swarms 7.8.4__tar.gz → 7.8.8__tar.gz

{swarms-7.8.4 → swarms-7.8.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: swarms
-Version: 7.8.4
+Version: 7.8.8
 Summary: Swarms - TGSC
 License: MIT
 Keywords: artificial intelligence,deep learning,optimizers,Prompt Engineering,swarms,agents,llms,transformers,multi-agent,swarms of agents,Enterprise-Grade Agents,Production-Grade Agents,Agents,Multi-Grade-Agents,Swarms,Transformers,LLMs,Prompt Engineering,Agents,Generative Agents,Generative AI,Agent Marketplace,Agent Store,quant,finance,algorithmic trading,portfolio optimization,risk management,financial modeling,machine learning for finance,natural language processing for finance
@@ -1424,15 +1424,13 @@ print(out)
 -------
 
 ## SpreadSheetSwarm
+
 SpreadSheetSwarm manages thousands of agents concurrently for efficient task processing. It supports one-to-many task distribution, scalability, and autosaving results. Initialized with a name, description, agents, and settings, the run method executes tasks and returns a dictionary of agent outputs.
 
 [Learn more:](https://docs.swarms.world/en/latest/swarms/structs/spreadsheet_swarm/)
 
 ```python
-import os
 from swarms import Agent, SpreadSheetSwarm
-from swarm_models import OpenAIChat
-
 # Define custom system prompts for each social media platform
 TWITTER_AGENT_SYS_PROMPT = """
 You are a Twitter marketing expert specializing in real estate. Your task is to create engaging, concise tweets to promote properties, analyze trends to maximize engagement, and use appropriate hashtags and timing to reach potential buyers.
@@ -1459,7 +1457,7 @@ agents = [
     Agent(
         agent_name="Twitter-RealEstate-Agent",
         system_prompt=TWITTER_AGENT_SYS_PROMPT,
-        model_name="gpt-4o",
+        model_name="gpt-4o-mini",
         max_loops=1,
         dynamic_temperature_enabled=True,
         saved_state_path="twitter_realestate_agent.json",
@@ -1469,7 +1467,7 @@ agents = [
     Agent(
         agent_name="Instagram-RealEstate-Agent",
         system_prompt=INSTAGRAM_AGENT_SYS_PROMPT,
-        model_name="gpt-4o",
+        model_name="gpt-4o-mini",
         max_loops=1,
         dynamic_temperature_enabled=True,
         saved_state_path="instagram_realestate_agent.json",
@@ -1479,7 +1477,7 @@ agents = [
     Agent(
         agent_name="Facebook-RealEstate-Agent",
         system_prompt=FACEBOOK_AGENT_SYS_PROMPT,
-        model_name="gpt-4o",
+        model_name="gpt-4o-mini",
         max_loops=1,
         dynamic_temperature_enabled=True,
         saved_state_path="facebook_realestate_agent.json",
@@ -1489,7 +1487,7 @@ agents = [
     Agent(
         agent_name="LinkedIn-RealEstate-Agent",
         system_prompt=LINKEDIN_AGENT_SYS_PROMPT,
-        model_name="gpt-4o",
+        model_name="gpt-4o-mini",
         max_loops=1,
         dynamic_temperature_enabled=True,
         saved_state_path="linkedin_realestate_agent.json",
@@ -1499,7 +1497,7 @@ agents = [
     Agent(
         agent_name="Email-RealEstate-Agent",
         system_prompt=EMAIL_AGENT_SYS_PROMPT,
-        model_name="gpt-4o",
+        model_name="gpt-4o-mini",
         max_loops=1,
         dynamic_temperature_enabled=True,
         saved_state_path="email_realestate_agent.json",
@@ -1963,32 +1961,18 @@ A production-grade multi-agent system enabling sophisticated group conversations
 
 
 ```python
-
-import os
-from dotenv import load_dotenv
-from swarm_models import OpenAIChat
 from swarms import Agent, GroupChat, expertise_based
 
 
 if __name__ == "__main__":
 
-    load_dotenv()
-
-    # Get the OpenAI API key from the environment variable
-    api_key = os.getenv("OPENAI_API_KEY")
-
-    # Create an instance of the OpenAIChat class
-    model = OpenAIChat(
-        openai_api_key=api_key,
-        model_name="gpt-4o-mini",
-        temperature=0.1,
-    )
 
     # Example agents
     agent1 = Agent(
         agent_name="Financial-Analysis-Agent",
         system_prompt="You are a financial analyst specializing in investment strategies.",
-        llm=model,
+        model_name="gpt-4o-mini",
+        temperature=0.1,        
         max_loops=1,
         autosave=False,
         dashboard=False,
@@ -2004,7 +1988,8 @@ if __name__ == "__main__":
     agent2 = Agent(
         agent_name="Tax-Adviser-Agent",
         system_prompt="You are a tax adviser who provides clear and concise guidance on tax-related queries.",
-        llm=model,
+        model_name="gpt-4o-mini",
+        temperature=0.1,           
         max_loops=1,
         autosave=False,
         dashboard=False,
@@ -2029,7 +2014,8 @@ if __name__ == "__main__":
     history = chat.run(
         "How to optimize tax strategy for investments?"
     )
-    print(history.model_dump_json(indent=2))
+    print(history)
+
 
 ```
 
@@ -2087,35 +2073,18 @@ if __name__ == "__main__":
 ----------
 
 ## Onboarding Session
+
 Get onboarded now with the creator and lead maintainer of Swarms, Kye Gomez, who will show you how to get started with the installation, usage examples, and starting to build your custom use case! [CLICK HERE](https://cal.com/swarms/swarms-onboarding-session)
 
 
 ---
 
 ## Documentation
+
 Documentation is located here at: [docs.swarms.world](https://docs.swarms.world)
 
 -----
 
-## Folder Structure
-The swarms package has been meticulously crafted for extreme usability and understanding,the swarms package is split up into various modules such as `swarms.agents` that holds pre-built agents, `swarms.structs` that holds a vast array of structures like `Agent` and multi agent structures. The package is split into various modules, with the most important being `structs`, `tools`, and `agents`.
-
-```sh
-├── __init__.py
-├── agents/
-├── artifacts/
-├── client/
-├── cli/
-├── prompts/
-├── schemas/
-├── structs/
-├── telemetry/
-├── tools/
-└── utils/
-```
-
-----
-
 ## 🫶 Contributions:
 
 The easiest way to contribute is to pick any issue with the `good first issue` tag 💪. Read the Contributing guidelines [here](/CONTRIBUTING.md). Bug Report? [File here](https://github.com/swarms/gateway/issues) | Feature Request? [File here](https://github.com/swarms/gateway/issues)
@@ -2125,17 +2094,24 @@ Swarms is an open-source project, and contributions are VERY welcome. If you wan
 ----
 
 
-## Community
+### Connect With Us
+
+| Platform | Link | Description |
+|----------|------|-------------|
+| 📚 Documentation | [docs.swarms.world](https://docs.swarms.world) | Official documentation and guides |
+| 📝 Blog | [Medium](https://medium.com/@kyeg) | Latest updates and technical articles |
+| 💬 Discord | [Join Discord](https://discord.gg/jM3Z6M9uMq) | Live chat and community support |
+| 🐦 Twitter | [@kyegomez](https://twitter.com/kyegomez) | Latest news and announcements |
+| 👥 LinkedIn | [The Swarm Corporation](https://www.linkedin.com/company/the-swarm-corporation) | Professional network and updates |
+| 📺 YouTube | [Swarms Channel](https://www.youtube.com/channel/UC9yXyitkbU_WSy7bd_41SqQ) | Tutorials and demos |
+| 🎫 Events | [Sign up here](https://lu.ma/5p2jnc2v) | Join our community events |
+
+
+
+## Citation
 
-Join our growing community around the world, for real-time support, ideas, and discussions on Swarms 😊 
+If you use **swarms** in your research, please cite the project by referencing the metadata in [CITATION.cff](./CITATION.cff).
 
-- View our official [Documents](https://docs.swarms.world)
-- View our official [Blog](https://medium.com/@kyeg)
-- Chat live with us on [Discord](https://discord.gg/jM3Z6M9uMq)
-- Follow us on [Twitter](https://twitter.com/kyegomez)
-- Connect with us on [LinkedIn](https://www.linkedin.com/company/the-swarm-corporation)
-- Visit us on [YouTube](https://www.youtube.com/channel/UC9yXyitkbU_WSy7bd_41SqQ)
-- Sign up for our events [Sign up here](https://lu.ma/5p2jnc2v)
 
 # License
 

{swarms-7.8.4 → swarms-7.8.8}/README.md

@@ -1381,15 +1381,13 @@ print(out)
 -------
 
 ## SpreadSheetSwarm
+
 SpreadSheetSwarm manages thousands of agents concurrently for efficient task processing. It supports one-to-many task distribution, scalability, and autosaving results. Initialized with a name, description, agents, and settings, the run method executes tasks and returns a dictionary of agent outputs.
 
 [Learn more:](https://docs.swarms.world/en/latest/swarms/structs/spreadsheet_swarm/)
 
 ```python
-import os
 from swarms import Agent, SpreadSheetSwarm
-from swarm_models import OpenAIChat
-
 # Define custom system prompts for each social media platform
 TWITTER_AGENT_SYS_PROMPT = """
 You are a Twitter marketing expert specializing in real estate. Your task is to create engaging, concise tweets to promote properties, analyze trends to maximize engagement, and use appropriate hashtags and timing to reach potential buyers.
@@ -1416,7 +1414,7 @@ agents = [
     Agent(
         agent_name="Twitter-RealEstate-Agent",
         system_prompt=TWITTER_AGENT_SYS_PROMPT,
-        model_name="gpt-4o",
+        model_name="gpt-4o-mini",
         max_loops=1,
         dynamic_temperature_enabled=True,
         saved_state_path="twitter_realestate_agent.json",
@@ -1426,7 +1424,7 @@ agents = [
     Agent(
         agent_name="Instagram-RealEstate-Agent",
         system_prompt=INSTAGRAM_AGENT_SYS_PROMPT,
-        model_name="gpt-4o",
+        model_name="gpt-4o-mini",
         max_loops=1,
         dynamic_temperature_enabled=True,
         saved_state_path="instagram_realestate_agent.json",
@@ -1436,7 +1434,7 @@ agents = [
     Agent(
         agent_name="Facebook-RealEstate-Agent",
         system_prompt=FACEBOOK_AGENT_SYS_PROMPT,
-        model_name="gpt-4o",
+        model_name="gpt-4o-mini",
         max_loops=1,
         dynamic_temperature_enabled=True,
         saved_state_path="facebook_realestate_agent.json",
@@ -1446,7 +1444,7 @@ agents = [
     Agent(
         agent_name="LinkedIn-RealEstate-Agent",
         system_prompt=LINKEDIN_AGENT_SYS_PROMPT,
-        model_name="gpt-4o",
+        model_name="gpt-4o-mini",
         max_loops=1,
         dynamic_temperature_enabled=True,
         saved_state_path="linkedin_realestate_agent.json",
@@ -1456,7 +1454,7 @@ agents = [
     Agent(
         agent_name="Email-RealEstate-Agent",
         system_prompt=EMAIL_AGENT_SYS_PROMPT,
-        model_name="gpt-4o",
+        model_name="gpt-4o-mini",
         max_loops=1,
         dynamic_temperature_enabled=True,
         saved_state_path="email_realestate_agent.json",
@@ -1920,32 +1918,18 @@ A production-grade multi-agent system enabling sophisticated group conversations
 
 
 ```python
-
-import os
-from dotenv import load_dotenv
-from swarm_models import OpenAIChat
 from swarms import Agent, GroupChat, expertise_based
 
 
 if __name__ == "__main__":
 
-    load_dotenv()
-
-    # Get the OpenAI API key from the environment variable
-    api_key = os.getenv("OPENAI_API_KEY")
-
-    # Create an instance of the OpenAIChat class
-    model = OpenAIChat(
-        openai_api_key=api_key,
-        model_name="gpt-4o-mini",
-        temperature=0.1,
-    )
 
     # Example agents
     agent1 = Agent(
         agent_name="Financial-Analysis-Agent",
         system_prompt="You are a financial analyst specializing in investment strategies.",
-        llm=model,
+        model_name="gpt-4o-mini",
+        temperature=0.1,        
         max_loops=1,
         autosave=False,
         dashboard=False,
@@ -1961,7 +1945,8 @@ if __name__ == "__main__":
     agent2 = Agent(
         agent_name="Tax-Adviser-Agent",
         system_prompt="You are a tax adviser who provides clear and concise guidance on tax-related queries.",
-        llm=model,
+        model_name="gpt-4o-mini",
+        temperature=0.1,           
         max_loops=1,
         autosave=False,
         dashboard=False,
@@ -1986,7 +1971,8 @@ if __name__ == "__main__":
     history = chat.run(
         "How to optimize tax strategy for investments?"
     )
-    print(history.model_dump_json(indent=2))
+    print(history)
+
 
 ```
 
@@ -2044,35 +2030,18 @@ if __name__ == "__main__":
 ----------
 
 ## Onboarding Session
+
 Get onboarded now with the creator and lead maintainer of Swarms, Kye Gomez, who will show you how to get started with the installation, usage examples, and starting to build your custom use case! [CLICK HERE](https://cal.com/swarms/swarms-onboarding-session)
 
 
 ---
 
 ## Documentation
+
 Documentation is located here at: [docs.swarms.world](https://docs.swarms.world)
 
 -----
 
-## Folder Structure
-The swarms package has been meticulously crafted for extreme usability and understanding,the swarms package is split up into various modules such as `swarms.agents` that holds pre-built agents, `swarms.structs` that holds a vast array of structures like `Agent` and multi agent structures. The package is split into various modules, with the most important being `structs`, `tools`, and `agents`.
-
-```sh
-├── __init__.py
-├── agents/
-├── artifacts/
-├── client/
-├── cli/
-├── prompts/
-├── schemas/
-├── structs/
-├── telemetry/
-├── tools/
-└── utils/
-```
-
-----
-
 ## 🫶 Contributions:
 
 The easiest way to contribute is to pick any issue with the `good first issue` tag 💪. Read the Contributing guidelines [here](/CONTRIBUTING.md). Bug Report? [File here](https://github.com/swarms/gateway/issues) | Feature Request? [File here](https://github.com/swarms/gateway/issues)
@@ -2082,17 +2051,24 @@ Swarms is an open-source project, and contributions are VERY welcome. If you wan
 ----
 
 
-## Community
+### Connect With Us
+
+| Platform | Link | Description |
+|----------|------|-------------|
+| 📚 Documentation | [docs.swarms.world](https://docs.swarms.world) | Official documentation and guides |
+| 📝 Blog | [Medium](https://medium.com/@kyeg) | Latest updates and technical articles |
+| 💬 Discord | [Join Discord](https://discord.gg/jM3Z6M9uMq) | Live chat and community support |
+| 🐦 Twitter | [@kyegomez](https://twitter.com/kyegomez) | Latest news and announcements |
+| 👥 LinkedIn | [The Swarm Corporation](https://www.linkedin.com/company/the-swarm-corporation) | Professional network and updates |
+| 📺 YouTube | [Swarms Channel](https://www.youtube.com/channel/UC9yXyitkbU_WSy7bd_41SqQ) | Tutorials and demos |
+| 🎫 Events | [Sign up here](https://lu.ma/5p2jnc2v) | Join our community events |
+
+
+
+## Citation
 
-Join our growing community around the world, for real-time support, ideas, and discussions on Swarms 😊 
+If you use **swarms** in your research, please cite the project by referencing the metadata in [CITATION.cff](./CITATION.cff).
 
-- View our official [Documents](https://docs.swarms.world)
-- View our official [Blog](https://medium.com/@kyeg)
-- Chat live with us on [Discord](https://discord.gg/jM3Z6M9uMq)
-- Follow us on [Twitter](https://twitter.com/kyegomez)
-- Connect with us on [LinkedIn](https://www.linkedin.com/company/the-swarm-corporation)
-- Visit us on [YouTube](https://www.youtube.com/channel/UC9yXyitkbU_WSy7bd_41SqQ)
-- Sign up for our events [Sign up here](https://lu.ma/5p2jnc2v)
 
 # License
 

{swarms-7.8.4 → swarms-7.8.8}/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "swarms"
-version = "7.8.4"
+version = "7.8.8"
 description = "Swarms - TGSC"
 license = "MIT"
 authors = ["Kye Gomez <kye@apac.ai>"]
@@ -86,7 +86,7 @@ swarms = "swarms.cli.main:main"
 
 [tool.poetry.group.lint.dependencies]
 black = ">=23.1,<26.0"
-ruff = ">=0.5.1,<0.11.9"
+ruff = ">=0.5.1,<0.11.14"
 types-toml = "^0.10.8.1"
 types-pytz = ">=2023.3,<2026.0"
 types-chardet = "^5.0.4.6"

{swarms-7.8.4 → swarms-7.8.8}/swarms/agents/ape_agent.py

@@ -1,27 +1,17 @@
-from typing import Any
+from typing import Callable
 
-from tenacity import retry, stop_after_attempt, wait_exponential
 
-from swarms.prompts.prompt_generator import (
-    prompt_generator_sys_prompt as second_sys_prompt,
-)
 from swarms.prompts.prompt_generator_optimizer import (
-    prompt_generator_sys_prompt,
+    OPENAI_PROMPT_GENERATOR_SYS_PROMPT,
 )
 from swarms.utils.loguru_logger import initialize_logger
 
 logger = initialize_logger(log_folder="ape_agent")
 
 
-@retry(
-    stop=stop_after_attempt(3),
-    wait=wait_exponential(multiplier=1, min=4, max=10),
-)
 def auto_generate_prompt(
     task: str = None,
-    model: Any = None,
-    max_tokens: int = 4000,
-    use_second_sys_prompt: bool = True,
+    model: Callable = None,
     *args,
     **kwargs,
 ):
@@ -38,16 +28,9 @@ def auto_generate_prompt(
     str: The generated prompt.
     """
     try:
-        system_prompt = (
-            second_sys_prompt.get_prompt()
-            if use_second_sys_prompt
-            else prompt_generator_sys_prompt.get_prompt()
-        )
-        output = model.run(
-            system_prompt + task, max_tokens=max_tokens
+        return model.run(
+            task=f"{OPENAI_PROMPT_GENERATOR_SYS_PROMPT} \n\n Task: {task}"
         )
-        print(output)
-        return output
     except Exception as e:
         logger.error(f"Error generating prompt: {str(e)}")
         raise

{swarms-7.8.4 → swarms-7.8.8}/swarms/agents/consistency_agent.py

@@ -7,7 +7,7 @@ from loguru import logger
 from swarms.structs.agent import Agent
 from swarms.structs.conversation import Conversation
 from swarms.structs.malt import majority_voting_prompt
-from swarms.structs.output_types import OutputType
+from swarms.utils.output_types import OutputType
 from swarms.utils.any_to_str import any_to_str
 from swarms.utils.history_output_formatter import (
     history_output_formatter,

{swarms-7.8.4 → swarms-7.8.8}/swarms/agents/i_agent.py

@@ -22,7 +22,7 @@ from typing import List, Tuple
 from loguru import logger
 from swarms.structs.agent import Agent
 from swarms.structs.conversation import Conversation
-from swarms.structs.output_types import OutputType
+from swarms.utils.output_types import OutputType
 from swarms.utils.history_output_formatter import (
     history_output_formatter,
 )

{swarms-7.8.4 → swarms-7.8.8}/swarms/agents/reasoning_agents.py

@@ -1,4 +1,4 @@
-from typing import List, Literal
+from typing import List, Literal, Dict, Callable, Any
 
 from swarms.agents.consistency_agent import SelfConsistencyAgent
 from swarms.agents.flexion_agent import ReflexionAgent
@@ -7,7 +7,7 @@ from swarms.agents.i_agent import (
     IterativeReflectiveExpansion as IREAgent,
 )
 from swarms.agents.reasoning_duo import ReasoningDuo
-from swarms.structs.output_types import OutputType
+from swarms.utils.output_types import OutputType
 from swarms.agents.agent_judge import AgentJudge
 
 agent_types = Literal[
@@ -62,13 +62,100 @@ class ReasoningAgentRouter:
         self.num_knowledge_items = num_knowledge_items
         self.memory_capacity = memory_capacity
 
+        # Added: Initialize the factory mapping dictionary
+        self._initialize_agent_factories()
+
+    # Added: Factory method initialization function
+    def _initialize_agent_factories(self) -> None:
+        """
+        Initialize the agent factory mapping dictionary, mapping various agent types to their respective creation functions.
+        This method replaces the original if-elif chain, making the code easier to maintain and extend.
+        """
+        self.agent_factories: Dict[str, Callable[[], Any]] = {
+            # ReasoningDuo factory methods
+            "reasoning-duo": self._create_reasoning_duo,
+            "reasoning-agent": self._create_reasoning_duo,
+            # SelfConsistencyAgent factory methods
+            "self-consistency": self._create_consistency_agent,
+            "consistency-agent": self._create_consistency_agent,
+            # IREAgent factory methods
+            "ire": self._create_ire_agent,
+            "ire-agent": self._create_ire_agent,
+            # Other agent type factory methods
+            "AgentJudge": self._create_agent_judge,
+            "ReflexionAgent": self._create_reflexion_agent,
+            "GKPAgent": self._create_gkp_agent,
+        }
+
+    # Added: Concrete factory methods for various agent types
+    def _create_reasoning_duo(self):
+        """Creates an agent instance for ReasoningDuo type"""
+        return ReasoningDuo(
+            agent_name=self.agent_name,
+            agent_description=self.description,
+            model_name=[self.model_name, self.model_name],
+            system_prompt=self.system_prompt,
+            output_type=self.output_type,
+        )
+
+    def _create_consistency_agent(self):
+        """Creates an agent instance for SelfConsistencyAgent type"""
+        return SelfConsistencyAgent(
+            agent_name=self.agent_name,
+            description=self.description,
+            model_name=self.model_name,
+            system_prompt=self.system_prompt,
+            max_loops=self.max_loops,
+            num_samples=self.num_samples,
+            output_type=self.output_type,
+        )
+
+    def _create_ire_agent(self):
+        """Creates an agent instance for IREAgent type"""
+        return IREAgent(
+            agent_name=self.agent_name,
+            description=self.description,
+            model_name=self.model_name,
+            system_prompt=self.system_prompt,
+            max_loops=self.max_loops,
+            max_iterations=self.num_samples,
+            output_type=self.output_type,
+        )
+
+    def _create_agent_judge(self):
+        """Creates an agent instance for AgentJudge type"""
+        return AgentJudge(
+            agent_name=self.agent_name,
+            model_name=self.model_name,
+            system_prompt=self.system_prompt,
+            max_loops=self.max_loops,
+        )
+
+    def _create_reflexion_agent(self):
+        """Creates an agent instance for ReflexionAgent type"""
+        return ReflexionAgent(
+            agent_name=self.agent_name,
+            system_prompt=self.system_prompt,
+            model_name=self.model_name,
+            max_loops=self.max_loops,
+        )
+
+    def _create_gkp_agent(self):
+        """Creates an agent instance for GKPAgent type"""
+        return GKPAgent(
+            agent_name=self.agent_name,
+            model_name=self.model_name,
+            num_knowledge_items=self.num_knowledge_items,
+        )
+
     def select_swarm(self):
         """
         Selects and initializes the appropriate reasoning swarm based on the specified swarm type.
-
         Returns:
             An instance of the selected reasoning swarm.
         """
+        # Commented out original if-elif chain implementation
+        """
         if (
             self.swarm_type == "reasoning-duo"
             or self.swarm_type == "reasoning-agent"
@@ -132,6 +219,15 @@ class ReasoningAgentRouter:
             )
         else:
             raise ValueError(f"Invalid swarm type: {self.swarm_type}")
+        """
+
+        # Added: Implementation using factory pattern and dictionary mapping
+        try:
+            # Get the corresponding creation function from the factory dictionary and call it
+            return self.agent_factories[self.swarm_type]()
+        except KeyError:
+            # Maintain the same error handling as the original code
+            raise ValueError(f"Invalid swarm type: {self.swarm_type}")
 
     def run(self, task: str, *args, **kwargs):
         """

{swarms-7.8.4 → swarms-7.8.8}/swarms/agents/reasoning_duo.py

@@ -4,7 +4,7 @@ from loguru import logger
 
 from swarms.prompts.reasoning_prompt import REASONING_PROMPT
 from swarms.structs.agent import Agent
-from swarms.structs.output_types import OutputType
+from swarms.utils.output_types import OutputType
 from swarms.structs.conversation import Conversation
 from swarms.utils.history_output_formatter import (
     history_output_formatter,

{swarms-7.8.4 → swarms-7.8.8}/swarms/cli/main.py

@@ -67,7 +67,7 @@ def show_ascii_art():
         Text(ASCII_ART, style=f"bold {COLORS['primary']}"),
         border_style=COLORS["secondary"],
         title="[bold]Welcome to Swarms[/bold]",
-        subtitle="[dim]Power to the Swarms[/dim]",
+        subtitle="[dim]swarms.ai[/dim]",
     )
     console.print(panel)
 

swarms-7.8.8/swarms/communication/__init__.py

@@ -0,0 +1 @@
+

{swarms-7.8.4 → swarms-7.8.8}/swarms/communication/duckdb_wrap.py

@@ -7,7 +7,6 @@ from contextlib import contextmanager
 from pathlib import Path
 from typing import Any, Callable, Dict, List, Optional, Union
 
-import duckdb
 import yaml
 
 from swarms.communication.base_communication import (
@@ -76,6 +75,37 @@ class DuckDBConversation(BaseCommunication):
         *args,
         **kwargs,
     ):
+        # Lazy load duckdb with auto-installation
+        try:
+            import duckdb
+
+            self.duckdb = duckdb
+            self.duckdb_available = True
+        except ImportError:
+            # Auto-install duckdb if not available
+            print("📦 DuckDB not found. Installing automatically...")
+            try:
+                import subprocess
+                import sys
+
+                # Install duckdb
+                subprocess.check_call(
+                    [sys.executable, "-m", "pip", "install", "duckdb"]
+                )
+                print("✅ DuckDB installed successfully!")
+
+                # Try importing again
+                import duckdb
+
+                self.duckdb = duckdb
+                self.duckdb_available = True
+                print("✅ DuckDB loaded successfully!")
+
+            except Exception as e:
+                raise ImportError(
+                    f"Failed to auto-install DuckDB. Please install manually with 'pip install duckdb': {e}"
+                )
+
         super().__init__(
             system_prompt=system_prompt,
             time_enabled=time_enabled,
@@ -171,7 +201,7 @@ class DuckDBConversation(BaseCommunication):
         conn = None
         for attempt in range(self.max_retries):
             try:
-                conn = duckdb.connect(str(self.db_path))
+                conn = self.duckdb.connect(str(self.db_path))
                 yield conn
                 break
             except Exception as e: