOrRunnable(), "sample_action")

Once registered, the chain (or Runnable) can be invoked from within a flow:

define flow
  ...
  $result = execute sample_action
  ...

For a complete example, check out the Runnable as Action Guide.

LangSmith Integration

NeMo Guardrails integrates out-of-the-box with LangSmith. To start sending trace information to LangSmith, you have to configure the following environment variables:

export LANGCHAIN_TRACING_V2=true
export LANGCHAIN_ENDPOINT=https://api.smith.langchain.com
export LANGCHAIN_API_KEY=<your-api-key>
export LANGCHAIN_PROJECT=<your-project>  # if not specified, defaults to "default"

For more details on configuring LangSmith check out the LangSmith documentation.