[README][ModelParallelizer]g

README.md

@@ -460,6 +460,48 @@ print(video_path)
 ```
 
 
+### `ModelParallelizer`
+- Run any models concurrent to compare outputs
+- Concurrent execution of various llms
+- Plug in and play with your models
+
+```python
+import os
+
+from dotenv import load_dotenv
+
+from swarms.models import Anthropic, Gemini, Mixtral, OpenAIChat
+from swarms.swarms import ModelParallelizer
+
+load_dotenv()
+
+# API Keys
+anthropic_api_key = os.getenv("ANTHROPIC_API_KEY")
+openai_api_key = os.getenv("OPENAI_API_KEY")
+gemini_api_key = os.getenv("GEMINI_API_KEY")
+
+# Initialize the models
+llm = OpenAIChat(openai_api_key=openai_api_key)
+anthropic = Anthropic(anthropic_api_key=anthropic_api_key)
+mixtral = Mixtral()
+gemini = Gemini(gemini_api_key=gemini_api_key)
+
+# Initialize the parallelizer
+llms = [llm, anthropic, mixtral, gemini]
+parallelizer = ModelParallelizer(llms)
+
+# Set the task
+task = "Generate a 10,000 word blog on health and wellness."
+
+# Run the task
+out = parallelizer.run(task)
+
+# Print the responses 1 by 1
+for i in range(len(out)):
+    print(f"Response from LLM {i}: {out[i]}")
+```
+
+
 ### Simple Conversational Agent
 - Plug in and play conversational agent with `GPT4`, `Mixytral`, or any of our models
 - Reliable conversational structure to hold messages together with dynamic handling for long context conversations and interactions with auto chunking

docs/swarms/swarms/godmode.md

@@ -102,8 +102,8 @@ Now that we have covered the class definition, let's delve into the functionalit
 One of the primary use cases of `ModelParallelizer` is to distribute a task to all registered LLMs and collect their responses. This can be achieved using the `run(task)` method. Below is an example:
 
 ```python
-god_mode = ModelParallelizer(llms)
-responses = god_mode.run("Translate the following English text to French: 'Hello, how are you?'")
+parallelizer = ModelParallelizer(llms)
+responses = parallelizer.run("Translate the following English text to French: 'Hello, how are you?'")
 ```
 
 ### Printing Responses
@@ -111,7 +111,7 @@ responses = god_mode.run("Translate the following English text to French: 'Hello
 To present the responses from all LLMs in a structured tabular format, use the `print_responses(task)` method. Example:
 
 ```python
-god_mode.print_responses("Summarize the main points of 'War and Peace.'")
+parallelizer.print_responses("Summarize the main points of 'War and Peace.'")
 ```
 
 ### Saving Responses to a File
@@ -119,7 +119,7 @@ god_mode.print_responses("Summarize the main points of 'War and Peace.'")
 Users can save the responses to a file using the `save_responses_to_file(filename)` method. This is useful for archiving and reviewing responses later. Example:
 
 ```python
-god_mode.save_responses_to_file("responses.txt")
+parallelizer.save_responses_to_file("responses.txt")
 ```
 
 ### Task History
@@ -127,7 +127,7 @@ god_mode.save_responses_to_file("responses.txt")
 The `ModelParallelizer` class keeps track of the task history. Developers can access the task history using the `get_task_history()` method. Example:
 
 ```python
-task_history = god_mode.get_task_history()
+task_history = parallelizer.get_task_history()
 for i, task in enumerate(task_history):
     print(f"Task {i + 1}: {task}")
 ```
@@ -186,13 +186,13 @@ worker3 = Worker(
 
 # Register the worker agents with ModelParallelizer
 agents = [worker1, worker2, worker3]
-god_mode = ModelParallelizer(agents)
+parallelizer = ModelParallelizer(agents)
 
 # Task for sentiment analysis
 task = "Please analyze the sentiment of the following sentence: 'This movie is amazing!'"
 
 # Print responses from all agents
-god_mode.print_responses(task)
+parallelizer.print_responses(task)
 ```
 
 ### Example 2: Translation
@@ -209,13 +209,13 @@ translator3 = OpenAIChat(model_name="translator-en-de", openai_api_key="api-key"
 
 # Register translation agents with ModelParallelizer
 translators = [translator1, translator2, translator3]
-god_mode = ModelParallelizer(translators)
+parallelizer = ModelParallelizer(translators)
 
 # Task for translation
 task = "Translate the following English text to French: 'Hello, how are you?'"
 
 # Print translated responses from all agents
-god_mode.print_responses(task)
+parallelizer.print_responses(task)
 ```
 
 ### Example 3: Summarization
@@ -233,13 +233,13 @@ summarizer3 = OpenAIChat(model_name="summarizer-en", openai_api_key="api-key", t
 
 # Register summarization agents with ModelParallelizer
 summarizers = [summarizer1, summarizer2, summarizer3]
-god_mode = ModelParallelizer(summarizers)
+parallelizer = ModelParallelizer(summarizers)
 
 # Task for summarization
 task = "Summarize the main points of the article titled 'Climate Change and Its Impact on the Environment.'"
 
 # Print summarized responses from all agents
-god_mode.print_responses(task)
+parallelizer.print_responses(task)
 ```
 
 ## 7. Conclusion <a name="conclusion"></a>

playground/swarms/godmode.py

@@ -1,16 +1,33 @@
-from swarms.swarms import ModelParallelizer
-from swarms.models import OpenAIChat
+import os
+
+from dotenv import load_dotenv
 
-api_key = ""
+from swarms.models import Anthropic, Gemini, Mixtral, OpenAIChat
+from swarms.swarms import ModelParallelizer
 
-llm = OpenAIChat(openai_api_key=api_key)
+load_dotenv()
 
+# API Keys
+anthropic_api_key = os.getenv("ANTHROPIC_API_KEY")
+openai_api_key = os.getenv("OPENAI_API_KEY")
+gemini_api_key = os.getenv("GEMINI_API_KEY")
 
-llms = [llm, llm, llm]
+# Initialize the models
+llm = OpenAIChat(openai_api_key=openai_api_key)
+anthropic = Anthropic(anthropic_api_key=anthropic_api_key)
+mixtral = Mixtral()
+gemini = Gemini(gemini_api_key=gemini_api_key)
 
-god_mode = ModelParallelizer(llms)
+# Initialize the parallelizer
+llms = [llm, anthropic, mixtral, gemini]
+parallelizer = ModelParallelizer(llms)
 
+# Set the task
 task = "Generate a 10,000 word blog on health and wellness."
 
-out = god_mode.run(task)
-god_mode.print_responses(task)
+# Run the task
+out = parallelizer.run(task)
+
+# Print the responses 1 by 1
+for i in range(len(out)):
+    print(f"Response from LLM {i}: {out[i]}")

swarms/swarms/model_parallizer.py

@@ -31,9 +31,9 @@ class ModelParallelizer:
     print_responses(task): print responses from all LLMs
 
     Usage:
-    god_mode = ModelParallelizer(llms)
-    god_mode.run(task)
-    god_mode.print_responses(task)
+    parallelizer = ModelParallelizer(llms)
+    parallelizer.run(task)
+    parallelizer.print_responses(task)
 
 
     """