bug: Guardrails won't work when llm is set to with_structured_output

Did you check docs and existing issues?

• I have read all the NeMo-Guardrails docs
• I have updated the package to the latest version before submitting this issue
• (optional) I have used the develop branch
• I have searched the existing issues of NeMo-Guardrails

Python version (python --version)

3.12.1

Operating system/version

Windows 11

NeMo-Guardrails version (if you must use a specific version and not the latest

No response

Describe the bug

Package versions used:

aiofiles==24.1.0
aiohappyeyeballs==2.4.4
aiohttp==3.11.11
aiolimiter==1.2.1
aiosignal==1.3.2
aiosqlite==0.20.0
alembic==1.14.0
annotated-types==0.7.0
annoy==1.17.3
anthropic==0.37.1
anyio==4.8.0
appdirs==1.4.4
asyncer==0.0.8
asyncio==3.4.3
asyncpg==0.30.0
attrs==24.3.0
backoff==2.2.1
boto3==1.35.94
botocore==1.35.94
cachetools==5.5.0
certifi==2024.12.14
cffi==1.17.1
cfgv==3.4.0
charset-normalizer==3.4.1
click==8.1.8
cloudpickle==3.1.0
cohere==5.13.6
colorama==0.4.6
coloredlogs==15.0.1
colorlog==6.9.0
cryptography==44.0.0
dataclasses-json==0.6.7
datasets==3.2.0
deepeval==1.6.2
defusedxml==0.7.1
Deprecated==1.2.15
dill==0.3.8
diskcache==5.6.3
distlib==0.3.9
distro==1.9.0
dnspython==2.7.0
docx2txt==0.8
dspy==2.5.42
dspy-ai==2.5.43
ecdsa==0.19.0
email_validator==2.2.0
execnet==2.1.1
fastapi==0.111.1
fastapi-cli==0.0.7
fastavro==1.10.0
fastembed==0.5.0
filelock==3.16.1
flatbuffers==24.12.23
frozenlist==1.5.0
fsspec==2024.9.0
googleapis-common-protos==1.66.0
greenlet==3.1.1
grpcio==1.63.2
h11==0.14.0
httpcore==1.0.7
httptools==0.6.4
httpx==0.28.1
httpx-sse==0.4.0
huggingface-hub==0.27.1
humanfriendly==10.0
identify==2.6.5
idna==3.10
importlib-metadata==7.0.0
iniconfig==2.0.0
Jinja2==3.1.5
jiter==0.8.2
jmespath==1.0.1
joblib==1.4.2
json_repair==0.35.0
jsonpatch==1.33
jsonpointer==3.0.0
jsonschema==4.23.0
jsonschema-specifications==2024.10.1
langchain==0.3.14
langchain-anthropic==0.2.4
langchain-aws==0.2.10
langchain-community==0.3.14
langchain-core==0.3.29
langchain-milvus==0.1.7
langchain-openai==0.2.14
langchain-text-splitters==0.3.5
langchain-voyageai==0.1.3
langgraph==0.2.61
langgraph-checkpoint==2.0.9
langgraph-checkpoint-sqlite==2.0.1
langgraph-sdk==0.1.48
langsmith==0.2.10
lark==1.1.9
litellm==1.51.0
loguru==0.7.3
magicattr==0.1.6
Mako==1.3.8
markdown-it-py==3.0.0
MarkupSafe==3.0.2
marshmallow==3.24.1
mdurl==0.1.2
mmh3==4.1.0
mpmath==1.3.0
msgpack==1.1.0
multidict==6.1.0
multiprocess==0.70.16
mypy-extensions==1.0.0
nemoguardrails==0.11.0
nest-asyncio==1.6.0
nodeenv==1.9.1
numpy==2.2.1
onnx==1.17.0
onnxruntime==1.20.1
openai==1.59.4
opentelemetry-api==1.24.0
opentelemetry-exporter-otlp-proto-common==1.24.0
opentelemetry-exporter-otlp-proto-grpc==1.24.0
opentelemetry-proto==1.24.0
opentelemetry-sdk==1.24.0
opentelemetry-semantic-conventions==0.45b0
optuna==4.1.0
orjson==3.10.13
packaging==24.2
pandas==2.2.3
parameterized==0.9.0
pillow==10.4.0
platformdirs==4.3.6
pluggy==1.5.0
portalocker==3.1.1
pre-commit==3.8.0
prompt_toolkit==3.0.48
propcache==0.2.1
protobuf==4.25.5
psycopg2==2.9.10
py_rust_stemmers==0.1.3
pyarrow==18.1.0
pyasn1==0.6.1
pycparser==2.22
pydantic==2.10.4
pydantic-settings==2.7.1
pydantic_core==2.27.2
Pygments==2.19.1
pymilvus==2.5.3
pyreadline3==3.5.4
pysbd==0.3.4
pytest==8.3.4
pytest-asyncio==0.25.2
pytest-order==1.3.0
pytest-repeat==0.9.3
pytest-xdist==3.6.1
python-dateutil==2.9.0.post0
python-dotenv==1.0.1
python-jose==3.3.0
python-multipart==0.0.20
pytz==2024.2
pywin32==308
PyYAML==6.0.2
ragas==0.2.10
redis==5.2.1
referencing==0.35.1
regex==2024.11.6
requests==2.32.3
requests-toolbelt==1.0.0
rich==13.9.4
rich-toolkit==0.12.0
rpds-py==0.22.3
rsa==4.9
s3transfer==0.10.4
sentry-sdk==2.19.2
setuptools==75.7.0
shellingham==1.5.4
simpleeval==1.0.3
six==1.17.0
sniffio==1.3.1
SQLAlchemy==2.0.36
sqlglot==25.34.1
starlette==0.37.2
sympy==1.13.3
tabulate==0.9.0
tenacity==8.4.2
tiktoken==0.8.0
tokenizers==0.21.0
tqdm==4.67.1
typer==0.15.1
types-requests==2.32.0.20241016
typing-inspect==0.9.0
typing_extensions==4.12.2
tzdata==2024.2
ujson==5.10.0
urllib3==2.3.0
uvicorn==0.29.0
virtualenv==20.28.1
voyageai==0.2.4
watchdog==6.0.0
watchfiles==1.0.3
wcwidth==0.2.13
websockets==14.1
win32_setctime==1.2.0
wrapt==1.17.0
xxhash==3.5.0
yarl==1.18.3
zipp==3.21.0

When I try to use the guardrails with a regular llm, it works just fine, but when I try to use with an llm which is wrapped with langchain's with_structured_output, I get the following error:

AttributeError("'ChatPromptValue' object has no attribute 'get'")

Steps To Reproduce

llm = ChatOpenAI()
llm = llm.with_structured_output(SOME_PYDANTIC_CLASS)
prompt = ChatPromptTemplate([("user", "{question}"])
guardrail_config = RailsConfig.from_path("src/agent/guardrail")
guardrails = RunnableRails(guardrail_config)
llm = prompt | (guardrails | llm)
llm.invoke({"question": "How are you?"})

Expected Behavior

This should work fine with or without the with_structured_output functionality.

Actual Behavior

When I invoke the chain when llm is set to with_structured_output, I receive the following error:

AttributeError("'ChatPromptValue' object has no attribute 'get'")