You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
langchain/libs/partners/anthropic
Bagatur 5fd1e67808
core[minor], integrations...[patch]: Support ToolCall as Tool input and ToolMessage as Tool output (#24038)
Changes:
- ToolCall, InvalidToolCall and ToolCallChunk can all accept a "type"
parameter now
- LLM integration packages add "type" to all the above
- Tool supports ToolCall inputs that have "type" specified
- Tool outputs ToolMessage when a ToolCall is passed as input
- Tools can separately specify ToolMessage.content and
ToolMessage.raw_output
- Tools emit events for validation errors (using on_tool_error and
on_tool_end)

Example:
```python
@tool("structured_api", response_format="content_and_raw_output")
def _mock_structured_tool_with_raw_output(
    arg1: int, arg2: bool, arg3: Optional[dict] = None
) -> Tuple[str, dict]:
    """A Structured Tool"""
    return f"{arg1} {arg2}", {"arg1": arg1, "arg2": arg2, "arg3": arg3}


def test_tool_call_input_tool_message_with_raw_output() -> None:
    tool_call: Dict = {
        "name": "structured_api",
        "args": {"arg1": 1, "arg2": True, "arg3": {"img": "base64string..."}},
        "id": "123",
        "type": "tool_call",
    }
    expected = ToolMessage("1 True", raw_output=tool_call["args"], tool_call_id="123")
    tool = _mock_structured_tool_with_raw_output
    actual = tool.invoke(tool_call)
    assert actual == expected

    tool_call.pop("type")
    with pytest.raises(ValidationError):
        tool.invoke(tool_call)

    actual_content = tool.invoke(tool_call["args"])
    assert actual_content == expected.content
```

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2 months ago
..
langchain_anthropic core[minor], integrations...[patch]: Support ToolCall as Tool input and ToolMessage as Tool output (#24038) 2 months ago
scripts
tests core[minor], integrations...[patch]: Support ToolCall as Tool input and ToolMessage as Tool output (#24038) 2 months ago
.gitignore
LICENSE
Makefile infra: update mypy 1.10, ruff 0.5 (#23721) 3 months ago
README.md anthropic[minor]: add tool calling (#18554) 7 months ago
poetry.lock infra: update mypy 1.10, ruff 0.5 (#23721) 3 months ago
pyproject.toml infra: update mypy 1.10, ruff 0.5 (#23721) 3 months ago

README.md

langchain-anthropic

This package contains the LangChain integration for Anthropic's generative models.

Installation

pip install -U langchain-anthropic

Chat Models

Anthropic recommends using their chat models over text completions.

You can see their recommended models here.

To use, you should have an Anthropic API key configured. Initialize the model as:

from langchain_anthropic import ChatAnthropic
from langchain_core.messages import AIMessage, HumanMessage

model = ChatAnthropic(model="claude-3-opus-20240229", temperature=0, max_tokens=1024)

Define the input message

message = HumanMessage(content="What is the capital of France?")

Generate a response using the model

response = model.invoke([message])

For a more detailed walkthrough see here.

LLMs (Legacy)

You can use the Claude 2 models for text completions.

from langchain_anthropic import AnthropicLLM

model = AnthropicLLM(model="claude-2.1", temperature=0, max_tokens=1024)
response = model.invoke("The best restaurant in San Francisco is: ")