%pip install--upgrade--quiet  multion langchain-q

%pip install-qU langchain-community

from langchain_community.agent_toolkitsimport MultionToolkit

toolkit= MultionToolkit()
toolkit

MultionToolkit()

tools= toolkit.get_tools()
tools

[MultionCreateSession(), MultionUpdateSession(), MultionCloseSession()]

# Authorize connection to your Browser extention
import multion

multion.login()

Logged in.

from langchainimport hub
from langchain.agentsimport AgentExecutor, create_openai_functions_agent
from langchain_openaiimport ChatOpenAI

# Prompt
instructions="""You are an assistant."""
base_prompt= hub.pull("langchain-ai/openai-functions-template")
prompt= base_prompt.partial(instructions=instructions)

# LLM
llm= ChatOpenAI(temperature=0)

# Agent
agent= create_openai_functions_agent(llm, toolkit.get_tools(), prompt)
agent_executor= AgentExecutor(
    agent=agent,
    tools=toolkit.get_tools(),
    verbose=False,
)

agent_executor.invoke(
{
"input":"Use multion to explain how AlphaCodium works, a recently released code language model."
}
)

WARNING: 'new_session' is deprecated and will be removed in a future version. Use 'create_session' instead.
WARNING: 'update_session' is deprecated and will be removed in a future version. Use 'step_session' instead.
WARNING: 'update_session' is deprecated and will be removed in a future version. Use 'step_session' instead.
WARNING: 'update_session' is deprecated and will be removed in a future version. Use 'step_session' instead.
WARNING: 'update_session' is deprecated and will be removed in a future version. Use 'step_session' instead.

{'input': 'Use multion to how AlphaCodium works, a recently released code language model.',
 'output': 'AlphaCodium is a recently released code language model that is designed to assist developers in writing code more efficiently. It is based on advanced machine learning techniques and natural language processing. AlphaCodium can understand and generate code in multiple programming languages, making it a versatile tool for developers.\n\nThe model is trained on a large dataset of code snippets and programming examples, allowing it to learn patterns and best practices in coding. It can provide suggestions and auto-complete code based on the context and the desired outcome.\n\nAlphaCodium also has the ability to analyze code and identify potential errors or bugs. It can offer recommendations for improving code quality and performance.\n\nOverall, AlphaCodium aims to enhance the coding experience by providing intelligent assistance and reducing the time and effort required to write high-quality code.\n\nFor more detailed information, you can visit the official AlphaCodium website or refer to the documentation and resources available online.\n\nI hope this helps! Let me know if you have any other questions.'}