English | 中文
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 |
---|---|
-
[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 Search 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!
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-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, ... | |
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
Example Applications
-
Model
-
Conversation
-
Game
-
Distribution
More models, services and examples are coming soon!
AgentScope requires Python 3.9 or higher.
Note: This project is currently in active development, it's recommended to install AgentScope 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 .\[distribute\]
- Install AgentScope from pip:
pip install agentscope
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 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()
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 provides an easy-to-use runtime user interface capable of
displaying multimodal output on the front end, including text, images,
audio and video. To start a studio, you should install the full
version
of AgentScope.
# On windows
pip install -e .[full]
# On mac
pip install -e .\[full\]
Once installed, you can just run
as_studio path/to/your/script.py
Then the studio will be launched at localhost:xxxx
, and you can see the UI similar to the
following:
To be able to use the
as_studio
functionality, please implement the main
function in your code. More detail can be found in src/agentscope/web/README.md.
AgentScope is released under Apache License 2.0.
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.
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},
}