clean up

Former-commit-id: e0f43399d5

groupchat.py

@@ -44,7 +44,7 @@ nodes = [
 messages = [
     {
         "role": "system",
-        "context": f"Create an a small feedforward in pytorch",
+        "context": "Create an a small feedforward in pytorch",
     }
 ]
 

swarms/agents/__init__.py

@@ -12,4 +12,4 @@ from swarms.agents.omni_modal_agent import OmniModalAgent
 #utils
 from swarms.agents.message import Message
 from swarms.agents.stream_response import stream
-# from swarms.agents.base import AbstractAgent
+from swarms.agents.base import Agent

swarms/agents/agent.py

@@ -1,133 +0,0 @@
-from __future__ import annotations
-
-from typing import List, Optional
-
-from langchain.chains.llm import LLMChain
-
-from swarms.agents.utils.Agent import AgentOutputParser
-from swarms.agents.utils.human_input import HumanInputRun
-from swarms.memory.base_memory import BaseChatMessageHistory, ChatMessageHistory
-from swarms.memory.document import Document
-from swarms.models.base import AbstractModel
-from swarms.models.prompts.agent_prompt_auto import (
-    MessageFormatter,
-    PromptConstructor,
-)
-from swarms.models.prompts.agent_prompt_generator import FINISH_NAME
-from swarms.models.prompts.base import (
-    AIMessage,
-    HumanMessage,
-    SystemMessage,
-)
-from swarms.tools.base import BaseTool
-
-
-class Agent:
-    """Base Agent class"""
-    def __init__(
-        self,
-        ai_name: str,
-        chain: LLMChain,
-        memory,
-        output_parser: AgentOutputParser,
-        tools: List[BaseTool],
-        feedback_tool: Optional[HumanInputRun] = None,
-        chat_history_memory: Optional[BaseChatMessageHistory] = None,
-    ):
-        self.ai_name = ai_name
-        self.chain = chain
-        self.memory = memory
-        self.next_action_count = 0
-        self.output_parser = output_parser
-        self.tools = tools
-        self.feedback_tool = feedback_tool
-        self.chat_history_memory = chat_history_memory or ChatMessageHistory()
-
-    @classmethod
-    def integrate(
-        cls,
-        ai_name: str,
-        ai_role: str,
-        memory,
-        tools: List[BaseTool],
-        llm: AbstractModel,
-        human_in_the_loop: bool = False,
-        output_parser: Optional[AgentOutputParser] = None,
-        chat_history_memory: Optional[BaseChatMessageHistory] = None,
-    ) -> Agent:
-        prompt_constructor = PromptConstructor(ai_name=ai_name,
-                                               ai_role=ai_role,
-                                               tools=tools)
-        message_formatter = MessageFormatter()
-        human_feedback_tool = HumanInputRun() if human_in_the_loop else None
-        chain = LLMChain(llm=llm, prompt_constructor=prompt_constructor, message_formatter=message_formatter)
-        return cls(
-            ai_name,
-            memory,
-            chain,
-            output_parser or AgentOutputParser(),
-            tools,
-            feedback_tool=human_feedback_tool,
-            chat_history_memory=chat_history_memory,
-        )
-
-    def run(self, goals: List[str]) -> str:
-        user_input = (
-            "Determine which next command to use, and respond using the format specified above:"
-        )
-        loop_count = 0
-        while True:
-            loop_count += 1
-
-            # Send message to AI, get response
-            assistant_reply = self.chain.run(
-                goals=goals,
-                messages=self.chat_history_memory.messages,
-                memory=self.memory,
-                user_input=user_input,
-            )
-
-            print(assistant_reply)
-            self.chat_history_memory.add_message(HumanMessage(content=user_input))
-            self.chat_history_memory.add_message(AIMessage(content=assistant_reply))
-
-            # Get command name and arguments
-            action = self.output_parser.parse(assistant_reply)
-            tools = {t.name: t for t in self.tools}
-            if action.name == FINISH_NAME:
-                return action.args["response"]
-            if action.name in tools:
-                tool = tools[action.name]
-                try:
-                    observation = tool.run(action.args)
-                except Exception as error:
-                    observation = (
-                        f"Validation Error in args: {str(error)}, args: {action.args}"
-                    )
-                except Exception as e:
-                    observation = (
-                        f"Error: {str(e)}, {type(e).__name__}, args: {action.args}"
-                    )
-                result = f"Command {tool.name} returned: {observation}"
-            elif action.name == "ERROR":
-                result = f"Error: {action.args}. "
-            else:
-                result = (
-                    f"""Unknown command '{action.name}'. 
-                    Please refer to the 'COMMANDS' list for available
-                    commands and only respond in the specified JSON format."""
-                )
-            memory_to_add = (
-                f"Assistant Reply: {assistant_reply} " f"\nResult: {result} "
-            )
-            if self.feedback_tool is not None:
-                feedback = f"\n{self.feedback_tool.run('Input: ')}"
-                if feedback in {"q", "stop"}:
-                    print("EXITING")
-                    return "EXITING"
-                memory_to_add += feedback
-
-            self.memory.add_documents([Document(page_content=memory_to_add)])
-            self.chat_history_memory.add_message(SystemMessage(content=result))
-
-

swarms/agents/base.py

@@ -1,28 +1,65 @@
+from typing import Dict, List, Optional, Union
+
+
+class Agent:
+    """(In preview) An abstract class for AI agent.
+
+    An agent can communicate with other agents and perform actions.
+    Different agents can differ in what actions they perform in the `receive` method.
+
+    Agents are full and completed:
+
+    Agents = llm + tools + memory
+    
+    
+    """
 
-class AbsractAgent:
     def __init__(
         self,
-        llm,
+        name: str,
-        temperature
+        #tools: List[Tool],
-    ) -> None:
+        #memory: Memory
-        pass
+    ):
+        """
+        Args:
+            name (str): name of the agent.
+        """
+        # a dictionary of conversations, default value is list
+        self._name = name
+
+    @property
+    def name(self):
+        """Get the name of the agent."""
+        return self._name
+
+    def tools(self, tools):
+        """init tools"""
     
-    #single query
+    def memory(self, memory_store):
-    def run(self, task: str):
+        """init memory"""
         pass
 
-    # conversational back and forth
+    def reset(self):
-    def chat(self, message: str):
+        """(Abstract method) Reset the agent."""
-        message_historys = []
-        message_historys.append(message)
 
-        reply = self.run(message)
+    def run(self, task: str):
-        message_historys.append(reply)
+        """Run the agent once"""
 
-        return message_historys
+    def _arun(self, taks: str):
+        """Run Async run"""
+        
+    def chat(self, messages: List[Dict]):
+        """Chat with the agent"""
 
-    def step(self, message):
+    def _achat(
-        pass
+        self,
-
+        messages: List[Dict]
-    def reset(self):
+    ):
-        pass
+        """Asynchronous Chat"""
+    
+    def step(self, message: str):
+        """Step through the agent"""
+    
+    def _astep(self, message: str):
+        """Asynchronous step"""
+    

swarms/swarms/groupchat.py

@@ -85,9 +85,9 @@ class GroupChatManager(Worker):
     ):
         super().__init__(
             ai_name=ai_name,
-            max_consecutive_auto_reply=max_consecutive_auto_reply,
+            # max_consecutive_auto_reply=max_consecutive_auto_reply,
-            human_input_mode=human_input_mode,
+            # human_input_mode=human_input_mode,
-            system_message=system_message,
+            # system_message=system_message,
             **kwargs
         )
         self.register_reply(

swarms/workers/__init__.py

@@ -1 +1,2 @@
-from swarms.workers.worker import Worker
+from swarms.workers.worker import Worker
+from swarms.workers.base import AbstractWorker

swarms/workers/base.py

@@ -0,0 +1,96 @@
+from typing import Dict, List, Optional, Union
+
+
+class AbstractWorker:
+    """(In preview) An abstract class for AI worker.
+
+    An worker can communicate with other workers and perform actions.
+    Different workers can differ in what actions they perform in the `receive` method.
+    """
+
+    def __init__(
+        self,
+        name: str,
+    ):
+        """
+        Args:
+            name (str): name of the worker.
+        """
+        # a dictionary of conversations, default value is list
+        self._name = name
+
+    @property
+    def name(self):
+        """Get the name of the worker."""
+        return self._name
+    
+    def run(
+        self,
+        task: str
+    ):
+        """Run the worker agent once"""
+
+    def send(
+        self, 
+        message: Union[Dict, str], 
+        recipient: "Agent", 
+        request_reply: Optional[bool] = None
+    ):
+        """(Abstract method) Send a message to another worker."""
+
+    async def a_send(
+        self, 
+        message: Union[Dict, str], 
+        recipient: "Agent", 
+        request_reply: Optional[bool] = None
+    ):
+        """(Aabstract async method) Send a message to another worker."""
+
+    def receive(
+        self, 
+        message: Union[Dict, str], 
+        sender: "Agent", 
+        request_reply: Optional[bool] = None
+    ):
+        """(Abstract method) Receive a message from another worker."""
+
+    async def a_receive(
+        self, 
+        message: Union[Dict, str], 
+        sender: "Agent", 
+        request_reply: Optional[bool] = None
+    ):
+        """(Abstract async method) Receive a message from another worker."""
+
+    def reset(self):
+        """(Abstract method) Reset the worker."""
+
+    def generate_reply(
+        self,
+        messages: Optional[List[Dict]] = None,
+        sender: Optional["Agent"] = None,
+        **kwargs,
+    ) -> Union[str, Dict, None]:
+        """(Abstract method) Generate a reply based on the received messages.
+
+        Args:
+            messages (list[dict]): a list of messages received.
+            sender: sender of an Agent instance.
+        Returns:
+            str or dict or None: the generated reply. If None, no reply is generated.
+        """
+
+    async def a_generate_reply(
+        self,
+        messages: Optional[List[Dict]] = None,
+        sender: Optional["Agent"] = None,
+        **kwargs,
+    ) -> Union[str, Dict, None]:
+        """(Abstract async method) Generate a reply based on the received messages.
+
+        Args:
+            messages (list[dict]): a list of messages received.
+            sender: sender of an Agent instance.
+        Returns:
+            str or dict or None: the generated reply. If None, no reply is generated.
+        """

swarms/workers/worker.py

@@ -5,7 +5,7 @@ from langchain.embeddings import OpenAIEmbeddings
 from langchain.tools.human.tool import HumanInputRun
 from langchain.vectorstores import FAISS
 from langchain_experimental.autonomous_agents import AutoGPT
-
+from typing import Dict, List, Optional, Union
 from swarms.agents.message import Message
 from swarms.tools.autogpt import (
     ReadFileTool,
@@ -302,4 +302,13 @@ class Worker:
         
         """
         for token in response.split():
-            yield token
+            yield token
+
+    @staticmethod
+    def _message_to_dict(message: Union[Dict, str]):
+        """Convert a message"""
+        if isinstance(message, str):
+            return {"content": message}
+        else:
+            return message
+