unitycatalog / unitycatalog/unitycatalog
Not compatible with langchain-core>=0.3.79
Open
Nobody has claimed this yet.
bug
- Dominant language
- Java
- Stars
- 3.5k
- Forks
- 672
- Avg merge
- 6d 16h
- Merged PRs (30d)
- 30
Description
Error message:
ModuleNotFoundError: No module named 'langchain_core.pydantic_v1'
Fix was to downgrade to langchain-core==0.3.79
Invoked by from databricks_langchain import ChatDatabricks
Stack trace:
17 from databricks.sdk import WorkspaceClient
18 from pydantic import BaseModel
File /local_disk0/.ephemeral_nfs/envs/pythonEnv-90c00629-c40f-4608-96d6-3c5713086415/lib/python3.12/site-packages/databricks_langchain/__init__.py:18
16 from unitycatalog.ai.core.base import set_uc_function_client
17 from unitycatalog.ai.core.databricks import DatabricksFunctionClient
---> 18 from unitycatalog.ai.langchain.toolkit import UCFunctionToolkit, UnityCatalogTool
20 from databricks_langchain.chat_models import ChatDatabricks
21 from databricks_langchain.embeddings import DatabricksEmbeddings
File /local_disk0/.ephemeral_nfs/envs/pythonEnv-90c00629-c40f-4608-96d6-3c5713086415/lib/python3.12/site-packages/unitycatalog/ai/langchain/toolkit.py:13
6 from langchain_core._api.deprecation import LangChainDeprecationWarning
8 warnings.filterwarnings(
9 "ignore",
10 message=r".*As of langchain-core 0\.3\.0, LangChain uses pydantic v2 internally.*",
11 category=LangChainDeprecationWarning,
12 )
---> 13 from langchain_core.pydantic_v1 import BaseModel, Field, root_validator
14 from langchain_core.tools import StructuredTool
16 from unitycatalog.ai.core.base import BaseFunctionClient
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with databricks_langchain/init.py and the import path through unitycatalog/ai/langchain/toolkit.py when importing ChatDatabricks. Check the langchain-core compatibility around version 0.3.79 and the pydantic_v1 import, then verify that ChatDatabricks imports successfully with langchain-core >=0.3.79.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 45/100