[DOCS FIX] [BUGF][Agent]

docs/swarms/structs/majorityvoting.md

@@ -1,6 +1,4 @@
-Due to the limitations of this platform and the scope of your request, I am unable to create a full 10,000-word documentation here. However, I can provide a structured outline for a comprehensive documentation guide that you could expand upon offline.
-
-# swarms.structs Documentation
+# `MajorityVoting` Documentation
 
 ## Overview
 
@@ -43,15 +41,6 @@ The `MajorityVoting` class is a high-level abstraction used to coordinate a grou
 
 ### Class Definition
 
-```python
-class MajorityVoting:
-    def __init__(self, agents, concurrent=False, multithreaded=False, multiprocess=False, asynchronous=False, output_parser=None, autosave=False, verbose=False, *args, **kwargs):
-        pass
-
-    def run(self, task, *args, **kwargs):
-        pass
-```
-
 ### Parameters
 
 | Parameter       | Type       | Default  | Description                                                          |
@@ -118,21 +107,3 @@ result = majority_voting.run("What is the square root of 16?")
 print(result)  # Output: 4
 ```
 
-## Advanced Features
-
-Detailed instructions on how to use multithreading, multiprocessing, asynchronous execution, and how to parse the output with custom functions would be included in this section.
-
-## Troubleshooting and FAQ
-
-This section would cover common problems and questions related to the `swarms.structs` library.
-
-## Conclusion
-
-A summary of the `swarms.structs` library's capabilities and potential applications in various domains.
-
-## References
-
-Links to external documentation, source code repository, and any further reading regarding swarms or collective decision-making algorithms.
-
----
-**Note:** Expand on each section by incorporating explanations, additional code examples, and in-depth descriptions of how the underlying mechanisms work for each method and functionality provided by the `MajorityVoting` class. Consider adding visual aids such as flowcharts or diagrams where appropriate.

docs/swarms/structs/taskqueuebase.md

@@ -1,8 +1,5 @@
-Due to the limitations of the platform, it's not possible to create documentation as long and detailed as 10,000 words within a single response. However, I can provide you with an outline and the starting point for a comprehensive and professional documentation in markdown format for the `TaskQueueBase` class according to the steps provided. 
 
-Here is the template you can follow to expand upon:
-
-# swarms.structs Documentation
+# `TaskQueueBase`
 
 ## Introduction
 The `swarms.structs` library is a key component of a multi-agent system's task management infrastructure. It provides the necessary classes and methods to create and manage queues of tasks that can be distributed among a swarm of agents. The purpose of this documentation is to guide users through the proper use of the `TaskQueueBase` class, which serves as an abstract base class for implementing task queues.
@@ -128,8 +125,3 @@ This section would provide insights on thread safety, error handling, and best p
 
 Links to further resources and any academic papers or external documentation related to task queues and multi-agent systems would be included here.
 
----
-
-Please note that this is just an outline of the structure and beginning of the documentation. For a full documentation, expand each section to include detail_sy examples, considerations for thread safety, performance implications, and subtleties of the implementation. You can also add a FAQ section, troubleshooting guide, and any benchmarks if available. 
-
-Remember, each method should be thoroughly explained with explicit examples that include handling successes and failures, as well as edge cases that might be encountered. The documentation should also consider various environments where the `TaskQueueBase` class may be used, such as different operating systems, and Python environments (i.e. CPython vs. PyPy).

playground/agents/multion_agent.py

@@ -64,9 +64,7 @@ class MultiOnAgent(AbstractLLM):
 
 
 # model
-model = MultiOnAgent(
-    multion_api_key=""
-)
+model = MultiOnAgent(multion_api_key="")
 
 # out = model.run("search for a recipe")
 agent = Agent(

playground/agents/perimeter_defense_agent.py

@@ -0,0 +1,70 @@
+import os
+from dotenv import load_dotenv
+from swarms.models import GPT4VisionAPI
+from swarms.structs import Agent
+import swarms.prompts.security_team as stsp
+
+# Load environment variables and initialize the Vision API
+load_dotenv()
+api_key = os.getenv("OPENAI_API_KEY")
+
+llm = GPT4VisionAPI(openai_api_key=api_key)
+
+# Image for analysis
+img = "bank_robbery.jpg"
+
+# Initialize agents with respective prompts for security tasks
+crowd_analysis_agent = Agent(
+    llm=llm,
+    sop=stsp.CROWD_ANALYSIS_AGENT_PROMPT,
+    max_loops=1,
+    multi_modal=True,
+)
+
+weapon_detection_agent = Agent(
+    llm=llm,
+    sop=stsp.WEAPON_DETECTION_AGENT_PROMPT,
+    max_loops=1,
+    multi_modal=True,
+)
+
+surveillance_monitoring_agent = Agent(
+    llm=llm,
+    sop=stsp.SURVEILLANCE_MONITORING_AGENT_PROMPT,
+    max_loops=1,
+    multi_modal=True,
+)
+
+emergency_response_coordinator = Agent(
+    llm=llm,
+    sop=stsp.EMERGENCY_RESPONSE_COORDINATOR_PROMPT,
+    max_loops=1,
+    multi_modal=True,
+)
+
+# Run agents with respective tasks on the same image
+crowd_analysis = crowd_analysis_agent.run(
+    "Analyze the crowd dynamics in the scene", img
+)
+
+weapon_detection_analysis = weapon_detection_agent.run(
+    "Inspect the scene for any potential threats", img
+)
+
+surveillance_monitoring_analysis = surveillance_monitoring_agent.run(
+    "Monitor the overall scene for unusual activities", img
+)
+
+emergency_response_analysis = emergency_response_coordinator.run(
+    "Develop a response plan based on the scene analysis", img
+)
+
+# Process and output results for each task
+# Example output (uncomment to use):
+print(f"Crowd Analysis: {crowd_analysis}")
+print(f"Weapon Detection Analysis: {weapon_detection_analysis}")
+print(
+    "Surveillance Monitoring Analysis:"
+    f" {surveillance_monitoring_analysis}"
+)
+print(f"Emergency Response Analysis: {emergency_response_analysis}")

swarms/structs/agent.py

@@ -29,6 +29,7 @@ from swarms.utils.pdf_to_text import pdf_to_text
 from swarms.utils.token_count_tiktoken import limit_tokens_from_string
 from swarms.tools.exec_tool import execute_tool_by_name
 from swarms.prompts.worker_prompt import worker_tools_sop_promp
+from swarms.structs.schemas import Step
 
 
 # Utils
@@ -50,6 +51,14 @@ def agent_id():
     return str(uuid.uuid4())
 
 
+def task_id():
+    return str(uuid.uuid4())
+
+
+def step_id():
+    return str(uuid.uuid1())
+
+
 class Agent:
     """
     Agent is the backbone to connect LLMs with tools and long term memory. Agent also provides the ability to
@@ -296,6 +305,9 @@ class Agent:
         # Initialize the llm with the conditional variables
         # self.llm = llm(*args, **kwargs)
 
+        # Step cache
+        self.step_cache = []
+
     def set_system_prompt(self, system_prompt: str):
         """Set the system prompt"""
         self.system_prompt = system_prompt
@@ -522,7 +534,7 @@ class Agent:
             # Activate Autonomous agent message
             self.activate_autonomous_agent()
 
-            response = task  # or combined_prompt
+            # response = task  # or combined_prompt
             history = self._history(self.user_name, task)
 
             # If dashboard = True then print the dashboard
@@ -541,20 +553,13 @@ class Agent:
                 self.loop_count_print(loop_count, self.max_loops)
                 print("\n")
 
-                # Check to see if stopping token is in the output to stop the loop
-                if self.stopping_token:
-                    if self._check_stopping_condition(
-                        response
-                    ) or parse_done_token(response):
-                        break
-
                 # Adjust temperature, comment if no work
                 if self.dynamic_temperature_enabled:
                     print(colored("Adjusting temperature...", "blue"))
                     self.dynamic_temperature()
 
                 # Preparing the prompt
-                task = self.agent_history_prompt(history=response)
+                task = self.agent_history_prompt(history=task)
 
                 attempt = 0
                 while attempt < self.retry_attempts:
@@ -573,6 +578,24 @@ class Agent:
                             )
                             print(response)
 
+                        # Log each step
+                        step = Step(
+                            input=task,
+                            task_id=task_id,
+                            step_id=step_id,
+                            output=response,
+                        )
+
+                        # Check to see if stopping token is in the output to stop the loop
+                        if self.stopping_token:
+                            if self._check_stopping_condition(
+                                response
+                            ) or parse_done_token(response):
+                                break
+
+                        self.step_cache.append(step)
+                        logging.info(f"Step: {step}")
+
                         # If parser exists then parse the response
                         if self.parser:
                             response = self.parser(response)
@@ -692,10 +715,8 @@ class Agent:
         else:
             system_prompt = self.system_prompt
             agent_history_prompt = f"""
-                SYSTEM_PROMPT: {system_prompt}
-
-
-                ################ CHAT HISTORY ####################
+                System : {system_prompt}
+                
                 {history}
             """
             return agent_history_prompt