[CLEANUP]

playground/agents/amazon_review_agent.py

@@ -4,8 +4,11 @@ from swarms import Agent, OpenAIChat
 agent = Agent(
     llm=OpenAIChat(),
     max_loops="auto",
-    agent_name = "Amazon Product Scraper",
-    system_prompt="Create the code in python to scrape amazon product reviews and return csv given a product url",
+    agent_name="Amazon Product Scraper",
+    system_prompt=(
+        "Create the code in python to scrape amazon product reviews"
+        " and return csv given a product url"
+    ),
     autosave=True,
     dashboard=False,
     streaming_on=True,
@@ -16,6 +19,7 @@ agent = Agent(
 
 # Run the workflow on a task
 agent(
-    "Create the code to scrape this amazon url and rturn a csv of reviews: https://www.amazon.com/Creative-Act-Way-Being/dp/0593652886/ref=sr_1_1?dib=eyJ2IjoiMSJ9.JVdL3JSDmBVH_jv4eM6YE4npUpG6jO6-ai6lgmax-Ya4nH3oPk8cxkmzKsx9yAMX-Eo4A1ErqipCeY-FhTqMc7hhNTqCoAvNd65rvXH1GnYv7WlfSDYTjMkB_vVrH-iitBXAY6uASm73ff2hPWzqhF3ldGkYr8fA5FtmoYMSOnarvCU11YpoSp3EqdK526XOxkRJqeFlZAoAkXOmYHe9B5sY8-zQlVgkIV3U-7rUQdY.UXen28vr2K-Tbbz9aB7vNLLurAiR2ZSblFOVNjXYaf8&dib_tag=se&hvadid=652633987879&hvdev=c&hvlocphy=9061268&hvnetw=g&hvqmt=e&hvrand=413884426001746223&hvtargid=kwd-1977743614989&hydadcr=8513_13545021&keywords=the+creative+act+rick+rubin+book&qid=1710541252&sr=8-1"
-    
+    "Create the code to scrape this amazon url and rturn a csv of"
+    " reviews:"
+    " https://www.amazon.com/Creative-Act-Way-Being/dp/0593652886/ref=sr_1_1?dib=eyJ2IjoiMSJ9.JVdL3JSDmBVH_jv4eM6YE4npUpG6jO6-ai6lgmax-Ya4nH3oPk8cxkmzKsx9yAMX-Eo4A1ErqipCeY-FhTqMc7hhNTqCoAvNd65rvXH1GnYv7WlfSDYTjMkB_vVrH-iitBXAY6uASm73ff2hPWzqhF3ldGkYr8fA5FtmoYMSOnarvCU11YpoSp3EqdK526XOxkRJqeFlZAoAkXOmYHe9B5sY8-zQlVgkIV3U-7rUQdY.UXen28vr2K-Tbbz9aB7vNLLurAiR2ZSblFOVNjXYaf8&dib_tag=se&hvadid=652633987879&hvdev=c&hvlocphy=9061268&hvnetw=g&hvqmt=e&hvrand=413884426001746223&hvtargid=kwd-1977743614989&hydadcr=8513_13545021&keywords=the+creative+act+rick+rubin+book&qid=1710541252&sr=8-1"
 )

playground/examples/example_agent.py

@@ -14,11 +14,17 @@ api_key = os.environ.get("OPENAI_API_KEY")
 
 # Initialize the language model
 llm = OpenAIChat(
-    temperature=0.5, model_name="gpt-4", openai_api_key=api_key, max_tokens=4000
+    temperature=0.5,
+    model_name="gpt-4",
+    openai_api_key=api_key,
+    max_tokens=4000,
 )
 
 
-print(f'this is a test msg for stdout and stderr: {sys.stdout}, {sys.stderr}')
+print(
+    f"this is a test msg for stdout and stderr: {sys.stdout},"
+    f" {sys.stderr}"
+)
 
 ## Initialize the workflow
 agent = Agent(llm=llm, max_loops=1, autosave=True, dashboard=True)

playground/examples/example_anthropic.py

@@ -9,5 +9,7 @@ model = Anthropic(anthropic_api_key="")
 # print(completion_1)
 
 # Using the __call__ method
-completion_2 = model("How far is the moon from the earth?", stop=["miles", "km"])
+completion_2 = model(
+    "How far is the moon from the earth?", stop=["miles", "km"]
+)
 print(completion_2)

playground/examples/example_dalle3.py

@@ -1,4 +1,4 @@
-'''from swarms.models import Dalle3
+"""from swarms.models import Dalle3
 
 # Create an instance of the Dalle3 class with high quality
 dalle3 = Dalle3(quality="high")
@@ -11,4 +11,4 @@ image_url = dalle3(task)
 
 # Print the generated image URL
 print(image_url)
-'''
+"""

playground/examples/example_gpt4vison.py

@@ -5,7 +5,10 @@ api = GPT4VisionAPI(max_tokens=1000)
 
 # Define the task and image URL
 task = "Describe the scene in the image."
-img = "/home/kye/.swarms/swarms/examples/Screenshot from 2024-02-20 05-55-34.png"
+img = (
+    "/home/kye/.swarms/swarms/examples/Screenshot from 2024-02-20"
+    " 05-55-34.png"
+)
 
 # Run the GPT-4 Vision model
 response = api.run(task, img)

playground/examples/example_huggingfacellm.py

@@ -11,19 +11,26 @@ try:
     device = "cuda" if torch.cuda.is_available() else "cpu"
     inference.model.to(device)
 
-    prompt_text = "Create a list of known biggest risks of structural collapse with references"
-    inputs = inference.tokenizer(prompt_text, return_tensors="pt").to(device)
-    
+    prompt_text = (
+        "Create a list of known biggest risks of structural collapse"
+        " with references"
+    )
+    inputs = inference.tokenizer(prompt_text, return_tensors="pt").to(
+        device
+    )
+
     generated_ids = inference.model.generate(
         **inputs,
         max_new_tokens=1000,  # Adjust the length of the generation
         temperature=0.7,  # Adjust creativity
         top_k=50,  # Limits the vocabulary considered at each step
         pad_token_id=inference.tokenizer.eos_token_id,
-        do_sample=True  # Enable sampling to utilize temperature
+        do_sample=True,  # Enable sampling to utilize temperature
+    )
+
+    generated_text = inference.tokenizer.decode(
+        generated_ids[0], skip_special_tokens=True
     )
-    
-    generated_text = inference.tokenizer.decode(generated_ids[0], skip_special_tokens=True)
     print(generated_text)
 except Exception as e:
     print(f"An error occurred: {e}")

playground/examples/example_logistics.py

@@ -48,7 +48,9 @@ productivity_agent = Agent(
 )
 
 # Initiailize safety agent
-safety_agent = Agent(llm=llm, sop=Safety_Agent_Prompt, max_loops=1, multi_modal=True)
+safety_agent = Agent(
+    llm=llm, sop=Safety_Agent_Prompt, max_loops=1, multi_modal=True
+)
 
 # Init the security agent
 security_agent = Agent(

playground/examples/example_qwenvlmultimodal.py

@@ -8,7 +8,9 @@ model = QwenVLMultiModal(
 )
 
 # Run the model
-response = model("Hello, how are you?", "https://example.com/image.jpg")
+response = model(
+    "Hello, how are you?", "https://example.com/image.jpg"
+)
 
 # Print the response
 print(response)

playground/examples/example_sequentialworkflow.py

@@ -10,7 +10,10 @@ api_key = os.getenv("OPENAI_API_KEY")
 
 # Initialize the language agent
 llm = OpenAIChat(
-    temperature=0.5, model_name="gpt-4", openai_api_key=api_key, max_tokens=4000
+    temperature=0.5,
+    model_name="gpt-4",
+    openai_api_key=api_key,
+    max_tokens=4000,
 )
 
 

playground/examples/example_simple_conversation_agent.py

@@ -29,7 +29,9 @@ def interactive_conversation(llm):
         conv.add("user", user_input)
         if user_input.lower() == "quit":
             break
-        task = conv.return_history_as_string()  # Get the conversation history
+        task = (
+            conv.return_history_as_string()
+        )  # Get the conversation history
         out = llm(task)
         conv.add("assistant", out)
         print(

playground/examples/example_swarmnetwork.py

@@ -40,5 +40,7 @@ print(out)
 
 
 # Run all the agents in the swarm network on a task
-out = swarmnet.run_many_agents("Generate a 10,000 word blog on health and wellness.")
+out = swarmnet.run_many_agents(
+    "Generate a 10,000 word blog on health and wellness."
+)
 print(out)

playground/examples/example_toolagent.py

@@ -3,7 +3,9 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 from swarms import ToolAgent
 
 # Load the pre-trained model and tokenizer
-model = AutoModelForCausalLM.from_pretrained("databricks/dolly-v2-12b")
+model = AutoModelForCausalLM.from_pretrained(
+    "databricks/dolly-v2-12b"
+)
 tokenizer = AutoTokenizer.from_pretrained("databricks/dolly-v2-12b")
 
 # Define a JSON schema for person's information
@@ -18,10 +20,14 @@ json_schema = {
 }
 
 # Define the task to generate a person's information
-task = "Generate a person's information based on the following schema:"
+task = (
+    "Generate a person's information based on the following schema:"
+)
 
 # Create an instance of the ToolAgent class
-agent = ToolAgent(model=model, tokenizer=tokenizer, json_schema=json_schema)
+agent = ToolAgent(
+    model=model, tokenizer=tokenizer, json_schema=json_schema
+)
 
 # Run the agent to generate the person's information
 generated_data = agent.run(task)

playground/examples/example_worker.py

@@ -27,7 +27,9 @@ worker = Worker(
 )
 
 # Running the worker with a prompt
-out = worker.run("Hello, how are you? Create an image of how your are doing!")
+out = worker.run(
+    "Hello, how are you? Create an image of how your are doing!"
+)
 
 # Printing the output
 print(out)

pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "swarms"
-version = "4.3.3"
+version = "4.3.7"
 description = "Swarms - Pytorch"
 license = "MIT"
 authors = ["Kye Gomez <kye@apac.ai>"]
@@ -26,7 +26,7 @@ classifiers = [
 [tool.poetry.dependencies]
 python = ">=3.9,<4.0"
 torch = ">=2.1.1,<3.0"
-transformers = "*"
+transformers = "4.39.0"
 asyncio = ">=3.4.3,<4.0"
 einops = "0.7.0"
 google-generativeai = "0.3.1"
@@ -36,8 +36,11 @@ faiss-cpu = "1.7.4"
 backoff = "2.2.1"
 datasets = "*"
 optimum = "1.15.0"
+supervision = "0.19.0"
+opencv-python = "4.9.0.80"
 diffusers = "*"
 langchain = "0.1.7"
+anthropic = "0.2.5"
 toml = "*"
 pypdf = "4.0.1"
 accelerate = "*"

requirements.txt

@@ -21,12 +21,14 @@ addict
 backoff==2.2.1
 ratelimit==2.2.1
 termcolor==2.2.0
+opencv-python==4.9.0.80
 langchain-community
 timm
 torchvision==0.16.1
 rich==13.5.2
 mkdocs
 mkdocs-material
+anthropic==0.2.5
 mkdocs-glightbox
 pre-commit==3.6.2
 psutil

swarms/telemetry/sentry_active.py

@@ -1,4 +1,4 @@
-import os 
+import os
 from dotenv import load_dotenv
 import sentry_sdk
 
@@ -8,6 +8,7 @@ os.environ["USE_TELEMETRY"] = "True"
 
 use_telementry = os.getenv("USE_TELEMETRY")
 
+
 def activate_sentry():
     if use_telementry == "True":
         sentry_sdk.init(
@@ -15,6 +16,5 @@ def activate_sentry():
             traces_sample_rate=1.0,
             profiles_sample_rate=1.0,
             enable_tracing=True,
-            debug = True,
+            debug=True,
         )
-        

swarms/tools/tool.py

@@ -1,6 +0,0 @@
-from langchain.tools import (
-    BaseTool,
-    Tool,
-    StructuredTool,
-    tool,
-)  # noqa F401