蘺h > d dl mZmZmZmZmZ d dlmZ d dlm Z m
Z
d dl m Z d dl
mZ d dlmZmZ d dlmZmZ d dlmZ d d lmZ d d
lmZ d d lm Z d d l m Z d d
l m Z d dl!m"Z" d dl#m$Z$ eddd G d de Z%de dee dedefdZ&dS ) )AnyListSequenceTupleUnion)
deprecated) AgentAction AgentFinish)BaseLanguageModel)BasePromptTemplate)AIMessagePromptTemplateChatPromptTemplate)RunnableRunnablePassthrough)BaseTool)BaseSingleActionAgent
format_xmlXMLAgentOutputParser)agent_instructions) Callbacks)LLMChain)render_text_descriptionz0.1.0create_xml_agentz0.2.0) alternativeremovalc ( e Zd ZU dZee ed< eed< edee fd Z
e de fd Z
e defd Z dd eeee f d
ed edeeef fd Z dd eeee f d
ed edeeef fd
ZdS )XMLAgentaO Agent that uses XML tags.
Args:
tools: list of tools the agent can choose from
llm_chain: The LLMChain to call to predict the next action
Examples:
.. code-block:: python
from langchain.agents import XMLAgent
from langchain
tools = ...
model =
tools llm_chainreturnc dgS )Ninput )selfs a/var/www/html/services/rag-service/venv/lib/python3.11/site-packages/langchain/agents/xml/base.py
input_keyszXMLAgent.input_keys. s
y c b t j t } | t j d z S )Nz{intermediate_steps})r
from_templater r
) base_prompts r' get_default_promptzXMLAgent.get_default_prompt2 s3 (67IJJ 4 B "
r) c t S Nr r% r) r' get_default_output_parserz"XMLAgent.get_default_output_parser9 s #%%%r) Nintermediate_steps callbackskwargsc d}|D ] \ }}|d|j d|j d| dz
} d}| j D ]}||j d|j dz
}|||d d d
gd } | | | }
|
| j j S
N zzzzz:
r$
z)r1 r questionstop)r2 )tool
tool_inputr name descriptionr!
output_key r& r1 r2 r3 logaction observationr r; inputsresponses r' planz
XMLAgent.plan= s #5 FK I I I9J I I-8I I I
CC J : :D 99T%5999 9EE"% w$&78
>>&I>>>122r) c K d}|D ] \ }}|d|j d|j d| dz
} d}| j D ]}||j d|j dz
}|||d d d
gd } | j | | d {V }
|
| j j S r5 )r; r< r r= r> r! acallr? r@ s r' aplanzXMLAgent.aplanU s #5 FK I I I9J I I-8I I I
CC J : :D 99T%5999 9EE"% w$&78
--f -JJJJJJJJ122r) r/ )__name__
__module__ __qualname____doc__r r __annotations__r propertystrr( staticmethodr r- r r0 r r r r r r
rF rI r% r) r' r r sw & >1)
DI X
2
\
&'; & & & \& $3 3 {C'7!8 93 3 3
{K' ( 3 3 3 36 $3 3 {C'7!8 93 3 3
{K' ( 3 3 3 3 3 3r) r llmr promptr" c J ddh |j }|rt d| | t t | }| dg }t j d |z |z t z }|S ) a Create an agent that uses XML to format its logic.
Examples:
.. code-block:: python
from langchain import hub
from langchain_community.chat_models import ChatAnthropic
from langchain.agents import AgentExecutor, create_xml_agent
prompt = hub.pull("hwchase17/xml-agent-convo")
model = ChatAnthropic()
tools = ...
agent = create_xml_agent(model, tools, prompt)
agent_executor = AgentExecutor(agent=agent, tools=tools)
agent_executor.invoke({"input": "hi"})
# Use with chat history
from langchain_core.messages import AIMessage, HumanMessage
agent_executor.invoke(
{
"input": "what's my name?",
# Notice that chat_history is a string
# since this prompt is aimed at LLMs, not chat models
"chat_history": "Human: My name is Bob
AI: Hello Bob!",
}
)
Args:
llm: LLM to use as the agent.
tools: Tools this agent has access to.
prompt: The prompt to use, must have input keys of
`tools` and `agent_scratchpad`.
Returns:
A runnable sequence representing an agent. It takes as input all the same input
variables as the prompt passed in does. It returns as output either an
AgentAction or AgentFinish.
r agent_scratchpadz#Prompt missing required variables: )r r8 )r: c , t | d S )Nr1 r )xs r' z"create_xml_agent.. s z!4H2I'J'J r) )rU )
differenceinput_variables
ValueErrorpartialr listbindr assignr )rR r rS missing_vars
llm_with_stopagents r' r r n s \ /0;;Frr s 4 4 4 4 4 4 4 4 4 4 4 4 4 4 * * * * * * : : : : : : : : < < < < < < : : : : : : S S S S S S S S B B B B B B B B ) ) ) ) ) ) 8 8 8 8 8 8 9 9 9 9 9 9 @ @ @ @ @ @ : : : : : : . . . . . . ) ) ) ) ) ) : : : : : : G!3WEEEV3 V3 V3 V3 V3$ V3 V3 FEV3r? ?#+H#5??Q?
? ? ? ? ? ?r)