Skip to content

fix(oss): genai tool calling example #1367

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Nov 10, 2025
+19 −18
Merged

fix(oss): genai tool calling example #1367

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions src/oss/langchain/models.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -576,11 +576,11 @@ sequenceDiagram
:::

:::python
To make tools that you have defined available for use by a model, you must bind them using @[`bind_tools()`][BaseChatModel.bind_tools]. In subsequent invocations, the model can choose to call any of the bound tools as needed.
To make tools that you have defined available for use by a model, you must bind them using @[`bind_tools`][BaseChatModel.bind_tools]. In subsequent invocations, the model can choose to call any of the bound tools as needed.
:::

:::js
To make tools that you have defined available for use by a model, you must bind them using @[`bindTools()`][BaseChatModel.bindTools]. In subsequent invocations, the model can choose to call any of the bound tools as needed.
To make tools that you have defined available for use by a model, you must bind them using @[`bindTools`][BaseChatModel.bindTools]. In subsequent invocations, the model can choose to call any of the bound tools as needed.
:::

Some model providers offer built-in tools that can be enabled via model or invocation parameters (e.g. [`ChatOpenAI`](/oss/integrations/chat/openai), [`ChatAnthropic`](/oss/integrations/chat/anthropic)). Check the respective [provider reference](/oss/integrations/providers/overview) for details.
Expand Down Expand Up @@ -639,7 +639,7 @@ for (const tool_call of toolCalls) {
```
:::

When binding user-defined tools, the model's response includes a **request** to execute a tool. When using a model separately from an [agent](/oss/langchain/agents), it is up to you to perform the requested action and return the result back to the model for use in subsequent reasoning. Note that when using an [agent](/oss/langchain/agents), the agent loop will handle the tool execution loop for you.
When binding user-defined tools, the model's response includes a **request** to execute a tool. When using a model separately from an [agent](/oss/langchain/agents), it is up to you to execute the requested tool and return the result back to the model for use in subsequent reasoning. When using an [agent](/oss/langchain/agents), the agent loop will handle the tool execution loop for you.

Below, we show some common ways you can use tool calling.

Expand Down
31 changes: 16 additions & 15 deletions src/oss/python/integrations/chat/google_generative_ai.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -260,6 +260,7 @@ You can equip the model with tools to call.

```python
from langchain.tools import tool
from langchain.messages import HumanMessage, ToolMessage
from langchain_google_genai import ChatGoogleGenerativeAI


Expand All @@ -269,33 +270,33 @@ def get_weather(location: str) -> str:
return "It's sunny."


# Initialize the model and bind the tool
llm = ChatGoogleGenerativeAI(model="gemini-2.5-flash-lite")
llm_with_tools = llm.bind_tools([get_weather])
# Initialize and bind (potentially multiple) tools to the model
model_with_tools = ChatGoogleGenerativeAI(model="gemini-2.5-flash-lite").bind_tools([get_weather])

# Invoke the model with a query that should trigger the tool
query = "What's the weather in San Francisco?"
ai_msg = llm_with_tools.invoke(query)
# Step 1: Model generates tool calls
messages = [HumanMessage("What's the weather in Boston?")]
ai_msg = model_with_tools.invoke(messages)
messages.append(ai_msg)

# Check the tool calls in the response
print(ai_msg.tool_calls)

# Example tool call message would be needed here if you were actually running the tool
from langchain.messages import ToolMessage
# Step 2: Execute tools and collect results
for tool_call in ai_msg.tool_calls:
# Execute the tool with the generated arguments
tool_result = get_weather.invoke(tool_call)
messages.append(tool_result)

tool_message = ToolMessage(
content=get_weather(*ai_msg.tool_calls[0]["args"]),
tool_call_id=ai_msg.tool_calls[0]["id"],
)
llm_with_tools.invoke([ai_msg, tool_message]) # Example of passing tool result back
# Step 3: Pass results back to model for final response
final_response = model_with_tools.invoke(messages)
```

```output
[{'name': 'get_weather', 'args': {'location': 'San Francisco'}, 'id': 'a6248087-74c5-4b7c-9250-f335e642927c', 'type': 'tool_call'}]
[{'name': 'get_weather', 'args': {'location': 'Boston'}, 'id': 'fb91e46d-e3f7-445b-a62f-50ae024bcdac', 'type': 'tool_call'}]
```

```output
AIMessage(content="OK. It's sunny in San Francisco.", additional_kwargs={}, response_metadata={'prompt_feedback': {'block_reason': 0, 'safety_ratings': []}, 'finish_reason': 'STOP', 'model_name': 'gemini-2.5-flash-lite', 'safety_ratings': []}, id='run-ac5bb52c-e244-4c72-9fbc-fb2a9cd7a72e-0', usage_metadata={'input_tokens': 29, 'output_tokens': 11, 'total_tokens': 40, 'input_token_details': {'cache_read': 0}})
AIMessage(content='The weather in Boston is sunny.', additional_kwargs={}, response_metadata={'prompt_feedback': {'block_reason': 0, 'safety_ratings': []}, 'finish_reason': 'STOP', 'model_name': 'gemini-2.5-flash-lite', 'safety_ratings': [], 'model_provider': 'google_genai'}, id='lc_run--3fb38729-285b-4b43-aa3e-499cbc910544-0', usage_metadata={'input_tokens': 83, 'output_tokens': 7, 'total_tokens': 90, 'input_token_details': {'cache_read': 0}})
```

## Structured output
Expand Down