`class ScalableGroupChat:`

Former-commit-id: e0f110fdef

swarms/swarms/scable_groupchat.py

@@ -15,91 +15,27 @@ class TaskStatus(Enum):
 
 class ScalableGroupChat:
     """
-    The Orchestrator takes in an agent, worker, or boss as input 
+    This is a class to enable scalable groupchat like a telegram, it takes an Worker as an input
-    then handles all the logic for
+    and handles all the logic to enable multi-agent collaboration at massive scale.
-    - task creation,
-    - task assignment,
-    - and task compeletion.
 
-    And, the communication for millions of agents to chat with eachother through
+    Worker -> ScalableGroupChat(Worker * 10) 
-    a vector database that each agent has access to chat with.
+    -> every response is embedded and placed in chroma
+    -> every response is then retrieved and sent to the worker
+    -> every worker is then updated with the new response
 
-    Each LLM agent chats with the orchestrator through a dedicated 
-    communication layer. The orchestrator assigns tasks to each LLM agent,
-    which the agents then complete and return. 
-
-    This setup allows for a high degree of flexibility, scalability, and robustness.
-
-    In the context of swarm LLMs, one could consider an **Omni-Vector Embedding Database
-    for communication. This database could store and manage 
-    the high-dimensional vectors produced by each LLM agent.
-
-    Strengths: This approach would allow for similarity-based lookup and matching of 
-    LLM-generated vectors, which can be particularly useful for tasks that involve finding similar outputs or recognizing patterns.
-
-    Weaknesses: An Omni-Vector Embedding Database might add complexity to the system in terms of setup and maintenance. 
-    It might also require significant computational resources, 
-    depending on the volume of data being handled and the complexity of the vectors. 
-    The handling and transmission of high-dimensional vectors could also pose challenges 
-    in terms of network load.
-
-    # Orchestrator
-    * Takes in an agent class with vector store, 
-    then handles all the communication and scales 
-    up a swarm with number of agents and handles task assignment and task completion
-
-    from swarms import OpenAI, Orchestrator, Swarm
-
-    orchestrated = Orchestrate(OpenAI, nodes=40) #handles all the task assignment and allocation and agent communication using a vectorstore as a universal communication layer and also handlles the task completion logic
-
-    Objective = "Make a business website for a marketing consultancy"
-
-    Swarms = Swarms(orchestrated, auto=True, Objective))
-    ```
-
-    In terms of architecture, the swarm might look something like this:
-
-    ```
-                                            (Orchestrator)
-                                                /        \
-            Tools + Vector DB -- (LLM Agent)---(Communication Layer)       (Communication Layer)---(LLM Agent)-- Tools + Vector DB 
-                /                  |                                           |                 \
-    (Task Assignment)      (Task Completion)                    (Task Assignment)       (Task Completion)
-
-    
-    ###Usage
-    ```
-    from swarms import Orchestrator 
-    
-    # Instantiate the Orchestrator with 10 agents
-    orchestrator = Orchestrator(llm, agent_list=[llm]*10, task_queue=[])
-
-    # Add tasks to the Orchestrator
-    tasks = [{"content": f"Write a short story about a {animal}."} for animal in ["cat", "dog", "bird", "fish", "lion", "tiger", "elephant", "giraffe", "monkey", "zebra"]]
-    orchestrator.assign_tasks(tasks)
-
-    # Run the Orchestrator
-    orchestrator.run()
-
-    # Retrieve the results
-    for task in tasks:
-    print(orchestrator.retrieve_result(id(task)))
-    ```
     """
     def __init__(
         self,
         worker_count: int = 5,
         collection_name: str = "swarm",
         api_key: str = None,
-        model_name: str = None,
-        worker = None
     ):
         self.workers = []
         self.worker_count = worker_count
 
         # Create a list of Worker instances with unique names
         for i in range(worker_count):
-            self.workers.append(Worker(openai_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):
         openai = embedding_functions.OpenAIEmbeddingFunction(