diff --git a/agent_with_all_agents_reflection.py b/agent_with_all_agents_reflection.py new file mode 100644 index 000000000..d819a3709 --- /dev/null +++ b/agent_with_all_agents_reflection.py @@ -0,0 +1,115 @@ + +from swarms import Agent +from swarm_models import OpenAIChat +from swarms_memory import ChromaDB +import os + +# Initialize memory for agents +memory_risk = ChromaDB(metric="cosine", output_dir="risk_analysis_results") +memory_sustainability = ChromaDB(metric="cosine", output_dir="sustainability_results") + +# Initialize model +model = OpenAIChat(api_key=os.getenv("OPENAI_API_KEY"), model_name="gpt-4o-mini", temperature=0.1) + +# Initialize Risk Analysis Agent +risk_analysis_agent = Agent( + agent_name="Delaware-C-Corp-Risk-Analysis-Agent", + system_prompt="You are a specialized risk analysis agent focused on assessing risks.", + agent_description="Performs risk analysis for Delaware C Corps.", + llm=model, + max_loops=3, + autosave=True, + dashboard=False, + verbose=True, + dynamic_temperature_enabled=True, + saved_state_path="delaware_c_corp_risk_analysis_agent.json", + user_name="risk_analyst_user", + retry_attempts=2, + context_length=200000, + long_term_memory=memory_risk, +) + +# Initialize Sustainability Agent +sustainability_agent = Agent( + agent_name="Delaware-C-Corp-Sustainability-Agent", + system_prompt="You are a sustainability analysis agent focused on ESG factors.", + agent_description="Analyzes sustainability practices for Delaware C Corps.", + llm=model, + max_loops=2, + autosave=True, + dashboard=False, + verbose=True, + dynamic_temperature_enabled=False, + saved_state_path="delaware_c_corp_sustainability_agent.json", + user_name="sustainability_specialist", + retry_attempts=3, + context_length=180000, + long_term_memory=memory_sustainability, +) + +# Run the agents +risk_analysis_agent.run("What are the top financial and operational risks for a Delaware C Corp in healthcare?") +sustainability_agent.run("How can a Delaware C Corp in manufacturing improve its sustainability practices?") + +from reflection_tuner import ReflectionTuner + +# Initialize Reflection Tuners for each agent +risk_reflection_tuner = ReflectionTuner(risk_analysis_agent, reflection_steps=2) +sustainability_reflection_tuner = ReflectionTuner(sustainability_agent, reflection_steps=2) + +# Run the agents with Reflection Tuning +risk_response = risk_reflection_tuner.reflect_and_tune("What are the top financial and operational risks for a Delaware C Corp in healthcare?") +sustainability_response = sustainability_reflection_tuner.reflect_and_tune("How can a Delaware C Corp in manufacturing improve its sustainability practices?") + +print("Risk Analysis Agent Response:", risk_response) +print("Sustainability Agent Response:", sustainability_response) + +# Initialize agents from agents_with_new.yaml +# Import ReflectionTuner +from reflection_tuner import ReflectionTuner + +# Initialize Reflection Tuner for all agents, including existing ones +deduction_agent = Agent( + agent_name="Delaware-C-Corp-Tax-Deduction-Agent", + system_prompt="Provide expert advice on tax deductions for Delaware C Corps.", + agent_description="Analyzes tax deduction strategies.", + llm=model, + max_loops=1, + autosave=True, + dashboard=False, + verbose=True, + dynamic_temperature_enabled=True, + saved_state_path="delaware_c_corp_tax_deduction_agent.json", + user_name="swarms_corp", + retry_attempts=1, + context_length=250000, + long_term_memory=memory_risk, # Reuse memory for testing purposes +) + +optimization_agent = Agent( + agent_name="Delaware-C-Corp-Tax-Optimization-Agent", + system_prompt="Provide expert advice on tax optimization strategies for Delaware C Corps.", + agent_description="Analyzes tax optimization.", + llm=model, + max_loops=2, + autosave=True, + dashboard=False, + verbose=True, + dynamic_temperature_enabled=False, + saved_state_path="delaware_c_corp_tax_optimization_agent.json", + user_name="tax_optimization_user", + retry_attempts=3, + context_length=200000, + long_term_memory=memory_risk, +) + +# Initialize Reflection Tuners +deduction_reflection_tuner = ReflectionTuner(deduction_agent, reflection_steps=2) +optimization_reflection_tuner = ReflectionTuner(optimization_agent, reflection_steps=2) + +# Run agents with Reflection Tuning +deduction_response = deduction_reflection_tuner.reflect_and_tune("What are the most effective tax deduction strategies for a Delaware C Corp in tech?") +optimization_response = optimization_reflection_tuner.reflect_and_tune("How can a Delaware C Corp in finance optimize its tax strategy?") + +print("Tax Deduction Agent Response:", deduction_response) +print("Tax Optimization Agent Response:", optimization_response) diff --git a/agent_with_all_agents_reflection_planner_collector.py b/agent_with_all_agents_reflection_planner_collector.py new file mode 100644 index 000000000..4069c692b --- /dev/null +++ b/agent_with_all_agents_reflection_planner_collector.py @@ -0,0 +1,175 @@ + +from swarms import Agent +from swarm_models import OpenAIChat +from swarms_memory import ChromaDB +import os + +# Initialize memory for agents +memory_risk = ChromaDB(metric="cosine", output_dir="risk_analysis_results") +memory_sustainability = ChromaDB(metric="cosine", output_dir="sustainability_results") + +# Initialize model +model = OpenAIChat(api_key=os.getenv("OPENAI_API_KEY"), model_name="gpt-4o-mini", temperature=0.1) + +# Initialize Risk Analysis Agent +risk_analysis_agent = Agent( + agent_name="Delaware-C-Corp-Risk-Analysis-Agent", + system_prompt="You are a specialized risk analysis agent focused on assessing risks.", + agent_description="Performs risk analysis for Delaware C Corps.", + llm=model, + max_loops=3, + autosave=True, + dashboard=False, + verbose=True, + dynamic_temperature_enabled=True, + saved_state_path="delaware_c_corp_risk_analysis_agent.json", + user_name="risk_analyst_user", + retry_attempts=2, + context_length=200000, + long_term_memory=memory_risk, +) + +# Initialize Sustainability Agent +sustainability_agent = Agent( + agent_name="Delaware-C-Corp-Sustainability-Agent", + system_prompt="You are a sustainability analysis agent focused on ESG factors.", + agent_description="Analyzes sustainability practices for Delaware C Corps.", + llm=model, + max_loops=2, + autosave=True, + dashboard=False, + verbose=True, + dynamic_temperature_enabled=False, + saved_state_path="delaware_c_corp_sustainability_agent.json", + user_name="sustainability_specialist", + retry_attempts=3, + context_length=180000, + long_term_memory=memory_sustainability, +) + +# Run the agents +risk_analysis_agent.run("What are the top financial and operational risks for a Delaware C Corp in healthcare?") +sustainability_agent.run("How can a Delaware C Corp in manufacturing improve its sustainability practices?") + +from reflection_tuner import ReflectionTuner + +# Initialize Reflection Tuners for each agent +risk_reflection_tuner = ReflectionTuner(risk_analysis_agent, reflection_steps=2) +sustainability_reflection_tuner = ReflectionTuner(sustainability_agent, reflection_steps=2) + +# Run the agents with Reflection Tuning +risk_response = risk_reflection_tuner.reflect_and_tune("What are the top financial and operational risks for a Delaware C Corp in healthcare?") +sustainability_response = sustainability_reflection_tuner.reflect_and_tune("How can a Delaware C Corp in manufacturing improve its sustainability practices?") + +print("Risk Analysis Agent Response:", risk_response) +print("Sustainability Agent Response:", sustainability_response) + +# Initialize agents from agents_with_new.yaml +# Import ReflectionTuner +from reflection_tuner import ReflectionTuner + +# Initialize Reflection Tuner for all agents, including existing ones +deduction_agent = Agent( + agent_name="Delaware-C-Corp-Tax-Deduction-Agent", + system_prompt="Provide expert advice on tax deductions for Delaware C Corps.", + agent_description="Analyzes tax deduction strategies.", + llm=model, + max_loops=1, + autosave=True, + dashboard=False, + verbose=True, + dynamic_temperature_enabled=True, + saved_state_path="delaware_c_corp_tax_deduction_agent.json", + user_name="swarms_corp", + retry_attempts=1, + context_length=250000, + long_term_memory=memory_risk, # Reuse memory for testing purposes +) + +optimization_agent = Agent( + agent_name="Delaware-C-Corp-Tax-Optimization-Agent", + system_prompt="Provide expert advice on tax optimization strategies for Delaware C Corps.", + agent_description="Analyzes tax optimization.", + llm=model, + max_loops=2, + autosave=True, + dashboard=False, + verbose=True, + dynamic_temperature_enabled=False, + saved_state_path="delaware_c_corp_tax_optimization_agent.json", + user_name="tax_optimization_user", + retry_attempts=3, + context_length=200000, + long_term_memory=memory_risk, +) + +# Initialize Reflection Tuners +deduction_reflection_tuner = ReflectionTuner(deduction_agent, reflection_steps=2) +optimization_reflection_tuner = ReflectionTuner(optimization_agent, reflection_steps=2) + +# Run agents with Reflection Tuning +deduction_response = deduction_reflection_tuner.reflect_and_tune("What are the most effective tax deduction strategies for a Delaware C Corp in tech?") +optimization_response = optimization_reflection_tuner.reflect_and_tune("How can a Delaware C Corp in finance optimize its tax strategy?") + +print("Tax Deduction Agent Response:", deduction_response) +print("Tax Optimization Agent Response:", optimization_response) + +from reflection_tuner import ReflectionTuner +import requests + +def duckduckgo_search(query): + # Simple DuckDuckGo search function for Data-Collector agent + url = f"https://api.duckduckgo.com/?q={query}&format=json&pretty=1" + response = requests.get(url) + if response.status_code == 200: + return response.json().get("AbstractText", "No data found") + return "Failed to retrieve data" + +# Initialize Planner and Data-Collector agents with DuckDuckGo search capability +planner_agent = Agent( + agent_name="Delaware-C-Corp-Planner-Agent", + system_prompt="Develop a quarterly strategic roadmap for a Delaware C Corp.", + agent_description="Creates detailed plans and schedules.", + llm=model, + max_loops=2, + autosave=True, + dashboard=False, + verbose=True, + dynamic_temperature_enabled=True, + saved_state_path="delaware_c_corp_planner_agent.json", + user_name="planner_user", + retry_attempts=2, + context_length=150000, + long_term_memory=memory_sustainability, # Reuse memory for demonstration purposes +) + +data_collector_agent = Agent( + agent_name="Delaware-C-Corp-Data-Collector-Agent", + system_prompt="Collect and synthesize information from DuckDuckGo search.", + agent_description="Gathers data from open-source search engines.", + llm=model, + max_loops=3, + autosave=True, + dashboard=False, + verbose=True, + dynamic_temperature_enabled=True, + saved_state_path="delaware_c_corp_data_collector_agent.json", + user_name="data_collector_user", + retry_attempts=3, + context_length=200000, + long_term_memory=memory_risk, # Reuse memory for demonstration +) + +# Initialize Reflection Tuners +planner_reflection_tuner = ReflectionTuner(planner_agent, reflection_steps=2) +data_collector_reflection_tuner = ReflectionTuner(data_collector_agent, reflection_steps=2) + +# Run Planner agent with Reflection Tuning +planner_response = planner_reflection_tuner.reflect_and_tune("Create a quarterly strategic roadmap for a Delaware C Corp in biotech.") +print("Planner Agent Response:", planner_response) + +# Run Data Collector agent with Reflection Tuning, using DuckDuckGo search +data_collector_task = "Find recent trends in tax strategies for corporations in the US." +search_result = duckduckgo_search(data_collector_task) +data_collector_response = data_collector_reflection_tuner.reflect_and_tune(f"{search_result}") +print("Data Collector Agent Response:", data_collector_response) diff --git a/agent_with_caching_adaptive_agents.py b/agent_with_caching_adaptive_agents.py new file mode 100644 index 000000000..0f083ded6 --- /dev/null +++ b/agent_with_caching_adaptive_agents.py @@ -0,0 +1,203 @@ + +from swarms import Agent +from swarm_models import OpenAIChat +from swarms_memory import ChromaDB +import os + +# Initialize memory for agents +memory_risk = ChromaDB(metric="cosine", output_dir="risk_analysis_results") +memory_sustainability = ChromaDB(metric="cosine", output_dir="sustainability_results") + +# Initialize model +model = OpenAIChat(api_key=os.getenv("OPENAI_API_KEY"), model_name="gpt-4o-mini", temperature=0.1) + +# Initialize Risk Analysis Agent +risk_analysis_agent = Agent( + agent_name="Delaware-C-Corp-Risk-Analysis-Agent", + system_prompt="You are a specialized risk analysis agent focused on assessing risks.", + agent_description="Performs risk analysis for Delaware C Corps.", + llm=model, + max_loops=3, + autosave=True, + dashboard=False, + verbose=True, + dynamic_temperature_enabled=True, + saved_state_path="delaware_c_corp_risk_analysis_agent.json", + user_name="risk_analyst_user", + retry_attempts=2, + context_length=200000, + long_term_memory=memory_risk, +) + +# Initialize Sustainability Agent +sustainability_agent = Agent( + agent_name="Delaware-C-Corp-Sustainability-Agent", + system_prompt="You are a sustainability analysis agent focused on ESG factors.", + agent_description="Analyzes sustainability practices for Delaware C Corps.", + llm=model, + max_loops=2, + autosave=True, + dashboard=False, + verbose=True, + dynamic_temperature_enabled=False, + saved_state_path="delaware_c_corp_sustainability_agent.json", + user_name="sustainability_specialist", + retry_attempts=3, + context_length=180000, + long_term_memory=memory_sustainability, +) + +# Run the agents +risk_analysis_agent.run("What are the top financial and operational risks for a Delaware C Corp in healthcare?") +sustainability_agent.run("How can a Delaware C Corp in manufacturing improve its sustainability practices?") + +from reflection_tuner import ReflectionTuner + +# Initialize Reflection Tuners for each agent +risk_reflection_tuner = ReflectionTuner(risk_analysis_agent, reflection_steps=2) +sustainability_reflection_tuner = ReflectionTuner(sustainability_agent, reflection_steps=2) + +# Run the agents with Reflection Tuning +risk_response = risk_reflection_tuner.reflect_and_tune("What are the top financial and operational risks for a Delaware C Corp in healthcare?") +sustainability_response = sustainability_reflection_tuner.reflect_and_tune("How can a Delaware C Corp in manufacturing improve its sustainability practices?") + +print("Risk Analysis Agent Response:", risk_response) +print("Sustainability Agent Response:", sustainability_response) + +# Initialize agents from agents_with_new.yaml +# Import ReflectionTuner +from reflection_tuner import ReflectionTuner + +# Initialize Reflection Tuner for all agents, including existing ones +deduction_agent = Agent( + agent_name="Delaware-C-Corp-Tax-Deduction-Agent", + system_prompt="Provide expert advice on tax deductions for Delaware C Corps.", + agent_description="Analyzes tax deduction strategies.", + llm=model, + max_loops=1, + autosave=True, + dashboard=False, + verbose=True, + dynamic_temperature_enabled=True, + saved_state_path="delaware_c_corp_tax_deduction_agent.json", + user_name="swarms_corp", + retry_attempts=1, + context_length=250000, + long_term_memory=memory_risk, # Reuse memory for testing purposes +) + +optimization_agent = Agent( + agent_name="Delaware-C-Corp-Tax-Optimization-Agent", + system_prompt="Provide expert advice on tax optimization strategies for Delaware C Corps.", + agent_description="Analyzes tax optimization.", + llm=model, + max_loops=2, + autosave=True, + dashboard=False, + verbose=True, + dynamic_temperature_enabled=False, + saved_state_path="delaware_c_corp_tax_optimization_agent.json", + user_name="tax_optimization_user", + retry_attempts=3, + context_length=200000, + long_term_memory=memory_risk, +) + +# Initialize Reflection Tuners +deduction_reflection_tuner = ReflectionTuner(deduction_agent, reflection_steps=2) +optimization_reflection_tuner = ReflectionTuner(optimization_agent, reflection_steps=2) + +# Run agents with Reflection Tuning +deduction_response = deduction_reflection_tuner.reflect_and_tune("What are the most effective tax deduction strategies for a Delaware C Corp in tech?") +optimization_response = optimization_reflection_tuner.reflect_and_tune("How can a Delaware C Corp in finance optimize its tax strategy?") + +print("Tax Deduction Agent Response:", deduction_response) +print("Tax Optimization Agent Response:", optimization_response) + +from reflection_tuner import ReflectionTuner +import requests + +def duckduckgo_search(query): + # Simple DuckDuckGo search function for Data-Collector agent + url = f"https://api.duckduckgo.com/?q={query}&format=json&pretty=1" + response = requests.get(url) + if response.status_code == 200: + return response.json().get("AbstractText", "No data found") + return "Failed to retrieve data" + +# Initialize Planner and Data-Collector agents with DuckDuckGo search capability +planner_agent = Agent( + agent_name="Delaware-C-Corp-Planner-Agent", + system_prompt="Develop a quarterly strategic roadmap for a Delaware C Corp.", + agent_description="Creates detailed plans and schedules.", + llm=model, + max_loops=2, + autosave=True, + dashboard=False, + verbose=True, + dynamic_temperature_enabled=True, + saved_state_path="delaware_c_corp_planner_agent.json", + user_name="planner_user", + retry_attempts=2, + context_length=150000, + long_term_memory=memory_sustainability, # Reuse memory for demonstration purposes +) + +data_collector_agent = Agent( + agent_name="Delaware-C-Corp-Data-Collector-Agent", + system_prompt="Collect and synthesize information from DuckDuckGo search.", + agent_description="Gathers data from open-source search engines.", + llm=model, + max_loops=3, + autosave=True, + dashboard=False, + verbose=True, + dynamic_temperature_enabled=True, + saved_state_path="delaware_c_corp_data_collector_agent.json", + user_name="data_collector_user", + retry_attempts=3, + context_length=200000, + long_term_memory=memory_risk, # Reuse memory for demonstration +) + +# Initialize Reflection Tuners +planner_reflection_tuner = ReflectionTuner(planner_agent, reflection_steps=2) +data_collector_reflection_tuner = ReflectionTuner(data_collector_agent, reflection_steps=2) + +# Run Planner agent with Reflection Tuning +planner_response = planner_reflection_tuner.reflect_and_tune("Create a quarterly strategic roadmap for a Delaware C Corp in biotech.") +print("Planner Agent Response:", planner_response) + +# Run Data Collector agent with Reflection Tuning, using DuckDuckGo search +data_collector_task = "Find recent trends in tax strategies for corporations in the US." +search_result = duckduckgo_search(data_collector_task) +data_collector_response = data_collector_reflection_tuner.reflect_and_tune(f"{search_result}") +print("Data Collector Agent Response:", data_collector_response) + +from token_cache_and_adaptive_factory import TokenCache, AdaptiveAgentFactory + +# Initialize TokenCache and AdaptiveAgentFactory +token_cache = TokenCache(cache_duration_minutes=30) # Cache duration for tokens +adaptive_factory = AdaptiveAgentFactory(model, token_cache) + +# Example of creating adaptive agents dynamically +adaptive_risk_agent = adaptive_factory.create_agent( + agent_name="Adaptive-Risk-Agent", + system_prompt="Assess new risk factors for changing economic conditions.", + task="Dynamic risk analysis in evolving markets.", + memory=memory_risk, +) + +adaptive_sustainability_agent = adaptive_factory.create_agent( + agent_name="Adaptive-Sustainability-Agent", + system_prompt="Evaluate sustainability strategies in response to new regulations.", + task="Dynamic sustainability strategy for manufacturing.", + memory=memory_sustainability, +) + +# Running adaptive agents +adaptive_risk_response = adaptive_risk_agent.run("Analyze potential economic risks for new market conditions.") +adaptive_sustainability_response = adaptive_sustainability_agent.run("Evaluate ESG strategies with upcoming regulation changes.") + +print("Adaptive Risk Agent Response:", adaptive_risk_response) +print("Adaptive Sustainability Agent Response:", adaptive_sustainability_response) diff --git a/agent_with_new_agents.py b/agent_with_new_agents.py new file mode 100644 index 000000000..7a03cf964 --- /dev/null +++ b/agent_with_new_agents.py @@ -0,0 +1,52 @@ + +from swarms import Agent +from swarm_models import OpenAIChat +from swarms_memory import ChromaDB +import os + +# Initialize memory for agents +memory_risk = ChromaDB(metric="cosine", output_dir="risk_analysis_results") +memory_sustainability = ChromaDB(metric="cosine", output_dir="sustainability_results") + +# Initialize model +model = OpenAIChat(api_key=os.getenv("OPENAI_API_KEY"), model_name="gpt-4o-mini", temperature=0.1) + +# Initialize Risk Analysis Agent +risk_analysis_agent = Agent( + agent_name="Delaware-C-Corp-Risk-Analysis-Agent", + system_prompt="You are a specialized risk analysis agent focused on assessing risks.", + agent_description="Performs risk analysis for Delaware C Corps.", + llm=model, + max_loops=3, + autosave=True, + dashboard=False, + verbose=True, + dynamic_temperature_enabled=True, + saved_state_path="delaware_c_corp_risk_analysis_agent.json", + user_name="risk_analyst_user", + retry_attempts=2, + context_length=200000, + long_term_memory=memory_risk, +) + +# Initialize Sustainability Agent +sustainability_agent = Agent( + agent_name="Delaware-C-Corp-Sustainability-Agent", + system_prompt="You are a sustainability analysis agent focused on ESG factors.", + agent_description="Analyzes sustainability practices for Delaware C Corps.", + llm=model, + max_loops=2, + autosave=True, + dashboard=False, + verbose=True, + dynamic_temperature_enabled=False, + saved_state_path="delaware_c_corp_sustainability_agent.json", + user_name="sustainability_specialist", + retry_attempts=3, + context_length=180000, + long_term_memory=memory_sustainability, +) + +# Run the agents +risk_analysis_agent.run("What are the top financial and operational risks for a Delaware C Corp in healthcare?") +sustainability_agent.run("How can a Delaware C Corp in manufacturing improve its sustainability practices?") diff --git a/agent_with_new_agents_reflection.py b/agent_with_new_agents_reflection.py new file mode 100644 index 000000000..3df20c3d1 --- /dev/null +++ b/agent_with_new_agents_reflection.py @@ -0,0 +1,65 @@ + +from swarms import Agent +from swarm_models import OpenAIChat +from swarms_memory import ChromaDB +import os + +# Initialize memory for agents +memory_risk = ChromaDB(metric="cosine", output_dir="risk_analysis_results") +memory_sustainability = ChromaDB(metric="cosine", output_dir="sustainability_results") + +# Initialize model +model = OpenAIChat(api_key=os.getenv("OPENAI_API_KEY"), model_name="gpt-4o-mini", temperature=0.1) + +# Initialize Risk Analysis Agent +risk_analysis_agent = Agent( + agent_name="Delaware-C-Corp-Risk-Analysis-Agent", + system_prompt="You are a specialized risk analysis agent focused on assessing risks.", + agent_description="Performs risk analysis for Delaware C Corps.", + llm=model, + max_loops=3, + autosave=True, + dashboard=False, + verbose=True, + dynamic_temperature_enabled=True, + saved_state_path="delaware_c_corp_risk_analysis_agent.json", + user_name="risk_analyst_user", + retry_attempts=2, + context_length=200000, + long_term_memory=memory_risk, +) + +# Initialize Sustainability Agent +sustainability_agent = Agent( + agent_name="Delaware-C-Corp-Sustainability-Agent", + system_prompt="You are a sustainability analysis agent focused on ESG factors.", + agent_description="Analyzes sustainability practices for Delaware C Corps.", + llm=model, + max_loops=2, + autosave=True, + dashboard=False, + verbose=True, + dynamic_temperature_enabled=False, + saved_state_path="delaware_c_corp_sustainability_agent.json", + user_name="sustainability_specialist", + retry_attempts=3, + context_length=180000, + long_term_memory=memory_sustainability, +) + +# Run the agents +risk_analysis_agent.run("What are the top financial and operational risks for a Delaware C Corp in healthcare?") +sustainability_agent.run("How can a Delaware C Corp in manufacturing improve its sustainability practices?") + +from reflection_tuner import ReflectionTuner + +# Initialize Reflection Tuners for each agent +risk_reflection_tuner = ReflectionTuner(risk_analysis_agent, reflection_steps=2) +sustainability_reflection_tuner = ReflectionTuner(sustainability_agent, reflection_steps=2) + +# Run the agents with Reflection Tuning +risk_response = risk_reflection_tuner.reflect_and_tune("What are the top financial and operational risks for a Delaware C Corp in healthcare?") +sustainability_response = sustainability_reflection_tuner.reflect_and_tune("How can a Delaware C Corp in manufacturing improve its sustainability practices?") + +print("Risk Analysis Agent Response:", risk_response) +print("Sustainability Agent Response:", sustainability_response) diff --git a/agents_with_new.yaml b/agents_with_new.yaml new file mode 100644 index 000000000..e5d86c7d1 --- /dev/null +++ b/agents_with_new.yaml @@ -0,0 +1,94 @@ +agents: + - agent_name: "Delaware-C-Corp-Tax-Deduction-Agent" + # model: + # model_name: "gpt-4o-mini" + # temperature: 0.1 + # max_tokens: 2500 + system_prompt: | + You are a highly specialized financial analysis agent focused on Delaware C Corps tax deductions. Your task is to provide expert advice on optimizing tax strategies for Delaware C Corps, ensuring compliance with all relevant tax laws and regulations. You should be well-versed in Delaware state tax codes and federal tax laws affecting C Corps. Your responses should include detailed explanations of tax deductions available to Delaware C Corps, including but not limited to: + - Research and Development (R&D) tax credits + - Depreciation and amortization + - Business expense deductions + - Charitable contributions + - State-specific tax incentives + - Federal tax deductions applicable to C Corps + max_loops: 1 + autosave: true + dashboard: false + verbose: true + dynamic_temperature_enabled: true + saved_state_path: "delaware_c_corp_tax_deduction_agent.json" + user_name: "swarms_corp" + retry_attempts: 1 + context_length: 250000 + return_step_meta: false + output_type: "str" # Can be "json" or any other format + task: "What are the most effective tax deduction strategies for a Delaware C Corp in the technology industry?" + + - agent_name: "Delaware-C-Corp-Tax-Optimization-Agent" + # model: + # model_name: "gpt-4o-mini" + # temperature: 0.2 + # max_tokens: 2000 + system_prompt: | + You are a highly specialized financial analysis agent focused on Delaware C Corps tax optimization. Your task is to provide expert advice on optimizing tax strategies for Delaware C Corps, ensuring compliance with all relevant tax laws and regulations. You should be well-versed in Delaware state tax codes and federal tax laws affecting C Corps. Your responses should include detailed explanations of tax optimization strategies available to Delaware C Corps, including but not limited to: + - Entity structure optimization + - Income shifting strategies + - Loss utilization and carryovers + - Tax-efficient supply chain management + - State-specific tax planning + - Federal tax planning applicable to C Corps + max_loops: 2 + autosave: true + dashboard: false + verbose: true + dynamic_temperature_enabled: false + saved_state_path: "delaware_c_corp_tax_optimization_agent.json" + user_name: "tax_optimization_user" + retry_attempts: 3 + context_length: 200000 + return_step_meta: true + output_type: "str" + task: "How can a Delaware C Corp in the finance industry optimize its tax strategy for maximum savings?" + + - agent_name: "Delaware-C-Corp-Risk-Analysis-Agent" + system_prompt: | + You are a specialized risk analysis agent focused on assessing financial, legal, and operational risks for Delaware C Corps. + Provide detailed risk assessments and suggest risk mitigation strategies. Your expertise should cover: + - Market risk analysis + - Operational risk analysis + - Compliance with Delaware and federal regulations + - Financial risk modeling + max_loops: 3 + autosave: true + dashboard: false + verbose: true + dynamic_temperature_enabled: true + saved_state_path: "delaware_c_corp_risk_analysis_agent.json" + user_name: "risk_analyst_user" + retry_attempts: 2 + context_length: 200000 + return_step_meta: true + output_type: "json" + task: "What are the top financial and operational risks for a Delaware C Corp in the healthcare industry?" + + - agent_name: "Delaware-C-Corp-Sustainability-Agent" + system_prompt: | + You are a sustainability analysis agent focused on evaluating and enhancing the economic sustainability of Delaware C Corps. + Your recommendations should address: + - Environmental, Social, and Governance (ESG) factors + - Resource management and waste reduction strategies + - Compliance with sustainability regulations and reporting + - Sustainable investment strategies + max_loops: 2 + autosave: true + dashboard: false + verbose: true + dynamic_temperature_enabled: false + saved_state_path: "delaware_c_corp_sustainability_agent.json" + user_name: "sustainability_specialist" + retry_attempts: 3 + context_length: 180000 + return_step_meta: true + output_type: "str" + task: "How can a Delaware C Corp in the manufacturing industry improve its sustainability practices?" diff --git a/agents_with_planner_collector.yaml b/agents_with_planner_collector.yaml new file mode 100644 index 000000000..214cfe5f2 --- /dev/null +++ b/agents_with_planner_collector.yaml @@ -0,0 +1,129 @@ +agents: + - agent_name: "Delaware-C-Corp-Tax-Deduction-Agent" + # model: + # model_name: "gpt-4o-mini" + # temperature: 0.1 + # max_tokens: 2500 + system_prompt: | + You are a highly specialized financial analysis agent focused on Delaware C Corps tax deductions. Your task is to provide expert advice on optimizing tax strategies for Delaware C Corps, ensuring compliance with all relevant tax laws and regulations. You should be well-versed in Delaware state tax codes and federal tax laws affecting C Corps. Your responses should include detailed explanations of tax deductions available to Delaware C Corps, including but not limited to: + - Research and Development (R&D) tax credits + - Depreciation and amortization + - Business expense deductions + - Charitable contributions + - State-specific tax incentives + - Federal tax deductions applicable to C Corps + max_loops: 1 + autosave: true + dashboard: false + verbose: true + dynamic_temperature_enabled: true + saved_state_path: "delaware_c_corp_tax_deduction_agent.json" + user_name: "swarms_corp" + retry_attempts: 1 + context_length: 250000 + return_step_meta: false + output_type: "str" # Can be "json" or any other format + task: "What are the most effective tax deduction strategies for a Delaware C Corp in the technology industry?" + + - agent_name: "Delaware-C-Corp-Tax-Optimization-Agent" + # model: + # model_name: "gpt-4o-mini" + # temperature: 0.2 + # max_tokens: 2000 + system_prompt: | + You are a highly specialized financial analysis agent focused on Delaware C Corps tax optimization. Your task is to provide expert advice on optimizing tax strategies for Delaware C Corps, ensuring compliance with all relevant tax laws and regulations. You should be well-versed in Delaware state tax codes and federal tax laws affecting C Corps. Your responses should include detailed explanations of tax optimization strategies available to Delaware C Corps, including but not limited to: + - Entity structure optimization + - Income shifting strategies + - Loss utilization and carryovers + - Tax-efficient supply chain management + - State-specific tax planning + - Federal tax planning applicable to C Corps + max_loops: 2 + autosave: true + dashboard: false + verbose: true + dynamic_temperature_enabled: false + saved_state_path: "delaware_c_corp_tax_optimization_agent.json" + user_name: "tax_optimization_user" + retry_attempts: 3 + context_length: 200000 + return_step_meta: true + output_type: "str" + task: "How can a Delaware C Corp in the finance industry optimize its tax strategy for maximum savings?" + + - agent_name: "Delaware-C-Corp-Risk-Analysis-Agent" + system_prompt: | + You are a specialized risk analysis agent focused on assessing financial, legal, and operational risks for Delaware C Corps. + Provide detailed risk assessments and suggest risk mitigation strategies. Your expertise should cover: + - Market risk analysis + - Operational risk analysis + - Compliance with Delaware and federal regulations + - Financial risk modeling + max_loops: 3 + autosave: true + dashboard: false + verbose: true + dynamic_temperature_enabled: true + saved_state_path: "delaware_c_corp_risk_analysis_agent.json" + user_name: "risk_analyst_user" + retry_attempts: 2 + context_length: 200000 + return_step_meta: true + output_type: "json" + task: "What are the top financial and operational risks for a Delaware C Corp in the healthcare industry?" + + - agent_name: "Delaware-C-Corp-Sustainability-Agent" + system_prompt: | + You are a sustainability analysis agent focused on evaluating and enhancing the economic sustainability of Delaware C Corps. + Your recommendations should address: + - Environmental, Social, and Governance (ESG) factors + - Resource management and waste reduction strategies + - Compliance with sustainability regulations and reporting + - Sustainable investment strategies + max_loops: 2 + autosave: true + dashboard: false + verbose: true + dynamic_temperature_enabled: false + saved_state_path: "delaware_c_corp_sustainability_agent.json" + user_name: "sustainability_specialist" + retry_attempts: 3 + context_length: 180000 + return_step_meta: true + output_type: "str" + task: "How can a Delaware C Corp in the manufacturing industry improve its sustainability practices?" + + - agent_name: "Delaware-C-Corp-Planner-Agent" + system_prompt: | + You are a planning agent focused on developing schedules, timelines, and strategic roadmaps for Delaware C Corps. + Your planning should account for company milestones, regulatory deadlines, and strategic goals. Provide organized, + step-by-step timelines, and resources. + max_loops: 2 + autosave: true + dashboard: false + verbose: true + dynamic_temperature_enabled: true + saved_state_path: "delaware_c_corp_planner_agent.json" + user_name: "planner_user" + retry_attempts: 2 + context_length: 150000 + return_step_meta: true + output_type: "json" + task: "Create a quarterly strategic roadmap for a Delaware C Corp in the biotech industry." + + - agent_name: "Delaware-C-Corp-Data-Collector-Agent" + system_prompt: | + You are a data collection agent specialized in gathering relevant data from open-source search engines, focusing on + market trends, regulatory updates, and industry insights. Use DuckDuckGo to collect accurate and up-to-date information. + max_loops: 3 + autosave: true + dashboard: false + verbose: true + dynamic_temperature_enabled: true + saved_state_path: "delaware_c_corp_data_collector_agent.json" + user_name: "data_collector_user" + retry_attempts: 3 + context_length: 200000 + return_step_meta: true + output_type: "str" + task: "Find recent trends in tax strategies for corporations in the US using DuckDuckGo search." diff --git a/reflection_tuner.py b/reflection_tuner.py new file mode 100644 index 000000000..078a151d4 --- /dev/null +++ b/reflection_tuner.py @@ -0,0 +1,26 @@ + +class ReflectionTuner: + def __init__(self, agent, reflection_steps=3): + self.agent = agent + self.reflection_steps = reflection_steps + + def reflect_and_tune(self, initial_task): + response = self.agent.run(initial_task) + for step in range(self.reflection_steps): + # Analyzing the response and adjusting based on findings + feedback = self.analyze_response(response) + if feedback: + print(f"Reflection step {step + 1}: Adjusting response based on feedback.") + response = self.agent.run(feedback) # Rerun with adjusted task or prompt + else: + print(f"No further tuning required at step {step + 1}. Final response achieved.") + break + return response + + def analyze_response(self, response): + # Basic logic to analyze the response quality and determine next steps + if "error" in response.lower() or "incomplete" in response.lower(): + return "Please refine the explanation and address missing points." + elif "unclear" in response.lower() or "vague" in response.lower(): + return "Provide a more detailed and specific analysis." + return None # No adjustment required if response is satisfactory diff --git a/token_cache_and_adaptive_factory.py b/token_cache_and_adaptive_factory.py new file mode 100644 index 000000000..648057979 --- /dev/null +++ b/token_cache_and_adaptive_factory.py @@ -0,0 +1,58 @@ + +import os +import json +from datetime import datetime, timedelta +from collections import defaultdict + +class TokenCache: + def __init__(self, cache_duration_minutes=30): + self.token_cache = defaultdict(lambda: {"token": None, "expires": datetime.now()}) + self.cache_duration = timedelta(minutes=cache_duration_minutes) + + def get_token(self, agent_name): + cached_token = self.token_cache[agent_name] + if cached_token["token"] and cached_token["expires"] > datetime.now(): + print(f"Using cached token for {agent_name}.") + return cached_token["token"] + return None # Token has expired or does not exist + + def set_token(self, agent_name, token): + self.token_cache[agent_name] = { + "token": token, + "expires": datetime.now() + self.cache_duration, + } + +class AdaptiveAgentFactory: + def __init__(self, model, token_cache, reflection_steps=2): + self.model = model + self.token_cache = token_cache + self.reflection_steps = reflection_steps + + def create_agent(self, agent_name, system_prompt, task, memory): + cached_token = self.token_cache.get_token(agent_name) + if cached_token: + return cached_token + + # Create new agent instance with unique parameters + new_agent = Agent( + agent_name=agent_name, + system_prompt=system_prompt, + agent_description=f"Adaptive agent for {task}", + llm=self.model, + max_loops=3, + autosave=True, + dashboard=False, + verbose=True, + dynamic_temperature_enabled=True, + saved_state_path=f"{agent_name.lower().replace(' ', '_')}.json", + user_name="adaptive_user", + retry_attempts=2, + context_length=200000, + long_term_memory=memory, + ) + + # Generate a token for the new agent and cache it + token = f"{agent_name}_{datetime.now().strftime('%Y%m%d%H%M%S')}" + self.token_cache.set_token(agent_name, token) + print(f"Created new agent {agent_name} with token {token}.") + return new_agent