|
from langchain_core.utils.function_calling import convert_to_openai_function |
|
from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder |
|
from langchain.memory import ConversationBufferWindowMemory |
|
from langchain.schema.runnable import RunnablePassthrough |
|
from langchain.agents.format_scratchpad import format_to_openai_functions |
|
from langchain.agents.output_parsers import OpenAIFunctionsAgentOutputParser |
|
from langchain.agents import AgentExecutor |
|
from langchain_groq import ChatGroq |
|
from functions import book_slot , check_slots , suggest_specialization , reschedule_event,delete_event |
|
|
|
def create_agent(general_prompt_template): |
|
|
|
|
|
API_KEY = "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" |
|
tools = [book_slot , delete_event , check_slots , suggest_specialization , reschedule_event] |
|
functions = [convert_to_openai_function(f) for f in tools] |
|
|
|
llm = ChatGroq( |
|
model="llama-3.1-70b-versatile", |
|
temperature=0, |
|
max_tokens=None, |
|
timeout=None, |
|
max_retries=2, |
|
api_key=API_KEY |
|
).bind_functions(functions=functions) |
|
|
|
prompt = ChatPromptTemplate.from_messages([("system", general_prompt_template), |
|
MessagesPlaceholder(variable_name="chat_history"), ("user", "{input}"), |
|
MessagesPlaceholder(variable_name="agent_scratchpad")]) |
|
|
|
|
|
|
|
memory = ConversationBufferWindowMemory(memory_key="chat_history" , return_messages=True, k=5) |
|
|
|
chain = RunnablePassthrough.assign(agent_scratchpad=lambda x: format_to_openai_functions(x["intermediate_steps"])) | prompt | llm | OpenAIFunctionsAgentOutputParser() |
|
|
|
agent_executor = AgentExecutor( |
|
agent=chain, tools=tools, memory=memory, verbose=True) |
|
|
|
return agent_executor |
|
|
