Server 500 error when multi function is defined.

[slee-pasonatquila]

When I run the code below, always got server 500 error.

def multiply(first_int: int, second_int: int) -> int:
    """Multiply two integers together."""
    return first_int * second_int

@tool
def add(first_int: int, second_int: int) -> int:
    "Add two integers."
    return first_int + second_int

@tool
def exponentiate(base: int, exponent: int) -> int:
    "Exponentiate the base to the exponent power."
    return base**exponent

tools = [multiply, add, exponentiate]
tool_executor = ToolExecutor(tools)
functions = [convert_to_openai_tool(t)["function"] for t in tools]
model = ChatGoogleGenerativeAI(model='gemini-pro', temperature=0)
model_with_tools = model.bind(functions=functions)

message = "What's four times 23"
result = model_with_tools.invoke(message)
check = hasattr(result, 'additional_kwargs')

try:
    action = ToolInvocation(
        tool=result.additional_kwargs["function_call"]["name"],
        tool_input=json.loads(
            result.additional_kwargs["function_call"]["arguments"]),
    )
    response = tool_executor.invoke(action)
    print(response)
except KeyError:
    result = model.invoke(message)
    print(result.content)

I think the code below https://github.com/langchain-ai/langchain-google/blob/6af9e3ba2bcc1f5002aa514d99529fa44876a523/libs/genai/langchain_google_genai/_function_utils.py#L31-L34 should be changed to

glm.Tool(
            function_declarations=[_convert_to_genai_function(fc) for fc in function_calls],
        )

eg.

calculator = glm.Tool(
    function_declarations=[
      glm.FunctionDeclaration(
        name='add',
        description="Returns the sum of two numbers.",
        parameters=glm.Schema(
            type=glm.Type.OBJECT,
            properties={
                'a': glm.Schema(type=glm.Type.NUMBER),
                'b': glm.Schema(type=glm.Type.NUMBER)
            },
            required=['a','b']
        )
      ),
      glm.FunctionDeclaration(
        name='multiply',
        description="Returns the product of two numbers.",
        parameters=glm.Schema(
            type=glm.Type.OBJECT,
            properties={
                'a':glm.Schema(type=glm.Type.NUMBER),
                'b':glm.Schema(type=glm.Type.NUMBER)
            },
            required=['a','b']
        )
      )
    ])

[lkuligin]

what are your libraries versions?

I tried your snippet, it works fine on my side:

from langgraph.prebuilt import ToolExecutor
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain_core.utils.function_calling import convert_to_openai_tool

tool_executor = ToolExecutor(tools)
functions = [convert_to_openai_tool(t)["function"] for t in tools]
model = ChatGoogleGenerativeAI(model='gemini-pro', temperature=0, google_api_key=api_key)
model_with_tools = model.bind(functions=functions)

message = "What's four times 23"
result = model_with_tools.invoke(message)
check = hasattr(result, 'additional_kwargs')

from langgraph.prebuilt import ToolInvocation
import json

action = ToolInvocation(
        tool=result.additional_kwargs["function_call"]["name"],
        tool_input=json.loads(
            result.additional_kwargs["function_call"]["arguments"]),
    )
response = tool_executor.invoke(action)

print(response)

return 92

[slee-pasonatquila]

@lkuligin Thanks for reply. The full code is as below.

import langchain
import json
import os
from langchain_core.tools import tool
from langchain_google_genai import ChatGoogleGenerativeAI
from langgraph.prebuilt import ToolInvocation
from langchain_core.utils.function_calling import convert_to_openai_tool
from langgraph.prebuilt import ToolExecutor

os.environ['GOOGLE_API_KEY'] = 'API KEY'
langchain.debug = True

@tool
def multiply(first_int: int, second_int: int) -> int:
    """Multiply two integers together."""
    return first_int * second_int

@tool
def add(first_int: int, second_int: int) -> int:
    "Add two integers."
    return first_int + second_int

@tool
def exponentiate(base: int, exponent: int) -> int:
    "Exponentiate the base to the exponent power."
    return base**exponent

tools = [multiply, add, exponentiate]
tool_executor = ToolExecutor(tools)
functions = [convert_to_openai_tool(t)["function"] for t in tools]
model = ChatGoogleGenerativeAI(model='gemini-pro', temperature=0)
model_with_tools = model.bind(functions=functions)

message = "What's four times 23"
result = model_with_tools.invoke(message)
check = hasattr(result, 'additional_kwargs')

try:
    action = ToolInvocation(
        tool=result.additional_kwargs["function_call"]["name"],
        tool_input=json.loads(
            result.additional_kwargs["function_call"]["arguments"]),
    )
    response = tool_executor.invoke(action)
    print(response)
except KeyError:
    result = model.invoke(message)
    print(result.content)

And the version of langchain is as below.

langchain                                0.1.9
langchain-community                      0.0.24
langchain-core                           0.1.27
langchain-experimental                   0.0.52
langchain-google-genai                   0.0.9
langchain-google-vertexai                0.1.0
langchainhub                             0.1.14
langdetect                               1.0.9
langgraph                                0.0.24
langsmith                                0.1.10

When I run the code, I got the error as below.

Retrying langchain_google_genai.chat_models._chat_with_retry.<locals>._chat_with_retry in 2.0 seconds as it raised InternalServerError: 500 An internal error has occurred. Please retry or report in https://developers.generativeai.google/guide/troubleshooting.

And When i changed the source to this, it is works fine.

glm.Tool(
            function_declarations=[_convert_to_genai_function(fc) for fc in function_calls],
        )

[lkuligin]

Please, try to downgrade langchain-google-genai to 0.0.7 for now, and it should work. And we'll need to figure out what's wrong in the meantime.

[lkuligin]

@slee-pasonatquila updating underlying dependency of google-generativeai to 0.4.0 seems to help, could you try that, please?

[slee-pasonatquila]

@slee-pasonatquila updating underlying dependency of google-generativeai to 0.4.0 seems to help, could you try that, please?

@lkuligin Thanks. That works for me.