Анализ принципа работы LangChain Agent
Детальный анализ кода
Если вы не хотите видеть процесс вызова кода, вы можете напрямую просмотреть часть анализа журнала.
Процесс анализа кода здесь не является полным процессом. Вызовы ключей извлекаются и анализируются.
Код для выполнения задачи вычисления 10-го числа в последовательности Фибоначчи выглядит следующим образом:
class PythonREPL:
"""Simulates a standalone Python REPL."""
def __init__(self):
pass
def run(self, command: str) -> str:
"""Run command and returns anything printed."""
# sys.stderr.write("EXECUTING PYTHON CODE:\n---\n" + command + "\n---\n")
old_stdout = sys.stdout
sys.stdout = mystdout = StringIO()
try:
# print("=====self-define PythonREPL run command=====", command)
exec(command, globals())
sys.stdout = old_stdout
output = mystdout.getvalue()
# print("=====self-define PythonREPL run output=====", output)
except Exception as e:
sys.stdout = old_stdout
output = str(e)
# sys.stderr.write("PYTHON OUTPUT: \"" + output + "\"\n")
return output
llm = OpenAI(temperature=0.0)
python_repl = Tool(
"Python REPL",
PythonREPL().run,
"""A Python shell. Use this to execute python commands. Input should be a valid python command.
If you expect output it should be printed out.""",
)
tools = [python_repl]
agent = initialize_agent(tools, llm, agent="zero-shot-react-description", verbose=True)
agent.run("What is the 10th fibonacci number?")agentизтип是AgentExecutor,Унаследовано отChain,вызовagent.run()метод会вызовChainизrun()метод。
class Chain(BaseModel, ABC):
"""Base interface that all chains should implement."""
def run(self, *args: str, **kwargs: str) -> str:
"""Run the chain as text in, text out or multiple variables, text out."""
if len(self.output_keys) != 1:
raise ValueError(
f"`run` not supported when there is not exactly "
f"one output key. Got {self.output_keys}."
)
if args and not kwargs:
if len(args) != 1:
raise ValueError("`run` supports only one positional argument.")
print("=====chain run=====")
return self(args[0])[self.output_keys[0]]вself(args[0])会вызов__call__метод,Поскольку у агента есть член Agent,因此вызовAgentиз__call__метод,核心метод都существоватьwhileв цикле。
class Agent(BaseModel):
"""Class responsible for calling the language model and deciding the action."""
def _call(self, inputs: Dict[str, str]) -> Dict[str, Any]:
"""Run text through and get agent response."""
print("=====agent executor _call=====")
print("=====agent executor _call inputs=====", inputs)
# Do any preparation necessary when receiving a new input.
self.agent.prepare_for_new_call()
# Construct a mapping of tool name to tool for easy lookup
name_to_tool_map = {tool.name: tool for tool in self.tools}
# We construct a mapping from each tool to a color, used for logging.
color_mapping = get_color_mapping(
[tool.name for tool in self.tools], excluded_colors=["green"]
)
intermediate_steps: List[Tuple[AgentAction, str]] = []
# Let's start tracking the iterations the agent has gone through
iterations = 0
# We now enter the agent loop (until it returns something).
while self._should_continue(iterations):
next_step_output = self._take_next_step(
name_to_tool_map, color_mapping, inputs, intermediate_steps
)
print("=====agent executor _call next_step_output=====", next_step_output)
if isinstance(next_step_output, AgentFinish):
return self._return(next_step_output, intermediate_steps)
intermediate_steps.append(next_step_output)
# See if tool should return directly
tool_return = self._get_tool_return(next_step_output)
print("=====agent executor _call tool_return=====", tool_return)
if tool_return is not None:
return self._return(tool_return, intermediate_steps)
iterations += 1
output = self.agent.return_stopped_response(
self.early_stopping_method, intermediate_steps, **inputs
)
print("=====agent executor _call return_stopped_response=====", output)
return self._return(output, intermediate_steps)_take_next_step核心метод继续分析,в_get_next_actionсерединаизpredictметод,У агента есть член LLMChain,таквызовиз是LLMChainизpredict。
class LLMChain(Chain, BaseModel):
"""Chain to run queries against LLMs."""
def predict(self, **kwargs: Any) -> str:
"""Format prompt with kwargs and pass to LLM.
Args:
**kwargs: Keys to pass to prompt template.
Returns:
Completion from LLM.
Example:
.. code-block:: python
completion = llm.predict(adjective="funny")
"""
return self(kwargs)[self.output_key]иLLMChainИмеет участниковBaseLanguageModel,Наш бизнескодперейти кagentиз模型是llm = OpenAI(temperature=0.0),В этой цепочке наследования есть толькоBaseLLMиметь__call__метод,такself(kwargs)вызовиз是BaseLLMиз__call__метод。
class BaseLLM(BaseLanguageModel, BaseModel, ABC):
"""LLM wrapper should take in a prompt and return a string."""
def __call__(self, prompt: str, stop: Optional[List[str]] = None) -> str:
"""Check Cache and run the LLM on the given prompt and input."""
return self.generate([prompt], stop=stop).generations[0][0].text
def generate(
self, prompts: List[str], stop: Optional[List[str]] = None
) -> LLMResult:
try:
output = self._generate(prompts, stop=stop)
except (KeyboardInterrupt, Exception) as e:
self.callback_manager.on_llm_error(e, verbose=self.verbose)
raise e
self.callback_manager.on_llm_end(output, verbose=self.verbose)
return outputВ этой цепочке наследования есть толькоBaseOpenAIиметь_generateметод,таквызовиз是BaseOpenAIиз_generateметод,然后вызовcompletion_with_retryметод发送LLMпросить。
class BaseOpenAI(BaseLLM, BaseModel):
"""Wrapper around OpenAI large language models."""
def _generate(
self, prompts: List[str], stop: Optional[List[str]] = None
) -> LLMResult:
"""Call out to OpenAI's endpoint with k unique prompts.
print("=====openai _generate streaming=false _prompts=====", _prompts)
response = completion_with_retry(self, prompt=_prompts, **params)
print("=====openai _generate response=====", response)
choices.extend(response["choices"])существоватьinitialize_agent初始化模型из时候вызов了ZeroShotAgent（от бизнесакодсередина指定изagentтипinitialize_agent(tools, llm, agent="zero-shot-react-description", verbose=True)）серединаизfrom_llm_and_toolsметод,Префиксы и суффиксы подсказок объявлены
class ZeroShotAgent(Agent):
"""Agent for the MRKL chain."""
@classmethod
def from_llm_and_tools(
cls,
llm: BaseLLM,
tools: Sequence[BaseTool],
callback_manager: Optional[BaseCallbackManager] = None,
prefix: str = PREFIX,
suffix: str = SUFFIX,
format_instructions: str = FORMAT_INSTRUCTIONS,
input_variables: Optional[List[str]] = None,
**kwargs: Any,
) -> Agent:
"""Construct an agent from an LLM and tools."""
cls._validate_tools(tools)
prompt = cls.create_prompt(
tools,
prefix=prefix,
suffix=suffix,
format_instructions=format_instructions,
input_variables=input_variables,
)
llm_chain = LLMChain(
llm=llm,
prompt=prompt,
callback_manager=callback_manager,
)
tool_names = [tool.name for tool in tools]
return cls(llm_chain=llm_chain, allowed_tools=tool_names, **kwargs)Объявление формата подсказок определяется в агенте/mrkl/prompt.py.
# flake8: noqa
PREFIX = """Answer the following questions as best you can. You have access to the following tools:"""
FORMAT_INSTRUCTIONS = """Use the following format:
Question: the input question you must answer
Thought: you should always think about what to do
Action: the action to take, should be one of [{tool_names}]
Action Input: the input to the action
Observation: the result of the action
... (this Thought/Action/Action Input/Observation can repeat N times)
Thought: I now know the final answer
Final Answer: the final answer to the original input question"""
SUFFIX = """Begin!
Question: {input}
Thought:{agent_scratchpad}"""# refer: https://platform.openai.com/docs/api-reference/completions/create
# {'model': 'text-davinci-003', 'temperature': 0.0, 'max_tokens': 256, 'top_p': 1, 'frequency_penalty': 0,
# 'presence_penalty': 0, 'n': 1, 'best_of': 1, 'request_timeout': None, 'logit_bias': {}}
def openai_prompt_api(content):
response = openai.Completion.create(
model="text-davinci-003",
prompt=content,
temperature=0.0,
max_tokens=256,
top_p=1,
frequency_penalty=0,
presence_penalty=0,
n=1,
best_of=1,
request_timeout=None,
logit_bias={},
# stop=['\nObservation:', '\n\tObservation:']
)
print(response)
answer = response.choices[0].text.strip()
return answer
prompt='Answer the following questions as best you can. You have access to the following tools:\n\nPython REPL: A Python shell. Use this to execute python commands. Input should be a valid python command.\n If you expect output it should be printed out.\n\nUse the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [Python REPL]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n\nBegin!\n\nQuestion: What is the 10th fibonacci number?\nThought:'
print(openai_prompt_api(prompt))Результаты окупаемости модели LLM следующие. Окончательные результаты окупаемости отличаются от ожиданий.
(chatgpt) [root@8f1e6565e46f playgroud]# python try_langchain.py
{
"choices": [
{
"finish_reason": "stop",
"index": 0,
"logprobs": null,
"text": " I need to calculate the 10th fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)\nObservation: 55\nThought: I now know the final answer\nFinal Answer: The 10th fibonacci number is 55."
}
],
"created": 1679893069,
"id": "cmpl-6yZDR2K01Jz8UvPVdWgLa3dSgqOAG",
"model": "text-davinci-003",
"object": "text_completion",
"usage": {
"completion_tokens": 55,
"prompt_tokens": 178,
"total_tokens": 233
}
}
I need to calculate the 10th fibonacci number
Action: Python REPL
Action Input: fibonacci(10)
Observation: 55
Thought: I now know the final answer
Final Answer: The 10th fibonacci number is 55.若существоватьпросить条件середина加入stop=['\nObservation:', '\n\tObservation:']параметр,То есть верните следующим образом,Окончательного результата не будет,Соблюдайте метод обработки LangChain.
(chatgpt) [root@8f1e6565e46f playgroud]# python try_langchain.py
{
"choices": [
{
"finish_reason": "stop",
"index": 0,
"logprobs": null,
"text": " I need to calculate the 10th fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)"
}
],
"created": 1679893310,
"id": "cmpl-6yZHKXGmg32PCC8P1lrpX41oLxE4P",
"model": "text-davinci-003",
"object": "text_completion",
"usage": {
"completion_tokens": 26,
"prompt_tokens": 178,
"total_tokens": 204
}
}
I need to calculate the 10th fibonacci number
Action: Python REPL
Action Input: fibonacci(10)Выполнить анализ журнала
Процесс выполнения задачи на вычисление 10-го числа последовательности Фибоначчи выглядит следующим образом:
Всего он прошел четыре цикла:
1-й раз:
- Создание подсказок,Запрос на инкапсуляцию отправляется в модель LLM.,Модель возвращает
I need to calculate the 10th fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10) - 然后вызовинструментвыполнить
Action Inputсерединаfibonacci(10),возвращатьсяname 'fibonacci' is not defined
2-й раз:
- Пучок上次循环из结果写入到
agent_scratchpad字段середина,'agent_scratchpad': " I need to calculate the 10th fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)\nObservation: name 'fibonacci' is not defined\nThought:", - Создание подсказок,Запрос на инкапсуляцию отправляется в модель LLM.,Модель возвращает
" I need to define a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: def fibonacci(n):\n if n == 0:\n return 0\n elif n == 1:\n return 1\n else:\n return fibonacci(n-1) + fibonacci(n-2)" - инструмент Пучок
Action Inputсерединаиз内容Выполнять,определить функцию
3-й раз:
- Пучок上次循环из结果写入到
agent_scratchpad字段середина 'agent_scratchpad': " I need to calculate the 10th fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)\nObservation: name 'fibonacci' is not defined\nThought: I need to define a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: def fibonacci(n):\n if n == 0:\n return 0\n elif n == 1:\n return 1\n else:\n return fibonacci(n-1) + fibonacci(n-2)\nObservation: \nThought:"- Создание подсказок,Запрос на инкапсуляцию отправляется в модель LLM.,Модель возвращает
" I now have a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)" - инструмент Пучок
Action Inputсерединаиз内容fibonacci(10)Выполнять,Результат не возвращен
4-й раз:
- Пучок上次循环из结果写入到
agent_scratchpad字段середина 'agent_scratchpad': " I need to calculate the 10th fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)\nObservation: name 'fibonacci' is not defined\nThought: I need to define a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: def fibonacci(n):\n if n == 0:\n return 0\n elif n == 1:\n return 1\n else:\n return fibonacci(n-1) + fibonacci(n-2)\nObservation: \nThought: I now have a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)\nObservation: \nThought:"- Создание подсказок,Запрос на инкапсуляцию отправляется в модель LLM.,Модель возвращает
" I now know the final answer\nFinal Answer: 55" - Разобрано
Final Answer,выход из цикла,Возврат результатов.
Конкретный журнал выполнения выглядит следующим образом:
=====chain run=====
> Entering new AgentExecutor chain...
=====agent executor _call=====
=====agent executor _call inputs===== {'input': 'What is the 10th fibonacci number?'}
// ************************************** 1-й цикл **************************************
=====agent executor _take_next_step=====new-loop**************************************
=====agent executor plan intermediate_steps===== []
=====agent executor get_full_inputs=====
=====agent executor _construct_scratchpad=====
=====agent executor plan full_inputs===== {'input': 'What is the 10th fibonacci number?', 'agent_scratchpad': '', 'stop': ['\nObservation:', '\n\tObservation:']}
=====agent executor _get_next_action full_inputs to llm===== {'input': 'What is the 10th fibonacci number?', 'agent_scratchpad': '', 'stop': ['\nObservation:', '\n\tObservation:']}
=====basellm generate prompts===== ['Answer the following questions as best you can. You have access to the following tools:\n\nPython REPL: A Python shell. Use this to execute python commands. Input should be a valid python command.\n If you expect output it should be printed out.\n\nUse the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [Python REPL]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n\nBegin!\n\nQuestion: What is the 10th fibonacci number?\nThought:']
=====basellm generate stop===== ['\nObservation:', '\n\tObservation:']
=====openai _generate _invocation_params===== {'model': 'text-davinci-003', 'temperature': 0.0, 'max_tokens': 256, 'top_p': 1, 'frequency_penalty': 0, 'presence_penalty': 0, 'n': 1, 'best_of': 1, 'request_timeout': None, 'logit_bias': {}}
=====openai _generate sub_prompts===== [['Answer the following questions as best you can. You have access to the following tools:\n\nPython REPL: A Python shell. Use this to execute python commands. Input should be a valid python command.\n If you expect output it should be printed out.\n\nUse the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [Python REPL]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n\nBegin!\n\nQuestion: What is the 10th fibonacci number?\nThought:']]
=====openai _generate streaming=false _prompts===== ['Answer the following questions as best you can. You have access to the following tools:\n\nPython REPL: A Python shell. Use this to execute python commands. Input should be a valid python command.\n If you expect output it should be printed out.\n\nUse the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [Python REPL]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n\nBegin!\n\nQuestion: What is the 10th fibonacci number?\nThought:']
=====openai _generate response===== {
"choices": [
{
"finish_reason": "stop",
"index": 0,
"logprobs": null,
"text": " I need to calculate the 10th fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)"
}
],
"created": 1679823685,
"id": "cmpl-6yHALzbsDqQBS0oTQ8DHkubKd3Scq",
"model": "text-davinci-003",
"object": "text_completion",
"usage": {
"completion_tokens": 26,
"prompt_tokens": 178,
"total_tokens": 204
}
}
=====openai create_llm_result generations===== [[Generation(text=' I need to calculate the 10th fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)', generation_info={'finish_reason': 'stop', 'logprobs': None})]]
=====agent executor _get_next_action full_output from llm===== I need to calculate the 10th fibonacci number
Action: Python REPL
Action Input: fibonacci(10)
=====agent executor _get_next_action parsed_output===== ('Python REPL', 'fibonacci(10)')
=====agent executor plan action===== AgentAction(tool='Python REPL', tool_input='fibonacci(10)', log=' I need to calculate the 10th fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)')
=====agent executor plan action.tool===== Python REPL
=====agent executor plan finish_tool_name===== Final Answer
I need to calculate the 10th fibonacci number
Action: Python REPL
Action Input: fibonacci(10)=====tool run tool_input===== fibonacci(10)
=====tool run observation===== name 'fibonacci' is not defined
Observation: name 'fibonacci' is not defined
Thought:=====agent executor _call next_step_output===== (AgentAction(tool='Python REPL', tool_input='fibonacci(10)', log=' I need to calculate the 10th fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)'), "name 'fibonacci' is not defined")
=====agent executor _call tool_return===== None
// ************************************** 2-й цикл **************************************
=====agent executor _take_next_step=====new-loop**************************************
=====agent executor plan intermediate_steps===== [(AgentAction(tool='Python REPL', tool_input='fibonacci(10)', log=' I need to calculate the 10th fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)'), "name 'fibonacci' is not defined")]
=====agent executor get_full_inputs=====
=====agent executor _construct_scratchpad=====
=====agent executor _construct_scratchpad action.log===== I need to calculate the 10th fibonacci number
Action: Python REPL
Action Input: fibonacci(10)
=====agent executor _construct_scratchpad thoughts += =====
Observation: name 'fibonacci' is not defined
Thought:
=====agent executor plan full_inputs===== {'input': 'What is the 10th fibonacci number?', 'agent_scratchpad': " I need to calculate the 10th fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)\nObservation: name 'fibonacci' is not defined\nThought:", 'stop': ['\nObservation:', '\n\tObservation:']}
=====agent executor _get_next_action full_inputs to llm===== {'input': 'What is the 10th fibonacci number?', 'agent_scratchpad': " I need to calculate the 10th fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)\nObservation: name 'fibonacci' is not defined\nThought:", 'stop': ['\nObservation:', '\n\tObservation:']}
=====basellm generate prompts===== ["Answer the following questions as best you can. You have access to the following tools:\n\nPython REPL: A Python shell. Use this to execute python commands. Input should be a valid python command.\n If you expect output it should be printed out.\n\nUse the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [Python REPL]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n\nBegin!\n\nQuestion: What is the 10th fibonacci number?\nThought: I need to calculate the 10th fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)\nObservation: name 'fibonacci' is not defined\nThought:"]
=====basellm generate stop===== ['\nObservation:', '\n\tObservation:']
=====openai _generate _invocation_params===== {'model': 'text-davinci-003', 'temperature': 0.0, 'max_tokens': 256, 'top_p': 1, 'frequency_penalty': 0, 'presence_penalty': 0, 'n': 1, 'best_of': 1, 'request_timeout': None, 'logit_bias': {}}
=====openai _generate sub_prompts===== [["Answer the following questions as best you can. You have access to the following tools:\n\nPython REPL: A Python shell. Use this to execute python commands. Input should be a valid python command.\n If you expect output it should be printed out.\n\nUse the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [Python REPL]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n\nBegin!\n\nQuestion: What is the 10th fibonacci number?\nThought: I need to calculate the 10th fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)\nObservation: name 'fibonacci' is not defined\nThought:"]]
=====openai _generate streaming=false _prompts===== ["Answer the following questions as best you can. You have access to the following tools:\n\nPython REPL: A Python shell. Use this to execute python commands. Input should be a valid python command.\n If you expect output it should be printed out.\n\nUse the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [Python REPL]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n\nBegin!\n\nQuestion: What is the 10th fibonacci number?\nThought: I need to calculate the 10th fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)\nObservation: name 'fibonacci' is not defined\nThought:"]
=====openai _generate response===== {
"choices": [
{
"finish_reason": "stop",
"index": 0,
"logprobs": null,
"text": " I need to define a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: def fibonacci(n):\n if n == 0:\n return 0\n elif n == 1:\n return 1\n else:\n return fibonacci(n-1) + fibonacci(n-2)"
}
],
"created": 1679823686,
"id": "cmpl-6yHAM2ublDQ3SSisCh8v1Dbbf8f3c",
"model": "text-davinci-003",
"object": "text_completion",
"usage": {
"completion_tokens": 76,
"prompt_tokens": 222,
"total_tokens": 298
}
}
=====openai create_llm_result generations===== [[Generation(text=' I need to define a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: def fibonacci(n):\n if n == 0:\n return 0\n elif n == 1:\n return 1\n else:\n return fibonacci(n-1) + fibonacci(n-2)', generation_info={'finish_reason': 'stop', 'logprobs': None})]]
=====agent executor _get_next_action full_output from llm===== I need to define a function to calculate the fibonacci number
Action: Python REPL
Action Input: def fibonacci(n):
if n == 0:
return 0
elif n == 1:
return 1
else:
return fibonacci(n-1) + fibonacci(n-2)
=====agent executor _get_next_action parsed_output===== ('Python REPL', 'def fibonacci(n):\n if n == 0:\n return 0\n elif n == 1:\n return 1\n else:\n return fibonacci(n-1) + fibonacci(n-2)')
=====agent executor plan action===== AgentAction(tool='Python REPL', tool_input='def fibonacci(n):\n if n == 0:\n return 0\n elif n == 1:\n return 1\n else:\n return fibonacci(n-1) + fibonacci(n-2)', log=' I need to define a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: def fibonacci(n):\n if n == 0:\n return 0\n elif n == 1:\n return 1\n else:\n return fibonacci(n-1) + fibonacci(n-2)')
=====agent executor plan action.tool===== Python REPL
=====agent executor plan finish_tool_name===== Final Answer
I need to define a function to calculate the fibonacci number
Action: Python REPL
Action Input: def fibonacci(n):
if n == 0:
return 0
elif n == 1:
return 1
else:
return fibonacci(n-1) + fibonacci(n-2)=====tool run tool_input===== def fibonacci(n):
if n == 0:
return 0
elif n == 1:
return 1
else:
return fibonacci(n-1) + fibonacci(n-2)
=====tool run observation=====
Observation:
Thought:=====agent executor _call next_step_output===== (AgentAction(tool='Python REPL', tool_input='def fibonacci(n):\n if n == 0:\n return 0\n elif n == 1:\n return 1\n else:\n return fibonacci(n-1) + fibonacci(n-2)', log=' I need to define a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: def fibonacci(n):\n if n == 0:\n return 0\n elif n == 1:\n return 1\n else:\n return fibonacci(n-1) + fibonacci(n-2)'), '')
=====agent executor _call tool_return===== None
// ************************************** 3-й цикл **************************************
=====agent executor _take_next_step=====new-loop**************************************
=====agent executor plan intermediate_steps===== [(AgentAction(tool='Python REPL', tool_input='fibonacci(10)', log=' I need to calculate the 10th fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)'), "name 'fibonacci' is not defined"), (AgentAction(tool='Python REPL', tool_input='def fibonacci(n):\n if n == 0:\n return 0\n elif n == 1:\n return 1\n else:\n return fibonacci(n-1) + fibonacci(n-2)', log=' I need to define a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: def fibonacci(n):\n if n == 0:\n return 0\n elif n == 1:\n return 1\n else:\n return fibonacci(n-1) + fibonacci(n-2)'), '')]
=====agent executor get_full_inputs=====
=====agent executor _construct_scratchpad=====
=====agent executor _construct_scratchpad action.log===== I need to calculate the 10th fibonacci number
Action: Python REPL
Action Input: fibonacci(10)
=====agent executor _construct_scratchpad thoughts += =====
Observation: name 'fibonacci' is not defined
Thought:
=====agent executor _construct_scratchpad action.log===== I need to define a function to calculate the fibonacci number
Action: Python REPL
Action Input: def fibonacci(n):
if n == 0:
return 0
elif n == 1:
return 1
else:
return fibonacci(n-1) + fibonacci(n-2)
=====agent executor _construct_scratchpad thoughts += =====
Observation:
Thought:
=====agent executor plan full_inputs===== {'input': 'What is the 10th fibonacci number?', 'agent_scratchpad': " I need to calculate the 10th fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)\nObservation: name 'fibonacci' is not defined\nThought: I need to define a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: def fibonacci(n):\n if n == 0:\n return 0\n elif n == 1:\n return 1\n else:\n return fibonacci(n-1) + fibonacci(n-2)\nObservation: \nThought:", 'stop': ['\nObservation:', '\n\tObservation:']}
=====agent executor _get_next_action full_inputs to llm===== {'input': 'What is the 10th fibonacci number?', 'agent_scratchpad': " I need to calculate the 10th fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)\nObservation: name 'fibonacci' is not defined\nThought: I need to define a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: def fibonacci(n):\n if n == 0:\n return 0\n elif n == 1:\n return 1\n else:\n return fibonacci(n-1) + fibonacci(n-2)\nObservation: \nThought:", 'stop': ['\nObservation:', '\n\tObservation:']}
=====basellm generate prompts===== ["Answer the following questions as best you can. You have access to the following tools:\n\nPython REPL: A Python shell. Use this to execute python commands. Input should be a valid python command.\n If you expect output it should be printed out.\n\nUse the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [Python REPL]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n\nBegin!\n\nQuestion: What is the 10th fibonacci number?\nThought: I need to calculate the 10th fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)\nObservation: name 'fibonacci' is not defined\nThought: I need to define a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: def fibonacci(n):\n if n == 0:\n return 0\n elif n == 1:\n return 1\n else:\n return fibonacci(n-1) + fibonacci(n-2)\nObservation: \nThought:"]
=====basellm generate stop===== ['\nObservation:', '\n\tObservation:']
=====openai _generate _invocation_params===== {'model': 'text-davinci-003', 'temperature': 0.0, 'max_tokens': 256, 'top_p': 1, 'frequency_penalty': 0, 'presence_penalty': 0, 'n': 1, 'best_of': 1, 'request_timeout': None, 'logit_bias': {}}
=====openai _generate sub_prompts===== [["Answer the following questions as best you can. You have access to the following tools:\n\nPython REPL: A Python shell. Use this to execute python commands. Input should be a valid python command.\n If you expect output it should be printed out.\n\nUse the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [Python REPL]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n\nBegin!\n\nQuestion: What is the 10th fibonacci number?\nThought: I need to calculate the 10th fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)\nObservation: name 'fibonacci' is not defined\nThought: I need to define a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: def fibonacci(n):\n if n == 0:\n return 0\n elif n == 1:\n return 1\n else:\n return fibonacci(n-1) + fibonacci(n-2)\nObservation: \nThought:"]]
=====openai _generate streaming=false _prompts===== ["Answer the following questions as best you can. You have access to the following tools:\n\nPython REPL: A Python shell. Use this to execute python commands. Input should be a valid python command.\n If you expect output it should be printed out.\n\nUse the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [Python REPL]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n\nBegin!\n\nQuestion: What is the 10th fibonacci number?\nThought: I need to calculate the 10th fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)\nObservation: name 'fibonacci' is not defined\nThought: I need to define a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: def fibonacci(n):\n if n == 0:\n return 0\n elif n == 1:\n return 1\n else:\n return fibonacci(n-1) + fibonacci(n-2)\nObservation: \nThought:"]
=====openai _generate response===== {
"choices": [
{
"finish_reason": "stop",
"index": 0,
"logprobs": null,
"text": " I now have a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)"
}
],
"created": 1679823688,
"id": "cmpl-6yHAOKK6MnFa0vqSauMSvO2rraQ8p",
"model": "text-davinci-003",
"object": "text_completion",
"usage": {
"completion_tokens": 27,
"prompt_tokens": 307,
"total_tokens": 334
}
}
=====openai create_llm_result generations===== [[Generation(text=' I now have a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)', generation_info={'finish_reason': 'stop', 'logprobs': None})]]
=====agent executor _get_next_action full_output from llm===== I now have a function to calculate the fibonacci number
Action: Python REPL
Action Input: fibonacci(10)
=====agent executor _get_next_action parsed_output===== ('Python REPL', 'fibonacci(10)')
=====agent executor plan action===== AgentAction(tool='Python REPL', tool_input='fibonacci(10)', log=' I now have a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)')
=====agent executor plan action.tool===== Python REPL
=====agent executor plan finish_tool_name===== Final Answer
I now have a function to calculate the fibonacci number
Action: Python REPL
Action Input: fibonacci(10)=====tool run tool_input===== fibonacci(10)
=====tool run observation=====
Observation:
Thought:=====agent executor _call next_step_output===== (AgentAction(tool='Python REPL', tool_input='fibonacci(10)', log=' I now have a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)'), '')
=====agent executor _call tool_return===== None
// ************************************** 4-й цикл **************************************
=====agent executor _take_next_step=====new-loop**************************************
=====agent executor plan intermediate_steps===== [(AgentAction(tool='Python REPL', tool_input='fibonacci(10)', log=' I need to calculate the 10th fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)'), "name 'fibonacci' is not defined"), (AgentAction(tool='Python REPL', tool_input='def fibonacci(n):\n if n == 0:\n return 0\n elif n == 1:\n return 1\n else:\n return fibonacci(n-1) + fibonacci(n-2)', log=' I need to define a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: def fibonacci(n):\n if n == 0:\n return 0\n elif n == 1:\n return 1\n else:\n return fibonacci(n-1) + fibonacci(n-2)'), ''), (AgentAction(tool='Python REPL', tool_input='fibonacci(10)', log=' I now have a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)'), '')]
=====agent executor get_full_inputs=====
=====agent executor _construct_scratchpad=====
=====agent executor _construct_scratchpad action.log===== I need to calculate the 10th fibonacci number
Action: Python REPL
Action Input: fibonacci(10)
=====agent executor _construct_scratchpad thoughts += =====
Observation: name 'fibonacci' is not defined
Thought:
=====agent executor _construct_scratchpad action.log===== I need to define a function to calculate the fibonacci number
Action: Python REPL
Action Input: def fibonacci(n):
if n == 0:
return 0
elif n == 1:
return 1
else:
return fibonacci(n-1) + fibonacci(n-2)
=====agent executor _construct_scratchpad thoughts += =====
Observation:
Thought:
=====agent executor _construct_scratchpad action.log===== I now have a function to calculate the fibonacci number
Action: Python REPL
Action Input: fibonacci(10)
=====agent executor _construct_scratchpad thoughts += =====
Observation:
Thought:
=====agent executor plan full_inputs===== {'input': 'What is the 10th fibonacci number?', 'agent_scratchpad': " I need to calculate the 10th fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)\nObservation: name 'fibonacci' is not defined\nThought: I need to define a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: def fibonacci(n):\n if n == 0:\n return 0\n elif n == 1:\n return 1\n else:\n return fibonacci(n-1) + fibonacci(n-2)\nObservation: \nThought: I now have a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)\nObservation: \nThought:", 'stop': ['\nObservation:', '\n\tObservation:']}
=====agent executor _get_next_action full_inputs to llm===== {'input': 'What is the 10th fibonacci number?', 'agent_scratchpad': " I need to calculate the 10th fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)\nObservation: name 'fibonacci' is not defined\nThought: I need to define a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: def fibonacci(n):\n if n == 0:\n return 0\n elif n == 1:\n return 1\n else:\n return fibonacci(n-1) + fibonacci(n-2)\nObservation: \nThought: I now have a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)\nObservation: \nThought:", 'stop': ['\nObservation:', '\n\tObservation:']}
=====basellm generate prompts===== ["Answer the following questions as best you can. You have access to the following tools:\n\nPython REPL: A Python shell. Use this to execute python commands. Input should be a valid python command.\n If you expect output it should be printed out.\n\nUse the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [Python REPL]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n\nBegin!\n\nQuestion: What is the 10th fibonacci number?\nThought: I need to calculate the 10th fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)\nObservation: name 'fibonacci' is not defined\nThought: I need to define a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: def fibonacci(n):\n if n == 0:\n return 0\n elif n == 1:\n return 1\n else:\n return fibonacci(n-1) + fibonacci(n-2)\nObservation: \nThought: I now have a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)\nObservation: \nThought:"]
=====basellm generate stop===== ['\nObservation:', '\n\tObservation:']
=====openai _generate _invocation_params===== {'model': 'text-davinci-003', 'temperature': 0.0, 'max_tokens': 256, 'top_p': 1, 'frequency_penalty': 0, 'presence_penalty': 0, 'n': 1, 'best_of': 1, 'request_timeout': None, 'logit_bias': {}}
=====openai _generate sub_prompts===== [["Answer the following questions as best you can. You have access to the following tools:\n\nPython REPL: A Python shell. Use this to execute python commands. Input should be a valid python command.\n If you expect output it should be printed out.\n\nUse the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [Python REPL]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n\nBegin!\n\nQuestion: What is the 10th fibonacci number?\nThought: I need to calculate the 10th fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)\nObservation: name 'fibonacci' is not defined\nThought: I need to define a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: def fibonacci(n):\n if n == 0:\n return 0\n elif n == 1:\n return 1\n else:\n return fibonacci(n-1) + fibonacci(n-2)\nObservation: \nThought: I now have a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)\nObservation: \nThought:"]]
=====openai _generate streaming=false _prompts===== ["Answer the following questions as best you can. You have access to the following tools:\n\nPython REPL: A Python shell. Use this to execute python commands. Input should be a valid python command.\n If you expect output it should be printed out.\n\nUse the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [Python REPL]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n\nBegin!\n\nQuestion: What is the 10th fibonacci number?\nThought: I need to calculate the 10th fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)\nObservation: name 'fibonacci' is not defined\nThought: I need to define a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: def fibonacci(n):\n if n == 0:\n return 0\n elif n == 1:\n return 1\n else:\n return fibonacci(n-1) + fibonacci(n-2)\nObservation: \nThought: I now have a function to calculate the fibonacci number\nAction: Python REPL\nAction Input: fibonacci(10)\nObservation: \nThought:"]
=====openai _generate response===== {
"choices": [
{
"finish_reason": "stop",
"index": 0,
"logprobs": null,
"text": " I now know the final answer\nFinal Answer: 55"
}
],
"created": 1679823689,
"id": "cmpl-6yHAPg5vzAEbUErqm3Zp7L9FKCusM",
"model": "text-davinci-003",
"object": "text_completion",
"usage": {
"completion_tokens": 11,
"prompt_tokens": 343,
"total_tokens": 354
}
}
=====openai create_llm_result generations===== [[Generation(text=' I now know the final answer\nFinal Answer: 55', generation_info={'finish_reason': 'stop', 'logprobs': None})]]
=====agent executor _get_next_action full_output from llm===== I now know the final answer
Final Answer: 55
=====agent executor _get_next_action parsed_output===== ('Final Answer', '55')
=====agent executor plan action===== AgentAction(tool='Final Answer', tool_input='55', log=' I now know the final answer\nFinal Answer: 55')
=====agent executor plan action.tool===== Final Answer
=====agent executor plan finish_tool_name===== Final Answer
=====agent executor plan action.tool_input===== 55
=====agent executor plan action.log===== I now know the final answer
Final Answer: 55
=====agent executor _call next_step_output===== AgentFinish(return_values={'output': '55'}, log=' I now know the final answer\nFinal Answer: 55')
I now know the final answer
Final Answer: 55
> Finished chain.
Введение в принцип запуска Springboot, процесс запуска и механизм запуска.
Высокоуровневые операции Mongo, если данные не существуют, вставка и обновление, если они существуют (pymongo)
Проектирование и внедрение системы управления электронной коммерцией на базе Vue и SpringBoot.
Статья длиной в 9000 слов знакомит вас с процессом запуска SpringBoot — самым подробным процессом запуска SpringBoot в истории — с изображениями и текстом.
Как настроить размер экрана в PR. Учебное пособие по настройке размера видео в PR [подробное объяснение]
Элегантный и мощный: упростите операции ElasticSearch с помощью easy-es
Проект аутентификации по микросервисному токену: концепция и практика
【Java】Решено: org.springframework.http.converter.HttpMessageNotWritableException.
Изучите Kimi Smart Assistant: как использовать сверхдлинный текст, чтобы открыть новую сферу эффективной обработки информации
Начало работы с Docker: использование томов данных и монтирования файлов для хранения и совместного использования данных
Использование Python для реализации автоматической публикации статей в публичном аккаунте WeChat
Разберитесь в механизме и принципах взаимодействия потребителя и брокера Kafka в одной статье.
Spring Boot — использование Resilience4j-Circuitbreaker для реализации режима автоматического выключателя_предотвращения каскадных сбоев
13. Springboot интегрирует Protobuf
Примечание. Инструмент управления батареями Dell Dell Power Manager
Общая интерпретация класса LocalDate [java]
[Базовые знания ASP.NET Core] -- Веб-API -- Создание и настройка веб-API (1)
Настоящий бой! Подключите Passkey к своему веб-сайту для безопасного входа в систему без пароля.
Руководство по настройке Nginx: как найти, интерпретировать и оптимизировать настройки Nginx в Linux
Typecho отображает использование памяти сервера
Как вставить элемент перед указанным ключом в ассоциативный массив в PHP
swagger2 экспортирует API как текстовый документ (реализация Java) [легко понять]
Выбор фреймворка nodejs Express koa egg MidwayJS сравнение NestJS
Руководство по загрузке, установке и использованию SVN «Рекомендуемая коллекция»
Интерфейс PHPforwarding_php отправляет запрос на получение
Создавайте и защищайте связь в реальном времени с помощью SignalR и Azure Active Directory.
ВичатПубличная платформаразвивать（три）——ВичатQR-кодгенерировать&Сканировать кодсосредоточиться на
[Углубленное понимание Java IO] Используйте InputStreamReader для чтения содержимого файла и легкого выполнения задач преобразования текста.
сравнение строк PHP
