mirror of
https://github.com/hwchase17/langchain
synced 2024-11-18 09:25:54 +00:00
21c1ce0bc1
```python
from langchain.agents import AgentExecutor, create_tool_calling_agent, tool
from langchain_anthropic import ChatAnthropic
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
prompt = ChatPromptTemplate.from_messages(
[
("system", "You are a helpful assistant"),
MessagesPlaceholder("chat_history", optional=True),
("human", "{input}"),
MessagesPlaceholder("agent_scratchpad"),
]
)
model = ChatAnthropic(model="claude-3-opus-20240229")
@tool
def magic_function(input: int) -> int:
"""Applies a magic function to an input."""
return input + 2
tools = [magic_function]
agent = create_tool_calling_agent(model, tools, prompt)
agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
agent_executor.invoke({"input": "what is the value of magic_function(3)?"})
```
```
> Entering new AgentExecutor chain...
Invoking: `magic_function` with `{'input': 3}`
responded: [{'text': '<thinking>\nThe user has asked for the value of magic_function applied to the input 3. Looking at the available tools, magic_function is the relevant one to use here, as it takes an integer input and returns an integer output.\n\nThe magic_function has one required parameter:\n- input (integer)\n\nThe user has directly provided the value 3 for the input parameter. Since the required parameter is present, we can proceed with calling the function.\n</thinking>', 'type': 'text'}, {'id': 'toolu_01HsTheJPA5mcipuFDBbJ1CW', 'input': {'input': 3}, 'name': 'magic_function', 'type': 'tool_use'}]
5
Therefore, the value of magic_function(3) is 5.
> Finished chain.
{'input': 'what is the value of magic_function(3)?',
'output': 'Therefore, the value of magic_function(3) is 5.'}
```
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
|
||
|---|---|---|
| .. | ||
| __init__.py | ||
| dump.py | ||
| load.py | ||
| mapping.py | ||
| serializable.py | ||