Merge branch 'kyegomez:master' into master

README.md

@@ -34,28 +34,35 @@ Run example in Collab: <a target="_blank" href="https://colab.research.google.co
 
 ```python
 
+import os
+
+from dotenv import load_dotenv
+
+# Import the OpenAIChat model and the Flow struct
 from swarms.models import OpenAIChat
 from swarms.structs import Flow
 
-api_key = ""
+# Load the environment variables
+load_dotenv()
 
-# Initialize the language model, this model can be swapped out with Anthropic, ETC, Huggingface Models like Mistral, ETC
+# Get the API key from the environment
+api_key = os.environ.get("OPENAI_API_KEY")
+
+# Initialize the language model
 llm = OpenAIChat(
-    openai_api_key=api_key,
     temperature=0.5,
+    openai_api_key=api_key,
 )
 
-## Initialize the workflow
-flow = Flow(
-    llm=llm,
-    max_loops=2,
-    dashboard=True,
 
-)
+## Initialize the workflow
+flow = Flow(llm=llm, max_loops=1, dashboard=True)
 
+# Run the workflow on a task
 out = flow.run("Generate a 10,000 word blog on health and wellness.")
 
 
+
 ```
 
 ------
@@ -125,24 +132,32 @@ for task in workflow.tasks:
 ```python
 from swarms.structs import Flow
 from swarms.models.gpt4_vision_api import GPT4VisionAPI
+from swarms.prompts.multi_modal_autonomous_instruction_prompt import (
+    MULTI_MODAL_AUTO_AGENT_SYSTEM_PROMPT_1,
+)
 
-# Initialize the llm
 llm = GPT4VisionAPI()
 
-task = "Analyze this image of an assembly line and identify any issues such as misaligned parts, defects, or deviations from the standard assembly process. IF there is anything unsafe in the image, explain why it is unsafe and how it could be improved."
+task = (
+    "Analyze this image of an assembly line and identify any issues such as"
+    " misaligned parts, defects, or deviations from the standard assembly"
+    " process. IF there is anything unsafe in the image, explain why it is"
+    " unsafe and how it could be improved."
+)
 img = "assembly_line.jpg"
 
 ## Initialize the workflow
 flow = Flow(
     llm=llm,
-    max_loops=1,
+    max_loops='auto'
+    sop=MULTI_MODAL_AUTO_AGENT_SYSTEM_PROMPT_1,
     dashboard=True,
 )
 
-# Run the flow
 flow.run(task=task, img=img)
 
 
+
 ```
 
 ---

example.py

@@ -1,9 +1,21 @@
+import os
+
+from dotenv import load_dotenv
+
+# Import the OpenAIChat model and the Flow struct
 from swarms.models import OpenAIChat
 from swarms.structs import Flow
 
+# Load the environment variables
+load_dotenv()
+
+# Get the API key from the environment
+api_key = os.environ.get("OPENAI_API_KEY")
+
 # Initialize the language model
 llm = OpenAIChat(
     temperature=0.5,
+    openai_api_key=api_key,
 )
 
 

multi_modal_auto_agent.py

@@ -1,5 +1,8 @@
 from swarms.structs import Flow
 from swarms.models.gpt4_vision_api import GPT4VisionAPI
+from swarms.prompts.multi_modal_autonomous_instruction_prompt import (
+    MULTI_MODAL_AUTO_AGENT_SYSTEM_PROMPT_1,
+)
 
 
 llm = GPT4VisionAPI()
@@ -10,6 +13,7 @@
 ## Initialize the workflow
 flow = Flow(
     llm=llm,
+    sop=MULTI_MODAL_AUTO_AGENT_SYSTEM_PROMPT_1,
     max_loops="auto",
 )
 

playground/demos/assembly/assembly.py

@@ -1,6 +1,8 @@
 from swarms.structs import Flow
 from swarms.models.gpt4_vision_api import GPT4VisionAPI
-
+from swarms.prompts.multi_modal_autonomous_instruction_prompt import (
+    MULTI_MODAL_AUTO_AGENT_SYSTEM_PROMPT_1,
+)
 
 llm = GPT4VisionAPI()
 

playground/demos/idea_2_img/main.py

@@ -0,0 +1,7 @@
+"""
+Idea 2 img
+
+task -> gpt4 text -> dalle3 img -> gpt4vision img + text analyze img -> dalle3 img -> loop    
+    
+"""
+from swarms.models.gpt4_vision_api import GPT4VisionAPI

playground/demos/swarm_of_mma_manufacturing/main.py

@@ -0,0 +1,15 @@
+"""
+Swarm of multi modal autonomous agents for manufacturing!
+---------------------------------------------------------    
+Health Security agent: Agent that monitors the health of working conditions: input image of factory output: health safety index 0.0 - 1.0 being the highest
+Quality Control agent: Agent that monitors the quality of the product: input image of product output: quality index 0.0 - 1.0 being the highest
+Productivity agent: Agent that monitors the productivity of the factory: input image of factory output: productivity index 0.0 - 1.0 being the highest
+Safety agent: Agent that monitors the safety of the factory: input image of factory output: safety index 0.0 - 1.0 being the highest
+Security agent: Agent that monitors the security of the factory: input image of factory output: security index 0.0 - 1.0 being the highest
+Sustainability agent: Agent that monitors the sustainability of the factory: input image of factory output: sustainability index 0.0 - 1.0 being the highest
+Efficiency agent: Agent that monitors the efficiency of the factory: input image of factory output: efficiency index 0.0 - 1.0 being the highest    
+
+
+Flow:
+health security agent -> quality control agent -> productivity agent -> safety agent -> security agent -> sustainability agent -> efficiency agent 
+"""

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "swarms"
-version = "2.4.1"
+version = "2.4.2"
 description = "Swarms - Pytorch"
 license = "MIT"
 authors = ["Kye Gomez <[email protected]>"]

swarms/models/base_multimodal_model.py

@@ -1,3 +1,4 @@
+from abc import abstractmethod
 import asyncio
 import base64
 import concurrent.futures
@@ -7,8 +8,8 @@
 from typing import List, Optional, Tuple
 
 import requests
-from ABC import abstractmethod
 from PIL import Image
+from termcolor import colored
 
 
 class BaseMultiModalModel:
@@ -37,7 +38,6 @@ def __init__(
         self.retries = retries
         self.chat_history = []
 
-
     @abstractmethod
     def __call__(self, text: str, img: str):
         """Run the model"""
@@ -61,17 +61,17 @@ def get_img_from_web(self, img: str):
         except requests.RequestException as error:
             print(f"Error fetching image from {img} and error: {error}")
             return None
-        
+
     def encode_img(self, img: str):
         """Encode the image to base64"""
         with open(img, "rb") as image_file:
             return base64.b64encode(image_file.read()).decode("utf-8")
-    
+
     def get_img(self, img: str):
         """Get the image from the path"""
         image_pil = Image.open(img)
         return image_pil
-    
+
     def clear_chat_history(self):
         """Clear the chat history"""
         self.chat_history = []
@@ -87,11 +87,11 @@ def run_many(
         Args:
             tasks (List[str]): List of tasks
             imgs (List[str]): List of image paths
-        
+
         Returns:
             List[str]: List of responses
-            
-        
+
+
         """
         # Instantiate the thread pool executor
         with ThreadPoolExecutor(max_workers=self.max_workers) as executor:
@@ -101,7 +101,6 @@ def run_many(
         for result in results:
             print(result)
 
-
     def run_batch(self, tasks_images: List[Tuple[str, str]]) -> List[str]:
         """Process a batch of tasks and images"""
         with concurrent.futures.ThreadPoolExecutor() as executor:
@@ -133,11 +132,11 @@ async def run_batch_async_with_retries(
             for task, img in tasks_images
         ]
         return await asyncio.gather(*futures)
-    
+
     def unique_chat_history(self):
         """Get the unique chat history"""
         return list(set(self.chat_history))
-    
+
     def run_with_retries(self, task: str, img: str):
         """Run the model with retries"""
         for i in range(self.retries):
@@ -146,7 +145,7 @@ def run_with_retries(self, task: str, img: str):
             except Exception as error:
                 print(f"Error with the request {error}")
                 continue
-    
+
     def run_batch_with_retries(self, tasks_images: List[Tuple[str, str]]):
         """Run the model with retries"""
         for i in range(self.retries):
@@ -188,28 +187,37 @@ def get_generation_time(self) -> float:
         if self.start_time and self.end_time:
             return self.end_time - self.start_time
         return 0
-    
+
     def get_chat_history(self):
         """Get the chat history"""
         return self.chat_history
-    
+
     def get_unique_chat_history(self):
         """Get the unique chat history"""
         return list(set(self.chat_history))
-    
+
     def get_chat_history_length(self):
         """Get the chat history length"""
         return len(self.chat_history)
-    
+
     def get_unique_chat_history_length(self):
         """Get the unique chat history length"""
         return len(list(set(self.chat_history)))
-    
+
     def get_chat_history_tokens(self):
         """Get the chat history tokens"""
         return self._num_tokens()
-    
+
     def print_beautiful(self, content: str, color: str = "cyan"):
         """Print Beautifully with termcolor"""
         content = colored(content, color)
-        print(content)
+        print(content)
+
+    def stream(self, content: str):
+        """Stream the output
+
+        Args:
+            content (str): _description_
+        """
+        for chunk in content:
+            print(chunk)