[CLEANUP OPERATION]

README.md

@@ -44,7 +44,7 @@ import os
 from dotenv import load_dotenv
 
 # Import the OpenAIChat model and the Agent struct
-from swarms import OpenAIChat, Agent
+from swarms import Agent, OpenAIChat
 
 # Load the environment variables
 load_dotenv()
@@ -54,10 +54,7 @@ api_key = os.environ.get("OPENAI_API_KEY")
 
 # Initialize the language model
 llm = OpenAIChat(
-    temperature=0.5,
+    temperature=0.5, model_name="gpt-4", openai_api_key=api_key, max_tokens=4000
-    model_name="gpt-4",
-    openai_api_key=api_key,
-    max_tokens=4000
 )
 
 
@@ -66,9 +63,6 @@ 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.")
-
-
-
 ```
 
 
@@ -79,6 +73,7 @@ ToolAgent is an agent that outputs JSON using any model from huggingface. It tak
 ```python
 # Import necessary libraries
 from transformers import AutoModelForCausalLM, AutoTokenizer
+
 from swarms import ToolAgent
 
 # Load the pre-trained model and tokenizer
@@ -107,8 +102,6 @@ generated_data = agent.run(task)
 
 # Print the generated data
 print(generated_data)
-
-
 ```
 
 
@@ -124,8 +117,10 @@ The `Worker` is a simple all-in-one agent equipped with an LLM, tools, and RAG f
 ```python
 # Importing necessary modules
 import os
+
 from dotenv import load_dotenv
-from swarms import Worker, OpenAIChat, tool
+
+from swarms import OpenAIChat, Worker, tool
 
 # Loading environment variables from .env file
 load_dotenv()
@@ -151,14 +146,10 @@ worker = Worker(
 )
 
 # Running the worker with a prompt
-out = worker.run(
+out = worker.run("Hello, how are you? Create an image of how your are doing!")
-    "Hello, how are you? Create an image of how your are doing!"
-)
 
 # Printing the output
 print(out)
-
-
 ```
 
 ------
@@ -174,10 +165,12 @@ Sequential Workflow enables you to sequentially execute tasks with `Agent` and t
 ✅  Utilizes Agent class
 
 ```python
-import os 
+import os
-from swarms import OpenAIChat, Agent, SequentialWorkflow 
+
 from dotenv import load_dotenv
 
+from swarms import Agent, OpenAIChat, SequentialWorkflow
+
 load_dotenv()
 
 # Load the environment variables
@@ -186,10 +179,7 @@ api_key = os.getenv("OPENAI_API_KEY")
 
 # Initialize the language agent
 llm = OpenAIChat(
-    temperature=0.5,
+    temperature=0.5, model_name="gpt-4", openai_api_key=api_key, max_tokens=4000
-    model_name="gpt-4",
-    openai_api_key=api_key,
-    max_tokens=4000
 )
 
 
@@ -207,12 +197,14 @@ workflow = SequentialWorkflow(max_loops=1)
 
 # Add tasks to the workflow
 workflow.add(
-    agent1, "Generate a 10,000 word blog on health and wellness.", 
+    agent1,
+    "Generate a 10,000 word blog on health and wellness.",
 )
 
 # Suppose the next task takes the output of the first task as input
 workflow.add(
-    agent2, "Summarize the generated blog",
+    agent2,
+    "Summarize the generated blog",
 )
 
 # Run the workflow
@@ -231,8 +223,10 @@ for task in workflow.tasks:
 
 ```python
 import os
+
 from dotenv import load_dotenv
-from swarms import OpenAIChat, Task, ConcurrentWorkflow, Agent
+
+from swarms import Agent, ConcurrentWorkflow, OpenAIChat, Task
 
 # Load environment variables from .env file
 load_dotenv()
@@ -254,16 +248,17 @@ workflow.add(tasks=[task1, task2, task3])
 
 # Run the workflow
 workflow.run()
-
 ```
 
 ### `RecursiveWorkflow`
 `RecursiveWorkflow` will keep executing the tasks until a specific token like <DONE> is located inside the text!
 
 ```python
-import os 
+import os
-from dotenv import load_dotenv 
+
-from swarms import OpenAIChat, Task, RecursiveWorkflow, Agent
+from dotenv import load_dotenv
+
+from swarms import Agent, OpenAIChat, RecursiveWorkflow, Task
 
 # Load environment variables from .env file
 load_dotenv()
@@ -287,8 +282,6 @@ workflow.add(task3)
 
 # Run the workflow
 workflow.run()
-
-
 ```
 
 
@@ -304,7 +297,7 @@ import os
 
 from dotenv import load_dotenv
 
-from swarms import Anthropic, Gemini, Mixtral, OpenAIChat, ModelParallelizer
+from swarms import Anthropic, Gemini, Mixtral, ModelParallelizer, OpenAIChat
 
 load_dotenv()
 
@@ -346,10 +339,7 @@ import os
 
 from dotenv import load_dotenv
 
-from swarms import (
+from swarms import Conversation, OpenAIChat
-    OpenAIChat,
-    Conversation,
-)
 
 conv = Conversation(
     time_enabled=True,
@@ -364,6 +354,7 @@ api_key = os.environ.get("OPENAI_API_KEY")
 # Initialize the language model
 llm = OpenAIChat(openai_api_key=api_key, model_name="gpt-4")
 
+
 # Run the language model in a loop
 def interactive_conversation(llm):
     conv = Conversation()
@@ -372,9 +363,7 @@ def interactive_conversation(llm):
         conv.add("user", user_input)
         if user_input.lower() == "quit":
             break
-        task = (
+        task = conv.return_history_as_string()  # Get the conversation history
-            conv.return_history_as_string()
-        )  # Get the conversation history
         out = llm(task)
         conv.add("assistant", out)
         print(
@@ -386,7 +375,6 @@ def interactive_conversation(llm):
 
 # Replace with your LLM instance
 interactive_conversation(llm)
-
 ```
 
 
@@ -405,7 +393,7 @@ import os
 from dotenv import load_dotenv
 
 # Import the OpenAIChat model and the Agent struct
-from swarms import OpenAIChat, Agent, SwarmNetwork
+from swarms import Agent, OpenAIChat, SwarmNetwork
 
 # Load the environment variables
 load_dotenv()
@@ -442,11 +430,8 @@ print(out)
 
 
 # Run all the agents in the swarm network on a task
-out = swarmnet.run_many_agents(
+out = swarmnet.run_many_agents("Generate a 10,000 word blog on health and wellness.")
-    "Generate a 10,000 word blog on health and wellness."
-)
 print(out)
-
 ```
 
 
@@ -513,8 +498,6 @@ else:
 
 # Output the result of the task
 print(f"Task result: {task.result}")
-
-
 ```
 
 ---
@@ -535,14 +518,7 @@ from dotenv import load_dotenv
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 # Import the models, structs, and telemetry modules
-from swarms import (
+from swarms import BlocksList, Gemini, GPT4VisionAPI, Mixtral, OpenAI, ToolAgent
-    Gemini,
-    GPT4VisionAPI,
-    Mixtral,
-    OpenAI,
-    ToolAgent,
-    BlocksList,
-)
 
 # Load the environment variables
 load_dotenv()
@@ -552,9 +528,7 @@ openai_api_key = os.getenv("OPENAI_API_KEY")
 gemini_api_key = os.getenv("GEMINI_API_KEY")
 
 # Tool Agent
-model = AutoModelForCausalLM.from_pretrained(
+model = AutoModelForCausalLM.from_pretrained("databricks/dolly-v2-12b")
-    "databricks/dolly-v2-12b"
-)
 tokenizer = AutoTokenizer.from_pretrained("databricks/dolly-v2-12b")
 json_schema = {
     "type": "object",
@@ -565,9 +539,7 @@ json_schema = {
         "courses": {"type": "array", "items": {"type": "string"}},
     },
 }
-toolagent = ToolAgent(
+toolagent = ToolAgent(model=model, tokenizer=tokenizer, json_schema=json_schema)
-    model=model, tokenizer=tokenizer, json_schema=json_schema
-)
 
 # Blocks List which enables you to build custom swarms by adding classes or functions
 swarm = BlocksList(
@@ -619,9 +591,7 @@ blocks_by_parent_name = swarm.get_by_parent_name(swarm.name)
 blocks_by_parent_type = swarm.get_by_parent_type(type(swarm).__name__)
 
 # Get blocks by parent description
-blocks_by_parent_description = swarm.get_by_parent_description(
+blocks_by_parent_description = swarm.get_by_parent_description(swarm.description)
-    swarm.description
-)
 
 # Run the block in the swarm
 inference = swarm.run_block(toolagent, "Hello World")
@@ -636,25 +606,27 @@ Here's a production grade swarm ready for real-world deployment in a factory and
 
 
 ```python
-from swarms.structs import Agent
 import os
+
 from dotenv import load_dotenv
+
 from swarms.models import GPT4VisionAPI
 from swarms.prompts.logistics import (
+    Efficiency_Agent_Prompt,
     Health_Security_Agent_Prompt,
-    Quality_Control_Agent_Prompt,
     Productivity_Agent_Prompt,
+    Quality_Control_Agent_Prompt,
     Safety_Agent_Prompt,
     Security_Agent_Prompt,
     Sustainability_Agent_Prompt,
-    Efficiency_Agent_Prompt,
 )
+from swarms.structs import Agent
 
 # Load ENV
 load_dotenv()
 api_key = os.getenv("OPENAI_API_KEY")
 
-# GPT4VisionAPI 
+# GPT4VisionAPI
 llm = GPT4VisionAPI(openai_api_key=api_key)
 
 # Image for analysis
@@ -686,9 +658,7 @@ productivity_agent = Agent(
 )
 
 # Initiailize safety agent
-safety_agent = Agent(
+safety_agent = Agent(llm=llm, sop=Safety_Agent_Prompt, max_loops=1, multi_modal=True)
-    llm=llm, sop=Safety_Agent_Prompt, max_loops=1, multi_modal=True
-)
 
 # Init the security agent
 security_agent = Agent(
@@ -748,7 +718,9 @@ Run the agent with multiple modalities useful for various real-world tasks in ma
 ```python
 # Description: This is an example of how to use the Agent class to run a multi-modal workflow
 import os
+
 from dotenv import load_dotenv
+
 from swarms.models.gpt4_vision_api import GPT4VisionAPI
 from swarms.structs import Agent
 
@@ -775,17 +747,11 @@ img = "assembly_line.jpg"
 
 ## Initialize the workflow
 agent = Agent(
-    llm=llm,
+    llm=llm, max_loops="auto", autosave=True, dashboard=True, multi_modal=True
-    max_loops="auto",
-    autosave=True,
-    dashboard=True,
-    multi_modal=True
 )
 
 # Run the workflow on a task
 agent.run(task=task, img=img)
-
-
 ```
 
 ---
@@ -857,14 +823,10 @@ model = QwenVLMultiModal(
 )
 
 # Run the model
-response = model(
+response = model("Hello, how are you?", "https://example.com/image.jpg")
-    "Hello, how are you?", "https://example.com/image.jpg"
-)
 
 # Print the response
 print(response)
-
-
 ```
 
 
@@ -882,7 +844,6 @@ out = model.run("Analyze the reciepts in this image", "docs.jpg")
 
 # Print the output
 print(out)
-
 ```
 
 
@@ -923,8 +884,6 @@ model.set_max_length(200)
 
 # Clear the chat history of the model
 model.clear_chat_history()
-
-
 ```
 
 ## Radically Simple AI Model APIs
@@ -941,9 +900,7 @@ We provide a vast array of language and multi-modal model APIs for you to genera
 from swarms.models import Anthropic
 
 # Initialize an instance of the Anthropic class
-model = Anthropic(
+model = Anthropic(anthropic_api_key="")
-    anthropic_api_key=""
-)
 
 # Using the run method
 completion_1 = model.run("What is the capital of France?")
@@ -952,7 +909,6 @@ print(completion_1)
 # Using the __call__ method
 completion_2 = model("How far is the moon from the earth?", stop=["miles", "km"])
 print(completion_2)
-
 ```
 
 
@@ -964,12 +920,16 @@ from swarms.models import HuggingfaceLLM
 custom_config = {
     "quantize": True,
     "quantization_config": {"load_in_4bit": True},
-    "verbose": True
+    "verbose": True,
 }
-inference = HuggingfaceLLM(model_id="NousResearch/Nous-Hermes-2-Vision-Alpha", **custom_config)
+inference = HuggingfaceLLM(
+    model_id="NousResearch/Nous-Hermes-2-Vision-Alpha", **custom_config
+)
 
 # Generate text based on a prompt
-prompt_text = "Create a list of known biggest risks of structural collapse with references"
+prompt_text = (
+    "Create a list of known biggest risks of structural collapse with references"
+)
 generated_text = inference(prompt_text)
 print(generated_text)
 ```
@@ -1027,7 +987,6 @@ task = "A person is walking on the street."
 # Generate the video!
 video_path = zeroscope(task)
 print(video_path)
-
 ```
 
 

docs/applications/discord.md

@@ -64,6 +64,7 @@ Initialize the `llm` (Language Learning Model) with your OpenAI API key:
 
 ```python
 from swarms.models import OpenAIChat
+
 llm = OpenAIChat(
     openai_api_key="Your_OpenAI_API_Key",
     temperature=0.5,
@@ -74,6 +75,7 @@ Initialize the bot with the `llm`:
 
 ```python
 from apps.discord import Bot
+
 bot = Bot(llm=llm)
 ```
 

docs/examples/bingchat.md

@@ -46,6 +46,7 @@ You can also specify the conversation style:
 
 ```python
 from bing_chat import ConversationStyle
+
 response = chat("Tell me a joke", style=ConversationStyle.creative)
 print(response)
 ```

docs/examples/flow.md

@@ -107,16 +107,17 @@ Now, let's create your first Agent. A Agent represents a chain-like structure th
 
 # Import necessary modules
 ```python
-from swarms.models import OpenAIChat # Zephr, Mistral
+from swarms.models import OpenAIChat  # Zephr, Mistral
 from swarms.structs import Agent
 
-api_key = ""# Initialize the language model (LLM)
+api_key = ""  # Initialize the language model (LLM)
-llm = OpenAIChat(openai_api_key=api_key, temperature=0.5, max_tokens=3000)# Initialize the Agent object
+llm = OpenAIChat(
+    openai_api_key=api_key, temperature=0.5, max_tokens=3000
+)  # Initialize the Agent object
 
-agent = Agent(llm=llm, max_loops=5)# Run the agent
+agent = Agent(llm=llm, max_loops=5)  # Run the agent
 out = agent.run("Create an financial analysis on the following metrics")
 print(out)
-
 ```
 
 ### [3. Initializing the Agent Object](https://github.com/kyegomez/swarms)

docs/examples/omni_agent.md

@@ -55,7 +55,7 @@ from swarms.models import OpenAIChat
 
 llm = OpenAIChat(openai_api_key="sk-")
 agent = OmniModalAgent(llm)
-response = agent.run("Create an video of a swarm of fish concept art, game art") 
+response = agent.run("Create an video of a swarm of fish concept art, game art")
 print(response)
 ```
 

docs/examples/revgpt.md

@@ -35,7 +35,6 @@ The abstraction provided in `revgpt.py` is designed to simplify your interaction
 1. **Import the Necessary Modules:**
 
 ```python
-import os
 from dotenv import load_dotenv
 from revgpt import AbstractChatGPT
 ```

docs/examples/stacked_worker.md

@@ -28,8 +28,8 @@ The provided code showcases a system built around a worker node that utilizes va
 The code begins with import statements, bringing in necessary modules and classes. Key imports include the `OpenAIChat` class, which represents a language model, and several custom agents and tools from the `swarms` package.
 
 ```python
-import os
 import interpreter  # Assuming this is a custom module
+
 from swarms.agents.hf_agents import HFAgent
 from swarms.agents.omni_modal_agent import OmniModalAgent
 from swarms.models import OpenAIChat
@@ -59,11 +59,7 @@ All defined tools are appended to a list called `tools`. This list is later used
 
 ```python
 # Append tools to a list
-tools = [
+tools = [hf_agent, omni_agent, compile]
-    hf_agent,
-    omni_agent,
-    compile
-]
 ```
 
 ### Initializing a Worker Node
@@ -263,8 +259,6 @@ response = node.run(task)
 
 # Print the response
 print(response)
-
-
 ```
 
 

docs/examples/worker.md

@@ -53,11 +53,11 @@ Voila! You’re now ready to summon your Worker.
 Here’s a simple way to invoke the Worker and give it a task:
 
 ```python
-from swarms.models import OpenAIChat
 from swarms import Worker
+from swarms.models import OpenAIChat
 
 llm = OpenAIChat(
-    #enter your api key
+    # enter your api key
     openai_api_key="",
     temperature=0.5,
 )
@@ -75,8 +75,6 @@ node = Worker(
 task = "What were the winning boston marathon times for the past 5 years (ending in 2022)? Generate a table of the year, name, country of origin, and times."
 response = node.run(task)
 print(response)
-
-
 ```
 
 

docs/swarms/agents/abstractagent.md

@@ -37,7 +37,6 @@ class AbstractAgent:
 
     def memory(self, memory_store):
         """init memory"""
-        pass
 
     def reset(self):
         """(Abstract method) Reset the agent."""
@@ -82,7 +81,7 @@ agent.reset()
 The `run` method allows the agent to perform a specific task.
 
 ```python
-agent.run('some_task')
+agent.run("some_task")
 ```
 
 #### 3. `chat`
@@ -90,7 +89,7 @@ agent.run('some_task')
 The `chat` method enables communication with the agent through a series of messages.
 
 ```python
-messages = [{'id': 1, 'text': 'Hello, agent!'}, {'id': 2, 'text': 'How are you?'}]
+messages = [{"id": 1, "text": "Hello, agent!"}, {"id": 2, "text": "How are you?"}]
 agent.chat(messages)
 ```
 
@@ -99,7 +98,7 @@ agent.chat(messages)
 The `step` method allows the agent to process a single message.
 
 ```python
-agent.step('Hello, agent!')
+agent.step("Hello, agent!")
 ```
 
 ### Asynchronous Methods

docs/swarms/agents/message.md

@@ -44,7 +44,7 @@ class Message:
     def __repr__(self):
         """
         __repr__ represents the string representation of the Message object.
-        
+
         Returns:
         (str) A string containing the timestamp, sender, and content of the message.
         """
@@ -60,10 +60,7 @@ The `Message` class represents a message in the agent system. Upon initializatio
 Creating a `Message` object and displaying its string representation.
 
 ```python
-mes = Message(
+mes = Message(sender="Kye", content="Hello! How are you?")
-    sender = "Kye",
-    content = "Hello! How are you?"
-)
 
 print(mes)
 ```
@@ -80,9 +77,7 @@ Creating a `Message` object with metadata.
 ```python
 metadata = {"priority": "high", "category": "urgent"}
 mes_with_metadata = Message(
-    sender = "Alice",
+    sender="Alice", content="Important update", metadata=metadata
-    content = "Important update",
-    metadata = metadata
 )
 
 print(mes_with_metadata)
@@ -98,10 +93,7 @@ Output:
 Creating a `Message` object without providing metadata.
 
 ```python
-mes_no_metadata = Message(
+mes_no_metadata = Message(sender="Bob", content="Reminder: Meeting at 2PM")
-    sender = "Bob",
-    content = "Reminder: Meeting at 2PM"
-)
 
 print(mes_no_metadata)
 ```

docs/swarms/agents/omni_agent.md

@@ -39,10 +39,12 @@ For streaming mode, this function yields the response token by token, ensuring a
 ## Examples & Use Cases
 Initialize the `OmniModalAgent` and communicate with it:
 ```python
+import os
+
+from dotenv import load_dotenv
+
 from swarms.agents.omni_modal_agent import OmniModalAgent, OpenAIChat
 from swarms.models import OpenAIChat
-from dotenv import load_dotenv
-import os
 
 # Load the environment variables
 load_dotenv()

docs/swarms/agents/toolagent.md

@@ -69,6 +69,7 @@ The `ToolAgent` class takes the following arguments:
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
+
 from swarms import ToolAgent
 
 # Creating a model and tokenizer
@@ -82,11 +83,8 @@ json_schema = {
         "name": {"type": "string"},
         "age": {"type": "number"},
         "is_student": {"type": "boolean"},
-        "courses": {
+        "courses": {"type": "array", "items": {"type": "string"}},
-            "type": "array",
+    },
-            "items": {"type": "string"}
-        }
-    }
 }
 
 # Defining a task

docs/swarms/agents/workeragent.md

@@ -38,7 +38,7 @@ worker = Worker(
     human_in_the_loop=False,
     temperature=0.5,
     llm=some_language_model,
-    openai_api_key="my_key"
+    openai_api_key="my_key",
 )
 worker.run("What's the weather in Miami?")
 ```
@@ -56,11 +56,11 @@ worker.send()
 ```python
 external_tools = [MyTool1(), MyTool2()]
 worker = Worker(
-name="My Worker",
+    name="My Worker",
-role="Worker",
+    role="Worker",
-external_tools=external_tools,
+    external_tools=external_tools,
-human_in_the_loop=False,
+    human_in_the_loop=False,
-temperature=0.5,
+    temperature=0.5,
 )
 ```
 

docs/swarms/chunkers/basechunker.md

@@ -69,7 +69,9 @@ from basechunker import BaseChunker, ChunkSeparator
 chunker = BaseChunker()
 
 # Text to be chunked
-input_text = "This is a long text that needs to be split into smaller chunks for processing."
+input_text = (
+    "This is a long text that needs to be split into smaller chunks for processing."
+)
 
 # Chunk the text
 chunks = chunker.chunk(input_text)

docs/swarms/chunkers/pdf_chunker.md

@@ -62,8 +62,8 @@ Let's explore how to use the `PdfChunker` class with different scenarios and app
 #### Example 1: Basic Chunking
 
 ```python
-from swarms.chunkers.pdf_chunker import PdfChunker
 from swarms.chunkers.chunk_seperator import ChunkSeparator
+from swarms.chunkers.pdf_chunker import PdfChunker
 
 # Initialize the PdfChunker
 pdf_chunker = PdfChunker()
@@ -82,8 +82,8 @@ for idx, chunk in enumerate(chunks, start=1):
 #### Example 2: Custom Separators
 
 ```python
-from swarms.chunkers.pdf_chunker import PdfChunker
 from swarms.chunkers.chunk_seperator import ChunkSeparator
+from swarms.chunkers.pdf_chunker import PdfChunker
 
 # Define custom separators for PDF chunking
 custom_separators = [ChunkSeparator("\n\n"), ChunkSeparator(". ")]

docs/swarms/index.md

@@ -28,7 +28,6 @@ We have a small gallery of examples to run here, [for more check out the docs to
 - Enterprise Grade + Production Grade: `Agent` is designed and optimized for automating real-world tasks at scale!
 
 ```python
-
 from swarms.models import OpenAIChat
 from swarms.structs import Agent
 
@@ -64,9 +63,6 @@ out = agent.run("Generate a 10,000 word blog on health and wellness.")
 # out = agent.print_history_and_memory()
 # # out = agent.save_state("flow_state.json")
 # print(out)
-
-
-
 ```
 
 ------
@@ -82,9 +78,7 @@ from swarms.structs import Agent
 from swarms.structs.sequential_workflow import SequentialWorkflow
 
 # Example usage
-api_key = (
+api_key = ""  # Your actual API key here
-    ""  # Your actual API key here
-)
 
 # Initialize the language agent
 llm = OpenAIChat(
@@ -118,7 +112,6 @@ workflow.run()
 # Output the results
 for task in workflow.tasks:
     print(f"Task: {task.description}, Result: {task.result}")
-
 ```
 
 ---

docs/swarms/memory/pg.md

@@ -110,7 +110,9 @@ def setup(
 
 ```python
 # Initialize the PgVectorVectorStore instance
-vector_store = PgVectorVectorStore(connection_string="your-db-connection-string", table_name="your-table-name")
+vector_store = PgVectorVectorStore(
+    connection_string="your-db-connection-string", table_name="your-table-name"
+)
 
 # Set up the database with default settings
 vector_store.setup()
@@ -120,10 +122,14 @@ vector_store.setup()
 
 ```python
 # Initialize the PgVectorVectorStore instance
-vector_store = PgVectorVectorStore(connection_string="your-db-connection-string", table_name="your-table-name")
+vector_store = PgVectorVectorStore(
+    connection_string="your-db-connection-string", table_name="your-table-name"
+)
 
 # Set up the database with customized settings
-vector_store.setup(create_schema=False, install_uuid_extension=True, install_vector_extension=True)
+vector_store.setup(
+    create_schema=False, install_uuid_extension=True, install_vector_extension=True
+)
 ```
 
 ### 4.2 Upserting Vectors <a name="upserting-vectors"></a>
@@ -137,7 +143,7 @@ def upsert_vector(
     vector_id: Optional[str] = None,
     namespace: Optional[str] = None,
     meta: Optional[dict] = None,
-    **kwargs
+    **kwargs,
 ) -> str:
     """
     Inserts or updates a vector in the collection.
@@ -158,7 +164,9 @@ def upsert_vector(
 
 ```python
 # Initialize the PgVectorVectorStore instance
-vector_store = PgVectorVectorStore(connection_string="your-db-connection-string", table_name="your-table-name")
+vector_store = PgVectorVectorStore(
+    connection_string="your-db-connection-string", table_name="your-table-name"
+)
 
 # Define a vector and upsert it
 vector = [0.1, 0.2, 0.3, 0.4]
@@ -167,10 +175,7 @@ namespace = "your-namespace"
 meta = {"key1": "value1", "key2": "value2"}
 
 vector_store.upsert_vector(
-    vector=vector,
+    vector=vector, vector_id=vector_id, namespace=namespace, meta=meta
-    vector_id=vector_id,
-    namespace=namespace,
-    meta=meta
 )
 ```
 
@@ -222,9 +227,7 @@ else:
 The `load_entries` method allows you to load all vector entries from the collection, optionally filtering by namespace.
 
 ```python
-def load_entries(
+def load_entries(self, namespace: Optional[str] = None) -> list[BaseVectorStore.Entry]:
-    self, namespace: Optional[str] = None
-) -> list[BaseVectorStore.Entry]:
     """
     Retrieves all vector entries from the collection, optionally filtering to only those that match the provided namespace.
 
@@ -240,7 +243,9 @@ def load_entries(
 
 ```python
 # Initialize the PgVectorVectorStore instance
-vector_store = PgVectorVectorStore(connection_string="your-db-connection-string", table_name="your-table-name")
+vector_store = PgVectorVectorStore(
+    connection_string="your-db-connection-string", table_name="your-table-name"
+)
 
 # Load all vector entries in the specified namespace
 entries = vector_store.load_entries(namespace="your-namespace")
@@ -266,7 +271,7 @@ def query(
     namespace: Optional[str] = None,
     include_vectors: bool = False,
     distance_metric: str = "cosine_distance",
-    **kwargs
+    **kwargs,
 ) -> list[BaseVectorStore.QueryResult]:
     """
     Performs a search on the collection to find vectors similar to the provided input vector,
@@ -290,7 +295,9 @@ def query(
 
 ```python
 # Initialize the PgVectorVectorStore instance
-vector_store = PgVectorVectorStore(connection_string="your-db-connection-string", table_name="your-table-name")
+vector_store = PgVectorVectorStore(
+    connection_string="your-db-connection-string", table_name="your-table-name"
+)
 
 # Perform a vector query
 query_string = "your-query-string"
@@ -304,7 +311,7 @@ results = vector_store.query(
     count=count,
     namespace=namespace,
     include_vectors=include_vectors,
-    distance_metric=distance_metric
+    distance_metric=distance_metric,
 )
 
 # Process the query results

docs/swarms/memory/pinecone.md

@@ -174,7 +174,7 @@ pv = PineconeVector(
     api_key="your-api-key",
     index_name="your-index-name",
     environment="us-west1-gcp",
-    project_name="your-project-name"
+    project_name="your-project-name",
 )
 ```
 
@@ -198,12 +198,7 @@ vector_id = "unique-vector-id"
 namespace = "your-namespace"
 meta = {"key1": "value1", "key2": "value2"}
 
-pv.upsert_vector(
+pv.upsert_vector(vector=vector, vector_id=vector_id, namespace=namespace, meta=meta)
-    vector=vector,
-    vector_id=vector_id,
-    namespace=namespace,
-    meta=meta
-)
 ```
 
 ### 4.4 Querying the Index <a name="querying-the-index"></a>
@@ -222,7 +217,7 @@ results = pv.query(
     count=count,
     namespace=namespace,
     include_vectors=include_vectors,
-    include_metadata=include_metadata
+    include_metadata=include_metadata,
 )
 
 # Process the query results

docs/swarms/memory/qdrant.md

@@ -14,8 +14,15 @@ pip install qdrant-client sentence-transformers httpx
 
 ```python
 class Qdrant:
-    def __init__(self, api_key: str, host: str, port: int = 6333, collection_name: str = "qdrant", model_name: str = "BAAI/bge-small-en-v1.5", https: bool = True):
+    def __init__(
-        ...
+        self,
+        api_key: str,
+        host: str,
+        port: int = 6333,
+        collection_name: str = "qdrant",
+        model_name: str = "BAAI/bge-small-en-v1.5",
+        https: bool = True,
+    ): ...
 ```
 
 ### Constructor Parameters
@@ -60,10 +67,7 @@ qdrant_client = Qdrant(api_key="your_api_key", host="localhost", port=6333)
 ### Example 2: Adding Vectors to a Collection
 
 ```python
-documents = [
+documents = [{"page_content": "Sample text 1"}, {"page_content": "Sample text 2"}]
-    {"page_content": "Sample text 1"},
-    {"page_content": "Sample text 2"}
-]
 
 operation_info = qdrant_client.add_vectors(documents)
 print(operation_info)

docs/swarms/memory/short_term_memory.md

@@ -125,7 +125,9 @@ def update_short_term(self, index, role: str, message: str, *args, **kwargs):
 
 ##### Example: Updating a Message in Short-Term Memory
 ```python
-memory.update_short_term(index=0, role="Updated Role", message="Updated message content.")
+memory.update_short_term(
+    index=0, role="Updated Role", message="Updated message content."
+)
 ```
 
 #### 7. `clear`

docs/swarms/memory/weaviate.md

@@ -82,7 +82,7 @@ weaviate_client.create_collection(
         {"name": "property1", "dataType": ["string"]},
         {"name": "property2", "dataType": ["int"]},
     ],
-    vectorizer_config=None  # Optional vectorizer configuration
+    vectorizer_config=None,  # Optional vectorizer configuration
 )
 ```
 
@@ -99,8 +99,7 @@ The `add` method allows you to add an object to a specified collection in Weavia
 
 ```python
 weaviate_client.add(
-    collection_name="my_collection",
+    collection_name="my_collection", properties={"property1": "value1", "property2": 42}
-    properties={"property1": "value1", "property2": 42}
 )
 ```
 
@@ -142,7 +141,7 @@ The `update` method allows you to update an object in a specified collection in
 weaviate_client.update(
     collection_name="my_collection",
     object_id="object123",
-    properties={"property1": "new_value", "property2": 99}
+    properties={"property1": "new_value", "property2": 99},
 )
 ```
 
@@ -158,10 +157,7 @@ The `delete` method allows you to delete an object from a specified collection i
 #### Usage
 
 ```python
-weaviate_client.delete(
+weaviate_client.delete(collection_name="my_collection", object_id="object123")
-    collection_name="my_collection",
-    object_id="object123"
-)
 ```
 
 ## Examples
@@ -175,28 +171,21 @@ weaviate_client.create_collection(
     name="people",
     properties=[
         {"name": "name", "dataType": ["string"]},
-        {"name": "age", "dataType": ["int"]}
+        {"name": "age", "dataType": ["int"]},
-    ]
+    ],
 )
 ```
 
 ### Example 2: Adding an Object
 
 ```python
-weaviate_client.add(
+weaviate_client.add(collection_name="people", properties={"name": "John", "age": 30})
-    collection_name="people",
-    properties={"name": "John", "age": 30}
-)
 ```
 
 ### Example 3: Querying Objects
 
 ```python
-results = weaviate_client.query(
+results = weaviate_client.query(collection_name="people", query="name:John", limit=5)
-    collection_name="people",
-    query="name:John",
-    limit=5
-)
 ```
 
 These examples cover the basic operations of creating collections, adding objects, and querying objects using the Weaviate API Client.

docs/swarms/models/anthropic.md

@@ -72,9 +72,7 @@ class Anthropic:
 from swarms.models import Anthropic
 
 # Initialize an instance of the Anthropic class
-model = Anthropic(
+model = Anthropic(anthropic_api_key="")
-    anthropic_api_key=""
-)
 
 # Using the run method
 completion_1 = model.run("What is the capital of France?")

docs/swarms/models/base_multimodal_model.md

@@ -149,7 +149,9 @@ model = BaseMultiModalModel(
 )
 
 # Run the model with a text task and an image URL
-response = model.run("Generate a summary of this text", "https://www.example.com/image.jpg")
+response = model.run(
+    "Generate a summary of this text", "https://www.example.com/image.jpg"
+)
 print(response)
 ```
 
@@ -209,6 +211,7 @@ for response in responses:
 ```python
 from swarms.models import BaseMultiModalModel
 
+
 class CustomMultiModalModel(BaseMultiModalModel):
     def __init__(self, model_name, custom_parameter, *args, **kwargs):
         # Call the parent class constructor
@@ -226,6 +229,7 @@ class CustomMultiModalModel(BaseMultiModalModel):
         # You can use self.custom_parameter and other inherited attributes
         pass
 
+
 # Create an instance of your custom multimodal model
 custom_model = CustomMultiModalModel(
     model_name="your_custom_model_name",
@@ -236,7 +240,9 @@ custom_model = CustomMultiModalModel(
 )
 
 # Run your custom model
-response = custom_model.run("Generate a summary of this text", "https://www.example.com/image.jpg")
+response = custom_model.run(
+    "Generate a summary of this text", "https://www.example.com/image.jpg"
+)
 print(response)
 
 # Generate a summary using your custom model

docs/swarms/models/bingchat.md

@@ -39,7 +39,6 @@ print(response)
 ```python
 from swarms.models.bing_chat import BingChat
 
-
 edgegpt = BingChat(cookies_path="./path/to/cookies.json")
 response = edgegpt("Hello, my name is ChatGPT")
 print(response)
@@ -48,7 +47,9 @@ print(response)
 3. Generate an image based on a text prompt:
 
 ```python
-image_path = edgegpt.create_img("Sunset over mountains", output_dir="./output", auth_cookie="your_auth_cookie")
+image_path = edgegpt.create_img(
+    "Sunset over mountains", output_dir="./output", auth_cookie="your_auth_cookie"
+)
 print(f"Generated image saved at {image_path}")
 ```
 
@@ -59,7 +60,9 @@ from swarms.models.bing_chat import BingChat
 
 edgegpt = BingChat(cookies_path="./path/to/cookies.json")
 
-image_path = edgegpt.create_img("Sunset over mountains", output_dir="./output", auth_cookie="your_auth_cookie")
+image_path = edgegpt.create_img(
+    "Sunset over mountains", output_dir="./output", auth_cookie="your_auth_cookie"
+)
 
 print(f"Generated image saved at {image_path}")
 ```

docs/swarms/models/biogpt.md

@@ -83,7 +83,6 @@ print(generated_text)
 ```python
 from swarms.models import BioGPT
 
-
 # Initialize the BioGPT model
 biogpt = BioGPT()
 
@@ -99,7 +98,6 @@ print(features)
 ```python
 from swarms.models import BioGPT
 
-
 # Initialize the BioGPT model
 biogpt = BioGPT()
 

docs/swarms/models/distilled_whisperx.md

@@ -29,7 +29,7 @@ from swarms.models import DistilWhisperModel
 model_wrapper = DistilWhisperModel()
 
 # Initialize with a specific model ID
-model_wrapper = DistilWhisperModel(model_id='distil-whisper/distil-large-v2')
+model_wrapper = DistilWhisperModel(model_id="distil-whisper/distil-large-v2")
 ```
 
 ## Attributes
@@ -62,7 +62,7 @@ Transcribes audio input synchronously.
 
 ```python
 # Synchronous transcription
-transcription = model_wrapper.transcribe('path/to/audio.mp3')
+transcription = model_wrapper.transcribe("path/to/audio.mp3")
 print(transcription)
 ```
 
@@ -84,7 +84,7 @@ Transcribes audio input asynchronously.
 import asyncio
 
 # Asynchronous transcription
-transcription = asyncio.run(model_wrapper.async_transcribe('path/to/audio.mp3'))
+transcription = asyncio.run(model_wrapper.async_transcribe("path/to/audio.mp3"))
 print(transcription)
 ```
 
@@ -103,7 +103,7 @@ Simulates real-time transcription of an audio file.
 
 ```python
 # Real-time transcription simulation
-model_wrapper.real_time_transcribe('path/to/audio.mp3', chunk_duration=5)
+model_wrapper.real_time_transcribe("path/to/audio.mp3", chunk_duration=5)
 ```
 
 ## Error Handling

docs/swarms/models/gpt4v.md

@@ -107,16 +107,16 @@ The `__call__` method is a convenient way to run the GPT-4 Vision model. It has
 ```python
 def __call__(task: str, img: str) -> str:
     """
-    Run the GPT-4 Vision model (callable).
+       Run the GPT-4 Vision model (callable).
 
-    Parameters:
+       Parameters:
-    - task (str): The task or question related to the image.
+       - task (str): The task or question related to the image.
-    - img
+       - img
 
- (str): URL of the image to analyze.
+    (str): URL of the image to analyze.
 
-    Returns:
+       Returns:
-    str: The model's response.
+       str: The model's response.
     """
 ```
 

docs/swarms/models/huggingface.md

@@ -114,9 +114,11 @@ from swarms.models import HuggingfaceLLM
 custom_config = {
     "quantize": True,
     "quantization_config": {"load_in_4bit": True},
-    "verbose": True
+    "verbose": True,
 }
-inference = HuggingfaceLLM(model_id="NousResearch/Nous-Hermes-2-Vision-Alpha", **custom_config)
+inference = HuggingfaceLLM(
+    model_id="NousResearch/Nous-Hermes-2-Vision-Alpha", **custom_config
+)
 
 # Generate text based on a prompt
 prompt_text = "Tell me a joke"

docs/swarms/models/idefics.md

@@ -36,7 +36,9 @@ model = Idefics()
 2. Generate text based on prompts:
 
 ```python
-prompts = ["User: What is in this image? https://upload.wikimedia.org/wikipedia/commons/8/86/Id%C3%A9fix.JPG"]
+prompts = [
+    "User: What is in this image? https://upload.wikimedia.org/wikipedia/commons/8/86/Id%C3%A9fix.JPG"
+]
 response = model(prompts)
 print(response)
 ```
@@ -47,7 +49,9 @@ print(response)
 from swarms.models import Idefics
 
 model = Idefics()
-prompts = ["User: What is in this image? https://upload.wikimedia.org/wikipedia/commons/8/86/Id%C3%A9fix.JPG"]
+prompts = [
+    "User: What is in this image? https://upload.wikimedia.org/wikipedia/commons/8/86/Id%C3%A9fix.JPG"
+]
 response = model(prompts)
 print(response)
 ```

docs/swarms/models/index.md

@@ -42,9 +42,10 @@ OpenAI(api_key: str, system: str = None, console: bool = True, model: str = None
 
 **Usage Example:**
 ```python
-from swarms import OpenAI
 import asyncio
 
+from swarms import OpenAI
+
 chat = OpenAI(api_key="YOUR_OPENAI_API_KEY")
 
 response = chat.generate("Hello, how can I assist you?")
@@ -126,7 +127,10 @@ GooglePalm(model_name: str = "models/chat-bison-001", google_api_key: str = None
 from swarms import GooglePalm
 
 google_palm = GooglePalm()
-messages = [{"role": "system", "content": "You are a helpful assistant"}, {"role": "user", "content": "Tell me a joke"}]
+messages = [
+    {"role": "system", "content": "You are a helpful assistant"},
+    {"role": "user", "content": "Tell me a joke"},
+]
 
 response = google_palm.generate(messages)
 print(response["choices"][0]["text"])

docs/swarms/models/kosmos.md

@@ -30,7 +30,9 @@ kosmos = Kosmos()
 2. Perform Multimodal Grounding:
 
 ```python
-kosmos.multimodal_grounding("Find the red apple in the image.", "https://example.com/apple.jpg")
+kosmos.multimodal_grounding(
+    "Find the red apple in the image.", "https://example.com/apple.jpg"
+)
 ```
 
 ### Example 1 - Multimodal Grounding
@@ -40,13 +42,17 @@ from swarms.models.kosmos_two import Kosmos
 
 kosmos = Kosmos()
 
-kosmos.multimodal_grounding("Find the red apple in the image.", "https://example.com/apple.jpg")
+kosmos.multimodal_grounding(
+    "Find the red apple in the image.", "https://example.com/apple.jpg"
+)
 ```
 
 3. Perform Referring Expression Comprehension:
 
 ```python
-kosmos.referring_expression_comprehension("Show me the green bottle.", "https://example.com/bottle.jpg")
+kosmos.referring_expression_comprehension(
+    "Show me the green bottle.", "https://example.com/bottle.jpg"
+)
 ```
 
 ### Example 2 - Referring Expression Comprehension
@@ -56,13 +62,17 @@ from swarms.models.kosmos_two import Kosmos
 
 kosmos = Kosmos()
 
-kosmos.referring_expression_comprehension("Show me the green bottle.", "https://example.com/bottle.jpg")
+kosmos.referring_expression_comprehension(
+    "Show me the green bottle.", "https://example.com/bottle.jpg"
+)
 ```
 
 4. Generate Referring Expressions:
 
 ```python
-kosmos.referring_expression_generation("It is on the table.", "https://example.com/table.jpg")
+kosmos.referring_expression_generation(
+    "It is on the table.", "https://example.com/table.jpg"
+)
 ```
 
 ### Example 3 - Referring Expression Generation
@@ -72,7 +82,9 @@ from swarms.models.kosmos_two import Kosmos
 
 kosmos = Kosmos()
 
-kosmos.referring_expression_generation("It is on the table.", "https://example.com/table.jpg")
+kosmos.referring_expression_generation(
+    "It is on the table.", "https://example.com/table.jpg"
+)
 ```
 
 5. Perform Grounded Visual Question Answering (VQA):
@@ -127,7 +139,10 @@ kosmos.grounded_image_captioning_detailed("https://example.com/beach.jpg")
 
 ```python
 image = kosmos.get_image("https://example.com/image.jpg")
-entities = [("apple", (0, 3), [(0.2, 0.3, 0.4, 0.5)]), ("banana", (4, 9), [(0.6, 0.2, 0.8, 0.4)])]
+entities = [
+    ("apple", (0, 3), [(0.2, 0.3, 0.4, 0.5)]),
+    ("banana", (4, 9), [(0.6, 0.2, 0.8, 0.4)]),
+]
 kosmos.draw_entity_boxes_on_image(image, entities, show=True)
 ```
 
@@ -139,24 +154,38 @@ from swarms.models.kosmos_two import Kosmos
 kosmos = Kosmos()
 
 image = kosmos.get_image("https://example.com/image.jpg")
-entities = [("apple", (0, 3), [(0.2, 0.3, 0.4, 0.5)]), ("banana", (4, 9), [(0.6, 0.2, 0.8, 0.4)])]
+entities = [
+    ("apple", (0, 3), [(0.2, 0.3, 0.4, 0.5)]),
+    ("banana", (4, 9), [(0.6, 0.2, 0.8, 0.4)]),
+]
 kosmos.draw_entity_boxes_on_image(image, entities, show=True)
 ```
 
 9. Generate Boxes for Entities:
 
 ```python
-entities = [("apple", (0, 3), [(0.2, 0.3, 0.4, 0.5)]), ("banana", (4, 9), [(0.6, 0.2, 0.8, 0.4)])]
+entities = [
-image = kosmos.generate_boxes("Find the apple and the banana in the image.", "https://example.com/image.jpg")
+    ("apple", (0, 3), [(0.2, 0.3, 0.4, 0.5)]),
+    ("banana", (4, 9), [(0.6, 0.2, 0.8, 0.4)]),
+]
+image = kosmos.generate_boxes(
+    "Find the apple and the banana in the image.", "https://example.com/image.jpg"
+)
 ```
 
 ### Example 8 - Generating Boxes for Entities
 
 ```python
 from swarms.models.kosmos_two import Kosmos
+
 kosmos = Kosmos()
-entities = [("apple", (0, 3), [(0.2, 0.3, 0.4, 0.5)]), ("banana", (4, 9), [(0.6, 0.2, 0.8, 0.4)])]
+entities = [
-image = kosmos.generate_boxes("Find the apple and the banana in the image.", "https://example.com/image.jpg")
+    ("apple", (0, 3), [(0.2, 0.3, 0.4, 0.5)]),
+    ("banana", (4, 9), [(0.6, 0.2, 0.8, 0.4)]),
+]
+image = kosmos.generate_boxes(
+    "Find the apple and the banana in the image.", "https://example.com/image.jpg"
+)
 ```
 
 ## How Kosmos Works

docs/swarms/models/mistral.md

@@ -150,7 +150,6 @@ Example:
 ```python
 from swarms.models import Mistral
 
-
 model = Mistral()
 task = "Translate the following English text to French: 'Hello, how are you?'"
 result = model.run(task)

docs/swarms/models/mpt.md

@@ -52,10 +52,10 @@ class MPT7B:
 from swarms.models import MPT7B
 
 # Initialize the MPT7B class
-mpt = MPT7B('mosaicml/mpt-7b-storywriter', 'EleutherAI/gpt-neox-20b', max_tokens=150)
+mpt = MPT7B("mosaicml/mpt-7b-storywriter", "EleutherAI/gpt-neox-20b", max_tokens=150)
 
 # Generate text
-output = mpt.run('generate', 'Once upon a time in a land far, far away...')
+output = mpt.run("generate", "Once upon a time in a land far, far away...")
 print(output)
 ```
 
@@ -77,13 +77,16 @@ print(outputs)
 
 ```python
 import asyncio
+
 from swarms.models import MPT7B
 
 # Initialize the MPT7B class
-mpt = MPT7B('mosaicml/mpt-7b-storywriter', 'EleutherAI/gpt-neox-20b', max_tokens=150)
+mpt = MPT7B("mosaicml/mpt-7b-storywriter", "EleutherAI/gpt-neox-20b", max_tokens=150)
 
 # Generate text asynchronously
-output = asyncio.run(mpt.run_async('generate', 'Once upon a time in a land far, far away...'))
+output = asyncio.run(
+    mpt.run_async("generate", "Once upon a time in a land far, far away...")
+)
 print(output)
 ```
 

docs/swarms/models/openai.md

@@ -168,7 +168,11 @@ prompt = "Translate the following English text to French: 'Hello, how are you?'"
 generated_text = openai.generate(prompt, max_tokens=50)
 
 # Generate text from multiple prompts
-prompts = ["Translate this: 'Good morning' to Spanish.", "Summarize the following article:", article_text]
+prompts = [
+    "Translate this: 'Good morning' to Spanish.",
+    "Summarize the following article:",
+    article_text,
+]
 generated_texts = openai.generate(prompts, max_tokens=100)
 
 # Generate text asynchronously
@@ -188,7 +192,7 @@ custom_options = {
     "max_tokens": 100,
     "top_p": 0.9,
     "frequency_penalty": 0.2,
-    "presence_penalty": 0.4
+    "presence_penalty": 0.4,
 }
 generated_text = openai.generate(prompt, **custom_options)
 ```

docs/swarms/models/openai_chat.md

@@ -150,7 +150,9 @@ user_message = "User: Tell me another joke."
 response = openai_chat.generate([user_message])
 
 # Print the generated response
-print(response[0][0].text)  # Output: "Assistant: Why don't scientists trust atoms? Because they make up everything!"
+print(
+    response[0][0].text
+)  # Output: "Assistant: Why don't scientists trust atoms? Because they make up everything!"
 ```
 
 ### Example 3: Asynchronous Generation
@@ -158,12 +160,14 @@ print(response[0][0].text)  # Output: "Assistant: Why don't scientists trust ato
 ```python
 import asyncio
 
+
 # Define an asynchronous function for generating responses
 async def generate_responses():
     user_message = "User: Tell me a fun fact."
     async for chunk in openai_chat.stream([user_message]):
         print(chunk.text)
 
+
 # Run the asynchronous generation function
 asyncio.run(generate_responses())
 ```

docs/swarms/models/vilt.md

@@ -26,20 +26,26 @@ To use the Vilt model, follow these steps:
 
 ```python
 from swarms.models import Vilt
+
 model = Vilt()
 ```
 
 2. Call the model with a text question and an image URL:
 
 ```python
-output = model("What is this image?", "http://images.cocodataset.org/val2017/000000039769.jpg")
+output = model(
+    "What is this image?", "http://images.cocodataset.org/val2017/000000039769.jpg"
+)
 ```
 
 ### Example 1 - Image Questioning
 
 ```python
 model = Vilt()
-output = model("What are the objects in this image?", "http://images.cocodataset.org/val2017/000000039769.jpg")
+output = model(
+    "What are the objects in this image?",
+    "http://images.cocodataset.org/val2017/000000039769.jpg",
+)
 print(output)
 ```
 
@@ -47,7 +53,10 @@ print(output)
 
 ```python
 model = Vilt()
-output = model("Describe the scene in this image.", "http://images.cocodataset.org/val2017/000000039769.jpg")
+output = model(
+    "Describe the scene in this image.",
+    "http://images.cocodataset.org/val2017/000000039769.jpg",
+)
 print(output)
 ```
 
@@ -55,7 +64,10 @@ print(output)
 
 ```python
 model = Vilt()
-output = model("Tell me more about the landmark in this image.", "http://images.cocodataset.org/val2017/000000039769.jpg")
+output = model(
+    "Tell me more about the landmark in this image.",
+    "http://images.cocodataset.org/val2017/000000039769.jpg",
+)
 print(output)
 ```
 

docs/swarms/models/vllm.md

@@ -63,7 +63,7 @@ custom_vllm = vLLM(
     trust_remote_code=True,
     revision="abc123",
     temperature=0.7,
-    top_p=0.8
+    top_p=0.8,
 )
 ```
 
@@ -108,7 +108,7 @@ custom_vllm = vLLM(
     trust_remote_code=True,
     revision="abc123",
     temperature=0.7,
-    top_p=0.8
+    top_p=0.8,
 )
 
 # Generate text with custom configuration
@@ -128,7 +128,7 @@ vllm = vLLM()
 tasks = [
     "Translate the following sentence to French: 'Hello, world!'",
     "Write a short story set in a futuristic world.",
-    "Summarize the main points of a news article about climate change."
+    "Summarize the main points of a news article about climate change.",
 ]
 
 for task in tasks:

docs/swarms/models/zephyr.md

@@ -45,6 +45,7 @@ To use the Zephyr model, follow these steps:
 
 ```python
 from swarms.models import Zephyr
+
 model = Zephyr(max_new_tokens=300, temperature=0.7, top_k=50, top_p=0.95)
 ```
 

docs/swarms/structs/abstractswarm.md

@@ -47,9 +47,11 @@ The `AbstractSwarm` class is an abstract base class that serves as the foundatio
 
 ```python
 from abc import ABC, abstractmethod
-from typing import Optional, List, Dict, Any
+from typing import List
+
 from swarms.swarms.base import AbstractWorker
 
+
 class AbstractSwarm(ABC):
     """
     Abstract class for swarm simulation architectures
@@ -58,12 +60,12 @@ class AbstractSwarm(ABC):
     ---------
     ...
     """
+
     # The class definition and constructor are provided here.
 
     @abstractmethod
     def __init__(self, workers: List["AbstractWorker"]):
         """Initialize the swarm with workers"""
-        pass
 
     # Other abstract methods are listed here.
 ```

docs/swarms/structs/agent.md

@@ -68,7 +68,9 @@ final_response = agent.run(initial_task)
 You can collect feedback during the conversation using the `provide_feedback` method:
 
 ```python
-agent.provide_feedback("Generate an SOP for new sales employees on the best cold sales practices")
+agent.provide_feedback(
+    "Generate an SOP for new sales employees on the best cold sales practices"
+)
 ```
 
 ### Stopping Condition
@@ -78,9 +80,11 @@ You can define a custom stopping condition using a function. For example, you ca
 ```python
 from swarms.structs import Agent
 
+
 def stop_when_repeats(response: str) -> bool:
     return "Stop" in response.lower()
 
+
 agent = Agent(llm=my_language_model, max_loops=5, stopping_condition=stop_when_repeats)
 ```
 
@@ -107,9 +111,9 @@ Here are three usage examples:
 ### Example 1: Simple Conversation
 
 ```python
-from swarms.structs import Agent
 # Select any Language model from the models folder
 from swarms.models import Mistral, OpenAIChat
+from swarms.structs import Agent
 
 llm = Mistral()
 # llm = OpenAIChat()
@@ -128,9 +132,11 @@ final_response = agent.run(initial_task)
 ```python
 from swarms.structs import Agent
 
+
 def stop_when_repeats(response: str) -> bool:
     return "Stop" in response.lower()
 
+
 agent = Agent(llm=llm, max_loops=5, stopping_condition=stop_when_repeats)
 ```
 

docs/swarms/structs/artifact.md

@@ -41,9 +41,7 @@ class Artifact(BaseModel):
     )
     relative_path: Optional[str] = Field(
         None,
-        description=(
+        description=("Relative path of the artifact in the agent's workspace"),
-            "Relative path of the artifact in the agent's workspace"
-        ),
         example="python/code/",
     )
 ```
@@ -64,7 +62,7 @@ from swarms.structs import Artifact
 artifact_instance = Artifact(
     artifact_id="b225e278-8b4c-4f99-a696-8facf19f0e56",
     file_name="main.py",
-    relative_path="python/code/"
+    relative_path="python/code/",
 )
 ```
 
@@ -85,8 +83,7 @@ If the `relative_path` attribute is not provided during artifact creation, it wi
 
 ```python
 artifact_instance_no_path = Artifact(
-    artifact_id="c280s347-9b7d-3c68-m337-7abvf50j23k",
+    artifact_id="c280s347-9b7d-3c68-m337-7abvf50j23k", file_name="script.js"
-    file_name="script.js"
 )
 
 print(artifact_instance_no_path.relative_path)

docs/swarms/structs/artifactupload.md

@@ -15,9 +15,7 @@ class ArtifactUpload(BaseModel):
     file: bytes = Field(..., description="File to upload")
     relative_path: Optional[str] = Field(
         None,
-        description=(
+        description=("Relative path of the artifact in the agent's workspace"),
-            "Relative path of the artifact in the agent's workspace"
-        ),
         example="python/code/",
     )
 ```
@@ -32,10 +30,12 @@ The `ArtifactUpload` class is used to create an instance of an artifact upload.
 from swarms.structs import ArtifactUpload
 
 # Uploading a file with no relative path
-upload_no_path = ArtifactUpload(file=b'example_file_contents')
+upload_no_path = ArtifactUpload(file=b"example_file_contents")
 
 # Uploading a file with a relative path
-upload_with_path = ArtifactUpload(file=b'example_file_contents', relative_path="python/code/")
+upload_with_path = ArtifactUpload(
+    file=b"example_file_contents", relative_path="python/code/"
+)
 ```
 
 In the above example, `upload_no_path` is an instance of `ArtifactUpload` with no specified `relative_path`, whereas `upload_with_path` is an instance of `ArtifactUpload` with the `relative_path` set to "python/code/".

docs/swarms/structs/autoscaler.md

@@ -36,7 +36,9 @@ Initializes the `AutoScaler` with a predefined number of agents and sets up conf
 ```python
 from swarms import AutoScaler
 
-scaler = AutoScaler(initial_agents=5, scale_up_factor=3, idle_threshold=0.1, busy_threshold=0.8)
+scaler = AutoScaler(
+    initial_agents=5, scale_up_factor=3, idle_threshold=0.1, busy_threshold=0.8
+)
 ```
 
 ---
@@ -140,7 +142,9 @@ scaler.start()
 from swarms import AutoScaler
 
 # Initialize the scaler
-auto_scaler = AutoScaler(initial_agents=15, scale_up_factor=2, idle_threshold=0.2, busy_threshold=0.7)
+auto_scaler = AutoScaler(
+    initial_agents=15, scale_up_factor=2, idle_threshold=0.2, busy_threshold=0.7
+)
 
 # Start the monitoring and task processing
 auto_scaler.start()
@@ -161,7 +165,6 @@ auto_scaler.start()
 
 for i in range(100):  # Adding tasks
     auto_scaler.add_task(f"Task {i}")
-
 ```
 
 

docs/swarms/structs/baseworkflow.md

@@ -13,19 +13,19 @@ Base class for workflows.
 
 Source Code:
 ```python
-   class BaseWorkflow(BaseStructure):
+class BaseWorkflow(BaseStructure):
-   """
+"""
-   Base class for workflows.
+Base class for workflows.
 
-    Attributes:
+ Attributes:
-        task_pool (list): A list to store tasks.
+     task_pool (list): A list to store tasks.
 
-    Methods:
+ Methods:
-        add(task: Task = None, tasks: List[Task] = None, *args, **kwargs):
+     add(task: Task = None, tasks: List[Task] = None, *args, **kwargs):
-            Adds a task or a list of tasks to the task pool.
+         Adds a task or a list of tasks to the task pool.
-        run():
+     run():
-            Abstract method to run the workflow.
+         Abstract method to run the workflow.
-   """
+"""
 ```
  
 For the usage examples and additional in-depth documentation please visit [BaseWorkflow](https://github.com/swarms-modules/structs/blob/main/baseworkflow.md#swarms-structs)

docs/swarms/structs/groupchatmanager.md

@@ -24,7 +24,7 @@ agents = Agent()
 manager = GroupChatManager(groupchat, selector)
 
 # Call the group chat manager passing a specific chat task
-result = manager('Discuss the agenda for the upcoming meeting')
+result = manager("Discuss the agenda for the upcoming meeting")
 ```
 
 Explanation:
@@ -67,9 +67,7 @@ class GroupChatManager:
         Returns:
             str: The response from the group chat.
         """
-        self.groupchat.messages.append(
+        self.groupchat.messages.append({"role": self.selector.name, "content": task})
-            {"role": self.selector.name, "content": task}
-        )
         for i in range(self.groupchat.max_round):
             speaker = self.groupchat.select_speaker(
                 last_speaker=self.selector, selector=self.selector

docs/swarms/structs/json.md

@@ -78,16 +78,17 @@ Suppose we have a JSON Schema in `config_schema.json` for application configurat
 Now we'll create a subclass `AppConfig` that uses this schema.
 
 ```python
-import json
 from swarms.structs import JSON
 
+
 class AppConfig(JSON):
     def __init__(self, schema_path):
         super().__init__(schema_path)
 
     def validate(self, config_data):
         # Here we'll use a JSON Schema validation library like jsonschema
-        from jsonschema import validate, ValidationError
+        from jsonschema import ValidationError, validate
+
         try:
             validate(instance=config_data, schema=self.schema)
         except ValidationError as e:
@@ -95,15 +96,13 @@ class AppConfig(JSON):
             return False
         return True
 
+
 # Main Example Usage
 
 if __name__ == "__main__":
-    config = {
+    config = {"debug": True, "window_size": [800, 600]}
-        "debug": True,
-        "window_size": [800, 600]
-    }
 
-    app_config = AppConfig('config_schema.json')
+    app_config = AppConfig("config_schema.json")
 
     if app_config.validate(config):
         print("Config is valid!")

docs/swarms/structs/majorityvoting.md

@@ -82,9 +82,11 @@ Executes the given task by all participating agents and aggregates the results t
 from swarms.structs.agent import Agent
 from swarms.structs.majority_voting import MajorityVoting
 
+
 def create_agent(name):
     return Agent(name)
 
+
 agents = [create_agent(name) for name in ["GPT-3", "Codex", "Tabnine"]]
 majority_voting = MajorityVoting(agents)
 result = majority_voting.run("What is the capital of France?")

docs/swarms/structs/nonlinearworkflow.md

@@ -60,7 +60,7 @@ task3 = Task(llm, "Find a hotel in Paris")
 # Initialize the NonlinearWorkflow
 workflow = NonlinearWorkflow()
 # Add tasks to the workflow with dependencies
-workflow.add(task1, task2.name) 
+workflow.add(task1, task2.name)
 workflow.add(task2, task3.name)
 workflow.add(task3, "OpenAIChat Initialization")
 # Execute the workflow
@@ -82,7 +82,7 @@ task3 = Task(llm, "Find a hotel in Paris")
 # Initialize the NonlinearWorkflow
 workflow = NonlinearWorkflow()
 # Add tasks to the workflow with dependencies
-workflow.add(task1) 
+workflow.add(task1)
 workflow.add(task2, task1.name)
 workflow.add(task3, task1.name, task2.name)
 # Execute the workflow

docs/swarms/structs/sequential_workflow.md

@@ -310,9 +310,7 @@ from swarms.structs import Agent
 from swarms.structs.sequential_workflow import SequentialWorkflow
 
 # Example usage
-api_key = (
+api_key = ""  # Your actual API key here
-    ""  # Your actual API key here
-)
 
 # Initialize the language agent
 llm = OpenAIChat(
@@ -350,9 +348,7 @@ from swarms.structs import Agent
 from swarms.structs.sequential_workflow import SequentialWorkflow
 
 # Example usage
-api_key = (
+api_key = ""  # Your actual API key here
-    ""  # Your actual API key here
-)
 
 # Initialize the language agent
 llm = OpenAIChat(
@@ -393,9 +389,7 @@ from swarms.structs import Agent
 from swarms.structs.sequential_workflow import SequentialWorkflow
 
 # Example usage
-api_key = (
+api_key = ""  # Your actual API key here
-    ""  # Your actual API key here
-)
 
 # Initialize the language agent
 llm = OpenAIChat(
@@ -436,9 +430,7 @@ from swarms.structs import Agent
 from swarms.structs.sequential_workflow import SequentialWorkflow
 
 # Example usage
-api_key = (
+api_key = ""  # Your actual API key here
-    ""  # Your actual API key here
-)
 
 # Initialize the language agent
 llm = OpenAIChat(

docs/swarms/structs/stackoverflowswarm.md

@@ -58,11 +58,13 @@ The design of the `StackOverflowSwarm` class is intended to allow easy tracking
 from swarms.structs.agent import Agent
 from swarms.structs.stack_overflow_swarm import StackOverflowSwarm
 
+
 # Define custom Agents with some logic (placeholder for actual Agent implementation)
 class CustomAgent(Agent):
     def run(self, conversation, *args, **kwargs):
         return "This is a response from CustomAgent."
 
+
 # Initialize agents
 agent1 = CustomAgent(ai_name="Agent1")
 agent2 = CustomAgent(ai_name="Agent2")

docs/swarms/structs/stepinput.md

@@ -12,10 +12,7 @@ The `StepInput` class is defined as follows:
 class StepInput(BaseModel):
     __root__: Any = Field(
         ...,
-        description=(
+        description=("Input parameters for the task step. Any value is" " allowed."),
-            "Input parameters for the task step. Any value is"
-            " allowed."
-        ),
         example='{\n"file_to_refactor": "models.py"\n}',
     )
 ```
@@ -29,10 +26,7 @@ The `StepInput` class is designed to accept any input value, providing flexibili
 ```python
 from swarms.structs import StepInput
 
-input_params = {
+input_params = {"file_to_refactor": "models.py", "refactor_method": "code"}
-    "file_to_refactor": "models.py",
-    "refactor_method": "code"
-}
 step_input = StepInput(__root__=input_params)
 ```
 
@@ -42,10 +36,7 @@ In this example, we import the `StepInput` class from the `swarms.structs` libra
 ```python
 from swarms.structs import StepInput
 
-input_params = {
+input_params = {"input_path": "data.csv", "output_path": "result.csv"}
-    "input_path": "data.csv",
-    "output_path": "result.csv"
-}
 step_input = StepInput(__root__=input_params)
 ```
 
@@ -56,7 +47,7 @@ In this example, we again create an instance of `StepInput` by passing a diction
 from swarms.structs import StepInput
 
 file_path = "config.json"
-with open(file_path, 'r') as f:
+with open(file_path) as f:
     input_data = json.load(f)
 
 step_input = StepInput(__root__=input_data)

docs/swarms/structs/swarmnetwork.md

@@ -28,6 +28,7 @@ The `SwarmNetwork` class has the following parameters:
   ```python
   from swarms.structs.agent import Agent
   from swarms.structs.swarm_net import SwarmNetwork
+
   agent = Agent()
   swarm = SwarmNetwork(agents=[agent])
   swarm.add_task("task")
@@ -41,6 +42,7 @@ The `SwarmNetwork` class has the following parameters:
   ```python
   from swarms.structs.agent import Agent
   from swarms.structs.swarm_net import SwarmNetwork
+
   agent = Agent()
   swarm = SwarmNetwork(agents=[agent])
   await swarm.async_add_task("task")
@@ -57,6 +59,7 @@ The `SwarmNetwork` class has the following parameters:
   ```python
   from swarms.structs.agent import Agent
   from swarms.structs.swarm_net import SwarmNetwork
+
   agent = Agent()
   swarm = SwarmNetwork(agents=[agent])
   swarm.run_single_agent(agent_id, "task")
@@ -72,6 +75,7 @@ The `SwarmNetwork` class has the following parameters:
   ```python
   from swarms.structs.agent import Agent
   from swarms.structs.swarm_net import SwarmNetwork
+
   agent = Agent()
   swarm = SwarmNetwork(agents=[agent])
   swarm.run_many_agents("task")
@@ -85,6 +89,7 @@ The `SwarmNetwork` class has the following parameters:
   ```python
   from swarms.structs.agent import Agent
   from swarms.structs.swarm_net import SwarmNetwork
+
   agent = Agent()
   swarm = SwarmNetwork(agents=[agent])
   swarm.list_agents()
@@ -98,6 +103,7 @@ The `SwarmNetwork` class has the following parameters:
   ```python
   from swarms.structs.agent import Agent
   from swarms.structs.swarm_net import SwarmNetwork
+
   agent = Agent()
   swarm = SwarmNetwork()
   swarm.add_agent(agent)
@@ -111,6 +117,7 @@ The `SwarmNetwork` class has the following parameters:
   ```python
   from swarms.structs.agent import Agent
   from swarms.structs.swarm_net import SwarmNetwork
+
   agent = Agent()
   swarm = SwarmNetwork(agents=[agent])
   swarm.remove_agent(agent_id)
@@ -124,6 +131,7 @@ The `SwarmNetwork` class has the following parameters:
   ```python
   from swarms.structs.agent import Agent
   from swarms.structs.swarm_net import SwarmNetwork
+
   swarm = SwarmNetwork()
   swarm.scale_up(num_agents=5)
   ```
@@ -136,6 +144,7 @@ The `SwarmNetwork` class has the following parameters:
   ```python
   from swarms.structs.agent import Agent
   from swarms.structs.swarm_net import SwarmNetwork
+
   swarm = SwarmNetwork(agents=[agent1, agent2, agent3, agent4, agent5])
   swarm.scale_down(num_agents=2)
   ```
@@ -146,6 +155,7 @@ The `SwarmNetwork` class has the following parameters:
   ```python
   from swarms.structs.agent import Agent
   from swarms.structs.swarm_net import SwarmNetwork
+
   agent = Agent()
   swarm = SwarmNetwork(agents=[agent])
   swarm.create_apis_for_agents()

docs/swarms/structs/task.md

@@ -8,8 +8,9 @@
 
 ```python
 # Example 1: Creating and executing a Task
-from swarms.structs import Task, Agent
 from swarms.models import OpenAIChat
+from swarms.structs import Agent, Task
+
 agent = Agent(llm=OpenAIChat(openai_api_key=""), max_loops=1, dashboard=False)
 task = Task(agent=agent)
 task.execute("What's the weather in miami")

docs/swarms/structs/taskinput.md

@@ -20,11 +20,14 @@ The `TaskInput` class encapsulates the input parameters in a structured format.
 #### Usage Example 1: Using TaskInput for Debugging
 ```python
 from pydantic import BaseModel, Field
+
 from swarms.structs import TaskInput
 
+
 class DebugInput(TaskInput):
     debug: bool
 
+
 # Creating an instance of DebugInput
 debug_params = DebugInput(__root__={"debug": True})
 
@@ -35,11 +38,14 @@ print(debug_params.debug)  # Output: True
 #### Usage Example 2: Using TaskInput for Task Modes
 ```python
 from pydantic import BaseModel, Field
+
 from swarms.structs import TaskInput
 
+
 class ModeInput(TaskInput):
     mode: str
 
+
 # Creating an instance of ModeInput
 mode_params = ModeInput(__root__={"mode": "benchmarks"})
 
@@ -50,12 +56,15 @@ print(mode_params.mode)  # Output: benchmarks
 #### Usage Example 3: Using TaskInput with Arbitrary Parameters
 ```python
 from pydantic import BaseModel, Field
+
 from swarms.structs import TaskInput
 
+
 class ArbitraryInput(TaskInput):
     message: str
     quantity: int
 
+
 # Creating an instance of ArbitraryInput
 arbitrary_params = ArbitraryInput(__root__={"message": "Hello, world!", "quantity": 5})
 

docs/swarms/structs/taskqueuebase.md

@@ -7,13 +7,14 @@ The `swarms.structs` library is a key component of a multi-agent system's task m
 ## TaskQueueBase Class
 
 ```python
-from abc import ABC, abstractmethod
 import threading
+from abc import ABC, abstractmethod
 
 # Include any additional imports that are relevant to decorators and other classes such as Task and Agent if needed
 
 # Definition of the synchronized_queue decorator (if necessary)
 
+
 class TaskQueueBase(ABC):
     def __init__(self):
         self.lock = threading.Lock()
@@ -27,12 +28,12 @@ class TaskQueueBase(ABC):
     @abstractmethod
     def get_task(self, agent: Agent) -> Task:
         pass
-    
+
     @synchronized_queue
     @abstractmethod
     def complete_task(self, task_id: str):
         pass
-    
+
     @synchronized_queue
     @abstractmethod
     def reset_task(self, task_id: str):
@@ -65,11 +66,12 @@ Below are three examples of how the `TaskQueueBase` class can be implemented and
 
 ```python
 # file: basic_queue.py
-import threading
-from swarms.structs import TaskQueueBase, Task, Agent
 
 # Assume synchronized_queue decorator is defined elsewhere
-from decorators import synchronized_queue 
+from decorators import synchronized_queue
+
+from swarms.structs import Agent, Task, TaskQueueBase
+
 
 class BasicTaskQueue(TaskQueueBase):
     def __init__(self):
@@ -95,6 +97,7 @@ class BasicTaskQueue(TaskQueueBase):
         # Logic to reset the task
         pass
 
+
 # Usage
 queue = BasicTaskQueue()
 # Add task, assuming Task object is created

docs/swarms/tokenizers/basetokenizer.md

@@ -25,6 +25,7 @@ The `BaseTokenizer` class provides the structure for creating tokenizers. It inc
 ```python
 from swarms.tokenizers import BaseTokenizer
 
+
 class SimpleTokenizer(BaseTokenizer):
 
     def count_tokens(self, text: Union[str, List[dict]]) -> int:
@@ -33,10 +34,11 @@ class SimpleTokenizer(BaseTokenizer):
             return len(text.split())
         elif isinstance(text, list):
             # Assume list of dictionaries with 'token' key
-            return sum(len(item['token'].split()) for item in text)
+            return sum(len(item["token"].split()) for item in text)
         else:
             raise TypeError("Unsupported type for text")
 
+
 # Usage example
 tokenizer = SimpleTokenizer(max_tokens=100)
 text = "This is an example sentence to tokenize."

docs/swarms/tokenizers/coheretokenizer.md

@@ -57,7 +57,7 @@ def count_tokens(self, text: str | list) -> int:
 
     Args:
         text (str | list): The input text to tokenize.
-        
+
     Returns:
         int: The number of tokens in the text.
 
@@ -82,13 +82,14 @@ First, the Cohere client must be initialized and passed in to create an instance
 
 ```python
 from cohere import Client
+
 from swarms.tokenizers import CohereTokenizer
 
 # Initialize Cohere client with your API key
-cohere_client = Client('your-api-key')
+cohere_client = Client("your-api-key")
 
 # Instantiate the tokenizer
-tokenizer = CohereTokenizer(model='your-model-name', client=cohere_client)
+tokenizer = CohereTokenizer(model="your-model-name", client=cohere_client)
 ```
 
 ### Count Tokens Example 1

docs/swarms/tokenizers/huggingfacetokenizer.md

@@ -76,7 +76,7 @@ Tokenizes given text when the object is called like a function.
 from swarms.tokenizers import HuggingFaceTokenizer
 
 # Initialize the tokenizer with the path to your tokenizer model.
-tokenizer = HuggingFaceTokenizer('/path/to/your/model_dir')
+tokenizer = HuggingFaceTokenizer("/path/to/your/model_dir")
 ```
 
 ### 2. Encoding Text

docs/swarms/tokenizers/openaitokenizer.md

@@ -50,7 +50,7 @@ Given the extensive nature of this class, several examples are provided for each
 ```python
 from swarms.tokenizers import OpenAITokenizer
 
-tokenizer = OpenAITokenizer(model='gpt-4')
+tokenizer = OpenAITokenizer(model="gpt-4")
 ```
 
 This example creates a new instance of `OpenAITokenizer` set to work with the GPT-4 model.
@@ -61,7 +61,7 @@ This example creates a new instance of `OpenAITokenizer` set to work with the GP
 text = "Hello, this is an example text to tokenize."
 
 # Initialize the tokenizer
-tokenizer = OpenAITokenizer(model='gpt-4')
+tokenizer = OpenAITokenizer(model="gpt-4")
 
 # Count tokens
 num_tokens = tokenizer.count_tokens(text)
@@ -78,7 +78,7 @@ messages = [
     {"name": "Bob", "message": "I'm good! Just working on some code."},
 ]
 
-tokenizer = OpenAITokenizer(model='gpt-3.5-turbo')
+tokenizer = OpenAITokenizer(model="gpt-3.5-turbo")
 
 # Count tokens for a list of messages
 num_tokens = tokenizer.len(messages, model="gpt-3.5-turbo-0613")

docs/swarms/tokenizers/sentencepiecetokenizer.md

@@ -14,7 +14,7 @@ In `SentencePieceTokenizer`, the tokenization process is language-agnostic and e
 class SentencePieceTokenizer:
     """
     Tokenizer of sentencepiece.
-    
+
     Args:
         model_file (str): the path of the tokenizer model
     """
@@ -45,7 +45,7 @@ Parameter | Type | Description
 ```python
 from swarms.tokenizers import SentencePieceTokenizer
 
-tokenizer = SentencePieceTokenizer(model_file='your_model.model')
+tokenizer = SentencePieceTokenizer(model_file="your_model.model")
 ```
 
 ### Properties: Vocabulary Information

docs/swarms/utils/check_device.md

@@ -36,16 +36,18 @@ This function does not take any mandatory argument. However, it supports optiona
 ### Example 1: Basic Usage 
 
 ```python
-import torch
 import logging
+
+import torch
+
 from swarms.utils import check_device
 
 # Basic usage
 device = check_device(
-            log_level=logging.INFO,
+    log_level=logging.INFO,
-            memory_threshold=0.8,
+    memory_threshold=0.8,
-            capability_threshold=3.5,
+    capability_threshold=3.5,
-            return_type="list"
+    return_type="list",
 )
 ```
 
@@ -53,24 +55,24 @@ device = check_device(
 
 ```python
 import torch
-import logging
+
 from swarms.utils import check_device
 
 # When CUDA is not available
 device = check_device()
-print(device) # If CUDA is not available it should return torch.device('cpu')
+print(device)  # If CUDA is not available it should return torch.device('cpu')
 ```
 
 ### Example 3: Multiple GPU Available
 
 ```python
 import torch
-import logging
+
 from swarms.utils import check_device
 
 # When multiple GPUs are available
 device = check_device()
-print(device) # Should return a list of available GPU devices
+print(device)  # Should return a list of available GPU devices
 ```
 
 ## Tips and Additional Information

docs/swarms/utils/extract_code_from_markdown.md

@@ -57,14 +57,13 @@ Below are three examples of how you might use this function:
 Extracting code blocks from a simple markdown string.
 
 ```python
-import re
 from swarms.utils import extract_code_from_markdown
 
-markdown_string = '''# Example
+markdown_string = """# Example
 This is an example of a code block:
 ```python
 print("Hello World!")
-``` '''
+``` """
 print(extract_code_from_markdown(markdown_string))
 ```
 
@@ -75,13 +74,15 @@ Extracting code blocks from a markdown file.
 ```python
 import re
 
+
 def extract_code_from_markdown(markdown_content: str) -> str:
     pattern = r"```(?:\w+\n)?(.*?)```"
     matches = re.findall(pattern, markdown_content, re.DOTALL)
     return "\n".join(code.strip() for code in matches)
 
+
 # Assume that 'example.md' contains multiple code blocks
-with open('example.md', 'r') as file:
+with open("example.md") as file:
     markdown_content = file.read()
 print(extract_code_from_markdown(markdown_content))
 ```
@@ -93,17 +94,20 @@ Using the function in a pipeline to extract and then analyze code blocks.
 ```python
 import re
 
+
 def extract_code_from_markdown(markdown_content: str) -> str:
     pattern = r"```(?:\w+\n)?(.*?)```"
     matches = re.findall(pattern, markdown_content, re.DOTALL)
     return "\n".join(code.strip() for code in matches)
 
+
 def analyze_code_blocks(code: str):
     # Add your analysis logic here
-    pass 
+    pass
+
 
 # Assume that 'example.md' contains multiple code blocks
-with open('example.md', 'r') as file:
+with open("example.md") as file:
     markdown_content = file.read()
 code_blocks = extract_code_from_markdown(markdown_content)
 analyze_code_blocks(code_blocks)

docs/swarms/utils/find_image_path.md

@@ -40,15 +40,9 @@ The function `find_image_path` performs text parsing and pattern recognition to
 ```python
 def find_image_path(text):
     pattern = r"([A-Za-z]:\\[^:\n]*?\.(png|jpg|jpeg|PNG|JPG|JPEG))|(/[^:\n]*?\.(png|jpg|jpeg|PNG|JPG|JPEG))"
-    matches = [
+    matches = [match.group() for match in re.finditer(pattern, text) if match.group()]
-        match.group()
-        for match in re.finditer(pattern, text)
-        if match.group()
-    ]
     matches += [match.replace("\\", "") for match in matches if match]
-    existing_paths = [
+    existing_paths = [match for match in matches if os.path.exists(match)]
-        match for match in matches if os.path.exists(match)
-    ]
     return max(existing_paths, key=len) if existing_paths else None
 ```
 
@@ -75,7 +69,9 @@ Consider the case where the text has multiple image paths.
 from swarms.utils import find_image_path
 
 text = "Here is an image path: /home/user/image1.png. Here is another one: C:\\Users\\User\\Documents\\image2.jpeg"
-print(find_image_path(text))  # Outputs: the longest image path (depends on your file system and existing files)
+print(
+    find_image_path(text)
+)  # Outputs: the longest image path (depends on your file system and existing files)
 ```
 
 **Example 3:**

docs/swarms/utils/limit_tokens_from_string.md

@@ -73,7 +73,7 @@ from swarms.utils import limit_tokens_from_string
 string = "In case the method does not find the specified model, it will fall back to gpt2 model."
 
 # model
-model = "gpt-4" 
+model = "gpt-4"
 
 output = limit_tokens_from_string(string, model=model)
 ```

docs/swarms/utils/load_model_torch.md

@@ -50,12 +50,14 @@ This function can be used directly inside your code as shown in the following ex
 Loading a model without specifying a device results in the function choosing the most optimal available device automatically.
 
 ```python
-from swarms.utils import load_model_torch
 import torch.nn as nn
 
+from swarms.utils import load_model_torch
+
 # Assume `mymodel.pth` is in the current directory
 model_path = "./mymodel.pth"
 
+
 # Define your model architecture if the model file only contains state dict
 class MyModel(nn.Module):
     def __init__(self):
@@ -65,6 +67,7 @@ class MyModel(nn.Module):
     def forward(self, x):
         return self.linear(x)
 
+
 model = MyModel()
 
 # Load the model

docs/swarms/utils/math_eval.md

@@ -15,6 +15,8 @@ Let's say you have two functions: `ground_truth` and `generated_func`, that have
 @math_eval(ground_truth, generated_func)
 def test_func(x):
     return x
+
+
 result1, result2 = test_func(5)
 print(f"Result from ground_truth: {result1}")
 print(f"Result from generated_func: {result2}")
@@ -46,6 +48,7 @@ Here's how to implement the `math_eval` decorator:
 import functools
 import logging
 
+
 def math_eval(func1, func2):
     """Math evaluation decorator."""
 
@@ -65,9 +68,7 @@ def math_eval(func1, func2):
                 result2 = None
 
             if result1 != result2:
-                logging.warning(
+                logging.warning(f"Outputs do not match: {result1} != {result2}")
-                    f"Outputs do not match: {result1} != {result2}"
-                )
 
             return result1, result2
 

docs/swarms/utils/metrics_decorator.md

@@ -70,6 +70,7 @@ def text_generator(self, text: str):
     # language generation implementation goes here
     return tokens
 
+
 # Instantiate the class and call the decorated function
 obj = ClassName()
 obj.text_generator("Hello, world!")

docs/swarms/utils/pdf_to_text.md

@@ -54,7 +54,7 @@ Here is an example of how to use `pdf_to_text`:
 
 ```python
 # Define the path to the pdf file
-pdf_path = 'sample.pdf'
+pdf_path = "sample.pdf"
 
 # Use the function to extract text
 text = pdf_to_text(pdf_path)

docs/swarms/utils/prep_torch_inference.md

@@ -56,7 +56,8 @@ Here are some examples of how you can use the `prep_torch_inference` method. Bef
 
 ```python
 import torch
-from swarms.utils import prep_torch_inference, load_model_torch
+
+from swarms.utils import load_model_torch, prep_torch_inference
 ```
 
 ### Example 1: Load a model for inference on CPU

docs/swarms/utils/print_class_parameters.md

@@ -94,16 +94,16 @@ def print_class_parameters(cls, api_format: bool = False):
         if api_format:
             param_dict = {}
             for name, param in params.items():
-              if name == "self":
+                if name == "self":
-                continue
+                    continue
-              param_dict[name] = str(param.annotation)
+                param_dict[name] = str(param.annotation)
             return param_dict
 
         # Print the parameters
         for name, param in params.items():
-          if name == "self":
+            if name == "self":
-            continue
+                continue
-          print(f"Parameter: {name}, Type: {param.annotation}")
+            print(f"Parameter: {name}, Type: {param.annotation}")
 
     except Exception as e:
         print(f"An error occurred while inspecting the class: {e}")

docs/swarms/workers/base.md

@@ -37,43 +37,46 @@ class AbstractWorker:
         Args:
             name (str): Name of the worker.
         """
-    
+
     @property
     def name(self):
         """Get the name of the worker."""
-        pass
 
     def run(self, task: str):
         """Run the worker agent once."""
-        pass
 
-    def send(self, message: Union[Dict, str], recipient, request_reply: Optional[bool] = None):
+    def send(
+        self, message: Union[Dict, str], recipient, request_reply: Optional[bool] = None
+    ):
         """Send a message to another worker."""
-        pass
 
-    async def a_send(self, message: Union[Dict, str], recipient, request_reply: Optional[bool] = None):
+    async def a_send(
+        self, message: Union[Dict, str], recipient, request_reply: Optional[bool] = None
+    ):
         """Send a message to another worker asynchronously."""
-        pass
 
-    def receive(self, message: Union[Dict, str], sender, request_reply: Optional[bool] = None):
+    def receive(
+        self, message: Union[Dict, str], sender, request_reply: Optional[bool] = None
+    ):
         """Receive a message from another worker."""
-        pass
 
-    async def a_receive(self, message: Union[Dict, str], sender, request_reply: Optional[bool] = None):
+    async def a_receive(
+        self, message: Union[Dict, str], sender, request_reply: Optional[bool] = None
+    ):
         """Receive a message from another worker asynchronously."""
-        pass
 
     def reset(self):
         """Reset the worker."""
-        pass
 
-    def generate_reply(self, messages: Optional[List[Dict]] = None, sender=None, **kwargs) -> Union[str, Dict, None]:
+    def generate_reply(
+        self, messages: Optional[List[Dict]] = None, sender=None, **kwargs
+    ) -> Union[str, Dict, None]:
         """Generate a reply based on received messages."""
-        pass
 
-    async def a_generate_reply(self, messages: Optional[List[Dict]] = None, sender=None, **kwargs) -> Union[str, Dict, None]:
+    async def a_generate_reply(
+        self, messages: Optional[List[Dict]] = None, sender=None, **kwargs
+    ) -> Union[str, Dict, None]:
         """Generate a reply based on received messages asynchronously."""
-        pass
 ```
 
 ### 2.2 Attributes <a name="attributes"></a>
@@ -121,6 +124,7 @@ class MyWorker(AbstractWorker):
     def run(self, task: str):
         print(f"{self.name} is performing task: {task}")
 
+
 worker = MyWorker("Worker1")
 worker.run("Collect data")
 ```
@@ -155,6 +159,7 @@ The `a_send()` method is an asynchronous version of the `send()` method, allowin
 ```python
 import asyncio
 
+
 async def main():
     worker1 = AbstractWorker("Worker1")
     worker2 = AbstractWorker("Worker2")
@@ -162,6 +167,7 @@ async def main():
     message = "Hello, Worker2!"
     await worker1.a_send(message, worker2)
 
+
 loop = asyncio.get_event_loop()
 loop.run_until_complete(main())
 ```
@@ -208,6 +214,7 @@ The `a_receive()` method is an asynchronous version of the `receive()` method, a
 ```python
 import asyncio
 
+
 async def main():
     worker1 = AbstractWorker("Worker1")
     worker2 = AbstractWorker("Worker2")
@@ -218,6 +225,7 @@ async def main():
     await worker1.a_receive(message1, worker2)
     await worker1.a_receive(message2, worker2)
 
+
 loop = asyncio.get_event_loop()
 loop.run_until_complete(main())
 ```
@@ -233,6 +241,7 @@ class MyWorker(AbstractWorker):
     def reset(self):
         print(f"{self.name} has been reset.")
 
+
 worker = MyWorker("Worker1")
 worker.reset()
 ```
@@ -253,13 +262,16 @@ The `generate_reply()` method is a placeholder for generating a reply based on r
 
 ```python
 class MyWorker(AbstractWorker):
-    def generate_reply(self, messages: Optional[List[Dict]] = None, sender=None, **kwargs) -> Union[str, Dict, None]:
+    def generate_reply(
+        self, messages: Optional[List[Dict]] = None, sender=None, **kwargs
+    ) -> Union[str, Dict, None]:
         if messages:
             # Generate a reply based on received messages
             return f"Received {len(messages)} messages from {sender.name}."
         else:
             return None
 
+
 worker1 = MyWorker("Worker1")
 worker2 = MyWorker("Worker2")
 
@@ -284,6 +296,7 @@ The `a_generate_reply()` method is an asynchronous version of the `generate_repl
 ```python
 import asyncio
 
+
 async def main():
     worker1 = AbstractWorker("Worker1")
     worker2 = AbstractWorker("Worker2")
@@ -294,6 +307,7 @@ async def main():
     if reply:
         print(f"{worker2.name} generated a reply: {reply}")
 
+
 loop = asyncio.get_event_loop()
 loop.run_until_complete(main())
 ```
@@ -312,12 +326,16 @@ Start by creating a custom worker class that inherits from `AbstractWorker`. Def
 class CustomWorker(AbstractWorker):
     def run(self, task: str):
         print(f"{self.name} is performing task: {task}")
-    
+
-    def receive(self, message: Union[Dict, str], sender, request_reply: Optional[bool] = None):
+    def receive(
+        self, message: Union[Dict, str], sender, request_reply: Optional[bool] = None
+    ):
         if isinstance(message, str):
             print(f"{self.name} received a text message from {sender.name}: {message}")
         elif isinstance(message, dict):
-            print(f"{self.name} received a dictionary message from {sender.name}: {message}")
+            print(
+                f"{self.name} received a dictionary message from {sender.name}: {message}"
+            )
 ```
 
 ### Step 2: Create Custom Worker Instances
@@ -355,7 +373,9 @@ Customize the `generate_reply()` method to allow your workers to generate replie
 
 ```python
 class CustomWorker(AbstractWorker):
-    def generate_reply(self, messages: Optional[List[Dict]] = None, sender=None, **kwargs) -> Union[str, Dict, None]:
+    def generate_reply(
+        self, messages: Optional[List[Dict]] = None, sender=None, **kwargs
+    ) -> Union[str, Dict, None]:
         if messages:
             # Generate a reply based on received messages
             return f"Received {len(messages)} messages from {sender.name}."

docs/swarms/workers/index.md

@@ -49,11 +49,11 @@ Makes the Worker class callable. When an instance of the class is called, it wil
 ### **Example 1**: Basic usage with default parameters:
 
 ```python
-from swarms.models import OpenAIChat
 from swarms import Worker
+from swarms.models import OpenAIChat
 
 llm = OpenAIChat(
-    #enter your api key
+    # enter your api key
     openai_api_key="",
     temperature=0.5,
 )
@@ -195,17 +195,16 @@ response = node.run(task)
 
 # Print the response
 print(response)
-
 ```
 
 ### **Example 3**: Usage with human in the loop:
 
 ```python
-from swarms.models import OpenAIChat
 from swarms import Worker
+from swarms.models import OpenAIChat
 
 llm = OpenAIChat(
-    #enter your api key
+    # enter your api key
     openai_api_key="",
     temperature=0.5,
 )
@@ -223,7 +222,6 @@ node = Worker(
 task = "What were the winning boston marathon times for the past 5 years (ending in 2022)? Generate a table of the year, name, country of origin, and times."
 response = node.run(task)
 print(response)
-
 ```
 
 ## **Mathematical Description**:

playground/agents/multi_modal_auto_agent_example.py

@@ -1,6 +1,8 @@
 # Description: This is an example of how to use the Agent class to run a multi-modal workflow
 import os
+
 from dotenv import load_dotenv
+
 from swarms.models.gpt4_vision_api import GPT4VisionAPI
 from swarms.structs import Agent
 

playground/agents/multion_agent.py

@@ -1,7 +1,8 @@
 import multion
-from swarms.structs.concurrent_workflow import ConcurrentWorkflow
+
 from swarms.models.base_llm import AbstractLLM
 from swarms.structs.agent import Agent
+from swarms.structs.concurrent_workflow import ConcurrentWorkflow
 from swarms.structs.task import Task
 
 

playground/agents/perimeter_defense_agent.py

@@ -1,8 +1,10 @@
 import os
+
 from dotenv import load_dotenv
+
+import swarms.prompts.security_team as stsp
 from swarms.models import GPT4VisionAPI
 from swarms.structs import Agent
-import swarms.prompts.security_team as stsp
 
 # Load environment variables and initialize the Vision API
 load_dotenv()

playground/agents/simple_agent_example.py

@@ -3,12 +3,11 @@ import os
 from dotenv import load_dotenv
 
 from swarms import (
-    OpenAIChat,
     Conversation,
+    OpenAIChat,
     detect_markdown,
     extract_code_from_markdown,
 )
-
 from swarms.tools.code_executor import CodeExecutor
 
 conv = Conversation(

playground/agents/tool_agent.py

@@ -1,5 +1,6 @@
 # Import necessary libraries
 from transformers import AutoModelForCausalLM, AutoTokenizer
+
 from swarms import ToolAgent
 
 # Load the pre-trained model and tokenizer

playground/agents/worker_example.py

@@ -1,8 +1,10 @@
 # Importing necessary modules
 import os
+
 from dotenv import load_dotenv
-from swarms.agents.worker_agent import Worker
+
 from swarms import OpenAIChat
+from swarms.agents.worker_agent import Worker
 
 # Loading environment variables from .env file
 load_dotenv()

playground/demos/accountant_team/account_team2_example.py

@@ -1,5 +1,7 @@
 import os
+
 from dotenv import load_dotenv
+
 from swarms.models import Anthropic, OpenAIChat
 from swarms.prompts.accountant_swarm_prompts import (
     DECISION_MAKING_PROMPT,

playground/demos/ad_gen/ad_gen_example.py

@@ -1,9 +1,11 @@
-import random
 import os
+import random
+
 from dotenv import load_dotenv
+
 from swarms.models import OpenAIChat
-from swarms.structs import Agent
 from swarms.models.stable_diffusion import StableDiffusion
+from swarms.structs import Agent
 
 load_dotenv()
 openai_api_key = os.getenv("OPENAI_API_KEY")

playground/demos/assembly/assembly_example.py

@@ -1,5 +1,5 @@
-from swarms.structs import Agent
 from swarms.models.gpt4_vision_api import GPT4VisionAPI
+from swarms.structs import Agent
 
 llm = GPT4VisionAPI()
 

playground/demos/autotemp/autotemp_example.py

@@ -1,4 +1,5 @@
 import re
+
 from swarms.models.openai_models import OpenAIChat
 
 

playground/demos/autotemp/blog_gen_example.py

@@ -1,7 +1,9 @@
 import os
+
+from autotemp import AutoTemp
 from termcolor import colored
+
 from swarms.models import OpenAIChat
-from autotemp import AutoTemp
 from swarms.structs import SequentialWorkflow
 
 

playground/demos/developer_swarm/main_example.py

@@ -6,7 +6,7 @@ This is a simple example of how to use the swarms library to create a swarm of d
 The swarm is composed of two agents:
     - Documentation agent: writes documentation for a given code snippet.
     - Tests agent: writes tests for a given code snippet.
-    
+
 The swarm is initialized with a language model that is used by the agents to generate text. In this example, we use the OpenAI GPT-3 language model.
 
 Agent:
@@ -14,6 +14,7 @@ Documentation agent -> Tests agent
 
 
 """
+
 import os
 
 from dotenv import load_dotenv

playground/demos/education/education_example.py

@@ -1,8 +1,10 @@
 import os
+
 from dotenv import load_dotenv
-from swarms.models import OpenAIChat
+
-from swarms import Agent, SequentialWorkflow
 import swarms.prompts.education as edu_prompts
+from swarms import Agent, SequentialWorkflow
+from swarms.models import OpenAIChat
 
 # Load environment variables
 load_dotenv()

playground/demos/gemini_benchmarking/gemini_chat_example.py

@@ -1,5 +1,7 @@
 import os
+
 from dotenv import load_dotenv
+
 from swarms.models.gemini import Gemini
 from swarms.prompts.react import react_prompt
 

playground/demos/gemini_benchmarking/gemini_react_example.py

@@ -1,5 +1,7 @@
 import os
+
 from dotenv import load_dotenv
+
 from swarms.models.gemini import Gemini
 from swarms.prompts.react import react_prompt
 

playground/demos/grupa/app_example.py

@@ -1,12 +1,12 @@
 import os
 
 from dotenv import load_dotenv
+from termcolor import colored
 
 from swarms.models import OpenAIChat
 from swarms.prompts.code_interpreter import CODE_INTERPRETER
+from swarms.prompts.programming import DOCUMENTATION_SOP, TEST_SOP
 from swarms.structs import Agent
-from swarms.prompts.programming import TEST_SOP, DOCUMENTATION_SOP
-from termcolor import colored
 
 load_dotenv()
 

playground/demos/jarvis_multi_modal_auto_agent/jarvis_example.py

@@ -1,9 +1,8 @@
-from swarms.structs import Agent
 from swarms.models.gpt4_vision_api import GPT4VisionAPI
 from swarms.prompts.multi_modal_autonomous_instruction_prompt import (
     MULTI_MODAL_AUTO_AGENT_SYSTEM_PROMPT_1,
 )
-
+from swarms.structs import Agent
 
 llm = GPT4VisionAPI()
 

playground/demos/langchain_example/langchain_example.py

@@ -1,8 +1,10 @@
 import os
+
 from dotenv import load_dotenv
-from swarms import Agent
 from langchain.llms import OpenAIChat
 
+from swarms import Agent
+
 # Loading environment variables from .env file
 load_dotenv()
 

playground/demos/logistics/logistics_example.py

@@ -1,16 +1,18 @@
-from swarms.structs import Agent
 import os
+
 from dotenv import load_dotenv
+
 from swarms.models import GPT4VisionAPI
 from swarms.prompts.logistics import (
+    Efficiency_Agent_Prompt,
     Health_Security_Agent_Prompt,
-    Quality_Control_Agent_Prompt,
     Productivity_Agent_Prompt,
+    Quality_Control_Agent_Prompt,
     Safety_Agent_Prompt,
     Security_Agent_Prompt,
     Sustainability_Agent_Prompt,
-    Efficiency_Agent_Prompt,
 )
+from swarms.structs import Agent
 
 # from swarms.utils.banana_wrapper import banana
 

playground/demos/multi_modal_autonomous_agents/multi_modal_auto_agent_example.py

@@ -1,6 +1,5 @@
-from swarms.structs import Agent
 from swarms.models.gpt4_vision_api import GPT4VisionAPI
-
+from swarms.structs import Agent
 
 llm = GPT4VisionAPI()
 

playground/demos/multimodal_tot/main_example.py

@@ -2,8 +2,8 @@
 Multi Modal tree of thoughts that leverages the GPT-4 language model and the
 Stable Diffusion model to generate a multimodal output and evaluate the
 output based a metric from 0.0 to 1.0 and then run a search algorithm using DFS and BFS and return the best output.
-    
+
-    
+
 task: Generate an image of a swarm of bees -> Image generator -> GPT4V evaluates the img from 0.0 to 1.0 -> DFS/BFS -> return the best output
 
 
@@ -16,10 +16,12 @@ task: Generate an image of a swarm of bees -> Image generator -> GPT4V evaluates
 """
 
 import os
+
 from dotenv import load_dotenv
+from termcolor import colored
+
 from swarms.models.gpt4_vision_api import GPT4VisionAPI
 from swarms.models.stable_diffusion import StableDiffusion
-from termcolor import colored
 
 # Load the environment variables
 load_dotenv()

playground/demos/nutrition/nutrition_example.py

@@ -1,7 +1,9 @@
-import os
 import base64
+import os
+
 import requests
 from dotenv import load_dotenv
+
 from swarms.models import OpenAIChat
 from swarms.structs import Agent
 

playground/demos/personal_assistant/better_communication_example.py

@@ -1,5 +1,5 @@
-import time
 import os
+import time
 
 import pygame
 import speech_recognition as sr

playground/demos/personal_stylist/personal_stylist_example.py

@@ -1,14 +1,16 @@
-from swarms.structs import Agent
 import os
+
 from dotenv import load_dotenv
+
 from swarms.models import GPT4VisionAPI
 from swarms.prompts.personal_stylist import (
-    HAIRCUT_STYLIST_AGENT_PROMPT,
+    ACCESSORIES_STYLIST_AGENT_PROMPT,
-    MAKEUP_STYLIST_AGENT_PROMPT,
     BEARD_STYLIST_AGENT_PROMPT,
     CLOTHING_STYLIST_AGENT_PROMPT,
-    ACCESSORIES_STYLIST_AGENT_PROMPT,
+    HAIRCUT_STYLIST_AGENT_PROMPT,
+    MAKEUP_STYLIST_AGENT_PROMPT,
 )
+from swarms.structs import Agent
 
 # Load environment variables
 load_dotenv()

playground/demos/positive_med/positive_med_example.py

@@ -20,6 +20,7 @@ Distribution Agent:
 - Optimize writer prompt to create longer and more enjoyeable blogs
 - Use Local Models like Storywriter
 """
+
 import os
 
 from termcolor import colored

playground/demos/security_team/security_team_example.py

@@ -1,8 +1,11 @@
 import os
+
 from dotenv import load_dotenv
+from termcolor import colored
+
+import swarms.prompts.security_team as stsp
 from swarms.models import GPT4VisionAPI
 from swarms.structs import Agent
-import swarms.prompts.security_team as stsp
 
 # Load environment variables and initialize the Vision API
 load_dotenv()
@@ -11,25 +14,21 @@ api_key = os.getenv("OPENAI_API_KEY")
 llm = GPT4VisionAPI(openai_api_key=api_key)
 
 # Image for analysis
-img = "bank_robbery.jpg"
+# img = "IMG_1617.jpeg"
+img = "ubase1.jpeg"
+img2 = "ubase2.jpeg"
 
 # Initialize agents with respective prompts for security tasks
 crowd_analysis_agent = Agent(
+    agent_name="Crowd Analysis Agent",
     llm=llm,
     sop=stsp.CROWD_ANALYSIS_AGENT_PROMPT,
     max_loops=1,
     multi_modal=True,
 )
 
-# Facial Recognition Agent is currently not operational
-# facial_recognition_agent = Agent(
-#     llm=llm,
-#     sop=stsp.FACIAL_RECOGNITION_AGENT_PROMPT,
-#     max_loops=1,
-#     multi_modal=True,
-# )
-
 weapon_detection_agent = Agent(
+    agent_name="Weapon Detection Agent",
     llm=llm,
     sop=stsp.WEAPON_DETECTION_AGENT_PROMPT,
     max_loops=1,
@@ -37,6 +36,7 @@ weapon_detection_agent = Agent(
 )
 
 surveillance_monitoring_agent = Agent(
+    agent_name="Surveillance Monitoring Agent",
     llm=llm,
     sop=stsp.SURVEILLANCE_MONITORING_AGENT_PROMPT,
     max_loops=1,
@@ -44,37 +44,27 @@ surveillance_monitoring_agent = Agent(
 )
 
 emergency_response_coordinator = Agent(
+    agent_name="Emergency Response Coordinator",  # "Emergency Response Coordinator
     llm=llm,
     sop=stsp.EMERGENCY_RESPONSE_COORDINATOR_PROMPT,
     max_loops=1,
     multi_modal=True,
 )
 
-# Run agents with respective tasks on the same image
+colored("Security Team Analysis", "green")
-crowd_analysis = crowd_analysis_agent.run(
+colored("Inspect the scene for any potential threats", "green")
-    "Analyze the crowd dynamics in the scene", img
+colored("Weapon Detection Analysis", "green")
-)
-
-# Facial Recognition Agent is currently not operational
-# facial_recognition_analysis = facial_recognition_agent.run(
-#     "Identify any known individuals in the scene", img
-# )
-
 weapon_detection_analysis = weapon_detection_agent.run(
     "Inspect the scene for any potential threats", img
 )
 
+
+colored("Surveillance Monitoring Analysis", "cyan")
 surveillance_monitoring_analysis = surveillance_monitoring_agent.run(
     "Monitor the overall scene for unusual activities", img
 )
 
+colored("Emergency Response Analysis", "red")
 emergency_response_analysis = emergency_response_coordinator.run(
     "Develop a response plan based on the scene analysis", img
 )
-
-# Process and output results for each task
-# Example output (uncomment to use):
-# print(f"Crowd Analysis: {crowd_analysis}")
-# print(f"Weapon Detection Analysis: {weapon_detection_analysis}")
-# print(f"Surveillance Monitoring Analysis: {surveillance_monitoring_analysis}")
-# print(f"Emergency Response Analysis: {emergency_response_analysis}")

playground/demos/simple_rag/simple_rag.py

@@ -1,4 +1,4 @@
-from swarms import Agent, OpenAIChat, ChromaDB
+from swarms import Agent, ChromaDB, OpenAIChat
 
 # Making an instance of the ChromaDB class
 memory = ChromaDB(