CODEWITHSUNDEEP
langchainpy-langchainlanggraph
Laizer
Laizer

Reputation: 6150

Using Langgraph - instruct Anthropic to disable parallel tool use

Using the Anthropic messsages API directly and providing multiple tools to the model, it's possible to instruct the model to only invoke one tool at a time by setting disable_parallel_tool_use=true in the tool_choice field.

I'm using LangGraph, and I'd like to be able to do the same thing - instruct the model to only choose one tool at a time.

Below is the heart of my code. I'm leaving out the tool method definitions and prompts, because they're not directly relevant.

model = ChatAnthropic(model="claude-3-5-sonnet-20241022")
tools = [search_word_forms, search_dictionaries, WordDetermination]
model_with_tools = model.bind_tools(tools, tool_choice="any")
response = model_with_tools.invoke(state["messages"])

Using this framework, how can I instruct the model to disable parallel tool use?

Upvotes: 0

Views: 247

Answers (2)

Chester Curme
Chester Curme

Reputation: 11

As of the latest version of langchain-anthropic you can specify parallel_tools_calls when calling bind_tools:

model = ChatAnthropic(model="claude-3-5-sonnet-20241022")

model_with_tools = model.bind_tools(tools, parallel_tool_calls=False)

Upvotes: 1

cw00h
cw00h

Reputation: 21

Check out Langchain's document of ChatAnthropic: https://python.langchain.com/api_reference/anthropic/chat_models/langchain_anthropic.chat_models.ChatAnthropic.html#langchain_anthropic.chat_models.ChatAnthropic.bind_tools

You can use the dictionary containing options like type or disable_parallel_tool_use as tool_choice argument of bind_tools.

So the example code would be like:

model = ChatAnthropic(model="claude-3-5-sonnet-20241022")

tool_choice = {
    "type": "any" if tool_call_only else "auto",
    "disable_parallel_tool_use": not enable_parallel_tool_calls,
}
model_with_tools = model.bind_tools(tools, tool_choice=tool_choice)

Upvotes: 2

Related Questions