Skip to content

Latest commit

 

History

History
364 lines (267 loc) · 27.3 KB

README.md

File metadata and controls

364 lines (267 loc) · 27.3 KB
Raw

English | 中文

AgentScope

agentscope-logo

Start building LLM-empowered multi-agent applications in an easier way.

If you find our work helpful, please kindly cite our paper.

Welcome to join our community on

Discord DingTalk

News

agentscope-logo

  • new[2024-05-24] We are pleased to announce that features related to the AgentScope Workstation will soon be open-sourced! The online website services are temporarily offline. The online website service will be upgraded and back online shortly. Stay tuned...

  • new[2024-05-15] A new Parser Module for formatted response is added in AgentScope! Refer to our tutorial for more details. The DictDialogAgent and werewolf game example are updated simultaneously.

Werewolf-running-example.mp4

  • new[2024-05-14] Dear AgentScope users, we are conducting a survey on AgentScope Workstation & Copilot user experience. We currently need your valuable feedback to help us improve the experience of AgentScope's Drag & Drop multi-agent application development and Copilot. Your feedback is valuable and the survey will take about 3~5 minutes. Please click URL to participate in questionnaire surveys. Thank you very much for your support and contribution!

  • new[2024-05-14] AgentScope supports gpt-4o as well as other OpenAI vision models now! Try gpt-4o with its model configuration and new example Conversation with gpt-4o!

  • [2024-04-30] We release AgentScope v0.0.4 now!

  • [2024-04-27] AgentScope Workstation is now online! You are welcome to try building your multi-agent application simply with our drag-and-drop platform and ask our copilot questions about AgentScope!

  • [2024-04-19] AgentScope supports Llama3 now! We provide scripts and example model configuration for quick set-up. Feel free to try llama3 in our examples!

  • [2024-04-06] We release AgentScope v0.0.3 now!

  • [2024-04-06] New examples Gomoku, Conversation with ReAct Agent, Conversation with RAG Agent and Distributed Parallel Optimization are available now!

  • [2024-03-19] We release AgentScope v0.0.2 now! In this new version, AgentScope supports ollama(A local CPU inference engine), DashScope and Google Gemini APIs.

  • [2024-03-19] New examples "Autonomous Conversation with Mentions" and "Basic Conversation with LangChain library" are available now!

  • [2024-03-19] The Chinese tutorial of AgentScope is online now!

  • [2024-02-27] We release AgentScope v0.0.1 now, which is also available in PyPI!

  • [2024-02-14] We release our paper "AgentScope: A Flexible yet Robust Multi-Agent Platform" in arXiv now!

What's AgentScope?

AgentScope is an innovative multi-agent platform designed to empower developers to build multi-agent applications with large-scale models. It features three high-level capabilities:

  • 🤝 Easy-to-Use: Designed for developers, with fruitful components, comprehensive documentation, and broad compatibility. Besides, AgentScope Workstation provides a drag-and-drop programming platform and a copilot for beginners of AgentScope!

  • ✅ High Robustness: Supporting customized fault-tolerance controls and retry mechanisms to enhance application stability.

  • 🚀 Actor-Based Distribution: Building distributed multi-agent applications in a centralized programming manner for streamlined development.

Supported Model Libraries

AgentScope provides a list of ModelWrapper to support both local model services and third-party model APIs.

API Task Model Wrapper Configuration Some Supported Models
OpenAI API Chat OpenAIChatWrapper guidance
template		 gpt-4o, gpt-4, gpt-3.5-turbo, ...
Embedding OpenAIEmbeddingWrapper guidance
template		 text-embedding-ada-002, ...
DALL·E OpenAIDALLEWrapper guidance
template		 dall-e-2, dall-e-3
DashScope API Chat DashScopeChatWrapper guidance
template		 qwen-plus, qwen-max, ...
Image Synthesis DashScopeImageSynthesisWrapper guidance
template		 wanx-v1
Text Embedding DashScopeTextEmbeddingWrapper guidance
template		 text-embedding-v1, text-embedding-v2, ...
Multimodal DashScopeMultiModalWrapper guidance
template		 qwen-vl-max, qwen-vl-chat-v1, qwen-audio-chat
Gemini API Chat GeminiChatWrapper guidance
template		 gemini-pro, ...
Embedding GeminiEmbeddingWrapper guidance
template		 models/embedding-001, ...
ZhipuAI API Chat ZhipuAIChatWrapper guidance
template		 glm-4, ...
Embedding ZhipuAIEmbeddingWrapper guidance
template		 embedding-2, ...
ollama Chat OllamaChatWrapper guidance
template		 llama3, llama2, Mistral, ...
Embedding OllamaEmbeddingWrapper guidance
template		 llama2, Mistral, ...
Generation OllamaGenerationWrapper guidance
template		 llama2, Mistral, ...
LiteLLM API Chat LiteLLMChatWrapper guidance
template		 models supported by litellm...
Post Request based API - PostAPIModelWrapper guidance
template		 -

Supported Local Model Deployment

AgentScope enables developers to rapidly deploy local model services using the following libraries.

Supported Services

  • Web Search
  • Data Query
  • Retrieval
  • Code Execution
  • File Operation
  • Text Processing
  • Multi Modality

Example Applications

More models, services and examples are coming soon!

Installation

AgentScope requires Python 3.9 or higher.

Note: This project is currently in active development, it's recommended to install AgentScope from source.

From source

  • Install AgentScope in editable mode:
# Pull the source code from GitHub
git clone https://github.com/modelscope/agentscope.git

# Install the package in editable mode
cd agentscope
pip install -e .
  • To build distributed multi-agent applications:
# On windows
pip install -e .[distribute]
# On mac
pip install -e .\[distribute\]

Using pip

  • Install AgentScope from pip:
pip install agentscope --pre

Quick Start

Configuration

In AgentScope, the model deployment and invocation are decoupled by ModelWrapper.

To use these model wrappers, you need to prepare a model config file as follows.

model_config = {
    # The identifies of your config and used model wrapper
    "config_name": "{your_config_name}",          # The name to identify the config
    "model_type": "{model_type}",                 # The type to identify the model wrapper

    # Detailed parameters into initialize the model wrapper
    # ...
}

Taking OpenAI Chat API as an example, the model configuration is as follows:

openai_model_config = {
    "config_name": "my_openai_config",             # The name to identify the config
    "model_type": "openai_chat",                   # The type to identify the model wrapper

    # Detailed parameters into initialize the model wrapper
    "model_name": "gpt-4",                         # The used model in openai API, e.g. gpt-4, gpt-3.5-turbo, etc.
    "api_key": "xxx",                              # The API key for OpenAI API. If not set, env
                                                   # variable OPENAI_API_KEY will be used.
    "organization": "xxx",                         # The organization for OpenAI API. If not set, env
                                                   # variable OPENAI_ORGANIZATION will be used.
}

More details about how to set up local model services and prepare model configurations is in our tutorial.

Create Agents

Create built-in user and assistant agents as follows.

from agentscope.agents import DialogAgent, UserAgent
import agentscope

# Load model configs
agentscope.init(model_configs="./model_configs.json")

# Create a dialog agent and a user agent
dialog_agent = DialogAgent(name="assistant",
                           model_config_name="my_openai_config")
user_agent = UserAgent()

Construct Conversation

In AgentScope, message is the bridge among agents, which is a dict that contains two necessary fields name and content and an optional field url to local files (image, video or audio) or website.

from agentscope.message import Msg

x = Msg(name="Alice", content="Hi!")
x = Msg("Bob", "What about this picture I took?", url="/path/to/picture.jpg")

Start a conversation between two agents (e.g. dialog_agent and user_agent) with the following code:

x = None
while True:
    x = dialog_agent(x)
    x = user_agent(x)
    if x.content == "exit":  # user input "exit" to exit the conversation_basic
        break

AgentScope Studio

AgentScope provides an easy-to-use runtime user interface capable of displaying multimodal output on the front end, including text, images, audio and video.

Refer to our tutorial for more details.

agentscope-logo

Tutorial

License

AgentScope is released under Apache License 2.0.

Contributing

Contributions are always welcomed!

We provide a developer version with additional pre-commit hooks to perform checks compared to the official version:

# For windows
pip install -e .[dev]
# For mac
pip install -e .\[dev\]

# Install pre-commit hooks
pre-commit install

Please refer to our Contribution Guide for more details.

References

If you find our work helpful for your research or application, please cite our paper:

@article{agentscope,
  author  = {Dawei Gao and
             Zitao Li and
             Weirui Kuang and
             Xuchen Pan and
             Daoyuan Chen and
             Zhijian Ma and
             Bingchen Qian and
             Liuyi Yao and
             Lin Zhu and
             Chen Cheng and
             Hongzhu Shi and
             Yaliang Li and
             Bolin Ding and
             Jingren Zhou},
  title   = {AgentScope: A Flexible yet Robust Multi-Agent Platform},
  journal = {CoRR},
  volume  = {abs/2402.14034},
  year    = {2024},
}