Supporting within NeMo guardrails serialization

[snassimr]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

I am using this code to create Langchain compatible Rail :

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

    nemo_guardrails_config = RailsConfig.from_content(
        colang_content=nemo_guardrails_data.get_colang_content(),
        yaml_content=nemo_guardrails_data.get_yaml_content()
    )

    import nest_asyncio
    nest_asyncio.apply()

    nemo_guardrails = RunnableRails(nemo_guardrails_config)

If I use it with other Langchain components and try to serialize with Langchain tools (langchain_core.load.dumps) :

import json
from langchain_core.load import dumps
from langchain_core.messages import messages_to_dict

# Serialize the composite chain to a JSON string
chain_json = dumps(chain, pretty=True)

Description

It has this definition in json like :

"middle": [
      {
        "lc": 1,
        "type": "not_implemented",
        "id": [
          "nemoguardrails",
          "integrations",
          "langchain",
          "runnable_rails",
          "RunnableRails"
        ],
        "repr": "<nemoguardrails.integrations.langchain.runnable_rails.RunnableRails object at 0x7d5f224dbf10>"
      },

Looks like it's not supported . Any another way to serialize ?

Thanks

System Info

System Information

OS: Linux
OS Version: #1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024
Python Version: 3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]

Package Information

langchain_core: 0.2.43
langchain: 0.2.17
langchain_community: 0.2.19
langsmith: 0.1.147
langchain_openai: 0.1.21
langchain_text_splitters: 0.2.4

Optional packages not installed

langgraph
langserve

Other Dependencies

aiohttp: 3.11.10
async-timeout: 4.0.3
dataclasses-json: 0.6.7
httpx: 0.28.1
jsonpatch: 1.33
langsmith-pyo3: Installed. No version info available.
numpy: 1.26.4
openai: 1.55.3
orjson: 3.10.12
packaging: 24.2
pydantic: 2.10.3
PyYAML: 6.0.2
requests: 2.32.3
requests-toolbelt: 1.0.0
SQLAlchemy: 2.0.36
tenacity: 8.5.0
tiktoken: 0.8.0
typing-extensions: 4.12.2

[feijoes]

@snassimr You could try creating custom serialization for RunnableRails. from_dict and to_dict are necessary for serialization and deserialization in Langchain.

class SerializableRunnableRails(RunnableRails):
    def to_dict(self):
        ...

[snassimr]

Hi,
Actually , I think pickle-wise solution is good enough for me . Good example that works for me here