[BUG] langchain could not determine a constructor for the tag error

[minkj1992]

Issues Policy acknowledgement

• I have read and agree to submit bug reports in accordance with the issues policy

Where did you encounter this bug?

Local machine

Willingness to contribute

Yes. I can contribute a fix for this bug independently.

MLflow version

mlflow --version
mlflow, version 2.12.1

System information

system_profiler SPSoftwareDataType SPHardwareDataType

Software:

System Software Overview:

  System Version: macOS 14.4.1 (23E224)
  Kernel Version: Darwin 23.4.0
  Secure Virtual Memory: Enabled
  System Integrity Protection: Enabled

Hardware:

Hardware Overview:
  Model Name: MacBook Pro
  Chip: Apple M1 Max
  System Firmware Version: 10151.101.3
  OS Loader Version: 10151.101.3

python --version
Python 3.12.2

Describe the problem

I've been attempting the approach outlined in the link below, but encountering an issue where the YAML isn't generated properly when I include the output parser.

https://mlflow.org/docs/latest/llms/langchain/notebooks/langchain-quickstart.html#Logging-the-Chain-in-MLflow

Of course, I'm aware of the statement 'MLflow does not guarantee support for LLMs outside of HuggingFaceHub and OpenAI, found Ollama', but I concluded it was a bug because excluding the code related to the parser prevents any errors besides the Ollama error from occurring.

Tracking information

REPLACE_ME

Code to reproduce issue

import mlflow
from langchain.chains import LLMChain
from langchain_community.llms import Ollama
from langchain_core.output_parsers import JsonOutputParser, PydanticOutputParser
from langchain_core.prompts import PromptTemplate
from langchain_core.pydantic_v1 import BaseModel, Field

coherence_template = """You are the judge evaluating coherence/logic when you receive the debate topic and the content of the discussion.

...skip...

## Input
  TOPIC: {topic},
  Debate: {debate}

Below are the criteria for deducting points based on coherence/logic.


"""

topic = "Mocking topic"
debate = "Mocking debate"


class LLMResult(BaseModel):
    a_score: int = Field(description="Score of Team A")
    a_reason: str = Field(description="Reason for deduction for Team A")
    b_score: int = Field(description="Score of Team B")
    b_reason: str = Field(description="Reason for deduction for Team B")


llm = Ollama(model="llama3", temperature=0, verbose=True)
parser = PydanticOutputParser(pydantic_object=LLMResult)
# parser = JsonOutputParser(pydantic_object=LLMResult)
coherence_prompt = PromptTemplate(
    template=coherence_template,
    input_variables=[
        "topic",
        "debate",
    ],
    partial_variables={"format_instructions": parser.get_format_instructions()},
)


chain = LLMChain(llm=llm, prompt=coherence_prompt, output_parser=parser)

mlflow.set_experiment("TEST 04")

with mlflow.start_run():
    model_info = mlflow.langchain.log_model(chain, "langchain_model")

loaded_model = mlflow.pyfunc.load_model(model_info.model_uri)
result = loaded_model.predict({"topic": topic, "debate": debate})
print(result)

Stack trace

2024/04/30 10:45:46 WARNING mlflow.utils.environment: Encountered an unexpected error while inferring pip requirements (model URI: /var/folders/j3/3llb09155g55ct9f02mqn4200000gn/T/tmpon9sez4r/model, flavor: langchain). Fall back to return ['langchain==0.1.16', 'pydantic==2.7.1', 'cloudpickle==3.0.0']. Set logging level to DEBUG to see the full traceback. 
Traceback (most recent call last):
  File "/Users/minwook/code/personal/eval/main.py", line 52, in <module>
    loaded_model = mlflow.pyfunc.load_model(model_info.model_uri)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/miniconda3/envs/mlops/lib/python3.12/site-packages/mlflow/pyfunc/__init__.py", line 892, in load_model
    model_impl = importlib.import_module(conf[MAIN])._load_pyfunc(data_path)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/miniconda3/envs/mlops/lib/python3.12/site-packages/mlflow/langchain/__init__.py", line 818, in _load_pyfunc
    return wrapper_cls(_load_model_from_local_fs(path))
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/miniconda3/envs/mlops/lib/python3.12/site-packages/mlflow/langchain/__init__.py", line 846, in _load_model_from_local_fs
    return _load_model(local_model_path, flavor_conf)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/miniconda3/envs/mlops/lib/python3.12/site-packages/mlflow/langchain/__init__.py", line 563, in _load_model
    model = _load_base_lcs(local_model_path, flavor_conf)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/miniconda3/envs/mlops/lib/python3.12/site-packages/mlflow/langchain/utils.py", line 522, in _load_base_lcs
    model = _patch_loader(load_chain)(lc_model_path)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/miniconda3/envs/mlops/lib/python3.12/site-packages/mlflow/langchain/utils.py", line 467, in patched_loader
    return loader_func(*args, **kwargs, allow_dangerous_deserialization=True)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/miniconda3/envs/mlops/lib/python3.12/site-packages/langchain/chains/loading.py", line 631, in load_chain
    return _load_chain_from_file(path, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/miniconda3/envs/mlops/lib/python3.12/site-packages/langchain/chains/loading.py", line 647, in _load_chain_from_file
    config = yaml.safe_load(f)
             ^^^^^^^^^^^^^^^^^
  File "/opt/miniconda3/envs/mlops/lib/python3.12/site-packages/yaml/__init__.py", line 125, in safe_load
    return load(stream, SafeLoader)
           ^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/miniconda3/envs/mlops/lib/python3.12/site-packages/yaml/__init__.py", line 81, in load
    return loader.get_single_data()
           ^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/miniconda3/envs/mlops/lib/python3.12/site-packages/yaml/constructor.py", line 51, in get_single_data
    return self.construct_document(node)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/miniconda3/envs/mlops/lib/python3.12/site-packages/yaml/constructor.py", line 60, in construct_document
    for dummy in generator:
  File "/opt/miniconda3/envs/mlops/lib/python3.12/site-packages/yaml/constructor.py", line 413, in construct_yaml_map
    value = self.construct_mapping(node)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/miniconda3/envs/mlops/lib/python3.12/site-packages/yaml/constructor.py", line 218, in construct_mapping
    return super().construct_mapping(node, deep=deep)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/miniconda3/envs/mlops/lib/python3.12/site-packages/yaml/constructor.py", line 143, in construct_mapping
    value = self.construct_object(value_node, deep=deep)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/miniconda3/envs/mlops/lib/python3.12/site-packages/yaml/constructor.py", line 100, in construct_object
    data = constructor(self, node)
           ^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/miniconda3/envs/mlops/lib/python3.12/site-packages/yaml/constructor.py", line 427, in construct_undefined
    raise ConstructorError(None, None,
yaml.constructor.ConstructorError: could not determine a constructor for the tag 'tag:yaml.org,2002:python/name:__main__.LLMResult'
  in "/Users/minwook/code/personal/eval/mlruns/732209676491018788/6f58a326322449e2a5fa620b94a4ff60/artifacts/langchain_model/model.yaml", line 33, column 20

Other info / logs

REPLACE_ME

What component(s) does this bug affect?

• area/artifacts: Artifact stores and artifact logging
• area/build: Build and test infrastructure for MLflow
• area/deployments: MLflow Deployments client APIs, server, and third-party Deployments integrations
• area/docs: MLflow documentation pages
• area/examples: Example code
• area/model-registry: Model Registry service, APIs, and the fluent client calls for Model Registry
• area/models: MLmodel format, model serialization/deserialization, flavors
• area/recipes: Recipes, Recipe APIs, Recipe configs, Recipe Templates
• area/projects: MLproject format, project running backends
• area/scoring: MLflow Model server, model deployment tools, Spark UDFs
• area/server-infra: MLflow Tracking server backend
• area/tracking: Tracking Service, tracking client APIs, autologging

What interface(s) does this bug affect?

• area/uiux: Front-end, user experience, plotting, JavaScript, JavaScript dev server
• area/docker: Docker use across MLflow's components, such as MLflow Projects and MLflow Models
• area/sqlalchemy: Use of SQLAlchemy in the Tracking Service or Model Registry
• area/windows: Windows support

What language(s) does this bug affect?

• language/r: R APIs and clients
• language/java: Java APIs and clients
• language/new: Proposals for new client languages

What integration(s) does this bug affect?

• integrations/azure: Azure and Azure ML integrations
• integrations/sagemaker: SageMaker integrations
• integrations/databricks: Databricks integrations

[WeichenXu123]

__main__.LLMResult
the class is defined in __main__ module.

You can move LLMResult class definition to a python file module and log the python file as the code_paths to address it.

[github-actions]

@mlflow/mlflow-team Please assign a maintainer and start triaging this issue.