swarms 7.6.2__py3-none-any.whl → 7.6.4__py3-none-any.whl

swarms/structs/agent.py

@@ -6,7 +6,6 @@ import random
 import threading
 import time
 import uuid
-
 from concurrent.futures import ThreadPoolExecutor
 from datetime import datetime
 from typing import (
@@ -39,10 +38,8 @@ from swarms.schemas.base_schemas import (
     ChatCompletionResponseChoice,
     ChatMessageResponse,
 )
-from swarms.structs.concat import concat_strings
+from swarms.structs.agent_roles import agent_roles
 from swarms.structs.conversation import Conversation
-
-# from swarms.structs.multi_agent_exec import run_agents_concurrently
 from swarms.structs.safe_loading import (
     SafeLoaderUtils,
     SafeStateManager,
@@ -54,9 +51,11 @@ from swarms.utils.any_to_str import any_to_str
 from swarms.utils.data_to_text import data_to_text
 from swarms.utils.file_processing import create_file_in_folder
 from swarms.utils.formatter import formatter
+from swarms.utils.history_output_formatter import (
+    history_output_formatter,
+)
 from swarms.utils.litellm_tokenizer import count_tokens
 from swarms.utils.pdf_to_text import pdf_to_text
-from swarms.structs.agent_roles import agent_roles
 from swarms.utils.str_to_dict import str_to_dict
 
 
@@ -473,12 +472,21 @@ class Agent:
         self.no_print = no_print
         self.tools_list_dictionary = tools_list_dictionary
 
+        if (
+            self.agent_name is not None
+            or self.agent_description is not None
+        ):
+            prompt = f"Your Name: {self.agent_name} \n\n Your Description: {self.agent_description} \n\n {system_prompt}"
+        else:
+            prompt = system_prompt
+
         # Initialize the short term memory
         self.short_memory = Conversation(
-            system_prompt=system_prompt,
+            system_prompt=prompt,
             time_enabled=False,
             user=user_name,
             rules=rules,
+            token_count=False,
             *args,
             **kwargs,
         )
@@ -504,24 +512,10 @@ class Agent:
                 tool_system_prompt=tool_system_prompt,
             )
 
-        # The max_loops will be set dynamically if the dynamic_loop
-        if self.dynamic_loops is True:
-            logger.info("Dynamic loops enabled")
-            self.max_loops = "auto"
-
-        # If multimodal = yes then set the sop to the multimodal sop
-        if self.multi_modal is True:
-            self.sop = MULTI_MODAL_AUTO_AGENT_SYSTEM_PROMPT_1
-
-        # If the preset stopping token is enabled then set the stopping token to the preset stopping token
-        if preset_stopping_token is not None:
-            self.stopping_token = "<DONE>"
-
-        # If the docs exist then ingest the docs
-        # if exists(self.docs):
-        #     threading.Thread(
-        #         target=self.ingest_docs, args=(self.docs)
-        #     ).start()
+        # Some common configuration settings
+        threading.Thread(
+            target=self.setup_config, daemon=True
+        ).start()
 
         # If docs folder exists then get the docs from docs folder
         if exists(self.docs_folder):
@@ -567,10 +561,6 @@ class Agent:
         if exists(self.sop) or exists(self.sop_list):
             threading.Thread(target=self.handle_sop_ops()).start()
 
-        # If agent_ops is on => activate agentops
-        if agent_ops_on is True:
-            threading.Thread(target=self.activate_agentops()).start()
-
         # Many steps
         self.agent_output = ManySteps(
             agent_id=agent_id,
@@ -634,12 +624,27 @@ class Agent:
                     temperature=self.temperature,
                     max_tokens=self.max_tokens,
                     system_prompt=self.system_prompt,
+                    stream=self.streaming_on,
                 )
             return llm
         except Exception as e:
             logger.error(f"Error in llm_handling: {e}")
             return None
 
+    def setup_config(self):
+        # The max_loops will be set dynamically if the dynamic_loop
+        if self.dynamic_loops is True:
+            logger.info("Dynamic loops enabled")
+            self.max_loops = "auto"
+
+        # If multimodal = yes then set the sop to the multimodal sop
+        if self.multi_modal is True:
+            self.sop = MULTI_MODAL_AUTO_AGENT_SYSTEM_PROMPT_1
+
+        # If the preset stopping token is enabled then set the stopping token to the preset stopping token
+        if self.preset_stopping_token is not None:
+            self.stopping_token = "<DONE>"
+
     def prepare_tools_list_dictionary(self):
         import json
 
@@ -775,18 +780,6 @@ class Agent:
         """,
         )
 
-    def loop_count_print(
-        self, loop_count: int, max_loops: int
-    ) -> None:
-        """loop_count_print summary
-
-        Args:
-            loop_count (_type_): _description_
-            max_loops (_type_): _description_
-        """
-        logger.info(f"\nLoop {loop_count} of {max_loops}")
-        print("\n")
-
     # Check parameters
     def check_parameters(self):
         if self.llm is None:
@@ -837,8 +830,6 @@ class Agent:
         try:
             self.check_if_no_prompt_then_autogenerate(task)
 
-            self.agent_output.task = task
-
             # Add task to memory
             self.short_memory.add(role=self.user_name, content=task)
 
@@ -848,17 +839,17 @@ class Agent:
 
             # Set the loop count
             loop_count = 0
+
             # Clear the short memory
             response = None
-            all_responses = []
 
             # Query the long term memory first for the context
             if self.long_term_memory is not None:
                 self.memory_query(task)
 
-            # Print the user's request
-
+            # Autosave
             if self.autosave:
+                log_agent_data(self.to_dict())
                 self.save()
 
             # Print the request
@@ -873,8 +864,11 @@ class Agent:
                 or loop_count < self.max_loops
             ):
                 loop_count += 1
-                self.loop_count_print(loop_count, self.max_loops)
-                print("\n")
+
+                # self.short_memory.add(
+                #     role=f"{self.agent_name}",
+                #     content=f"Internal Reasoning Loop: {loop_count} of {self.max_loops}",
+                # )
 
                 # Dynamic temperature
                 if self.dynamic_temperature_enabled is True:
@@ -905,48 +899,24 @@ class Agent:
                             if img is None
                             else (task_prompt, img, *args)
                         )
+
+                        # Call the LLM
                         response = self.call_llm(
                             *response_args, **kwargs
                         )
 
                         # Convert to a str if the response is not a str
-                        response = self.llm_output_parser(response)
+                        response = self.parse_llm_output(response)
 
-                        # if correct_answer is not None:
-                        #     if correct_answer not in response:
-                        #         logger.info("Correct answer found in response")
-                        #         # break
+                        self.short_memory.add(
+                            role=self.agent_name, content=response
+                        )
 
                         # Print
-                        if self.no_print is False:
-                            if self.streaming_on is True:
-                                # self.stream_response(response)
-                                formatter.print_panel_token_by_token(
-                                    f"{self.agent_name}: {response}",
-                                    title=f"Agent Name: {self.agent_name} [Max Loops: {loop_count}]",
-                                )
-                            else:
-                                # logger.info(f"Response: {response}")
-                                formatter.print_panel(
-                                    f"{self.agent_name}: {response}",
-                                    f"Agent Name {self.agent_name} [Max Loops: {loop_count} ]",
-                                )
-
-                        # Check if response is a dictionary and has 'choices' key
-                        if (
-                            isinstance(response, dict)
-                            and "choices" in response
-                        ):
-                            response = response["choices"][0][
-                                "message"
-                            ]["content"]
-                        elif isinstance(response, str):
-                            # If response is already a string, use it as is
-                            pass
-                        else:
-                            raise ValueError(
-                                f"Unexpected response format: {type(response)}"
-                            )
+                        self.pretty_print(response, loop_count)
+
+                        # Output Cleaner
+                        self.output_cleaner_op(response)
 
                         # Check and execute tools
                         if self.tools is not None:
@@ -978,34 +948,7 @@ class Agent:
                                 role=self.agent_name, content=out
                             )
 
-                        # Add the response to the memory
-                        self.short_memory.add(
-                            role=self.agent_name, content=response
-                        )
-
-                        # Add to all responses
-                        all_responses.append(response)
-
-                        # # TODO: Implement reliability check
-
-                        if self.evaluator:
-                            logger.info("Evaluating response...")
-                            evaluated_response = self.evaluator(
-                                response
-                            )
-                            print(
-                                "Evaluated Response:"
-                                f" {evaluated_response}"
-                            )
-                            self.short_memory.add(
-                                role="Evaluator",
-                                content=evaluated_response,
-                            )
-
-                        # Sentiment analysis
-                        if self.sentiment_analyzer:
-                            logger.info("Analyzing sentiment...")
-                            self.sentiment_analysis_handler(response)
+                        self.sentiment_and_evaluator(response)
 
                         success = True  # Mark as successful to exit the retry loop
 
@@ -1062,7 +1005,7 @@ class Agent:
                         break
 
                     self.short_memory.add(
-                        role=self.user_name, content=user_input
+                        role="User", content=user_input
                     )
 
                 if self.loop_interval:
@@ -1077,91 +1020,14 @@ class Agent:
                 if self.autosave is True:
                     self.save()
 
-            # Apply the cleaner function to the response
-            if self.output_cleaner is not None:
-                logger.info("Applying output cleaner to response.")
-                response = self.output_cleaner(response)
-                logger.info(
-                    f"Response after output cleaner: {response}"
-                )
-                self.short_memory.add(
-                    role="Output Cleaner",
-                    content=response,
-                )
-
-            if self.agent_ops_on is True and is_last is True:
-                self.check_end_session_agentops()
-
-            # Merge all responses
-            all_responses = [
-                response
-                for response in all_responses
-                if response is not None
-            ]
-
-            self.agent_output.steps = self.short_memory.to_dict()
-            self.agent_output.full_history = (
-                self.short_memory.get_str()
-            )
-            self.agent_output.total_tokens = count_tokens(
-                self.short_memory.get_str()
-            )
-
-            # # Handle artifacts
-            # if self.artifacts_on is True:
-            #     self.handle_artifacts(
-            #         concat_strings(all_responses),
-            #         self.artifacts_output_path,
-            #         self.artifacts_file_extension,
-            # )
-
             log_agent_data(self.to_dict())
 
             if self.autosave is True:
                 self.save()
 
-            # More flexible output types
-            if (
-                self.output_type == "string"
-                or self.output_type == "str"
-            ):
-                return concat_strings(all_responses)
-            elif self.output_type == "list":
-                return all_responses
-            elif (
-                self.output_type == "json"
-                or self.return_step_meta is True
-            ):
-                return self.agent_output.model_dump_json(indent=4)
-            elif self.output_type == "csv":
-                return self.dict_to_csv(
-                    self.agent_output.model_dump()
-                )
-            elif self.output_type == "dict":
-                return self.agent_output.model_dump()
-            elif self.output_type == "yaml":
-                return yaml.safe_dump(
-                    self.agent_output.model_dump(), sort_keys=False
-                )
-
-            elif self.output_type == "memory-list":
-                return self.short_memory.return_messages_as_list()
-
-            elif self.output_type == "memory-dict":
-                return (
-                    self.short_memory.return_messages_as_dictionary()
-                )
-            elif self.return_history is True:
-                history = self.short_memory.get_str()
-
-                formatter.print_panel(
-                    history, title=f"{self.agent_name} History"
-                )
-                return history
-            else:
-                raise ValueError(
-                    f"Invalid output type: {self.output_type}"
-                )
+            return history_output_formatter(
+                self.short_memory, type=self.output_type
+            )
 
         except Exception as error:
             self._handle_run_error(error)
@@ -1937,7 +1803,7 @@ class Agent:
         """Send a message to the agent"""
         try:
             logger.info(f"Sending agent message: {message}")
-            message = f"{agent_name}: {message}"
+            message = f"To: {agent_name}: {message}"
             return self.run(message, *args, **kwargs)
         except Exception as error:
             logger.info(f"Error sending agent message: {error}")
@@ -2014,20 +1880,6 @@ class Agent:
             )
             raise error
 
-    def check_end_session_agentops(self):
-        if self.agent_ops_on is True:
-            try:
-                from swarms.utils.agent_ops_check import (
-                    end_session_agentops,
-                )
-
-                # Try ending the session
-                return end_session_agentops()
-            except ImportError:
-                logger.error(
-                    "Could not import agentops, try installing agentops: $ pip3 install agentops"
-                )
-
     def memory_query(self, task: str = None, *args, **kwargs) -> None:
         try:
             # Query the long term memory
@@ -2154,50 +2006,6 @@ class Agent:
 
         return out
 
-    def activate_agentops(self):
-        if self.agent_ops_on is True:
-            try:
-                from swarms.utils.agent_ops_check import (
-                    try_import_agentops,
-                )
-
-                # Try importing agent ops
-                logger.info(
-                    "Agent Ops Initializing, ensure that you have the agentops API key and the pip package installed."
-                )
-                try_import_agentops()
-                self.agent_ops_agent_name = self.agent_name
-
-                logger.info("Agentops successfully activated!")
-            except ImportError:
-                logger.error(
-                    "Could not import agentops, try installing agentops: $ pip3 install agentops"
-                )
-
-    def llm_output_parser(self, response: Any) -> str:
-        """Parse the output from the LLM"""
-        try:
-            if isinstance(response, dict):
-                if "choices" in response:
-                    return response["choices"][0]["message"][
-                        "content"
-                    ]
-                else:
-                    return json.dumps(
-                        response
-                    )  # Convert dict to string
-            elif isinstance(response, str):
-                return response
-            else:
-                return str(
-                    response
-                )  # Convert any other type to string
-        except Exception as e:
-            logger.error(f"Error parsing LLM output: {e}")
-            return str(
-                response
-            )  # Return string representation as fallback
-
     def log_step_metadata(
         self, loop: int, task: str, response: str
     ) -> Step:
@@ -2693,9 +2501,88 @@ class Agent:
         """
         return self.role
 
-    # def __getstate__(self):
-    #     state = self.__dict__.copy()
-    #     # Remove or replace unpicklable attributes.
-    #     if '_queue' in state:
-    #         del state['_queue']
-    #     return state
+    def pretty_print(self, response: str, loop_count: int):
+        if self.no_print is False:
+            if self.streaming_on is True:
+                # self.stream_response(response)
+                formatter.print_panel_token_by_token(
+                    f"{self.agent_name}: {response}",
+                    title=f"Agent Name: {self.agent_name} [Max Loops: {loop_count}]",
+                )
+            else:
+                # logger.info(f"Response: {response}")
+                formatter.print_panel(
+                    f"{self.agent_name}: {response}",
+                    f"Agent Name {self.agent_name} [Max Loops: {loop_count} ]",
+                )
+
+    def parse_llm_output(self, response: Any) -> str:
+        """Parse and standardize the output from the LLM.
+
+        Args:
+            response (Any): The response from the LLM in any format
+
+        Returns:
+            str: Standardized string output
+
+        Raises:
+            ValueError: If the response format is unexpected and can't be handled
+        """
+        try:
+            # Handle dictionary responses
+            if isinstance(response, dict):
+                if "choices" in response:
+                    return response["choices"][0]["message"][
+                        "content"
+                    ]
+                return json.dumps(
+                    response
+                )  # Convert other dicts to string
+
+            # Handle string responses
+            elif isinstance(response, str):
+                return response
+
+            # Handle list responses (from check_llm_outputs)
+            elif isinstance(response, list):
+                return "\n".join(response)
+
+            # Handle any other type by converting to string
+            else:
+                return str(response)
+
+        except Exception as e:
+            logger.error(f"Error parsing LLM output: {e}")
+            raise ValueError(
+                f"Failed to parse LLM output: {type(response)}"
+            )
+
+    def sentiment_and_evaluator(self, response: str):
+        if self.evaluator:
+            logger.info("Evaluating response...")
+
+            evaluated_response = self.evaluator(response)
+            print("Evaluated Response:" f" {evaluated_response}")
+            self.short_memory.add(
+                role="Evaluator",
+                content=evaluated_response,
+            )
+
+        # Sentiment analysis
+        if self.sentiment_analyzer:
+            logger.info("Analyzing sentiment...")
+            self.sentiment_analysis_handler(response)
+
+    def output_cleaner_op(self, response: str):
+        # Apply the cleaner function to the response
+        if self.output_cleaner is not None:
+            logger.info("Applying output cleaner to response.")
+
+            response = self.output_cleaner(response)
+
+            logger.info(f"Response after output cleaner: {response}")
+
+            self.short_memory.add(
+                role="Output Cleaner",
+                content=response,
+            )

swarms/structs/base_swarm.py

@@ -89,7 +89,6 @@ class BaseSwarm(ABC):
         stopping_function: Optional[Callable] = None,
         stopping_condition: Optional[str] = "stop",
         stopping_condition_args: Optional[Dict] = None,
-        agentops_on: Optional[bool] = False,
         speaker_selection_func: Optional[Callable] = None,
         rules: Optional[str] = None,
         collective_memory_system: Optional[Any] = False,
@@ -112,7 +111,6 @@ class BaseSwarm(ABC):
         self.stopping_function = stopping_function
         self.stopping_condition = stopping_condition
         self.stopping_condition_args = stopping_condition_args
-        self.agentops_on = agentops_on
         self.speaker_selection_func = speaker_selection_func
         self.rules = rules
         self.collective_memory_system = collective_memory_system
@@ -167,11 +165,6 @@ class BaseSwarm(ABC):
             self.stopping_condition_args = stopping_condition_args
             self.stopping_condition = stopping_condition
 
-        # If agentops is enabled, try to import agentops
-        if agentops_on is True:
-            for agent in self.agents:
-                agent.agent_ops_on = True
-
         # Handle speaker selection function
         if speaker_selection_func is not None:
             if not callable(speaker_selection_func):

swarms/structs/concurrent_workflow.py

@@ -262,7 +262,7 @@ class ConcurrentWorkflow(BaseSwarm):
         ) -> AgentOutputSchema:
             start_time = datetime.now()
             try:
-                output = agent.run(task=task, img=img)
+                output = agent.run(task=task)
 
                 self.conversation.add(
                     agent.agent_name,

swarms/structs/conversation.py

@@ -119,7 +119,7 @@ class Conversation(BaseStructure):
             content (Union[str, dict, list]): The content of the message to be added.
         """
         now = datetime.datetime.now()
-        timestamp = now.strftime("%Y-%m-%d %H:%M:%S")
+        now.strftime("%Y-%m-%d %H:%M:%S")
 
         # Base message with role
         message = {
@@ -129,8 +129,12 @@ class Conversation(BaseStructure):
         # Handle different content types
         if isinstance(content, dict) or isinstance(content, list):
             message["content"] = content
+        elif self.time_enabled:
+            message["content"] = (
+                f"Time: {now.strftime('%Y-%m-%d %H:%M:%S')} \n {content}"
+            )
         else:
-            message["content"] = f"Time: {timestamp} \n {content}"
+            message["content"] = content
 
         # Add the message to history immediately without waiting for token count
         self.conversation_history.append(message)
@@ -510,6 +514,16 @@ class Conversation(BaseStructure):
         """
         return f"{self.conversation_history[-1]['role']}: {self.conversation_history[-1]['content']}"
 
+    def get_final_message_content(self):
+        """Return the content of the final message from the conversation history.
+
+        Returns:
+            str: The content of the final message.
+        """
+        output = self.conversation_history[-1]["content"]
+        # print(output)
+        return output
+
 
 # # Example usage
 # # conversation = Conversation()

swarms/structs/de_hallucination_swarm.py

@@ -4,7 +4,8 @@ from loguru import logger
 from swarms.structs.agent import Agent
 
 # Prompt templates for different agent roles
-GENERATOR_PROMPT = """You are a knowledgeable assistant tasked with providing accurate information on a wide range of topics.
+GENERATOR_PROMPT = """
+You are a knowledgeable assistant tasked with providing accurate information on a wide range of topics.
 
 Your responsibilities:
 1. Provide accurate information based on your training data
@@ -22,7 +23,8 @@ When responding to queries:
 Remember, it's better to acknowledge ignorance than to provide incorrect information.
 """
 
-CRITIC_PROMPT = """You are a critical reviewer tasked with identifying potential inaccuracies, hallucinations, or unsupported claims in AI-generated text.
+CRITIC_PROMPT = """
+You are a critical reviewer tasked with identifying potential inaccuracies, hallucinations, or unsupported claims in AI-generated text.
 
 Your responsibilities:
 1. Carefully analyze the provided text for factual errors
@@ -47,7 +49,8 @@ Focus particularly on:
 Be thorough and specific in your critique. Provide actionable feedback for improvement.
 """
 
-REFINER_PROMPT = """You are a refinement specialist tasked with improving text based on critical feedback.
+REFINER_PROMPT = """
+You are a refinement specialist tasked with improving text based on critical feedback.
 
 Your responsibilities:
 1. Carefully review the original text and the critical feedback
@@ -67,7 +70,8 @@ Guidelines for refinement:
 The refined text should be helpful and informative while being scrupulously accurate.
 """
 
-VALIDATOR_PROMPT = """You are a validation expert tasked with ensuring the highest standards of accuracy in refined AI outputs.
+VALIDATOR_PROMPT = """
+You are a validation expert tasked with ensuring the highest standards of accuracy in refined AI outputs.
 
 Your responsibilities:
 1. Verify that all critical issues from previous feedback have been properly addressed