mirror of https://github.com/hwchase17/langchain
groq[patch]: Make stream robust to ToolMessage (#20417)
```python from langchain.agents import AgentExecutor, create_tool_calling_agent, tool from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder from langchain_groq import ChatGroq prompt = ChatPromptTemplate.from_messages( [ ("system", "You are a helpful assistant"), ("human", "{input}"), MessagesPlaceholder("agent_scratchpad"), ] ) model = ChatGroq(model_name="mixtral-8x7b-32768", temperature=0) @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}` 5The value of magic\_function(3) is 5. > Finished chain. {'input': 'what is the value of magic_function(3)?', 'output': 'The value of magic\\_function(3) is 5.'} ```pull/20422/head
parent
6dc4f592ba
commit
4b6b0a87b6
Loading…
Reference in New Issue