lagent: A Python repository from aceyin

👋 join us on 𝕏 (Twitter), Discord and WeChat

What's Lagent?

Lagent is a lightweight open-source framework that allows users to efficiently build large language model(LLM)-based agents. It also provides some typical tools to augment LLM. The overview of our framework is shown below:

💻Tech Stack

Major Features

0.1.2 was released in 24/10/2023:

Support an efficient inference engine. Lagent now supports efficient inference engine lmdeploy turbomind.
Support multiple kinds of agents out of the box. Lagent now supports ReAct, AutoGPT and ReWOO, which can drive the large language models(LLMs) for multiple trials of reasoning and function calling.
Extremely simple and easy to extend. The framework is quite simple with a clear structure. With only 20 lines of code, you are able to construct your own agent. It also supports three typical tools: Python interpreter, API call, and google search.
Support various large language models. We support different LLMs, including API-based (GPT-3.5/4) and open-source (LLaMA 2, InternLM) models.

Getting Started

Please see the overview for the general introduction of Lagent. Meanwhile, we provide extremely simple code for quick start. You may refer to examples for more details.

Installation

Install with pip (Recommended).

pip install lagent

Optionally, you could also build Lagent from source in case you want to modify the code:

git clone https://github.com/InternLM/lagent.git
cd lagent
pip install -e .

Run ReAct Web Demo

# You need to install streamlit first
# pip install streamlit
streamlit run examples/react_web_demo.py

Then you can chat through the UI shown as below

Run a ReWOO agent with GPT-3.5

Below is an example of running ReWOO with GPT-3.5

# Import necessary modules and classes from the "lagent" library.
from lagent.agents import ReWOO
from lagent.actions import ActionExecutor, GoogleSearch, LLMQA
from lagent.llms import GPTAPI

# Initialize the Language Model (llm) and provide your API key.
llm = GPTAPI(model_type='gpt-3.5-turbo', key=['Your OPENAI_API_KEY'])

# Initialize the Google Search tool and provide your API key.
search_tool = GoogleSearch(api_key='Your SERPER_API_KEY')

# Initialize the LLMQA tool using the Language Model (llm).
llmqa_tool = LLMQA(llm)

# Create a chatbot by configuring the ReWOO agent.
chatbot = ReWOO(
    llm=llm,  # Provide the Language Model instance.
    action_executor=ActionExecutor(
        actions=[search_tool, llmqa_tool]  # Specify the actions the chatbot can perform.
    ),
)

# Ask the chatbot a question and store the response.
response = chatbot.chat('What profession does Nicholas Ray and Elia Kazan have in common')

# Print the chatbot's response.
print(response.response)  # Output the response generated by the chatbot.
>>> Film director.

Run a ReAct agent with InternLM

NOTE: If you want to run a HuggingFace model, please run pip install -e .[all] first.

# Import necessary modules and classes from the "lagent" library.
from lagent.agents import ReAct
from lagent.actions import ActionExecutor, GoogleSearch, PythonInterpreter
from lagent.llms import HFTransformer

# Initialize the HFTransformer-based Language Model (llm) and provide the model name.
llm = HFTransformer('internlm/internlm-chat-7b-v1_1')

# Initialize the Google Search tool and provide your API key.
search_tool = GoogleSearch(api_key='Your SERPER_API_KEY')

# Initialize the Python Interpreter tool.
python_interpreter = PythonInterpreter()

# Create a chatbot by configuring the ReAct agent.
chatbot = ReAct(
    llm=llm,  # Provide the Language Model instance.
    action_executor=ActionExecutor(
        actions=[search_tool, python_interpreter]  # Specify the actions the chatbot can perform.
    ),
)
# Ask the chatbot a mathematical question in LaTeX format.
response = chatbot.chat('若$z=-1+\sqrt{3}i$,则$\frac{z}{{z\overline{z}-1}}=\left(\ \ \right)$')

# Print the chatbot's response.
print(response.response)  # Output the response generated by the chatbot.
>>> $-\\frac{1}{3}+\\frac{{\\sqrt{3}}}{3}i$

All Thanks To Our Contributors:

Citation

If you find this project useful in your research, please consider cite:

@misc{lagent2023,
    title={{Lagent: InternLM} a lightweight open-source framework that allows users to efficiently build large language model(LLM)-based agents},
    author={Lagent Developer Team},
    howpublished = {\url{https://github.com/InternLM/lagent}},
    year={2023}
}

License

This project is released under the Apache 2.0 license.

🔼 Back to top

aceyin/lagent