[CLEANUP]

playground/models/speecht5_example.py

@@ -1,8 +0,0 @@
-from swarms.models.speecht5 import SpeechT5Wrapper
-
-speechT5 = SpeechT5Wrapper()
-
-result = speechT5("Hello, how are you?")
-
-speechT5.save_speech(result)
-print("Speech saved successfully!")

playground/structs/dialogue_simulator_example.py

@@ -1,42 +0,0 @@
-from swarms import DialogueSimulator, Worker
-from swarms.models import OpenAIChat
-
-llm = OpenAIChat(
-    model_name="gpt-4", openai_api_key="api-key", temperature=0.5
-)
-
-worker1 = Worker(
-    llm=llm,
-    ai_name="Bumble Bee",
-    ai_role="Worker in a swarm",
-    external_tools=None,
-    human_in_the_loop=False,
-    temperature=0.5,
-)
-worker2 = Worker(
-    llm=llm,
-    ai_name="Optimus Prime",
-    ai_role="Worker in a swarm",
-    external_tools=None,
-    human_in_the_loop=False,
-    temperature=0.5,
-)
-worker3 = Worker(
-    llm=llm,
-    ai_name="Megatron",
-    ai_role="Worker in a swarm",
-    external_tools=None,
-    human_in_the_loop=False,
-    temperature=0.5,
-)
-
-collab = DialogueSimulator(
-    [worker1, worker2],
-    # DialogueSimulator.select_next_speaker
-)
-
-collab.run(
-    max_iters=4,
-    name="plinus",
-    message="how can we enable multi agent collaboration",
-)

playground/structs/godmode_example.py

@@ -1,33 +0,0 @@
-import os
-
-from dotenv import load_dotenv
-
-from swarms import ModelParallelizer
-from swarms.models import Anthropic, Gemini, Mixtral, OpenAIChat
-
-load_dotenv()
-
-# API Keys
-anthropic_api_key = os.getenv("ANTHROPIC_API_KEY")
-openai_api_key = os.getenv("OPENAI_API_KEY")
-gemini_api_key = os.getenv("GEMINI_API_KEY")
-
-# Initialize the models
-llm = OpenAIChat(openai_api_key=openai_api_key)
-anthropic = Anthropic(anthropic_api_key=anthropic_api_key)
-mixtral = Mixtral()
-gemini = Gemini(gemini_api_key=gemini_api_key)
-
-# Initialize the parallelizer
-llms = [llm, anthropic, mixtral, gemini]
-parallelizer = ModelParallelizer(llms)
-
-# Set the task
-task = "Generate a 10,000 word blog on health and wellness."
-
-# Run the task
-out = parallelizer.run(task)
-
-# Print the responses 1 by 1
-for i in range(len(out)):
-    print(f"Response from LLM {i}: {out[i]}")

playground/structs/gui_app_example.py

@@ -1,4 +1,4 @@
-from swarms import HierarchicalSwarm
+from swarms.structs.hiearchical_swarm import HierarchicalSwarm
 
 # Retrieve your API key from the environment or replace with your actual key
 api_key = "sksdsds"

playground/structs/multi_agent_debate_example.py

@@ -1,5 +1,5 @@
 from swarms.models import OpenAIChat
-from swarms.swarms.multi_agent_debate import (
+from swarms.structs.multi_agent_debate import (
     MultiAgentDebate,
     select_speaker,
 )
@@ -11,7 +11,6 @@ worker1 = Worker(
     llm=llm,
     ai_name="Bumble Bee",
     ai_role="Worker in a swarm",
-    external_tools=None,
     human_in_the_loop=False,
     temperature=0.5,
 )
@@ -19,7 +18,6 @@ worker2 = Worker(
     llm=llm,
     ai_name="Optimus Prime",
     ai_role="Worker in a swarm",
-    external_tools=None,
     human_in_the_loop=False,
     temperature=0.5,
 )
@@ -27,7 +25,6 @@ worker3 = Worker(
     llm=llm,
     ai_name="Megatron",
     ai_role="Worker in a swarm",
-    external_tools=None,
     human_in_the_loop=False,
     temperature=0.5,
 )

playground/structs/multi_modal_flow_example.py

@@ -1,7 +1,6 @@
-# This might not work in the beginning but it's a starting point
+from swarms import GPT4VisionAPI, Agent
-from swarms.structs import GPT4V, Agent
 
-llm = GPT4V()
+llm = GPT4VisionAPI()
 
 agent = Agent(
     max_loops="auto",

playground/structs/nonlinear_worfklow_example.py

@@ -1,18 +0,0 @@
-from swarms.agents.base import agent
-from swarms.structs.nonlinear_worfklow import NonLinearWorkflow, Task
-
-prompt = "develop a feedforward network in pytorch"
-prompt2 = "Develop a self attention using pytorch"
-
-task1 = Task("task1", prompt)
-task2 = Task("task2", prompt2, parents=[task1])
-
-# add tasks to workflow
-workflow = NonLinearWorkflow(agent)
-
-# add tasks to tree
-workflow.add(task1)
-workflow.add(task2)
-
-# run
-workflow.run()

playground/structs/orchestrate_example.py

@@ -1,17 +0,0 @@
-from swarms import Orchestrator, Worker
-
-node = Worker(
-    openai_api_key="",
-    ai_name="Optimus Prime",
-)
-
-
-# Instantiate the Orchestrator with 10 agents
-orchestrator = Orchestrator(node, agent_list=[node] * 10, task_queue=[])
-
-# Agent 7 sends a message to Agent 9
-orchestrator.chat(
-    sender_id=7,
-    receiver_id=9,
-    message="Can you help me with this task?",
-)

playground/structs/society_of_agents.py

@@ -0,0 +1,66 @@
+from swarms import Agent, Anthropic
+from swarms.structs.society_of_agents import SocietyOfAgents
+
+# Initialize the director agent
+
+director = Agent(
+    agent_name="Director",
+    system_prompt="Directs the tasks for the workers",
+    llm=Anthropic(),
+    max_loops=1,
+    dashboard=False,
+    streaming_on=True,
+    verbose=True,
+    stopping_token="<DONE>",
+    state_save_file_type="json",
+    saved_state_path="director.json",
+)
+
+
+# Initialize worker 1
+
+worker1 = Agent(
+    agent_name="Worker1",
+    system_prompt="Generates a transcript for a youtube video on what swarms are",
+    llm=Anthropic(),
+    max_loops=1,
+    dashboard=False,
+    streaming_on=True,
+    verbose=True,
+    stopping_token="<DONE>",
+    state_save_file_type="json",
+    saved_state_path="worker1.json",
+)
+
+
+# Initialize worker 2
+worker2 = Agent(
+    agent_name="Worker2",
+    system_prompt="Summarizes the transcript generated by Worker1",
+    llm=Anthropic(),
+    max_loops=1,
+    dashboard=False,
+    streaming_on=True,
+    verbose=True,
+    stopping_token="<DONE>",
+    state_save_file_type="json",
+    saved_state_path="worker2.json",
+)
+
+
+# Create a list of agents
+agents = [director, worker1, worker2]
+
+# Create the swarm
+society = SocietyOfAgents(
+    name="Society of Agents",
+    description="A society of agents that work together to complete a task",
+    agents=agents,
+    max_loops=1,
+    rules="Don't stop until the task is done",
+)
+
+# Run the swarm
+output = society.run(
+    "Create a format to express and communicate swarms of llms in a structured manner for youtube"
+)

pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "swarms"
-version = "5.0.5"
+version = "5.0.6"
 description = "Swarms - Pytorch"
 license = "MIT"
 authors = ["Kye Gomez <kye@apac.ai>"]

swarms/prompts/documentation.py

@@ -2,7 +2,8 @@ def DOCUMENTATION_WRITER_SOP(
     task: str,
     module: str,
 ):
-    documentation = f"""Create multi-page long and explicit professional pytorch-like documentation for the {module} code below follow the outline for the {module} library,
+    documentation = f"""
+    Create multi-page long and explicit professional pytorch-like documentation for the {module} code below follow the outline for the {module} library,
     provide many examples and teach the user about the code, provide examples for every function, make the documentation 10,000 words,
     provide many usage examples and note this is markdown docs, create the documentation for the code to document,
     put the arguments and methods in a table in markdown to make it visually seamless

swarms/structs/hiearchical_swarm.py

@@ -6,6 +6,25 @@ from beartype import beartype
 from swarms.structs.agent import Agent
 from swarms.structs.base_swarm import BaseSwarm
 from swarms.utils.loguru_logger import logger
+from pydantic import BaseModel, Field
+
+
+class HiearchicalRequest(BaseModel):
+    task: str = Field(
+        None,
+        title="Task",
+        description="The task to send to the director agent.",
+    )
+    agents: Agent = Field(
+        None,
+        title="Agents",
+        description="The list of agents in the hierarchical swarm.",
+    )
+    rules: str = Field(
+        None,
+        title="Rules",
+        description="The rules for the hierarchical swarm.",
+    )
 
 
 class HiearchicalSwarm(BaseSwarm):
@@ -34,6 +53,8 @@ class HiearchicalSwarm(BaseSwarm):
             for agent in agents:
                 agent.long_term_memory = long_term_memory_system
 
+        # Set the max loops of every agent to max loops
+
     def parse_function_activate_agent(
         self, json_data: str = None, *args, **kwargs
     ):
@@ -52,14 +73,30 @@ class HiearchicalSwarm(BaseSwarm):
         """
         try:
             data = json.loads(json_data)
-            name = data.get("name")
-            task = data.get("task")
 
-            response = self.select_agent_and_send_task(
+            # Check if the data is a list of agent task pairs
-                name, task, *args, **kwargs
+            if isinstance(data, list):
-            )
+                responses = []
+                # Iterate over the list of agent task pairs
+                for agent_task in data:
+                    name = agent_task.get("name")
+                    task = agent_task.get("task")
 
-            return response
+                    response = self.select_agent_and_send_task(
+                        name, task, *args, **kwargs
+                    )
+
+                    responses.append(response)
+                return responses
+            else:
+                name = data.get("name")
+                task = data.get("task")
+
+                response = self.select_agent_and_send_task(
+                    name, task, *args, **kwargs
+                )
+
+                return response
         except json.JSONDecodeError:
             logger.error("Invalid JSON data, try again.")
             raise json.JSONDecodeError
@@ -124,6 +161,8 @@ class HiearchicalSwarm(BaseSwarm):
 
                 loop += 1
 
+                task = response
+
             return response
         except Exception as e:
             logger.error(f"Error: {e}")

swarms/structs/society_of_agents.py

@@ -0,0 +1,50 @@
+from typing import List
+from swarms.structs.agent import Agent
+from swarms.structs.base_swarm import BaseSwarm
+from swarms.structs.conversation import Conversation
+from swarms.utils.loguru_logger import logger
+
+
+class SocietyOfAgents(BaseSwarm):
+    def __init__(
+        self,
+        name: str = None,
+        description: str = None,
+        agents: List[Agent] = None,
+        max_loops: int = 1,
+        rules: str = None,
+        *args,
+        **kwargs,
+    ):
+        super().__init__(*args, **kwargs)
+        self.name = name
+        self.description = description
+        self.agents = agents
+        self.max_loops = max_loops
+        self.conversation = Conversation(
+            time_enabled=True, rules=rules, *args, **kwargs
+        )
+
+    def run(self, task: str = None, *args, **kwargs):
+        loop = 0
+
+        try:
+            while loop < self.max_loops:
+                for agent in self.agents:
+                    out = agent.run(task, *args, **kwargs)
+
+                    # Save the conversation
+                    self.conversation.add(agent.agent_name, out)
+
+                    task = out
+
+                    # Log the agent's output
+                    logger.info(f"Agent {agent.agent_name} output: {out}")
+
+                loop += 1
+
+        except Exception as e:
+            logger.error(f"An error occurred: {e}")
+            return None
+
+        return out

swarms/structs/utils.py

@@ -26,7 +26,11 @@ def parse_tasks(
 
 
 def find_agent_by_id(
-    agent_id: str = None, agents: List[Agent] = None, *args, **kwargs
+    agent_id: str = None,
+    agents: List[Agent] = None,
+    task: str = None,
+    *args,
+    **kwargs,
 ) -> Agent:
     """Find agent by id
 
@@ -39,7 +43,11 @@ def find_agent_by_id(
     """
     for agent in agents:
         if agent.id == agent_id:
-            return agent
+            if task:
+                return agent.run(task, *args, **kwargs)
+            else:
+                return agent
+
     return None