The output format of the Langchain create_react_agent() method does not meet expectations #25845
Replies: 1 comment
-
|
Hello, @code-isnot-cold! I'm here to assist you with any issues or questions you have. Let's work on solving this problem together. I found a similar discussion that might be relevant to your issue: ReAct agent tries to continue action and does not make final answer [1]. The issue there was related to the stop tokens in the custom LLM, which might also be affecting your output format. To address the issues you're facing with the import re
from typing import Union
from langchain_core.agents import AgentAction, AgentFinish
from langchain_core.exceptions import OutputParserException
from langchain.agents.agent import AgentOutputParser
from langchain.agents.structured_chat.prompt import FORMAT_INSTRUCTIONS
FINAL_ANSWER_ACTION = "Final Answer:"
MISSING_ACTION_AFTER_THOUGHT_ERROR_MESSAGE = (
"Invalid Format: Missing 'Action:' after 'Thought:"
)
MISSING_ACTION_INPUT_AFTER_ACTION_ERROR_MESSAGE = (
"Invalid Format: Missing 'Action Input:' after 'Action:'"
)
FINAL_ANSWER_AND_PARSABLE_ACTION_ERROR_MESSAGE = (
"Parsing LLM output produced both a final answer and a parse-able action:"
)
class ReActSingleInputOutputParser(AgentOutputParser):
"""Parses ReAct-style LLM calls that have a single tool input."""
def get_format_instructions(self) -> str:
return FORMAT_INSTRUCTIONS
def parse(self, text: str) -> Union[AgentAction, AgentFinish]:
includes_answer = FINAL_ANSWER_ACTION in text
regex = (
r"Thought\s*:[\s]*(.*?)\s*Action\s*:[\s]*(.*?)\s*Action\s*Input\s*:[\s]*(.*)"
)
action_match = re.search(regex, text, re.DOTALL)
if action_match:
if includes_answer:
raise OutputParserException(
f"{FINAL_ANSWER_AND_PARSABLE_ACTION_ERROR_MESSAGE}: {text}"
)
thought = action_match.group(1).strip()
action = action_match.group(2).strip()
action_input = action_match.group(3).strip()
tool_input = action_input.strip(" ")
tool_input = tool_input.strip('"')
# Print the required sections to the console
print(f"Thought: {thought}")
print(f"Observation: {action_input}")
return AgentAction(action, tool_input, text)
elif includes_answer:
return AgentFinish(
{"output": text.split(FINAL_ANSWER_ACTION)[-1].strip()}, text
)
if not re.search(r"Action\s*:[\s]*(.*?)", text, re.DOTALL):
raise OutputParserException(
f"Could not parse LLM output: `{text}`",
observation=MISSING_ACTION_AFTER_THOUGHT_ERROR_MESSAGE,
llm_output=text,
send_to_llm=True,
)
elif not re.search(
r"[\s]*Action\s*Input\s*:[\s]*(.*)", text, re.DOTALL
):
raise OutputParserException(
f"Could not parse LLM output: `{text}`",
observation=MISSING_ACTION_INPUT_AFTER_ACTION_ERROR_MESSAGE,
llm_output=text,
send_to_llm=True,
)
else:
raise OutputParserException(f"Could not parse LLM output: `{text}`")
@property
def _type(self) -> str:
return "react-single-input"
from langchain_core.language_models import BaseLanguageModel
from langchain_core.prompts import BasePromptTemplate
from langchain_core.runnables import Runnable, RunnablePassthrough
from langchain_core.tools import BaseTool
from langchain_core.tools.render import ToolsRenderer, render_text_description
def create_react_agent(
llm: BaseLanguageModel,
tools: Sequence[BaseTool],
prompt: BasePromptTemplate,
output_parser: Optional[AgentOutputParser] = None,
tools_renderer: ToolsRenderer = render_text_description,
*,
stop_sequence: Union[bool, List[str]] = True,
) -> Runnable:
"""Create an agent that uses ReAct prompting."""
missing_vars = {"tools", "tool_names", "agent_scratchpad"}.difference(
prompt.input_variables + list(prompt.partial_variables)
)
if missing_vars:
raise ValueError(f"Prompt missing required variables: {missing_vars}")
prompt = prompt.partial(
tools=tools_renderer(list(tools)),
tool_names=", ".join([t.name for t in tools]),
)
if stop_sequence:
stop = ["\nObservation"] if stop_sequence is True else stop_sequence
llm_with_stop = llm.bind(stop=stop)
else:
llm_with_stop = llm
output_parser = output_parser or ReActSingleInputOutputParser()
agent = (
RunnablePassthrough.assign(
agent_scratchpad=lambda x: format_log_to_str(x["intermediate_steps"]),
)
| prompt
| llm_with_stop
| output_parser
)
return agentIn this modification, the This should help you achieve the expected output format. |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
Checked other resources
Commit to Help
Example Code
Description
My problem is that the output format of the agent in console is not the expected format. Please help me explain and improve it.
Console output:
Below is the output in picture format:
Second, here are my problems:
Final, My expected the output format:
System Info
Linux
python 3.10
langchain 0.2.14
Beta Was this translation helpful? Give feedback.
All reactions