[CLEANUP]

README.md

@@ -407,56 +407,6 @@ print(f"Generated data: {generated_data}")
 ```
 
 
-### `Worker`
-The `Worker` is a simple all-in-one agent equipped with an LLM, tools, and RAG for low level tasks.
-
-✅ 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 OpenAIChat, Worker, 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)
-```
-
-------
-
-
 
 
 
@@ -1189,6 +1139,7 @@ Apache License
 
 # Citation
 Please cite Swarms in your paper or your project if you found it beneficial in any way! Appreciate you.
+
 ```bibtex
 @misc{swarms,
   author = {Gomez, Kye},

pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "swarms"
-version = "5.1.5"
+version = "5.1.6"
 description = "Swarms - Pytorch"
 license = "MIT"
 authors = ["Kye Gomez <kye@apac.ai>"]

swarms/models/kosmos_two.py

@@ -1,3 +1,4 @@
+
 import requests
 from PIL import Image
 from transformers import AutoModelForVision2Seq, AutoProcessor
@@ -13,6 +14,23 @@ def is_overlapping(rect1, rect2):
 
 
 class Kosmos(BaseMultiModalModel):
+    """A class representing the Kosmos model.
+
+    This model is used for multi-modal tasks such as grounding, referring expression comprehension,
+    referring expression generation, grounded VQA, grounded image captioning, and more.
+
+    Args:
+        model_name (str): The name or path of the pre-trained model.
+        max_new_tokens (int): The maximum number of new tokens to generate.
+        verbose (bool): Whether to print verbose output.
+        *args: Variable length argument list.
+        **kwargs: Arbitrary keyword arguments.
+
+    Attributes:
+        max_new_tokens (int): The maximum number of new tokens to generate.
+        model (AutoModelForVision2Seq): The pre-trained model for vision-to-sequence tasks.
+        processor (AutoProcessor): The pre-trained processor for vision-to-sequence tasks.
+    """
 
     def __init__(
         self,
@@ -37,10 +55,10 @@ class Kosmos(BaseMultiModalModel):
         """Get image from url
 
         Args:
-            url (str): url of image
+            url (str): The URL of the image.
 
         Returns:
-            _type_: _description_
+            PIL.Image: The image object.
         """
         return Image.open(requests.get(url, stream=True).raw)
 
@@ -48,8 +66,8 @@ class Kosmos(BaseMultiModalModel):
         """Run the model
 
         Args:
-            task (str): task to run
+            task (str): The task to run.
-            image (str): img url
+            image (str): The URL of the image.
         """
         inputs = self.processor(
             text=task, images=image, return_tensors="pt"