Start work on lints

.github/workflows/codacy.yml

@@ -12,7 +12,7 @@
 # For more information on Codacy Analysis CLI in general, see
 # https://github.com/codacy/codacy-analysis-cli.
 
-name: Codacy Security Scan
+name: Codacy
 on:
   push:
     branches: ["master"]

.github/workflows/docs.yml

@@ -1,5 +1,5 @@
 ---
-name: Docs WorkAgent
+name: Documentation
 on:
   push:
     branches:
@@ -18,9 +18,3 @@ jobs:
       - run: pip install mkdocs-glightbox
       - run: pip install "mkdocstrings[python]"
       - run: mkdocs gh-deploy --force
-  preview:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: readthedocs/actions/preview@v1
-        with:
-          project-slug: swarms

.github/workflows/docs_preview.yml

@@ -0,0 +1,16 @@
+name: Documentation Links
+on:
+  pull_request_target:
+    types:
+      - opened
+
+permissions:
+  pull-requests: write
+
+jobs:
+  documentation-links:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: readthedocs/actions/preview@v1
+        with:
+          project-slug: "swarms"

.github/workflows/stale.yml

@@ -4,11 +4,11 @@
 # You can adjust the behavior by modifying this file.
 # For more information, see:
 # https://github.com/actions/stale
-name: Mark stale issues and pull requests
+name: Stale
 on:
   schedule:
     # Scheduled to run at 1.30 UTC everyday
-    - cron: '30 1 * * *'
+    - cron: "0 0 * * *"
 jobs:
   stale:
     runs-on: ubuntu-latest
@@ -44,6 +44,6 @@ jobs:
             Please open a new pull request if you need further assistance. Thanks!
 
           # Label that can be assigned to issues to exclude them from being marked as stale
-          exempt-issue-labels: 'override-stale'
+          exempt-issue-labels: "override-stale"
           # Label that can be assigned to PRs to exclude them from being marked as stale
           exempt-pr-labels: "override-stale"

.github/workflows/welcome.yml

@@ -1,5 +1,5 @@
 ---
-name: Welcome WorkAgent
+name: Welcome
 on:
   issues:
     types: [opened]
@@ -14,7 +14,9 @@ jobs:
       - uses: actions/first-interaction@v1.3.0
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
-          issue-message: "Hello there, thank you for opening an Issue ! 🙏🏻 The team
+          issue-message:
+            "Hello there, thank you for opening an Issue ! 🙏🏻 The team
             was notified and they will get back to you asap."
-          pr-message: "Hello there, thank you for opening an PR ! 🙏🏻 The team was
+          pr-message:
+            "Hello there, thank you for opening an PR ! 🙏🏻 The team was
             notified and they will get back to you asap."

example.py

@@ -1,6 +1,6 @@
 from swarms import Agent, Anthropic
 
-## Initialize the workflow
+# Initialize the workflow
 agent = Agent(
     agent_name="Transcript Generator",
     agent_description=(

playground/agents/amazon_review_agent.py

@@ -1,6 +1,6 @@
 from swarms import Agent, OpenAIChat
 
-## Initialize the workflow
+# Initialize the workflow
 agent = Agent(
     llm=OpenAIChat(),
     max_loops="auto",

playground/agents/full_stack_agent.py

@@ -10,7 +10,7 @@ def search_api(query: str, max_results: int = 10):
     return f"Search API: {query} -> {max_results} results"
 
 
-## Initialize the workflow
+# Initialize the workflow
 agent = Agent(
     agent_name="Youtube Transcript Generator",
     agent_description=(

playground/agents/multi_modal_auto_agent_example.py

@@ -21,7 +21,7 @@ llm = GPT4VisionAPI(
 task = "What is the color of the object?"
 img = "images/swarms.jpeg"
 
-## Initialize the workflow
+# Initialize the workflow
 agent = Agent(
     llm=llm,
     max_loops="auto",

playground/demos/assembly/assembly_example.py

@@ -11,7 +11,7 @@ task = (
 )
 img = "assembly_line.jpg"
 
-## Initialize the workflow
+# Initialize the workflow
 agent = Agent(
     llm=llm,
     max_loops=1,

playground/demos/jarvis_multi_modal_auto_agent/jarvis_example.py

@@ -9,7 +9,7 @@ llm = GPT4VisionAPI()
 task = "What is the color of the object?"
 img = "images/swarms.jpeg"
 
-## Initialize the workflow
+# Initialize the workflow
 agent = Agent(
     llm=llm,
     sop=MULTI_MODAL_AUTO_AGENT_SYSTEM_PROMPT_1,

playground/demos/multi_modal_autonomous_agents/multi_modal_auto_agent_example.py

@@ -6,7 +6,7 @@ llm = GPT4VisionAPI()
 task = "What is the color of the object?"
 img = "images/swarms.jpeg"
 
-## Initialize the workflow
+# Initialize the workflow
 agent = Agent(
     llm=llm,
     max_loops="auto",

playground/demos/multi_modal_chain_of_thought/vcot_example.py

@@ -22,7 +22,7 @@ llm = GPT4VisionAPI(
 task = "This is an eye test. What do you see?"
 img = "playground/demos/multi_modal_chain_of_thought/eyetest.jpg"
 
-## Initialize the workflow
+# Initialize the workflow
 agent = Agent(
     llm=llm,
     max_loops=2,

playground/demos/visuo/text_to_sql_agent_example.py

@@ -19,7 +19,7 @@ llm = HuggingfaceLLM(
     temperature=0.5,
 )
 
-## Initialize the workflow
+# Initialize the workflow
 agent = Agent(
     llm=llm,
     max_loops="auto",

playground/examples/example_agent.py

@@ -26,7 +26,7 @@ print(
     f" {sys.stderr}"
 )
 
-## Initialize the workflow
+# Initialize the workflow
 agent = Agent(llm=llm, max_loops=1, autosave=True, dashboard=True)
 
 # Run the workflow on a task

playground/examples/example_swarmnetwork.py

@@ -17,7 +17,7 @@ llm = OpenAIChat(
     openai_api_key=api_key,
 )
 
-## Initialize the workflow
+# Initialize the workflow
 agent = Agent(llm=llm, max_loops=1, agent_name="Social Media Manager")
 agent2 = Agent(llm=llm, max_loops=1, agent_name=" Product Manager")
 agent3 = Agent(llm=llm, max_loops=1, agent_name="SEO Manager")

playground/structs/agent_basic_customize.py

@@ -11,7 +11,7 @@ llm = OpenAIChat(
     # max_tokens=100,
 )
 
-## Initialize the workflow
+# Initialize the workflow
 agent = Agent(
     llm=llm,
     max_loops=2,

playground/structs/agent_with_longterm_memory.py

@@ -26,7 +26,7 @@ llm = OpenAIChat(
     max_tokens=1000,
 )
 
-## Initialize the workflow
+# Initialize the workflow
 agent = Agent(
     llm=llm,
     max_loops=4,

playground/structs/agent_with_tools_example.py

@@ -66,7 +66,7 @@ llm = OpenAIChat(
 )
 
 
-## Initialize the workflow
+# Initialize the workflow
 agent = Agent(
     agent_name="Research Agent",
     llm=llm,

playground/structs/autoscaler_example.py

@@ -20,7 +20,7 @@ llm = OpenAIChat(
 )
 
 
-## Initialize the workflow
+# Initialize the workflow
 agent = Agent(llm=llm, max_loops=1, dashboard=True)
 
 

playground/structs/basic_agent_with_azure_openai.py

@@ -1,6 +1,6 @@
 from swarms import Agent, AzureOpenAI
 
-## Initialize the workflow
+# Initialize the workflow
 agent = Agent(
     llm=AzureOpenAI(),
     max_loops="auto",

playground/structs/custom_model_with_agent.py

@@ -10,7 +10,7 @@ class ExampleLLM(AbstractLLM):
         pass
 
 
-## Initialize the workflow
+# Initialize the workflow
 agent = Agent(
     llm=ExampleLLM(),
     max_loops="auto",

playground/structs/easy_example.py

@@ -1,6 +1,6 @@
 from swarms import Agent, OpenAIChat
 
-## Initialize the workflow
+# Initialize the workflow
 agent = Agent(
     llm=OpenAIChat(),
     max_loops=1,

playground/structs/swarm_network_example.py

@@ -31,7 +31,7 @@ together_llm = TogetherLLM(
     together_api_key=os.getenv("TOGETHER_API_KEY"), max_tokens=3000
 )
 
-## Initialize the workflow
+# Initialize the workflow
 agent = Agent(
     llm=anthropic,
     max_loops=1,

playground/tools/agent_with_tools_example.py

@@ -26,7 +26,7 @@ def search_api(query: str) -> str:
     print(f"Searching API for {query}")
 
 
-## Initialize the workflow
+# Initialize the workflow
 agent = Agent(
     llm=llm,
     max_loops=5,

pyproject.toml

@@ -71,13 +71,14 @@ pandas = "^2.2.2"
 fastapi = "^0.110.1"
 
 [tool.ruff]
-line-length = 127
+line-length = 128
 
 [tool.ruff.lint]
-select = ["E4", "E7", "E9", "F", "W", "E501", "I", "UP"]
+select = ["E", "F", "W", "I", "UP"]
 ignore = []
 fixable = ["ALL"]
 unfixable = []
+preview = true
 
 [tool.black]
 line-length = 70

scripts/auto_tests_docs/auto_docs.py

@@ -1,4 +1,4 @@
-###### VERISON2
+# VERISON2
 import inspect
 import os
 import threading

swarms/prompts/tools.py

@@ -34,7 +34,7 @@ commands: {
 """
 
 
-########### FEW SHOT EXAMPLES ################
+# FEW SHOT EXAMPLES ################
 SCENARIOS = """
 commands: {
     "tools": {

swarms/structs/graph_workflow.py

@@ -17,7 +17,8 @@ class GraphWorkflow(BaseStructure):
         connect(from_node, to_node): Connects two nodes in the graph.
         set_entry_point(node_name): Sets the entry point node for the workflow.
         add_edge(from_node, to_node): Adds an edge between two nodes in the graph.
-        add_conditional_edges(from_node, condition, edge_dict): Adds conditional edges from a node to multiple nodes based on a condition.
+        add_conditional_edges(from_node, condition, edge_dict):
+            Adds conditional edges from a node to multiple nodes based on a condition.
         run(): Runs the workflow and returns the graph.
 
     Examples:
@@ -126,15 +127,11 @@ class GraphWorkflow(BaseStructure):
         if from_node in self.graph:
             for condition_value, to_node in edge_dict.items():
                 if to_node in self.graph:
-                    self.graph[from_node]["edges"][
-                        to_node
-                    ] = condition
+                    self.graph[from_node]["edges"][to_node] = condition
                 else:
                     raise ValueError("Node does not exist in graph")
         else:
-            raise ValueError(
-                f"Node {from_node} does not exist in graph"
-            )
+            raise ValueError(f"Node {from_node} does not exist in graph")
 
     def run(self):
         """
@@ -160,9 +157,7 @@ class GraphWorkflow(BaseStructure):
             ValueError: _description_
         """
         if node_name not in self.graph:
-            raise ValueError(
-                f"Node {node_name} does not exist in graph"
-            )
+            raise ValueError(f"Node {node_name} does not exist in graph")
 
     def _check_nodes_exist(self, from_node, to_node):
         """

swarms/structs/message_pool.py

@@ -20,9 +20,7 @@ def _hash(input: str):
     return hex_dig
 
 
-def msg_hash(
-    agent: Agent, content: str, turn: int, msg_type: str = "text"
-):
+def msg_hash(agent: Agent, content: str, turn: int, msg_type: str = "text"):
     """
     Generate a hash value for a message.
 
@@ -37,8 +35,7 @@ def msg_hash(
     """
     time = time_ns()
     return _hash(
-        f"agent: {agent.agent_name}\ncontent: {content}\ntimestamp:"
-        f" {str(time)}\nturn: {turn}\nmsg_type: {msg_type}"
+        f"agent: {agent.agent_name}\ncontent: {content}\ntimestamp:" f" {str(time)}\nturn: {turn}\nmsg_type: {msg_type}"
     )
 
 
@@ -67,11 +64,17 @@ class MessagePool:
     >>> message_pool.add(agent=agent2, content="Hello, agent1!", turn=1)
     >>> message_pool.add(agent=agent3, content="Hello, agent1!", turn=1)
     >>> message_pool.get_all_messages()
-    [{'agent': Agent(agent_name='agent1'), 'content': 'Hello, agent2!', 'turn': 1, 'visible_to': 'all', 'logged': True}, {'agent': Agent(agent_name='agent2'), 'content': 'Hello, agent1!', 'turn': 1, 'visible_to': 'all', 'logged': True}, {'agent': Agent(agent_name='agent3'), 'content': 'Hello, agent1!', 'turn': 1, 'visible_to': 'all', 'logged': True}]
+    [{'agent': Agent(agent_name='agent1'), 'content': 'Hello, agent2!', 'turn': 1, 'visible_to': 'all', 'logged': True},
+     {'agent': Agent(agent_name='agent2'), 'content': 'Hello, agent1!', 'turn': 1, 'visible_to': 'all', 'logged': True},
+     {'agent': Agent(agent_name='agent3'), 'content': 'Hello, agent1!', 'turn': 1, 'visible_to': 'all', 'logged': True}]
     >>> message_pool.get_visible_messages(agent=agent1, turn=1)
-    [{'agent': Agent(agent_name='agent1'), 'content': 'Hello, agent2!', 'turn': 1, 'visible_to': 'all', 'logged': True}, {'agent': Agent(agent_name='agent2'), 'content': 'Hello, agent1!', 'turn': 1, 'visible_to': 'all', 'logged': True}, {'agent': Agent(agent_name='agent3'), 'content': 'Hello, agent1!', 'turn': 1, 'visible_to': 'all', 'logged': True}]
+    [{'agent': Agent(agent_name='agent1'), 'content': 'Hello, agent2!', 'turn': 1, 'visible_to': 'all', 'logged': True},
+     {'agent': Agent(agent_name='agent2'), 'content': 'Hello, agent1!', 'turn': 1, 'visible_to': 'all', 'logged': True},
+     {'agent': Agent(agent_name='agent3'), 'content': 'Hello, agent1!', 'turn': 1, 'visible_to': 'all', 'logged': True}]
     >>> message_pool.get_visible_messages(agent=agent2, turn=1)
-    [{'agent': Agent(agent_name='agent1'), 'content': 'Hello, agent2!', 'turn': 1, 'visible_to': 'all', 'logged': True}, {'agent': Agent(agent_name='agent2'), 'content': 'Hello, agent1!', 'turn': 1, 'visible_to': 'all', 'logged': True}, {'agent': Agent(agent_name='agent3'), 'content': 'Hello, agent1!', 'turn': 1, 'visible_to': 'all', 'logged': True}]
+    [{'agent': Agent(agent_name='agent1'), 'content': 'Hello, agent2!', 'turn': 1, 'visible_to': 'all', 'logged': True},
+     {'agent': Agent(agent_name='agent2'), 'content': 'Hello, agent1!', 'turn': 1, 'visible_to': 'all', 'logged': True},
+     {'agent': Agent(agent_name='agent3'), 'content': 'Hello, agent1!', 'turn': 1, 'visible_to': 'all', 'logged': True}]
     """
 
     def __init__(
@@ -98,9 +101,7 @@ class MessagePool:
 
         logger.info("MessagePool initialized")
         logger.info(f"Number of agents: {len(agents)}")
-        logger.info(
-            f"Agents: {[agent.agent_name for agent in agents]}"
-        )
+        logger.info(f"Agents: {[agent.agent_name for agent in agents]}")
         logger.info(f"moderator: {moderator.agent_name} is available")
         logger.info(f"Number of turns: {turns}")
 
@@ -187,18 +188,11 @@ class MessagePool:
             List[Dict]: The list of visible messages.
         """
         # Get the messages before the current turn
-        prev_messages = [
-            message
-            for message in self.messages
-            if message["turn"] < turn
-        ]
+        prev_messages = [message for message in self.messages if message["turn"] < turn]
 
         visible_messages = []
         for message in prev_messages:
-            if (
-                message["visible_to"] == "all"
-                or agent.agent_name in message["visible_to"]
-            ):
+            if message["visible_to"] == "all" or agent.agent_name in message["visible_to"]:
                 visible_messages.append(message)
         return visible_messages
 

swarms/structs/meta_system_prompt.py

@@ -7,20 +7,18 @@ from swarms.prompts.meta_system_prompt import (
 )
 from swarms.structs.agent import Agent
 
-meta_prompter_llm = OpenAIChat(
-    system_prompt=str(meta_system_prompt_generator)
-)
+meta_prompter_llm = OpenAIChat(system_prompt=str(meta_system_prompt_generator))
 
 
-def meta_system_prompt(
-    agent: Union[Agent, AbstractLLM], system_prompt: str
-) -> str:
+def meta_system_prompt(agent: Union[Agent, AbstractLLM], system_prompt: str) -> str:
     """
     Generates a meta system prompt for the given agent using the provided system prompt.
 
     Args:
-        agent (Union[Agent, AbstractLLM]): The agent or LLM (Language Learning Model) for which the meta system prompt is generated.
-        system_prompt (str): The system prompt used to generate the meta system prompt.
+        agent (Union[Agent, AbstractLLM]):
+            The agent or LLM (Language Learning Model) for which the meta system prompt is generated.
+        system_prompt (str):
+            The system prompt used to generate the meta system prompt.
 
     Returns:
         str: The generated meta system prompt.

swarms/tools/tool_utils.py

@@ -17,7 +17,8 @@ def scrape_tool_func_docs(fn: Callable) -> str:
         fn (Callable): The function to scrape.
 
     Returns:
-        str: A string containing the function's name, documentation string, and a list of its parameters. Each parameter is represented as a line containing the parameter's name, default value, and annotation.
+        str: A string containing the function's name, documentation string, and a list of its parameters.
+             Each parameter is represented as a line containing the parameter's name, default value, and annotation.
     """
     try:
         # If the function is a tool, get the original function
@@ -34,10 +35,7 @@ def scrape_tool_func_docs(fn: Callable) -> str:
                 f" {param.annotation if param.annotation is not param.empty else 'None'}"
             )
         parameters_str = "\n".join(parameters)
-        return (
-            f"Function: {fn.__name__}\nDocstring:"
-            f" {inspect.getdoc(fn)}\nParameters:\n{parameters_str}"
-        )
+        return f"Function: {fn.__name__}\nDocstring:" f" {inspect.getdoc(fn)}\nParameters:\n{parameters_str}"
     except Exception as error:
         print(
             colored(

swarms/utils/load_model_torch.py

@@ -18,7 +18,8 @@ def load_model_torch(
         model_path (str): Path to the saved model file.
         device (torch.device): Device to move the model to.
         model (nn.Module): The model architecture, if the model file only contains the state dictionary.
-        strict (bool): Whether to strictly enforce that the keys in the state dictionary match the keys returned by the model's `state_dict()` function.
+        strict (bool): Whether to strictly enforce that the keys in the state dictionary match
+            the keys returned by the model's `state_dict()` function.
         map_location (callable): A function to remap the storage locations of the loaded model.
         *args: Additional arguments to pass to `torch.load`.
         **kwargs: Additional keyword arguments to pass to `torch.load`.
@@ -31,15 +32,11 @@ def load_model_torch(
         RuntimeError: If there is an error while loading the model.
     """
     if device is None:
-        device = torch.device(
-            "cuda" if torch.cuda.is_available() else "cpu"
-        )
+        device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
     try:
         if model is None:
-            model = torch.load(
-                model_path, map_location=map_location, *args, **kwargs
-            )
+            model = torch.load(model_path, map_location=map_location, *args, **kwargs)
         else:
             model.load_state_dict(
                 torch.load(

tests/models/test_huggingface.py

@@ -18,10 +18,7 @@ def llm_instance():
 
 # Test for instantiation and attributes
 def test_llm_initialization(llm_instance):
-    assert (
-        llm_instance.model_id
-        == "NousResearch/Nous-Hermes-2-Vision-Alpha"
-    )
+    assert llm_instance.model_id == "NousResearch/Nous-Hermes-2-Vision-Alpha"
     assert llm_instance.max_length == 500
     # ... add more assertions for all default attributes
 
@@ -88,15 +85,11 @@ def test_llm_memory_consumption(llm_instance):
 )
 def test_llm_initialization_params(model_id, max_length):
     if max_length:
-        instance = HuggingfaceLLM(
-            model_id=model_id, max_length=max_length
-        )
+        instance = HuggingfaceLLM(model_id=model_id, max_length=max_length)
         assert instance.max_length == max_length
     else:
         instance = HuggingfaceLLM(model_id=model_id)
-        assert (
-            instance.max_length == 500
-        )  # Assuming 500 is the default max_length
+        assert instance.max_length == 500  # Assuming 500 is the default max_length
 
 
 # Test for setting an invalid device
@@ -144,9 +137,7 @@ def test_llm_run_output_length(mock_run, llm_instance):
 # Test the tokenizer handling special tokens correctly
 @patch("swarms.models.huggingface.HuggingfaceLLM._tokenizer.encode")
 @patch("swarms.models.huggingface.HuggingfaceLLM._tokenizer.decode")
-def test_llm_tokenizer_special_tokens(
-    mock_decode, mock_encode, llm_instance
-):
+def test_llm_tokenizer_special_tokens(mock_decode, mock_encode, llm_instance):
     mock_encode.return_value = "encoded input with special tokens"
     mock_decode.return_value = "decoded output with special tokens"
     result = llm_instance.run("test task with special tokens")
@@ -172,9 +163,7 @@ def test_llm_response_time(mock_run, llm_instance):
     start_time = time.time()
     llm_instance.run("test task for response time")
     end_time = time.time()
-    assert (
-        end_time - start_time < 1
-    )  # Assuming the response should be faster than 1 second
+    assert end_time - start_time < 1  # Assuming the response should be faster than 1 second
 
 
 # Test the logging of a warning for long inputs
@@ -197,13 +186,9 @@ def test_llm_run_model_exception(mock_generate, llm_instance):
 
 # Test the behavior when GPU is forced but not available
 @patch("torch.cuda.is_available", return_value=False)
-def test_llm_force_gpu_when_unavailable(
-    mock_is_available, llm_instance
-):
+def test_llm_force_gpu_when_unavailable(mock_is_available, llm_instance):
     with pytest.raises(EnvironmentError):
-        llm_instance.set_device(
-            "cuda"
-        )  # Attempt to set CUDA when it's not available
+        llm_instance.set_device("cuda")  # Attempt to set CUDA when it's not available
 
 
 # Test for proper cleanup after model use (releasing resources)
@@ -221,9 +206,7 @@ def test_llm_multilingual_input(mock_run, llm_instance):
     mock_run.return_value = "mocked multilingual output"
     multilingual_input = "Bonjour, ceci est un test multilingue."
     result = llm_instance.run(multilingual_input)
-    assert isinstance(
-        result, str
-    )  # Simple check to ensure output is string type
+    assert isinstance(result, str)  # Simple check to ensure output is string type
 
 
 # Test caching mechanism to prevent re-running the same inputs
@@ -238,5 +221,7 @@ def test_llm_caching_mechanism(mock_run, llm_instance):
     assert first_run_result == second_run_result
 
 
-# These tests are provided as examples. In real-world scenarios, you will need to adapt these tests to the actual logic of your `HuggingfaceLLM` class.
-# For instance, "mock_model.delete.assert_called_once()" and similar lines are based on hypothetical methods and behaviors that you need to replace with actual implementations.
+# These tests are provided as examples.
+# In real-world scenarios, you will need to adapt these tests to the actual logic of your `HuggingfaceLLM` class.
+# For instance, "mock_model.delete.assert_called_once()" and similar lines are based on hypothetical methods and behaviors
+# that you need to replace with actual implementations.