Basic langchain example throwing agent_scratchpad should be a list of base messages, got of type ⇐ Python

[Anonymous]

Это очень простой пример, как я пытаюсь использовать Langchain, чтобы вызвать LLM и найти инструмент для использования < /p>

Код: Выделить всё

import asyncio
import json
from langchain.agents import AgentExecutor, create_structured_chat_agent, Tool
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain_core.messages import AIMessage, ToolCall
from langchain_community.chat_models.fake import FakeMessagesListChatModel

# 1. Define a simple, predictable tool
def simple_tool_function(input: str) -> str:
"""A simple tool that returns a fixed string."""
print(f"Tool called with input: '{input}'")
return "The tool says hello back!"

tools = [
Tool(
name="simple_tool",
func=simple_tool_function,
description="A simple test tool.",
)
]

# 2. Create responses that follow the structured chat format
responses = [
# First response: Agent decides to use a tool
AIMessage(
content=json.dumps({
"action": "simple_tool",
"action_input": {"input": "hello"}
})
),
# Second response: Agent provides final answer after tool execution
AIMessage(
content=json.dumps({
"action": "Final Answer",
"action_input": "The tool call was successful. The tool said: 'The tool says hello back!'"
})
),
]

# Use the modern FakeMessagesListChatModel
llm = FakeMessagesListChatModel(responses=responses)

# 3. Create the prompt using the standard structured chat prompt format
prompt = ChatPromptTemplate.from_messages([
("system", """Respond to the human as helpfully and accurately as possible. You have access to the following tools:

{tools}

Use a json blob to specify a tool by providing an action key (tool name) and an action_input key (tool input).

Valid "action" values: "Final Answer" or {tool_names}

Provide only ONE action per $JSON_BLOB, as shown:

< /code>
{{
"action": $ tool_name,
"action_input": $ input
}} < /p>

Follow this format:

Question: input question to answer
Thought: consider previous and subsequent steps
Action:
< /code>
$ json_blob < /p>
Observation: action result
... (repeat Thought/Action/Observation as needed)
Thought: I know what to respond
Action:
< /code>
{{
"action": "Окончательный ответ",
"action_input": "Окончательный ответ на человека"
}} < /p>

Begin! Reminder to ALWAYS respond with a valid json blob of a single action. Use tools if necessary. Respond directly if appropriate. Format is Action:```$JSON_BLOB```then Observation"""),
("human", "{input}"),
MessagesPlaceholder(variable_name="agent_scratchpad"),
])

# 4. Create the agent and executor
try:
agent = create_structured_chat_agent(llm, tools, prompt)
agent_executor = AgentExecutor(
agent=agent,
tools=tools,
verbose=True,
handle_parsing_errors=True,
max_iterations=3
)
print("✅ Agent and Executor created successfully.")
except Exception as e:
print(f"❌ Failed to create agent: {e}")
exit()

# 5. Run the agent
async def main():
print("\n--- Invoking Agent ---")
try:
result = await agent_executor.ainvoke({"input": "call the tool"})
print("\n--- Agent Finished ---")
print(f"✅ Final Result: {result}")
except Exception as e:
print(f"❌ Agent failed during invocation.")
import traceback
traceback.print_exc()

if __name__ == "__main__":
asyncio.run(main())

Python requirements i am using

Код: Выделить всё

langchain==0.3.27
langchain-community==0.3.27
langchain-core==0.3.74
langchain-aws==0.2.30
langchain-openai==0.3.29

python версия 3.9
Как избавиться от значения ошибки.>

Подробнее здесь: https://stackoverflow.com/questions/797 ... base-messa