langchain-ai/langgraph
1
0
Fork 0
mirror of https://github.com/langchain-ai/langgraph.git synced 2026-07-15 12:35:43 -04:00
Code Issues 314 Packages Projects Releases 17 Wiki Activity

Missing langchain dependency in langgraph.prebuild pyproject.toml file. #723

New Issue
Closed
opened 2026-02-20 17:41:26 -05:00 by yindo · 2 comments
yindo commented 2026-02-20 17:41:26 -05:00
Owner
Copy Link
Copy Source

Originally created by @Andrii-Osipov on GitHub (Jun 13, 2025).

Checked other resources

  • This is a bug, not a usage question. For questions, please use GitHub Discussions.
  • I added a clear and detailed title that summarizes the issue.
  • I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example).
  • I included a self-contained, minimal example that demonstrates the issue INCLUDING all the relevant imports. The code run AS IS to reproduce the issue.

Example Code

"""create or replace procedure langgraph_sp()
returns string
language python
packages=('snowflake-snowpark-python', 'langgraph', 'langchain-core')
runtime_version={runtime_version}
handler='handler'
as
$$
from langgraph.prebuilt import create_react_agent

def get_weather(city: str) -> str:
    '''Get weather for a given city.'''
    return f"It's always sunny in {{city}}!"
def handler(session):
    agent = create_react_agent(
    model="anthropic:claude-3-7-sonnet-latest",
    tools=[get_weather],
    prompt="You are a helpful assistant"
    )

    # Run the agent
    agent.invoke(
        {{"messages": [{{"role": "user", "content": "what is the weather in sf"}}]}}
    )
    return "success"
   

$$;
        """

Error Message and Stack Trace (if applicable)

{'errno': 100357, 'sqlstate': 'P0000', 'message': 'Python Interpreter Error:\nTraceback (most recent call last):\n  File "/usr/lib/python_udf/55a7560e83fb5b8c54caeb201b949065cb47b174e805e8dfd83b565878d5ded7/lib/python3.9/site-packages/langgraph/prebuilt/chat_agent_executor.py", line 434, in create_react_agent\n    from langchain.chat_models import (  # type: ignore[import-not-found]\nModuleNotFoundError: No module named \'langchain\'\n\nDuring handling of the above exception, another exception occurred:\n\nTraceback (most recent call last):\n  File "_udf_code.py", line 8, in handler\n    agent = create_react_agent(\n  File "/usr/lib/python_udf/55a7560e83fb5b8c54caeb201b949065cb47b174e805e8dfd83b565878d5ded7/lib/python3.9/site-packages/langgraph/prebuilt/chat_agent_executor.py", line 438, in create_react_agent\n    raise ImportError(\nImportError: Please install langchain (`pip install langchain`) to use \'<provider>:<model>\' string syntax for `model` parameter.\n in function LANGGRAPH_SP with handler handler'}

Description

langgraph 0.4.7
I am trying to use create_react_agent as in the example of: https://github.com/langchain-ai/langgraph/blob/0.4.7/libs/prebuilt/langgraph/prebuilt/chat_agent_executor.py#L385-L400
These are the requirements that I used to build the pkg: https://github.com/AnacondaRecipes/langgraph-prebuilt-feedstock/blob/main/recipe/meta.yaml#L22
These are the requirements in upstream langgraph-prebuild: https://github.com/langchain-ai/langgraph/blob/0.4.7/libs/prebuilt/pyproject.toml#L14
Expected that the code must work through the langchain-core >=0.3.22, but it used langchain (which means that langchain-core is not used).
I don`t get why langchain.chat_models is used instead of langchain-core.language_models.chat_models.BaseChatModel, for example.
In this case, we needed to add langchain as an optional dependency in pyproject.toml for langgraph-prebuild, or rewrite the logic of create_react_agent to work through the langchain-core.
Thanks in advance!

System Info

Originally created by @Andrii-Osipov on GitHub (Jun 13, 2025). ### Checked other resources - [x] This is a bug, not a usage question. For questions, please use GitHub Discussions. - [x] I added a clear and detailed title that summarizes the issue. - [x] I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example). - [x] I included a self-contained, minimal example that demonstrates the issue INCLUDING all the relevant imports. The code run AS IS to reproduce the issue. ### Example Code ```python """create or replace procedure langgraph_sp() returns string language python packages=('snowflake-snowpark-python', 'langgraph', 'langchain-core') runtime_version={runtime_version} handler='handler' as $$ from langgraph.prebuilt import create_react_agent def get_weather(city: str) -> str: '''Get weather for a given city.''' return f"It's always sunny in {{city}}!" def handler(session): agent = create_react_agent( model="anthropic:claude-3-7-sonnet-latest", tools=[get_weather], prompt="You are a helpful assistant" ) # Run the agent agent.invoke( {{"messages": [{{"role": "user", "content": "what is the weather in sf"}}]}} ) return "success" $$; """ ``` ### Error Message and Stack Trace (if applicable) ```shell {'errno': 100357, 'sqlstate': 'P0000', 'message': 'Python Interpreter Error:\nTraceback (most recent call last):\n File "/usr/lib/python_udf/55a7560e83fb5b8c54caeb201b949065cb47b174e805e8dfd83b565878d5ded7/lib/python3.9/site-packages/langgraph/prebuilt/chat_agent_executor.py", line 434, in create_react_agent\n from langchain.chat_models import ( # type: ignore[import-not-found]\nModuleNotFoundError: No module named \'langchain\'\n\nDuring handling of the above exception, another exception occurred:\n\nTraceback (most recent call last):\n File "_udf_code.py", line 8, in handler\n agent = create_react_agent(\n File "/usr/lib/python_udf/55a7560e83fb5b8c54caeb201b949065cb47b174e805e8dfd83b565878d5ded7/lib/python3.9/site-packages/langgraph/prebuilt/chat_agent_executor.py", line 438, in create_react_agent\n raise ImportError(\nImportError: Please install langchain (`pip install langchain`) to use \'<provider>:<model>\' string syntax for `model` parameter.\n in function LANGGRAPH_SP with handler handler'} ``` ### Description **langgraph 0.4.7** I am trying to use **create_react_agent** as in the example of: https://github.com/langchain-ai/langgraph/blob/0.4.7/libs/prebuilt/langgraph/prebuilt/chat_agent_executor.py#L385-L400 These are the **requirements** that I used to build the pkg: https://github.com/AnacondaRecipes/langgraph-prebuilt-feedstock/blob/main/recipe/meta.yaml#L22 These are the **requirements** in upstream **langgraph-prebuild**: https://github.com/langchain-ai/langgraph/blob/0.4.7/libs/prebuilt/pyproject.toml#L14 Expected that the code must work through the **langchain-core >=0.3.22**, but it used **langchain** (which means that **langchain-core** is not used). I don`t get why **langchain.chat_models** is used instead of **langchain-core.language_models.chat_models.BaseChatModel**, for example. In this case, we needed to add **langchain** as an **optional dependency** in **pyproject.toml** for **langgraph-prebuild**, or rewrite the logic of **create_react_agent** to work through the **langchain-core**. Thanks in advance! ### System Info -
yindo added the bugpending labels 2026-02-20 17:41:26 -05:00
yindo closed this issue 2026-02-20 17:41:26 -05:00
yindo commented 2026-02-20 17:41:27 -05:00
Author
Owner
Copy Link
Copy Source

@sydney-runkle commented on GitHub (Jun 13, 2025):

if isinstance(model, str):
        try:
            from langchain.chat_models import (  # type: ignore[import-not-found]
                init_chat_model,
            )
        except ImportError:
            raise ImportError(
                "Please install langchain (`pip install langchain`) to use '<provider>:<model>' string syntax for `model` parameter."
            )

You'll need to install langchain if you want to use that syntax for models, else you can use ChatOpenAI directly with the required langchian-openai dependency.

@sydney-runkle commented on GitHub (Jun 13, 2025): ```py if isinstance(model, str): try: from langchain.chat_models import ( # type: ignore[import-not-found] init_chat_model, ) except ImportError: raise ImportError( "Please install langchain (`pip install langchain`) to use '<provider>:<model>' string syntax for `model` parameter." ) ``` You'll need to install langchain if you want to use that syntax for models, else you can use `ChatOpenAI` directly with the required `langchian-openai` dependency.
yindo commented 2026-02-20 17:41:27 -05:00
Author
Owner
Copy Link
Copy Source

@Andrii-Osipov commented on GitHub (Jun 13, 2025):

@sydney-runkle But why not add langchain as an optional dependency?

@Andrii-Osipov commented on GitHub (Jun 13, 2025): @sydney-runkle But why not add **langchain** as an **optional** dependency?
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
agents
awaiting author revision
bug
change
chat models
checkpointer
ci
code quality
code quality
dependencies
documentation
drawing
duplicate
enhancement
good first issue
help wanted
invalid
maintainer
meta
missing information
not maintained by langchain
open-swe-auto
open-swe-max
open-swe-max-auto
pending
performance
pull-request
Mirrored from GitHub Pull Request
 question
requires design
sdk
server
stale
studio
tests
type checking
usage question
v0.5
v1.1
No Label bug pending
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/langgraph#723
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?