[README]

README.md

@@ -108,6 +108,56 @@ generated_data = agent.run(task)
 
 print(generated_data)
 
+```
+
+
+### `Worker`
+The `Worker` is a simple all-in-one agent equipped with an LLM, tools, and RAG. Get started below:
+
+✅ Plug in and Play LLM. Utilize any LLM from anywhere and any framework
+
+✅ Reliable RAG: Utilizes FAISS for efficient RAG but it's modular so you can use any DB.
+
+✅ Multi-Step Parallel Function Calling: Use any tool
+
+```python
+# Importing necessary modules
+import os
+from dotenv import load_dotenv
+from swarms import Worker, OpenAIChat, tool
+
+# Loading environment variables from .env file
+load_dotenv()
+
+# Retrieving the OpenAI API key from environment variables
+api_key = os.getenv("OPENAI_API_KEY")
+
+
+# Create a tool
+@tool
+def search_api(query: str):
+    pass
+
+
+# Creating a Worker instance
+worker = Worker(
+    name="My Worker",
+    role="Worker",
+    human_in_the_loop=False,
+    tools=[search_api],
+    temperature=0.5,
+    llm=OpenAIChat(openai_api_key=api_key),
+)
+
+# Running the worker with a prompt
+out = worker.run(
+    "Hello, how are you? Create an image of how your are doing!"
+)
+
+# Printing the output
+print(out)
+
+
 ```
 
 ------

playground/agents/worker_example.py

@@ -1,12 +1,16 @@
+# Importing necessary modules
 import os
 from dotenv import load_dotenv
 from swarms.agents.worker_agent import Worker
 from swarms import OpenAIChat
 
+# Loading environment variables from .env file
 load_dotenv()
 
+# Retrieving the OpenAI API key from environment variables
 api_key = os.getenv("OPENAI_API_KEY")
 
+# Creating a Worker instance
 worker = Worker(
     name="My Worker",
     role="Worker",
@@ -14,9 +18,13 @@ worker = Worker(
     tools=[],
     temperature=0.5,
     llm=OpenAIChat(openai_api_key=api_key),
+    verbose = True,
 )
 
+# Running the worker with a prompt
 out = worker.run(
     "Hello, how are you? Create an image of how your are doing!"
 )
+
+# Printing the output
 print(out)

playground/demos/fof/langchain.py

@@ -0,0 +1,5 @@
+"""
+This tutorial shows you how to integrate swarms with Langchain
+
+"""
+

swarms/agents/__init__.py

@@ -15,6 +15,7 @@ from swarms.agents.stopping_conditions import (
 )
 from swarms.agents.tool_agent import ToolAgent
 from swarms.agents.worker_agent import Worker
+from swarms.agents.agent_wrapper import agent_wrapper
 
 __all__ = [
     "AbstractAgent",
@@ -32,4 +33,5 @@ __all__ = [
     "check_exit",
     "check_end",
     "Worker",
+    "agent_wrapper",
 ]

swarms/agents/agent_wrapper.py

@@ -0,0 +1,25 @@
+from swarms.structs.agent import Agent
+
+def agent_wrapper(ClassToWrap):
+    """
+    This function takes a class 'ClassToWrap' and returns a new class that
+    inherits from both 'ClassToWrap' and 'Agent'. The new class overrides
+    the '__init__' method of 'Agent' to call the '__init__' method of 'ClassToWrap'.
+    
+    Args:
+        ClassToWrap (type): The class to be wrapped and made to inherit from 'Agent'.
+        
+    Returns:
+        type: The new class that inherits from both 'ClassToWrap' and 'Agent'.
+    """
+    
+    class WrappedClass(ClassToWrap, Agent):
+        def __init__(self, *args, **kwargs):
+            try:
+                Agent.__init__(self, *args, **kwargs)
+                ClassToWrap.__init__(self, *args, **kwargs)
+            except Exception as e:
+                print(f"Error initializing WrappedClass: {e}")
+                raise e
+    
+    return WrappedClass

swarms/agents/worker_agent.py

@@ -51,6 +51,7 @@ class Worker:
         tools: List[Any] = None,
         embedding_size: int = 1536,
         search_kwargs: dict = {"k": 8},
+        verbose: bool = False,
         *args,
         **kwargs,
     ):
@@ -64,6 +65,7 @@ class Worker:
         self.tools = tools
         self.embedding_size = embedding_size
         self.search_kwargs = search_kwargs
+        self.verbose = verbose
 
         self.setup_tools(external_tools)
         self.setup_memory()

swarms/models/anthropic.py

@@ -29,9 +29,7 @@ from langchain.schema.language_model import BaseLanguageModel
 from langchain.schema.output import GenerationChunk
 from langchain.schema.prompt import PromptValue
 from langchain.utils import (
-    check_package_version,
     get_from_dict_or_env,
-    get_pydantic_field_names,
 )
 from packaging.version import parse
 from requests import HTTPError, Response

swarms/structs/task.py

@@ -233,6 +233,7 @@ class Task:
                     if task.description is not None
                     else ""
                 )
+                
                 result = (
                     task.result if task.result is not None else ""
                 )