black reformat

example.py

@@ -1,6 +1,7 @@
+"""Example of using the swarms package to run a workflow."""
 from swarms import Agent, OpenAIChat
 
-## Initialize the workflow
+# Initialize the workflow
 agent = Agent(
     llm=OpenAIChat(),
     max_loops="auto",

swarms/models/anthropic.py

@@ -25,7 +25,9 @@ from langchain_community.callbacks.manager import (
 )
 from langchain_community.llms.base import LLM
 from pydantic import Field, SecretStr, root_validator
-from langchain_community.schema.language_model import BaseLanguageModel
+from langchain_community.schema.language_model import (
+    BaseLanguageModel,
+)
 from langchain_community.schema.output import GenerationChunk
 from langchain_community.schema.prompt import PromptValue
 from langchain_community.utils import (

swarms/models/kosmos_two.py

@@ -88,9 +88,10 @@ class Kosmos(BaseMultiModalModel):
             skip_special_tokens=True,
         )[0]
 
-        processed_text, entities = (
-            self.processor.post_process_generation(generated_texts)
-        )
+        (
+            processed_text,
+            entities,
+        ) = self.processor.post_process_generation(generated_texts)
 
         return processed_text, entities
 

swarms/models/medical_sam.py

@@ -115,13 +115,14 @@ class MedicalSAM:
         if len(box_torch.shape) == 2:
             box_torch = box_torch[:, None, :]
 
-        sparse_embeddings, dense_embeddings = (
-            self.model.prompt_encoder(
+        (
+            sparse_embeddings,
+            dense_embeddings,
+        ) = self.model.prompt_encoder(
             points=None,
             boxes=box_torch,
             masks=None,
         )
-        )
 
         low_res_logits, _ = self.model.mask_decoder(
             image_embeddings=img,

swarms/models/openai_embeddings.py

@@ -208,9 +208,9 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
     """Maximum number of texts to embed in each batch"""
     max_retries: int = 6
     """Maximum number of retries to make when generating."""
-    request_timeout: Optional[Union[float, Tuple[float, float]]] = (
-        None
-    )
+    request_timeout: Optional[
+        Union[float, Tuple[float, float]]
+    ] = None
     """Timeout in seconds for the OpenAPI request."""
     headers: Any = None
     tiktoken_model_name: Optional[str] = None

swarms/models/openai_models.py

@@ -244,9 +244,9 @@ class BaseOpenAI(BaseLLM):
             attributes["openai_api_base"] = self.openai_api_base
 
         if self.openai_organization != "":
-            attributes["openai_organization"] = (
-                self.openai_organization
-            )
+            attributes[
+                "openai_organization"
+            ] = self.openai_organization
 
         if self.openai_proxy != "":
             attributes["openai_proxy"] = self.openai_proxy
@@ -287,9 +287,9 @@ class BaseOpenAI(BaseLLM):
     openai_proxy: Optional[str] = None
     batch_size: int = 20
     """Batch size to use when passing multiple documents to generate."""
-    request_timeout: Optional[Union[float, Tuple[float, float]]] = (
-        None
-    )
+    request_timeout: Optional[
+        Union[float, Tuple[float, float]]
+    ] = None
     """Timeout for requests to OpenAI completion API. Default is 600 seconds."""
     logit_bias: Optional[Dict[str, float]] = Field(
         default_factory=dict

swarms/models/palm.py

@@ -3,7 +3,9 @@ from __future__ import annotations
 import logging
 from typing import Any, Callable, Dict, List, Optional
 
-from langchain_community.callbacks.manager import CallbackManagerForLLMRun
+from langchain_community.callbacks.manager import (
+    CallbackManagerForLLMRun,
+)
 from langchain_community.llms import BaseLLM
 from langchain_community.pydantic_v1 import BaseModel, root_validator
 from langchain_community.schema import Generation, LLMResult

swarms/prompts/base.py

@@ -86,7 +86,9 @@ class BaseMessage(Serializable):
         return True
 
     def __add__(self, other: Any) -> ChatPromptTemplate:
-        from langchain_community.prompts.chat import ChatPromptTemplate
+        from langchain_community.prompts.chat import (
+            ChatPromptTemplate,
+        )
 
         prompt = ChatPromptTemplate(messages=[self])
         return prompt + other

swarms/prompts/worker_prompt.py

@@ -62,6 +62,8 @@ def worker_tools_sop_promp(name: str, memory: str):
     [{memory}]
     
     Human: Determine which next command to use, and respond using the format specified above:
-    """.format(name=name, memory=memory, time=time)
+    """.format(
+        name=name, memory=memory, time=time
+    )
 
     return str(out)

swarms/structs/concurrent_workflow.py

@@ -36,9 +36,9 @@ class ConcurrentWorkflow(BaseStructure):
     max_loops: int = 1
     max_workers: int = 5
     autosave: bool = False
-    saved_state_filepath: Optional[str] = (
-        "runs/concurrent_workflow.json"
-    )
+    saved_state_filepath: Optional[
+        str
+    ] = "runs/concurrent_workflow.json"
     print_results: bool = False
     return_results: bool = False
     use_processes: bool = False

swarms/structs/multi_agent_collab.py

@@ -317,9 +317,9 @@ class MultiAgentCollaboration:
         """Tracks and reports the performance of each agent"""
         performance_data = {}
         for agent in self.agents:
-            performance_data[agent.name] = (
-                agent.get_performance_metrics()
-            )
+            performance_data[
+                agent.name
+            ] = agent.get_performance_metrics()
         return performance_data
 
     def set_interaction_rules(self, rules):

swarms/structs/sequential_workflow.py

@@ -42,9 +42,9 @@ class SequentialWorkflow:
     task_pool: List[Task] = field(default_factory=list)
     max_loops: int = 1
     autosave: bool = False
-    saved_state_filepath: Optional[str] = (
-        "sequential_workflow_state.json"
-    )
+    saved_state_filepath: Optional[
+        str
+    ] = "sequential_workflow_state.json"
     restore_state_filepath: Optional[str] = None
     dashboard: bool = False
 

swarms/structs/swarm_redis_registry.py

@@ -84,7 +84,9 @@ class RedisSwarmRegistry(AbstractSwarm):
         query = f"""
         {match_query}
         CREATE (a)-[r:joined]->(b) RETURN r
-        """.replace("\n", "")
+        """.replace(
+            "\n", ""
+        )
 
         self.redis_graph.query(query)
 

swarms/structs/swarming_architectures.py

@@ -105,7 +105,7 @@ def prime_swarm(agents: List[Agent], tasks: List[str]):
 
 
 def power_swarm(agents: List[str], tasks: List[str]):
-    powers = [2**i for i in range(int(len(agents) ** 0.5))]
+    powers = [2 ** i for i in range(int(len(agents) ** 0.5))]
     for power in powers:
         if power < len(agents) and tasks:
             task = tasks.pop(0)
@@ -114,14 +114,14 @@ def power_swarm(agents: List[str], tasks: List[str]):
 
 def log_swarm(agents: List[Agent], tasks: List[str]):
     for i in range(len(agents)):
-        if 2**i < len(agents) and tasks:
+        if 2 ** i < len(agents) and tasks:
             task = tasks.pop(0)
-            agents[2**i].run(task)
+            agents[2 ** i].run(task)
 
 
 def exponential_swarm(agents: List[Agent], tasks: List[str]):
     for i in range(len(agents)):
-        index = min(int(2**i), len(agents) - 1)
+        index = min(int(2 ** i), len(agents) - 1)
         if tasks:
             task = tasks.pop(0)
             agents[index].run(task)
@@ -130,7 +130,7 @@ def exponential_swarm(agents: List[Agent], tasks: List[str]):
 def geometric_swarm(agents, tasks):
     ratio = 2
     for i in range(range(len(agents))):
-        index = min(int(ratio**2), len(agents) - 1)
+        index = min(int(ratio ** 2), len(agents) - 1)
         if tasks:
             task = tasks.pop(0)
             agents[index].run(task)

swarms/telemetry/sys_info.py

@@ -48,9 +48,9 @@ def get_cpu_info():
 
 def get_ram_info():
     vm = psutil.virtual_memory()
-    used_ram_gb = vm.used / (1024**3)
-    free_ram_gb = vm.free / (1024**3)
-    total_ram_gb = vm.total / (1024**3)
+    used_ram_gb = vm.used / (1024 ** 3)
+    free_ram_gb = vm.free / (1024 ** 3)
+    total_ram_gb = vm.total / (1024 ** 3)
     return (
         f"{total_ram_gb:.2f} GB, used: {used_ram_gb:.2f}, free:"
         f" {free_ram_gb:.2f}"

swarms/tools/tool.py

@@ -902,9 +902,9 @@ def tool(
 
                 coroutine = ainvoke_wrapper
                 func = invoke_wrapper
-                schema: Optional[Type[BaseModel]] = (
-                    runnable.input_schema
-                )
+                schema: Optional[
+                    Type[BaseModel]
+                ] = runnable.input_schema
                 description = repr(runnable)
             elif inspect.iscoroutinefunction(dec_func):
                 coroutine = dec_func

swarms/utils/load_environment.py

@@ -8,4 +8,3 @@ def load_environment():
     api_key = os.environ.get("OPENAI_API_KEY")
 
     return api_key, os.environ
-