[CLEANUP]

README.md

@@ -75,29 +75,54 @@ Features:
 
 ```python
 import os
+from swarms import Agent, Anthropic
 
-from dotenv import load_dotenv
-
-# Import the OpenAIChat model and the Agent struct
-from swarms import Agent, OpenAIChat
-
-# Load the environment variables
-load_dotenv()
-
-# Get the API key from the environment
-api_key = os.environ.get("OPENAI_API_KEY")
 
-# Initialize the language model
+# Initialize the agent
-llm = OpenAIChat(
+agent = Agent(
-    temperature=0.5, openai_api_key=api_key, max_tokens=4000
+    agent_name="Accounting Assistant",
+    system_prompt="You're the accounting agent, your purpose is to generate a profit report for a company!",
+    agent_description="Generate a profit report for a company!",
+    llm=Anthropic(
+        anthropic_api_key = os.getenv("ANTHROPIC_API_KEY")
+    ),
+    max_loops="auto",
+    autosave=True,
+    # dynamic_temperature_enabled=True,
+    dashboard=False,
+    verbose=True,
+    streaming_on=True,
+    # interactive=True, # Set to False to disable interactive mode
+    saved_state_path="accounting_agent.json",
+    # tools=[
+    #     # calculate_profit,
+    #     # generate_report,
+    #     # search_knowledge_base,
+    #     # write_memory_to_rag,
+    #     # search_knowledge_base,
+    #     # generate_speech,
+    # ],
+    stopping_token="Stop!",
+    interactive=True,
+    # docs_folder="docs",
+    # pdf_path="docs/accounting_agent.pdf",
+    # sop="Calculate the profit for a company.",
+    # sop_list=["Calculate the profit for a company."],
+    # user_name="User",
+    # # docs=
+    # # docs_folder="docs",
+    # retry_attempts=3,
+    # context_length=1000,
+    # tool_schema = dict
+    context_length=1000,
+    # agent_ops_on=True,
+    # long_term_memory=ChromaDB(docs_folder="artifacts"),
 )
 
+agent.run(
+    "Search the knowledge base for the swarms github framework and how it works"
+)
 
-## Initialize the workflow
-agent = Agent(llm=llm, max_loops=1, autosave=True, dashboard=True)
-
-# Run the workflow on a task
-agent.run("Generate a 10,000 word blog on health and wellness.")
 ```
 
 
@@ -131,6 +156,7 @@ llm = OpenAIChat(
 ## Initialize the workflow
 agent = Agent(
     llm=llm,
+    agent_name: str = "WellNess Agent",
     name = "Health and Wellness Blog",
     system_prompt="Generate a 10,000 word blog on health and wellness.",
     max_loops=4,

example.py

@@ -1,34 +1,5 @@
 from swarms import Agent, Anthropic
 
-
-def calculate_profit(revenue: float, expenses: float):
-    """
-    Calculates the profit by subtracting expenses from revenue.
-
-    Args:
-        revenue (float): The total revenue.
-        expenses (float): The total expenses.
-
-    Returns:
-        float: The calculated profit.
-    """
-    return revenue - expenses
-
-
-def generate_report(company_name: str, profit: float):
-    """
-    Generates a report for a company's profit.
-
-    Args:
-        company_name (str): The name of the company.
-        profit (float): The calculated profit.
-
-    Returns:
-        str: The report for the company's profit.
-    """
-    return f"The profit for {company_name} is ${profit}."
-
-
 # Initialize the agent
 agent = Agent(
     agent_name="Accounting Assistant",

playground/structs/agent_registry.py

@@ -77,3 +77,12 @@ registry.add("Marketing Specialist", growth_agent1)
 registry.add("Sales Specialist", growth_agent2)
 registry.add("Product Development Specialist", growth_agent3)
 registry.add("Customer Service Specialist", growth_agent4)
+
+
+# Query the agents
+registry.get("Marketing Specialist")
+registry.get("Sales Specialist")
+registry.get("Product Development Specialist")
+
+# Get all the agents
+registry.list_agents()

scripts/auto_tests_docs/docs.py

@@ -110,7 +110,8 @@ def TEST_WRITER_SOP_PROMPT(
     TESTS_PROMPT = f"""
 
    Create 5,000 lines of extensive and thorough tests for the code below using the guide, do not worry about your limits you do not have any
-   just write the best tests possible, the module is {module}, the file path is {path}
+   just write the best tests possible, the module is {module}, the file path is {path} return all of the code in one file, make sure to test all the functions and methods in the code.
+   
 
 
    ######### TESTING GUIDE #############

swarms/structs/rearrange.py

@@ -50,6 +50,7 @@ class AgentRearrange(BaseSwarm):
         self.human_in_the_loop = human_in_the_loop
         self.custom_human_in_the_loop = custom_human_in_the_loop
         self.swarm_history = {agent.agent_name: [] for agent in agents}
+        self.sub_swarm = {}
 
         # Verbose is True
         if verbose is True:
@@ -66,6 +67,14 @@ class AgentRearrange(BaseSwarm):
             )
         )
 
+    def add_sub_swarm(self, name: str, flow: str):
+        self.sub_swarm[name] = flow
+        logger.info(f"Sub-swarm {name} added with flow: {flow}")
+
+    def set_custom_flow(self, flow: str):
+        self.flow = flow
+        logger.info(f"Custom flow set: {flow}")
+
     def add_agent(self, agent: Agent):
         """
         Adds an agent to the swarm.
@@ -251,6 +260,77 @@ class AgentRearrange(BaseSwarm):
             logger.error(f"An error occurred: {e}")
             return e
 
+    def process_agent_or_swarm(
+        self, name: str, task: str, img: str, *args, **kwargs
+    ):
+        """
+
+        process_agent_or_swarm: Processes the agent or sub-swarm based on the given name.
+
+        Args:
+            name (str): The name of the agent or sub-swarm to process.
+            task (str): The task to be executed.
+            img (str): The image to be processed by the agents.
+            *args: Variable length argument list.
+            **kwargs: Arbitrary keyword arguments.
+
+        Returns:
+            str: The result of the last executed task.
+
+        """
+        if name.startswith("Human"):
+            return self.human_intervention(task)
+        elif name in self.sub_swarm:
+            return self.run_sub_swarm(task, name, img, *args, **kwargs)
+        else:
+            agent = self.agents[name]
+            return agent.run(task, *args, **kwargs)
+
+    def human_intervention(self, task: str) -> str:
+        if self.human_in_the_loop and self.custom_human_in_the_loop:
+            return self.custom_human_in_the_loop(task)
+        else:
+            return input(
+                "Human intervention required. Enter your response: "
+            )
+
+    def run_sub_swarm(
+        self, swarm_name: str, task: str, img: str, *args, **kwargs
+    ):
+        """
+        Runs a sub-swarm by executing a sequence of tasks on a set of agents.
+
+        Args:
+            swarm_name (str): The name of the sub-swarm to run.
+            task (str): The initial task to be executed.
+            img (str): The image to be processed by the agents.
+            *args: Variable length argument list.
+            **kwargs: Arbitrary keyword arguments.
+
+        Returns:
+            str: The result of the last executed task.
+
+        """
+        sub_flow = self.sub_swarm[swarm_name]
+        sub_tasks = sub_flow.split("->")
+        current_task = task
+
+        for sub_task in sub_tasks:
+            agent_names = [name.strip() for name in sub_task.split(",")]
+            if len(agent_names) > 1:
+                results = []
+                for agent_name in agent_names:
+                    result = self.process_agent_or_swarm(
+                        agent_name, current_task, img, *args, **kwargs
+                    )
+                    results.append(result)
+                current_task = "; ".join(results)
+            else:
+                current_task = self.process_agent_or_swarm(
+                    agent_names[0], current_task, img, *args, **kwargs
+                )
+        return current_task
+
 
 def rearrange(
     agents: List[Agent] = None,