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

crfeate_react_agent does not support already bound tools with gemini models #295

New Issue
Closed
opened 2026-02-20 17:35:43 -05:00 by yindo · 1 comment
yindo commented 2026-02-20 17:35:43 -05:00
Owner
Copy Link
Copy Source

Originally created by @vidit-bhatia on GitHub (Oct 30, 2024).

Checked other resources

  • I added a very descriptive title to this issue.
  • I searched the LangGraph/LangChain documentation with the integrated search.
  • I used the GitHub search to find a similar question and didn't find it.
  • I am sure that this is a bug in LangGraph/LangChain rather than my code.
  • I am sure this is better as an issue rather than a GitHub discussion, since this is a LangGraph bug and not a design question.

Example Code

from langchain_google_genai import ChatGoogleGenerativeAI
from configs.configs import llm_api_key
from langchain.tools import tool, BaseTool, StructuredTool
from typing import Annotated, List, Dict  
from string import Template 
import logging
from langchain_core.runnables.config import RunnableConfig
from json import loads, dumps
from typing import Optional, Type

llm = ChatGoogleGenerativeAI(model="gemini-1.5-flash-8b",google_api_key=llm_api_key.gemini_api_key,temperature=1, tool_call  = True)

@tool
def authoring_tool(user_information: RunnableConfig,
           template: Annotated[str,"The template created by LLM to be used for personalization"]) -> str:
    """The tool gets a python string template as an input and the user information . Returns the result of personalizing the template with the user information"""
    # t = Template(template) 
    user = user_information.get("configurable", {}).get("user")
    # final_to_print = t.substitute(loads(user)) 
    final_to_print = template.format(user)
    logging.info(final_to_print)
    return final_to_print


authoring_tool_llm = llm.bind_tools(tools=[authoring_tool],tool_choice="any")
author_agent = create_react_agent(authoring_tool_llm, tools=[authoring_tool],state_modifier=author_agent_prompt)

Error Message and Stack Trace (if applicable)

Traceback (most recent call last):
  File "/Users/vibhatia/anaconda3/lib/python3.11/runpy.py", line 198, in _run_module_as_main
    return _run_code(code, main_globals, None,
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/vibhatia/anaconda3/lib/python3.11/runpy.py", line 88, in _run_code
    exec(code, run_globals)
  File "/Users/vibhatia/.vscode/extensions/ms-python.debugpy-2024.12.0-darwin-arm64/bundled/libs/debugpy/adapter/../../debugpy/launcher/../../debugpy/__main__.py", line 71, in <module>
    cli.main()
  File "/Users/vibhatia/.vscode/extensions/ms-python.debugpy-2024.12.0-darwin-arm64/bundled/libs/debugpy/adapter/../../debugpy/launcher/../../debugpy/../debugpy/server/cli.py", line 501, in main
    run()
  File "/Users/vibhatia/.vscode/extensions/ms-python.debugpy-2024.12.0-darwin-arm64/bundled/libs/debugpy/adapter/../../debugpy/launcher/../../debugpy/../debugpy/server/cli.py", line 351, in run_file
    runpy.run_path(target, run_name="__main__")
  File "/Users/vibhatia/.vscode/extensions/ms-python.debugpy-2024.12.0-darwin-arm64/bundled/libs/debugpy/_vendored/pydevd/_pydevd_bundle/pydevd_runpy.py", line 310, in run_path
    return _run_module_code(code, init_globals, run_name, pkg_name=pkg_name, script_name=fname)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/vibhatia/.vscode/extensions/ms-python.debugpy-2024.12.0-darwin-arm64/bundled/libs/debugpy/_vendored/pydevd/_pydevd_bundle/pydevd_runpy.py", line 127, in _run_module_code
    _run_code(code, mod_globals, init_globals, mod_name, mod_spec, pkg_name, script_name)
  File "/Users/vibhatia/.vscode/extensions/ms-python.debugpy-2024.12.0-darwin-arm64/bundled/libs/debugpy/_vendored/pydevd/_pydevd_bundle/pydevd_runpy.py", line 118, in _run_code
    exec(code, run_globals)
  File "/Users/vibhatia/Documents/external/Agents/MarketingAgent/marketingagents/src/usecases/B2BResearchMarketing/main.py", line 6, in <module>
    from Agents import  author_node, supervisor_agent, send_email_node,members
  File "/Users/vibhatia/Documents/external/Agents/MarketingAgent/marketingagents/src/usecases/B2BResearchMarketing/Agents.py", line 33, in <module>
    author_agent = create_react_agent(authoring_tool_llm, tools=[authoring_tool,send_email_tool],state_modifier=author_agent_prompt)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/vibhatia/anaconda3/lib/python3.11/site-packages/langgraph/_api/deprecation.py", line 80, in wrapper
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/Users/vibhatia/anaconda3/lib/python3.11/site-packages/langgraph/prebuilt/chat_agent_executor.py", line 511, in create_react_agent
    if _should_bind_tools(model, tool_classes):
       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/vibhatia/anaconda3/lib/python3.11/site-packages/langgraph/prebuilt/chat_agent_executor.py", line 139, in _should_bind_tools
    raise ValueError(
ValueError: Number of tools in the model.bind_tools() and tools passed to create_react_agent must match

Description

I am trying to use the gemini models ChatGoogleGenerativeAI library from langchain_google_genai to create a react agent using the pre build create_react_agent function . But I need to bind the tools before calling the create_react_agent as I nned to pass some specific tool config. when I do this _should_bind_tools gives error raise ValueError(f"Missing tools '{missing_tools}' in the model.bind_tools()")

System Info

langchain==0.3.4
langchain-core==0.3.13
langchain-google-genai==2.0.1
langchain-openai==0.2.4
langchain-text-splitters==0.3.0
langgraph==0.2.39
langgraph-checkpoint==2.0.1
langgraph-sdk==0.1.33

Originally created by @vidit-bhatia on GitHub (Oct 30, 2024). ### Checked other resources - [X] I added a very descriptive title to this issue. - [X] I searched the [LangGraph](https://langchain-ai.github.io/langgraph/)/LangChain documentation with the integrated search. - [X] I used the GitHub search to find a similar question and didn't find it. - [X] I am sure that this is a bug in LangGraph/LangChain rather than my code. - [X] I am sure this is better as an issue [rather than a GitHub discussion](https://github.com/langchain-ai/langgraph/discussions/new/choose), since this is a LangGraph bug and not a design question. ### Example Code ```python from langchain_google_genai import ChatGoogleGenerativeAI from configs.configs import llm_api_key from langchain.tools import tool, BaseTool, StructuredTool from typing import Annotated, List, Dict from string import Template import logging from langchain_core.runnables.config import RunnableConfig from json import loads, dumps from typing import Optional, Type llm = ChatGoogleGenerativeAI(model="gemini-1.5-flash-8b",google_api_key=llm_api_key.gemini_api_key,temperature=1, tool_call = True) @tool def authoring_tool(user_information: RunnableConfig, template: Annotated[str,"The template created by LLM to be used for personalization"]) -> str: """The tool gets a python string template as an input and the user information . Returns the result of personalizing the template with the user information""" # t = Template(template) user = user_information.get("configurable", {}).get("user") # final_to_print = t.substitute(loads(user)) final_to_print = template.format(user) logging.info(final_to_print) return final_to_print authoring_tool_llm = llm.bind_tools(tools=[authoring_tool],tool_choice="any") author_agent = create_react_agent(authoring_tool_llm, tools=[authoring_tool],state_modifier=author_agent_prompt) ``` ### Error Message and Stack Trace (if applicable) ```shell Traceback (most recent call last): File "/Users/vibhatia/anaconda3/lib/python3.11/runpy.py", line 198, in _run_module_as_main return _run_code(code, main_globals, None, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/vibhatia/anaconda3/lib/python3.11/runpy.py", line 88, in _run_code exec(code, run_globals) File "/Users/vibhatia/.vscode/extensions/ms-python.debugpy-2024.12.0-darwin-arm64/bundled/libs/debugpy/adapter/../../debugpy/launcher/../../debugpy/__main__.py", line 71, in <module> cli.main() File "/Users/vibhatia/.vscode/extensions/ms-python.debugpy-2024.12.0-darwin-arm64/bundled/libs/debugpy/adapter/../../debugpy/launcher/../../debugpy/../debugpy/server/cli.py", line 501, in main run() File "/Users/vibhatia/.vscode/extensions/ms-python.debugpy-2024.12.0-darwin-arm64/bundled/libs/debugpy/adapter/../../debugpy/launcher/../../debugpy/../debugpy/server/cli.py", line 351, in run_file runpy.run_path(target, run_name="__main__") File "/Users/vibhatia/.vscode/extensions/ms-python.debugpy-2024.12.0-darwin-arm64/bundled/libs/debugpy/_vendored/pydevd/_pydevd_bundle/pydevd_runpy.py", line 310, in run_path return _run_module_code(code, init_globals, run_name, pkg_name=pkg_name, script_name=fname) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/vibhatia/.vscode/extensions/ms-python.debugpy-2024.12.0-darwin-arm64/bundled/libs/debugpy/_vendored/pydevd/_pydevd_bundle/pydevd_runpy.py", line 127, in _run_module_code _run_code(code, mod_globals, init_globals, mod_name, mod_spec, pkg_name, script_name) File "/Users/vibhatia/.vscode/extensions/ms-python.debugpy-2024.12.0-darwin-arm64/bundled/libs/debugpy/_vendored/pydevd/_pydevd_bundle/pydevd_runpy.py", line 118, in _run_code exec(code, run_globals) File "/Users/vibhatia/Documents/external/Agents/MarketingAgent/marketingagents/src/usecases/B2BResearchMarketing/main.py", line 6, in <module> from Agents import author_node, supervisor_agent, send_email_node,members File "/Users/vibhatia/Documents/external/Agents/MarketingAgent/marketingagents/src/usecases/B2BResearchMarketing/Agents.py", line 33, in <module> author_agent = create_react_agent(authoring_tool_llm, tools=[authoring_tool,send_email_tool],state_modifier=author_agent_prompt) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/vibhatia/anaconda3/lib/python3.11/site-packages/langgraph/_api/deprecation.py", line 80, in wrapper return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/Users/vibhatia/anaconda3/lib/python3.11/site-packages/langgraph/prebuilt/chat_agent_executor.py", line 511, in create_react_agent if _should_bind_tools(model, tool_classes): ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/vibhatia/anaconda3/lib/python3.11/site-packages/langgraph/prebuilt/chat_agent_executor.py", line 139, in _should_bind_tools raise ValueError( ValueError: Number of tools in the model.bind_tools() and tools passed to create_react_agent must match ``` ### Description I am trying to use the gemini models ChatGoogleGenerativeAI library from langchain_google_genai to create a react agent using the pre build create_react_agent function . But I need to bind the tools before calling the create_react_agent as I nned to pass some specific tool config. when I do this _should_bind_tools gives error raise ValueError(f"Missing tools '{missing_tools}' in the model.bind_tools()") ### System Info langchain==0.3.4 langchain-core==0.3.13 langchain-google-genai==2.0.1 langchain-openai==0.2.4 langchain-text-splitters==0.3.0 langgraph==0.2.39 langgraph-checkpoint==2.0.1 langgraph-sdk==0.1.33
yindo closed this issue 2026-02-20 17:35:45 -05:00
yindo commented 2026-02-20 17:35:47 -05:00
Author
Owner
Copy Link
Copy Source

@vbarda commented on GitHub (Oct 31, 2024):

hi @vidit-bhatia -- please update to langchain-google-genai==2.0.3. let me know if that doesn't resolve the issue for you. i confirmed with the code below that it's working as intended

from langchain_core.tools import tool
from langchain_google_genai import ChatGoogleGenerativeAI
from langgraph.prebuilt import create_react_agent

llm = ChatGoogleGenerativeAI(model="gemini-1.5-flash-8b", tool_call=True)

@tool
def add(a: int, b: int):
    """Add two numbers"""
    return a + b

llm_with_tools = llm.bind_tools([add])
# this has "tools" key
llm_with_tools.kwargs

# this works as expected for me
agent = create_react_agent(llm_with_tools, [add])
agent.invoke({"messages": [("user", "what's 2 + 3. use tools")]})```

i am using the latest version of `langchain-google-genai` (2.0.3)
@vbarda commented on GitHub (Oct 31, 2024): hi @vidit-bhatia -- please update to `langchain-google-genai==2.0.3`. let me know if that doesn't resolve the issue for you. i confirmed with the code below that it's working as intended ```python from langchain_core.tools import tool from langchain_google_genai import ChatGoogleGenerativeAI from langgraph.prebuilt import create_react_agent llm = ChatGoogleGenerativeAI(model="gemini-1.5-flash-8b", tool_call=True) @tool def add(a: int, b: int): """Add two numbers""" return a + b llm_with_tools = llm.bind_tools([add]) # this has "tools" key llm_with_tools.kwargs # this works as expected for me agent = create_react_agent(llm_with_tools, [add]) agent.invoke({"messages": [("user", "what's 2 + 3. use tools")]})``` i am using the latest version of `langchain-google-genai` (2.0.3)
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
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#295
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?