From b9634f95384d2bb1299a614f7c1be5197ba4f58e Mon Sep 17 00:00:00 2001
From: Kye <kye@apacmediasolutions.com>
Date: Tue, 3 Oct 2023 13:23:03 -0400
Subject: [PATCH] clean up godmode exampleg

---
 README.md                         | 24 ++++++++++++++++++++----
 swarms/swarms/god_mode.py         | 29 ++++++++++++++++++++++++++++-
 swarms/swarms/scable_groupchat.py | 31 ++++++++++++++++++++++---------
 3 files changed, 70 insertions(+), 14 deletions(-)

diff --git a/README.md b/README.md
index c257b2d5..6361e721 100644
--- a/README.md
+++ b/README.md
@@ -57,15 +57,31 @@ print(response)
 ---
 
 ## Usage
-
+- `GodMode` is a simple class that takes in x amount of llms and when given a task runs them all concurrently!
 ```python
 
-from swarms import HuggingFaceLLM
 
-hugging_face_model = HuggingFaceLLM(model_id="Voicelab/trurl-2-13b")
-generated_text = hugging_face_model.generate("In a world where AI")
+from swarms.models import Anthropic, GooglePalm, OpenAIChat
+from swarms.swarms import GodMode
+
+claude = Anthropic(anthropic_api_key="")
+palm = GooglePalm(google_api_key="")
+gpt = OpenAIChat(openai_api_key="")
+
+# Usage
+llms = [
+   claude,
+   palm,
+   gpt 
+]
+
+god_mode = GodMode(llms)
+
+task = f"What are the biggest risks facing humanity?"
 
+god_mode.print_responses(task)
 ```
+- The `Worker` is an fully feat
 ```python
 
 from swarms import Worker
diff --git a/swarms/swarms/god_mode.py b/swarms/swarms/god_mode.py
index 00f32be7..1fd5f50e 100644
--- a/swarms/swarms/god_mode.py
+++ b/swarms/swarms/god_mode.py
@@ -4,10 +4,37 @@ from tabulate import tabulate
 
 
 class GodMode:
+    """
+    GodMode
+    -----
+
+    Architecture:
+    How it works:
+    1. GodMode receives a task from the user.
+    2. GodMode distributes the task to all LLMs.
+    3. GodMode collects the responses from all LLMs.
+    4. GodMode prints the responses from all LLMs.
+
+    Parameters:
+    llms: list of LLMs
+
+    Methods:
+    run(task): distribute task to all LLMs and collect responses
+    print_responses(task): print responses from all LLMs
+
+    Usage:
+    god_mode = GodMode(llms)
+    god_mode.run(task)
+    god_mode.print_responses(task)
+
+    
+
+
+    """
     def __init__(self, llms):
         self.llms = llms
 
-    def run_all(self, task):
+    def run(self, task):
         with ThreadPoolExecutor() as executor:
             responses = executor.map(lambda llm: llm(task), self.llms)
         return list(responses)
diff --git a/swarms/swarms/scable_groupchat.py b/swarms/swarms/scable_groupchat.py
index f4c60c4c..61787d4f 100644
--- a/swarms/swarms/scable_groupchat.py
+++ b/swarms/swarms/scable_groupchat.py
@@ -20,8 +20,10 @@ class ScalableGroupChat:
 
     Worker -> ScalableGroupChat(Worker * 10) 
     -> every response is embedded and placed in chroma
-    -> every response is then retrieved and sent to the worker
+    -> every response is then retrieved by querying the database and sent then passed into the prompt of the worker
     -> every worker is then updated with the new response
+    -> every worker can communicate at any time
+    -> every worker can communicate without restrictions in parallel
 
     """
     def __init__(
@@ -32,21 +34,34 @@ class ScalableGroupChat:
     ):
         self.workers = []
         self.worker_count = worker_count
+        self.collection_name = collection_name
+        self.api_key = api_key
 
         # Create a list of Worker instances with unique names
         for i in range(worker_count):
-            self.workers.append(Worker(openai_api_key=api_key, ai_name=f"Worker-{i}"))
+            self.workers.append(
+                Worker(
+                    openai_api_key=api_key, 
+                    ai_name=f"Worker-{i}"
+                )
+            )
         
-    def embed(self, input, api_key, model_name):
+    def embed(
+        self, 
+        input, 
+        model_name
+    ):
+        """Embeds an input of size N into a vector of size M"""
         openai = embedding_functions.OpenAIEmbeddingFunction(
-            api_key=api_key,
+            api_key=self.api_key,
             model_name=model_name
         )
+
         embedding = openai(input)
+
         return embedding
                 
     
-    # @abstractmethod
     def retrieve_results(
         self, 
         agent_id: int
@@ -115,8 +130,8 @@ class ScalableGroupChat:
         
         Allows the agents to chat with eachother thrught the vectordatabase
 
-        # Instantiate the Orchestrator with 10 agents
-        orchestrator = Orchestrator(
+        # Instantiate the ScalableGroupChat with 10 agents
+        orchestrator = ScalableGroupChat(
             llm, 
             agent_list=[llm]*10, 
             task_queue=[]
@@ -131,8 +146,6 @@ class ScalableGroupChat:
         
         message_vector = self.embed(
             message,
-            self.api_key,
-            self.model_name
         )
 
         #store the mesage in the vector database