Autogenstudio - Add GroupChat Support to UI (microsoft#1352)

* support groupchat, other QOL fixes

* remove gallery success toast

* Update website/blog/2023-12-01-AutoGenStudio/index.mdx

Co-authored-by: Chi Wang <[email protected]>

---------

Co-authored-by: Chi Wang <[email protected]>

samples/apps/autogen-studio/MANIFEST.in

@@ -1,5 +1,7 @@
 recursive-include autogenstudio/web/ui *
+recursive-include autogenstudio/web/database.sqlite
 recursive-exclude notebooks *
+
 recursive-exclude frontend *
 recursive-exclude docs *
 recursive-exclude tests *

samples/apps/autogen-studio/README.md

@@ -28,6 +28,8 @@ Project Structure:
 
 ### Installation
 
+There are two ways to install AutoGen Studio - from PyPi or from source. We **recommend installing from PyPi** unless you plan to modify the source code.
+
 1. **Install from PyPi**
 
  We recommend using a virtual environment (e.g., conda) to avoid conflicts with existing Python packages. With Python 3.10 or newer active in your virtual environment, use pip to install AutoGen Studio:
@@ -108,6 +110,18 @@ The agent workflow responds by _writing and executing code_ to create a python p
 
 <!-- ![ARA](./docs/ara_console.png) -->
 
+## Contribution Guide
+
+We welcome contributions to AutoGen Studio. We recommend the following general steps to contribute to the project:
+
+- Review the overall AutoGen project [contribution guide](https://github.com/microsoft/autogen?tab=readme-ov-file#contributing)
+- Please review the AutoGen Studio [roadmap](https://github.com/microsoft/autogen/issues/737) to get a sense of the current priorities for the project. Help is appreciated especially with Studio issues tagged with `help-wanted`
+- Please initiate a discussion on the roadmap issue or a new issue to discuss your proposed contribution.
+- Please review the autogenstudio dev branch here [dev branch](https://github.com/microsoft/autogen/tree/autogenstudio) and use as a base for your contribution. This way, your contribution will be aligned with the latest changes in the AutoGen Studio project.
+- Submit a pull request with your contribution!
+- If you are modifying AutoGen Studio, it has its own devcontainer. See instructions in `.devcontainer/README.md` to use it
+- Please use the tag `studio` for any issues, questions, and PRs related to Studio
+
 ## FAQ
 
 **Q: Where can I adjust the default skills, agent and workflow configurations?**
@@ -119,6 +133,10 @@ A: To reset your conversation history, you can delete the `database.sqlite` file
 **Q: Is it possible to view the output and messages generated by the agents during interactions?**
 A: Yes, you can view the generated messages in the debug console of the web UI, providing insights into the agent interactions. Alternatively, you can inspect the `database.sqlite` file for a comprehensive record of messages.
 
+**Q: Can I use other models with AutoGen Studio?**
+Yes. AutoGen standardizes on the openai model api format, and you can use any api server that offers an openai compliant endpoint. In the AutoGen Studio UI, each agent has an `llm_config` field where you can input your model endpoint details including `model name`, `api key`, `base url`, `model type` and `api version`. For Azure OpenAI models, you can find these details in the Azure portal. Note that for Azure OpenAI, the `model name` is the deployment id or engine, and the `model type` is "azure".
+For other OSS models, we recommend using a server such as vllm to instantiate an openai compliant endpoint.
+
 ## Acknowledgements
 
 AutoGen Studio is Based on the [AutoGen](https://microsoft.github.io/autogen) project. It was adapted from a research prototype built in October 2023 (original credits: Gagan Bansal, Adam Fourney, Victor Dibia, Piali Choudhury, Saleema Amershi, Ahmed Awadallah, Chi Wang).

samples/apps/autogen-studio/autogenstudio/chatmanager.py

@@ -19,7 +19,6 @@ def chat(self, message: Message, history: List, flow_config: AgentWorkFlowConfig
  if flow_config is None:
  flow_config = get_default_agent_config(scratch_dir)
 
- # print("Flow config: ", flow_config)
  flow = AutoGenWorkFlowManager(config=flow_config, history=history, work_dir=scratch_dir)
  message_text = message.content.strip()
 

samples/apps/autogen-studio/autogenstudio/cli.py

@@ -4,6 +4,7 @@
 import uvicorn
 
 from .version import VERSION
+from .utils.dbutils import DBManager
 
 app = typer.Typer()
 
@@ -15,12 +16,23 @@ def ui(
  workers: int = 1,
  reload: Annotated[bool, typer.Option("--reload")] = False,
  docs: bool = False,
+ appdir: str = None,
 ):
  """
- Launch the AutoGen Studio UI CLI .Pass in parameters host, port, workers, and reload to override the default values.
+ Run the AutoGen Studio UI.
+
+ Args:
+ host (str, optional): Host to run the UI on. Defaults to 127.0.0.1 (localhost).
+ port (int, optional): Port to run the UI on. Defaults to 8081.
+ workers (int, optional): Number of workers to run the UI with. Defaults to 1.
+ reload (bool, optional): Whether to reload the UI on code changes. Defaults to False.
+ docs (bool, optional): Whether to generate API docs. Defaults to False.
+ appdir (str, optional): Path to the AutoGen Studio app directory. Defaults to None.
  """
 
- os.environ["AUTOGENUI_API_DOCS"] = str(docs)
+ os.environ["AUTOGENSTUDIO_API_DOCS"] = str(docs)
+ if appdir:
+ os.environ["AUTOGENSTUDIO_APPDIR"] = appdir
 
  uvicorn.run(
  "autogenstudio.web.app:app",
@@ -37,7 +49,7 @@ def version():
  Print the version of the AutoGen Studio UI CLI.
  """
 
- typer.echo(f"AutoGen Studio UI CLI version: {VERSION}")
+ typer.echo(f"AutoGen Studio CLI version: {VERSION}")
 
 
 def run():

samples/apps/autogen-studio/autogenstudio/datamodel.py

@@ -58,25 +58,46 @@ def dict(self):
 
 # autogenflow data models
 @dataclass
-class ModelConfig:
+class Model:
  """Data model for Model Config item in LLMConfig for AutoGen"""
 
  model: str
  api_key: Optional[str] = None
  base_url: Optional[str] = None
  api_type: Optional[str] = None
  api_version: Optional[str] = None
+ id: Optional[str] = None
+ timestamp: Optional[str] = None
+ user_id: Optional[str] = None
+ description: Optional[str] = None
+
+ def dict(self):
+ result = asdict(self)
+ return result
+
+ def __post_init__(self):
+ if self.id is None:
+ self.id = str(uuid.uuid4())
+ if self.timestamp is None:
+ self.timestamp = datetime.now().isoformat()
+ if self.user_id is None:
+ self.user_id = "default"
 
 
 @dataclass
 class LLMConfig:
  """Data model for LLM Config for AutoGen"""
 
- config_list: List[Any] = field(default_factory=List)
+ config_list: List[Any] = field(default_factory=list)
  temperature: float = 0
  cache_seed: Optional[Union[int, None]] = None
  timeout: Optional[int] = None
 
+ def dict(self):
+ result = asdict(self)
+ result["config_list"] = [c.dict() for c in self.config_list]
+ return result
+
 
 @dataclass
 class AgentConfig:
@@ -101,8 +122,8 @@ def dict(self):
 class AgentFlowSpec:
  """Data model to help flow load agents from config"""
 
- type: Literal["assistant", "userproxy", "groupchat"]
- config: AgentConfig = field(default_factory=AgentConfig)
+ type: Literal["assistant", "userproxy"]
+ config: AgentConfig
  id: Optional[str] = None
  timestamp: Optional[str] = None
  user_id: Optional[str] = None
@@ -122,24 +143,80 @@ def dict(self):
  return result
 
 
+@dataclass
+class GroupChatConfig:
+ """Data model for GroupChat Config for AutoGen"""
+
+ agents: List[AgentFlowSpec] = field(default_factory=list)
+ admin_name: str = "Admin"
+ messages: List[Dict] = field(default_factory=list)
+ max_round: Optional[int] = 10
+ admin_name: Optional[str] = "Admin"
+ speaker_selection_method: Optional[str] = "auto"
+ allow_repeat_speaker: Optional[Union[bool, List[AgentConfig]]] = True
+
+ def dict(self):
+ result = asdict(self)
+ result["agents"] = [a.dict() for a in self.agents]
+ return result
+
+
+@dataclass
+class GroupChatFlowSpec:
+ """Data model to help flow load agents from config"""
+
+ type: Literal["groupchat"]
+ config: AgentConfig = field(default_factory=AgentConfig)
+ groupchat_config: Optional[GroupChatConfig] = field(default_factory=GroupChatConfig)
+ id: Optional[str] = None
+ timestamp: Optional[str] = None
+ user_id: Optional[str] = None
+ description: Optional[str] = None
+
+ def __post_init__(self):
+ if self.timestamp is None:
+ self.timestamp = datetime.now().isoformat()
+ if self.id is None:
+ self.id = str(uuid.uuid4())
+ if self.user_id is None:
+ self.user_id = "default"
+
+ def dict(self):
+ result = asdict(self)
+ # result["config"] = self.config.dict()
+ # result["groupchat_config"] = self.groupchat_config.dict()
+ return result
+
+
 @dataclass
 class AgentWorkFlowConfig:
  """Data model for Flow Config for AutoGen"""
 
  name: str
  description: str
  sender: AgentFlowSpec
- receiver: Union[AgentFlowSpec, List[AgentFlowSpec]]
- type: Literal["default", "groupchat"] = "default"
+ receiver: Union[AgentFlowSpec, GroupChatFlowSpec]
+ type: Literal["twoagents", "groupchat"] = "twoagents"
  id: Optional[str] = None
  user_id: Optional[str] = None
  timestamp: Optional[str] = None
  # how the agent message summary is generated. last: only last message is used, none: no summary, llm: use llm to generate summary
  summary_method: Optional[Literal["last", "none", "llm"]] = "last"
 
+ def init_spec(self, spec: Dict):
+ """initialize the agent spec"""
+ if not isinstance(spec, dict):
+ spec = spec.dict()
+ if spec["type"] == "groupchat":
+ return GroupChatFlowSpec(**spec)
+ else:
+ return AgentFlowSpec(**spec)
+
  def __post_init__(self):
  if self.id is None:
  self.id = str(uuid.uuid4())
+ self.sender = self.init_spec(self.sender)
+ self.receiver = self.init_spec(self.receiver)
  if self.user_id is None:
  self.user_id = "default"
  if self.timestamp is None:
@@ -148,10 +225,7 @@ def __post_init__(self):
  def dict(self):
  result = asdict(self)
  result["sender"] = self.sender.dict()
- if isinstance(self.receiver, list):
- result["receiver"] = [r.dict() for r in self.receiver]
- else:
- result["receiver"] = self.receiver.dict()
+ result["receiver"] = self.receiver.dict()
  return result
 
 
@@ -221,3 +295,4 @@ class DBWebRequestModel(object):
  tags: Optional[List[str]] = None
  agent: Optional[AgentFlowSpec] = None
  workflow: Optional[AgentWorkFlowConfig] = None
+ model: Optional[Model] = None