[PLAYGROUND][Cleanup]

multion_agent.py

@@ -1,10 +1,9 @@
 from swarms.agents.multion_agent import MultiOnAgent
 import timeit
 from swarms import Agent, ConcurrentWorkflow, Task
-from swarms.utils.loguru_logger import logger
 
 # model
-model = MultiOnAgent(multion_api_key="")
+model = MultiOnAgent(multion_api_key="535ae401948b4c59bc1b2c61eec90fe6")
 
 # out = model.run("search for a recipe")
 agent = Agent(
@@ -15,27 +14,26 @@ agent = Agent(
     system_prompt=None,
 )
 
-logger.info("[Agent][ID][MultiOnAgent][Initialized][Successfully")
+# logger.info("[Agent][ID][MultiOnAgent][Initialized][Successfully")
 
 # Task
 task = Task(
     agent=agent,
     description=(
-        "send an email to vyom on superhuman for a partnership with"
+        "Download https://www.coachcamel.com/"
-        " multion"
     ),
 )
 
 # Swarm
-logger.info(
+# logger.info(
-    f"Running concurrent workflow with task: {task.description}"
+#     f"Running concurrent workflow with task: {task.description}"
-)
+# )
 
 # Measure execution time
 start_time = timeit.default_timer()
 
 workflow = ConcurrentWorkflow(
-    max_workers=1,
+    max_workers=20,
     autosave=True,
     print_results=True,
     return_results=True,
@@ -47,4 +45,5 @@ workflow.run()
 
 # Calculate execution time
 execution_time = timeit.default_timer() - start_time
-logger.info(f"Execution time: {execution_time} seconds")
+# logger.info(f"Execution time: {execution_time} seconds")
+print(f"Execution time: {execution_time} seconds")

playground/diy/hierchical_example.py

@@ -1,28 +0,0 @@
-from swarms import HierarchicalSwarm
-
-swarm = HierarchicalSwarm(
-    openai_api_key="key",
-    model_type="openai",
-    model_id="gpt-4",
-    use_vectorstore=False,
-    use_async=False,
-    human_in_the_loop=False,
-    logging_enabled=False,
-)
-
-# run the swarm with an objective
-result = swarm.run("Design a new car")
-
-# or huggingface
-swarm = HierarchicalSwarm(
-    model_type="huggingface",
-    model_id="tiaueu/falcon",
-    use_vectorstore=True,
-    embedding_size=768,
-    use_async=False,
-    human_in_the_loop=True,
-    logging_enabled=False,
-)
-
-# Run the swarm with a particular objective
-result = swarm.run("Write a sci-fi short story")

playground/memory/chroma_usage_example.py

@@ -1,11 +1,17 @@
-from swarms.memory import chroma
+from swarms.memory import ChromaDB
 
-chromadbcl = chroma.ChromaClient()
 
-chromadbcl.add_vectors(
+# Initialize the memory
-    ["This is a document", "BONSAIIIIIII", "the walking dead"]
+chroma = ChromaDB(
+    metric="cosine",
+    limit_tokens=1000,
+    verbose=True,
 )
 
-results = chromadbcl.search_vectors("zombie", limit=1)
+# Add text
+text = "This is a test"
+chroma.add(text)
+
+# Search for similar text
+similar_text = chroma.query(text)
 
-print(results)

playground/structs/agent_with_longterm_memory.py

@@ -14,7 +14,7 @@ api_key = os.environ.get("OPENAI_API_KEY")
 
 # Initilaize the chromadb client
 chromadb = ChromaDB(
-    metric="cosine",
+    metric="cosine",g
     output="results",
 )
 

playground/structs/chat_example.py

@@ -1,11 +0,0 @@
-from swarms import Orchestrator, Worker
-
-# Instantiate the Orchestrator with 10 agents
-orchestrator = Orchestrator(
-    Worker, agent_list=[Worker] * 10, task_queue=[]
-)
-
-# Agent 1 sends a message to Agent 2
-orchestrator.chat(
-    sender_id=1, receiver_id=2, message="Hello, Agent 2!"
-)

playground/structs/company_example.py

@@ -1,4 +1,3 @@
-# Example
 
 import os
 

playground/structs/dialogue_simulator_example.py

@@ -1,6 +1,5 @@
 from swarms.models import OpenAIChat
-from swarms.swarms import DialogueSimulator
+from swarms import DialogueSimulator, Worker
-from swarms.workers.worker import Worker
 
 llm = OpenAIChat(
     model_name="gpt-4", openai_api_key="api-key", temperature=0.5

playground/structs/easy_example.py

@@ -1,7 +1,14 @@
-from swarms import swarm
+from swarms import Agent, OpenAIChat
 
-# Use the function
+## Initialize the workflow
-api_key = "APIKEY"
+agent = Agent(
-objective = "What is the capital of the UK?"
+    llm=OpenAIChat(),
-result = swarm(api_key, objective)
+    max_loops=1,
-print(result)  # Prints: "The capital of the UK is London."
+    autosave=True,
+    dashboard=False,
+    streaming_on=True,
+    verbose=True,
+)
+
+# Run the workflow on a task
+agent("Find a chick fil a equivalent in hayes valley")

playground/structs/godmode_example.py

@@ -3,7 +3,7 @@ import os
 from dotenv import load_dotenv
 
 from swarms.models import Anthropic, Gemini, Mixtral, OpenAIChat
-from swarms.swarms import ModelParallelizer
+from swarms import ModelParallelizer
 
 load_dotenv()
 

playground/structs/orchestrator_example.py

@@ -1,19 +0,0 @@
-from swarms import Orchestrator, Worker
-
-node = Worker(
-    openai_api_key="",
-    ai_name="Optimus Prime",
-)
-
-
-# Instantiate the Orchestrator with 10 agents
-orchestrator = Orchestrator(
-    node, agent_list=[node] * 10, task_queue=[]
-)
-
-# Agent 7 sends a message to Agent 9
-orchestrator.chat(
-    sender_id=7,
-    receiver_id=9,
-    message="Can you help me with this task?",
-)

playground/structs/social_app_example.py

@@ -1,19 +0,0 @@
-from ..swarms import HierarchicalSwarm
-
-# Retrieve your API key from the environment or replace with your actual key
-api_key = "sksdsds"
-
-# Initialize HierarchicalSwarm with your API key
-swarm = HierarchicalSwarm(openai_api_key=api_key)
-
-# Define an objective
-objective = """
-Please develop and serve a simple community web service.
-People can signup, login, post, comment.
-Post and comment should be visible at once.
-I want it to have neumorphism-style.
-The ports you can use are 4500 and 6500.
-"""
-
-# Run HierarchicalSwarm
-swarm.run(objective)

playground/structs/swarms_example.py

@@ -1,16 +0,0 @@
-from swarms import HierarchicalSwarm
-
-# Retrieve your API key from the environment or replace with your actual key
-api_key = ""
-
-# Initialize HierarchicalSwarm with your API key
-swarm = HierarchicalSwarm(api_key)
-
-# Define an objective
-objective = (
-    "Find 20 potential customers for a HierarchicalSwarm based AI"
-    " Agent automation infrastructure"
-)
-
-# Run HierarchicalSwarm
-swarm.run(objective)

playground/structs/todo_app_example.py

@@ -1,19 +0,0 @@
-from swarms import HierarchicalSwarm
-
-# Retrieve your API key from the environment or replace with your actual key
-api_key = "sksdsds"
-
-# Initialize HierarchicalSwarm with your API key
-swarm = HierarchicalSwarm(openai_api_key=api_key)
-
-# Define an objective
-objective = """
-Please develop and serve a simple web TODO app.
-The user can list all TODO items and add or delete each TODO item.
-I want it to have neumorphism-style.
-The ports you can use are 4500 and 6500.
-
-"""
-
-# Run HierarchicalSwarm
-swarm.run(objective)

playground/structs/tool_utils_example.py

@@ -1,19 +0,0 @@
-from swarms.tools.tool import tool
-from swarms.tools.tool_func_doc_scraper import scrape_tool_func_docs
-
-
-@tool
-def search_api(query: str) -> str:
-    """Search API
-
-    Args:
-        query (str): _description_
-
-    Returns:
-        str: _description_
-    """
-    print(f"Searching API for {query}")
-
-
-tool_docs = scrape_tool_func_docs(search_api)
-print(tool_docs)

playground/structs/workflow_example.py

@@ -1,7 +0,0 @@
-from swarms.models import OpenAIChat
-from swarms.structs.workflow import Workflow
-
-llm = OpenAIChat()
-
-
-workflow = Workflow(llm)

playground/tools/agent_with_tools_example.py

@@ -2,8 +2,8 @@ import os
 
 from dotenv import load_dotenv
 
-from swarms.models import OpenAIChat
+from swarms import OpenAIChat, Agent
-from swarms.structs import Agent
+from swarms.tools.tool import tool
 
 load_dotenv()
 
@@ -12,24 +12,24 @@ api_key = os.environ.get("OPENAI_API_KEY")
 
 llm = OpenAIChat(api_key=api_key)
 
-# @tool
+@tool
-# def search_api(query: str) -> str:
+def search_api(query: str) -> str:
-#     """Search API
+    """Search API
 
-#     Args:
+    Args:
-#         query (str): _description_
+        query (str): _description_
 
-#     Returns:
+    Returns:
-#         str: _description_
+        str: _description_
-#     """
+    """
-#     print(f"Searching API for {query}")
+    print(f"Searching API for {query}")
 
 
 ## Initialize the workflow
 agent = Agent(
     llm=llm,
     max_loops=5,
-    # tools=[search_api],
+    tools=[search_api],
     dashboard=True,
 )
 

playground/tools/tool_prompt_scaper_example.py

@@ -1,22 +0,0 @@
-from swarms.tools.tool import tool
-from swarms.tools.tool_func_doc_scraper import scrape_tool_func_docs
-
-# Define a tool by decorating a function with the tool decorator and providing a docstring
-
-
-@tool(return_direct=True)
-def search_api(query: str):
-    """Search the web for the query
-
-    Args:
-        query (str): _description_
-
-    Returns:
-        _type_: _description_
-    """
-    return f"Search results for {query}"
-
-
-# Scrape the tool func docs to prepare for injection into the agent prompt
-out = scrape_tool_func_docs(search_api)
-print(out)

playground/workflow_example_example.py

@@ -1,10 +0,0 @@
-from swarms import Workflow
-from swarms.models import ChatOpenAI
-
-workflow = Workflow(ChatOpenAI)
-
-workflow.add("What's the weather in miami")
-workflow.add("Provide details for {{ parent_output }}")
-workflow.add("Summarize the above information: {{ parent_output}}")
-
-workflow.run()

swarms/agents/multion_agent.py

@@ -37,12 +37,7 @@ class MultiOnAgent(AbstractLLM):
         self.max_steps = max_steps
         self.starting_url = starting_url
 
-        self.multion = multion.login(
+
-            use_api=True,
-            multion_api_key=str(multion_api_key),
-            *args,
-            **kwargs,
-        )
 
     def run(self, task: str, *args, **kwargs):
         """
@@ -56,7 +51,14 @@ class MultiOnAgent(AbstractLLM):
         Returns:
             dict: The response from the browsing task.
         """
-        response = self.multion.browse(
+        multion.login(
+            use_api=True,
+            multion_api_key=str(self.multion_api_key),
+            *args,
+            **kwargs,
+        )
+        
+        response = multion.browse(
             {
                 "cmd": task,
                 "url": self.starting_url,