[Bug] [Dependency]: Import LabelingAgent is failing due to langchain and pydantic dependency issue with refuel-autolabel

[diljeet1994]

Hi, I tried importing LabelingAgent using below code : from autolabel import LabelingAgent getting pydantic error, please check full issue in attached file ​Basically, issue is with langchain, it needs pydantic version >= 2, but this is not supported by refuel-autolable 0.0.15, when I tried to upgrade langchain (which supports pydantic>=2.0), again refuel-autolable 0.0.15 doesn't support langchain >=0.0.210

Using Python 3.9.18 OS: windows 11

ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
langchain 0.0.226 requires pydantic<2,>=1, but you have pydantic 2.0 which is incompatible.
langchainplus-sdk 0.0.20 requires pydantic<2,>=1, but you have pydantic 2.0 which is incompatible.
refuel-autolabel 0.0.15 requires langchain==0.0.210, but you have langchain 0.0.226 which is incompatible.

`---------------------------------------------------------------------------
PydanticUserError                         Traceback (most recent call last)
Cell In[8], line 3
      1 import json
----> 3 from autolabel import LabelingAgent

File c:\users\hp\appdata\local\programs\python\python39\lib\site-packages\autolabel\__init__.py:3
      1 from importlib import metadata
----> 3 from .labeler import LabelingAgent
      4 from .utils import get_data
      5 from .dataset import AutolabelDataset

File c:\users\hp\appdata\local\programs\python\python39\lib\site-packages\autolabel\labeler.py:13
     10 from rich.console import Console
     11 from rich.prompt import Confirm
---> 13 from autolabel.cache import SQLAlchemyGenerationCache, SQLAlchemyTransformCache
     14 from autolabel.confidence import ConfidenceCalculator
     15 from autolabel.configs import AutolabelConfig

File c:\users\hp\appdata\local\programs\python\python39\lib\site-packages\autolabel\cache\__init__.py:2
      1 from .base import BaseCache
----> 2 from .sqlalchemy_generation_cache import SQLAlchemyGenerationCache
      3 from .sqlalchemy_transform_cache import SQLAlchemyTransformCache

File c:\users\hp\appdata\local\programs\python\python39\lib\site-packages\autolabel\cache\sqlalchemy_generation_cache.py:3
      1 from sqlalchemy.orm import sessionmaker
      2 from typing import Optional
----> 3 from autolabel.schema import GenerationCacheEntry
      4 from autolabel.database import create_db_engine
      5 from autolabel.data_models import Base

File c:\users\hp\appdata\local\programs\python\python39\lib\site-packages\autolabel\schema.py:6
      3 from typing import Any, Dict, List, Optional, Union
      5 import pandas as pd
----> 6 from langchain.schema import Generation
      7 from pydantic import BaseModel
      9 from autolabel.configs import AutolabelConfig

File c:\users\hp\appdata\local\programs\python\python39\lib\site-packages\langchain\__init__.py:6
      3 from importlib import metadata
      4 from typing import Optional
----> 6 from langchain.agents import MRKLChain, ReActChain, SelfAskWithSearchChain
      7 from langchain.cache import BaseCache
      8 from langchain.chains import (
      9     ConversationChain,
     10     LLMBashChain,
   (...)
     18     VectorDBQAWithSourcesChain,
     19 )

File c:\users\hp\appdata\local\programs\python\python39\lib\site-packages\langchain\agents\__init__.py:2
      1 """Interface for agents."""
----> 2 from langchain.agents.agent import (
      3     Agent,
      4     AgentExecutor,
      5     AgentOutputParser,
      6     BaseMultiActionAgent,
      7     BaseSingleActionAgent,
      8     LLMSingleActionAgent,
      9 )
     10 from langchain.agents.agent_toolkits import (
     11     create_csv_agent,
     12     create_json_agent,
   (...)
     21     create_vectorstore_router_agent,
     22 )
     23 from langchain.agents.agent_types import AgentType

File c:\users\hp\appdata\local\programs\python\python39\lib\site-packages\langchain\agents\agent.py:16
     13 from pydantic import BaseModel, root_validator
     15 from langchain.agents.agent_types import AgentType
---> 16 from langchain.agents.tools import InvalidTool
     17 from langchain.base_language import BaseLanguageModel
     18 from langchain.callbacks.base import BaseCallbackManager

File c:\users\hp\appdata\local\programs\python\python39\lib\site-packages\langchain\agents\tools.py:4
      1 """Interface for tools."""
      2 from typing import Optional
----> 4 from langchain.callbacks.manager import (
      5     AsyncCallbackManagerForToolRun,
      6     CallbackManagerForToolRun,
      7 )
      8 from langchain.tools.base import BaseTool, Tool, tool
     11 class InvalidTool(BaseTool):

File c:\users\hp\appdata\local\programs\python\python39\lib\site-packages\langchain\callbacks\__init__.py:3
      1 """Callback handlers that allow listening to events in LangChain."""
----> 3 from langchain.callbacks.aim_callback import AimCallbackHandler
      4 from langchain.callbacks.argilla_callback import ArgillaCallbackHandler
      5 from langchain.callbacks.arize_callback import ArizeCallbackHandler

File c:\users\hp\appdata\local\programs\python\python39\lib\site-packages\langchain\callbacks\aim_callback.py:4
      1 from copy import deepcopy
      2 from typing import Any, Dict, List, Optional, Union
----> 4 from langchain.callbacks.base import BaseCallbackHandler
      5 from langchain.schema import AgentAction, AgentFinish, LLMResult
      8 def import_aim() -> Any:

File c:\users\hp\appdata\local\programs\python\python39\lib\site-packages\langchain\callbacks\base.py:7
      4 from typing import Any, Dict, List, Optional, Union
... (54 lines left)

[rajasbansal]

Hey @diljeet1994, with the new version, we have upgraded the langchain version and you should now be able to build autolabel. Let me know if you are still having issues!

[NLPBrewer]

Hi @rajasbansal , Thanks for the update, but please update the langchain to a newer version that support pydantic>2.0 so that the rest of the production level code doesn't breaks, with your current update, langchain version is 0.0226 which supports pydantic < 2. Please make this change cause it may give issue to lot of folks trying latest pydantic version for their apps.