KKi N S SK Jr S SKJr S SKJr S SKJrJr S SK J
r
S SK J r S SK
Jr S SKJrJr S S KJrJr S S
KJr S S KJrJr S S KJr S S
K J r S SK J r S SK J!r! S SK"J#r# S SK$J%r% \" SSSS9 " S S\ 5 5 r&\4SS.S\ S\\ S \S \S \'\(\) - S \4 S jjjr*g!)" )Sequence)Any)
deprecated) AgentAction AgentFinish) Callbacks)BaseLanguageModel)BasePromptTemplate)AIMessagePromptTemplateChatPromptTemplate)RunnableRunnablePassthrough)BaseTool)
ToolsRendererrender_text_description)override)BaseSingleActionAgent
format_xmlXMLAgentOutputParser)agent_instructions)LLMChainz0.1.0create_xml_agentz1.0) alternativeremovalc \ rS rSr% Sr\\ \S' \\S' \ \
S\\ 4S j5 5 r \
S\4S j5 r\
S\4S j5 r\
SS
\\\\ 4 S \S \S\\- 4S
jj5 r\
SS
\\\\ 4 S \S \S\\- 4S jj5 rSrg )XMLAgent a 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:
```python
from langchain_classic.agents import XMLAgent
from langchain
tools = ...
model =
```
tools llm_chainreturnc S/$ )Ninput )selfs c/var/www/html/dynamic-report/venv/lib/python3.13/site-packages/langchain_classic/agents/xml/base.py
input_keysXMLAgent.input_keys. s y c h [ R " [ 5 n U [ R " S5 - $ )z,Return the default prompt for the XML agent.z{intermediate_steps})r
from_templater r ) base_prompts r' get_default_promptXMLAgent.get_default_prompt3 s3 )667IJ 4 B B "
r* c [ 5 $ )z Return an XMLAgentOutputParser.r r% r* r' get_default_output_parser"XMLAgent.get_default_output_parser; s
$%%r* Nintermediate_steps callbackskwargsc . SnU H( u pVUSUR SUR SU S3-
nM* SnU R H! nXxR SUR S3-
nM# UUUS S S
/S .n U R XS 9n
XR
R $
N zzzzz:
r$
z)r3 r questionstop)r4 )tool
tool_inputr name descriptionr!
output_key r& r3 r4 r5 logaction observationr r= inputsresponses r' plan
XMLAgent.plan@ s #5 F
%89J9J8K,[M I
C $6
JJD {"T%5%5$6b9 9E #& w$&78
>>&>>1122r* c ^ # SnU H( u pVUSUR SUR SU S3-
nM* SnU R H! nXxR SUR S3-
nM# UUUS S S
/S .n U R
R
XS 9I S h vN n
XR
R $ N 7fr7 )r= r> r r? r@ r! acallrA rB s r' aplanXMLAgent.aplanY s #5 F
%89J9J8K,[M I
C $6
JJD {"T%5%5$6b9 9E #& w$&78
--f-JJ1122 Ks B B-B+ B-r% )N)__name__
__module__ __qualname____firstlineno____doc__listr __annotations__r propertyr strr( staticmethodr r. r r1 tupler r r r rH rL __static_attributes__r% r* r' r r s" " >1)
DI
2
&'; & & $3 {C'7!8 93 3 3
{ " 3 30 $3 {C'7!8 93 3 3
{ " 3 3r* r T)
stop_sequencellmr prompttools_rendererrZ r" c d SS1R UR [ UR 5 - 5 nU( a SU 3n[ U5 eUR U" [ U5 5 S9nU( a USL a S/OUnU R
US9nOU n[ R " S S 9U- U- [ 5 - $ )
a Create an agent that uses XML to format its logic.
Args:
llm: LLM to use as the agent.
tools: Tools this agent has access to.
prompt: The prompt to use, must have input keys
`tools`: contains descriptions for each tool.
`agent_scratchpad`: contains previous agent actions and tool outputs.
tools_renderer: This controls how the tools are converted into a string and
then passed into the LLM.
stop_sequence: bool or list of str.
If `True`, adds a stop token of "" to avoid hallucinates.
If `False`, does not add a stop token.
If a list of str, uses the provided list as the stop tokens.
You may to set this to False if the LLM you are using
does not support stop sequences.
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.
Example:
```python
from langchain_classic import hub
from langchain_anthropic import ChatAnthropic
from langchain_classic.agents import AgentExecutor, create_xml_agent
prompt = hub.pull("hwchase17/xml-agent-convo")
model = ChatAnthropic(model="claude-3-haiku-20240307")
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\nAI: Hello Bob!",
}
)
```
Prompt:
The prompt must have input keys:
* `tools`: contains descriptions for each tool.
* `agent_scratchpad`: contains previous agent actions and tool outputs as
an XML string.
Here's an example:
```python
from langchain_core.prompts import PromptTemplate
template = '''You are a helpful assistant. Help the user answer any questions.
You have access to the following tools:
{tools}
In order to use a tool, you can use and tags. You will then get back a response in the form
For example, if you have a tool called 'search' that could run a google search, in order to search for the weather in SF you would respond:
searchweather in SF
64 degrees
When you are done, respond with a final answer between . For example:
The weather in SF is 64 degrees
Begin!
Previous Conversation:
{chat_history}
Question: {input}
{agent_scratchpad}'''
prompt = PromptTemplate.from_template(template)
```
r agent_scratchpadz#Prompt missing required variables: )r Tr: )r< c [ U S 5 $ )Nr3 r )xs r' "create_xml_agent.. s z!4H2I'Jr* )r_ )
differenceinput_variablesrS partial_variables
ValueErrorpartialbindr assignr ) r[ r r\ r] rZ missing_varsmsgr<
llm_with_stops r' r r s s B /0;; f&>&>!??L 3L>Bo
^^ T%[) F $1T$9 }d+
"" J
!r* N)+collections.abcr typingr langchain_core._apir langchain_core.agentsr r langchain_core.callbacksr langchain_core.language_modelsr langchain_core.prompts.baser
langchain_core.prompts.chatr r langchain_core.runnablesr
r langchain_core.toolsr langchain_core.tools.renderr r typing_extensionsr langchain_classic.agents.agentr *langchain_classic.agents.format_scratchpadr 'langchain_classic.agents.output_parsersr #langchain_classic.agents.xml.promptr langchain_classic.chains.llmr r boolrS rV r r% r* r' r s $ * : . < : S B ) N & @ A H B 1 G!3UCY3$ Y3 DY3@ %< y '+
y y H y
y " y $s)#
y yr*