langchain/templates/openai-functions-agent/openai_functions_agent/agent.py

73 lines
2.5 KiB
Python
Raw Normal View History

from typing import List, Tuple
2023-10-27 02:44:30 +00:00
from langchain.agents import AgentExecutor
from langchain.agents.format_scratchpad import format_to_openai_functions
from langchain.agents.output_parsers import OpenAIFunctionsAgentOutputParser
2023-10-27 02:44:30 +00:00
from langchain.chat_models import ChatOpenAI
from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain.pydantic_v1 import BaseModel, Field
2023-10-27 02:44:30 +00:00
from langchain.schema.messages import AIMessage, HumanMessage
from langchain.tools.render import format_tool_to_openai_function
from langchain.tools.tavily_search import TavilySearchResults
from langchain.utilities.tavily_search import TavilySearchAPIWrapper
# Create the tool
search = TavilySearchAPIWrapper()
description = """"A search engine optimized for comprehensive, accurate, \
and trusted results. Useful for when you need to answer questions \
about current events or about recent information. \
Input should be a search query. \
If the user is asking about something that you don't know about, \
you should probably use this tool to see if that can provide any information."""
tavily_tool = TavilySearchResults(api_wrapper=search, description=description)
tools = [tavily_tool]
llm = ChatOpenAI(temperature=0)
assistant_system_message = """You are a helpful assistant. \
Use tools (only if necessary) to best answer the users questions."""
2023-10-27 02:44:30 +00:00
prompt = ChatPromptTemplate.from_messages(
[
("system", assistant_system_message),
2023-10-27 02:44:30 +00:00
MessagesPlaceholder(variable_name="chat_history"),
("user", "{input}"),
MessagesPlaceholder(variable_name="agent_scratchpad"),
]
)
2023-10-27 02:44:30 +00:00
llm_with_tools = llm.bind(functions=[format_tool_to_openai_function(t) for t in tools])
def _format_chat_history(chat_history: List[Tuple[str, str]]):
buffer = []
for human, ai in chat_history:
buffer.append(HumanMessage(content=human))
buffer.append(AIMessage(content=ai))
return buffer
2023-10-27 02:44:30 +00:00
agent = (
{
"input": lambda x: x["input"],
"chat_history": lambda x: _format_chat_history(x["chat_history"]),
"agent_scratchpad": lambda x: format_to_openai_functions(
x["intermediate_steps"]
),
}
| prompt
| llm_with_tools
| OpenAIFunctionsAgentOutputParser()
)
class AgentInput(BaseModel):
input: str
chat_history: List[Tuple[str, str]] = Field(
..., extra={"widget": {"type": "chat", "input": "input", "output": "output"}}
)
2023-10-27 02:44:30 +00:00
agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True).with_types(
input_type=AgentInput
)