diff --git a/docs/mkdocs.yml b/docs/mkdocs.yml index f32f9cbd..d154c6b1 100644 --- a/docs/mkdocs.yml +++ b/docs/mkdocs.yml @@ -410,10 +410,10 @@ nav: - Hiearchical Marketing Team: "examples/marketing_team.md" - Gold ETF Research with HeavySwarm: "examples/gold_etf_research.md" - Hiring Swarm: "examples/hiring_swarm.md" + - Advanced Research: "examples/av.md" - Tools & Integrations: - Web Search with Exa: "examples/exa_search.md" - - Advanced Research: "examples/av.md" - Browser Use: "examples/browser_use.md" - Yahoo Finance: "swarms/examples/yahoo_finance.md" - Firecrawl: "developer_guides/firecrawl.md" diff --git a/docs/swarms/examples/aop_server_example.md b/docs/swarms/examples/aop_server_example.md new file mode 100644 index 00000000..e8ebeca9 --- /dev/null +++ b/docs/swarms/examples/aop_server_example.md @@ -0,0 +1,164 @@ +# AOP Server Setup Example + +This example demonstrates how to set up an Agent Orchestration Protocol (AOP) server with multiple specialized agents. + +## Overview + +The AOP server allows you to deploy multiple agents that can be discovered and called by other agents or clients in the network. This example shows how to create a server with specialized agents for different tasks. + +## Code Example + +```python +from swarms import Agent +from swarms.structs.aop import ( + AOP, +) + +# Create specialized agents +research_agent = Agent( + agent_name="Research-Agent", + agent_description="Expert in research, data collection, and information gathering", + model_name="anthropic/claude-sonnet-4-5", + max_loops=1, + top_p=None, + dynamic_temperature_enabled=True, + system_prompt="""You are a research specialist. Your role is to: + 1. Gather comprehensive information on any given topic + 2. Analyze data from multiple sources + 3. Provide well-structured research findings + 4. Cite sources and maintain accuracy + 5. Present findings in a clear, organized manner + + Always provide detailed, factual information with proper context.""", +) + +analysis_agent = Agent( + agent_name="Analysis-Agent", + agent_description="Expert in data analysis, pattern recognition, and generating insights", + model_name="anthropic/claude-sonnet-4-5", + max_loops=1, + top_p=None, + dynamic_temperature_enabled=True, + system_prompt="""You are an analysis specialist. Your role is to: + 1. Analyze data and identify patterns + 2. Generate actionable insights + 3. Create visualizations and summaries + 4. Provide statistical analysis + 5. Make data-driven recommendations + + Focus on extracting meaningful insights from information.""", +) + +writing_agent = Agent( + agent_name="Writing-Agent", + agent_description="Expert in content creation, editing, and communication", + model_name="anthropic/claude-sonnet-4-5", + max_loops=1, + top_p=None, + dynamic_temperature_enabled=True, + system_prompt="""You are a writing specialist. Your role is to: + 1. Create engaging, well-structured content + 2. Edit and improve existing text + 3. Adapt tone and style for different audiences + 4. Ensure clarity and coherence + 5. Follow best practices in writing + + Always produce high-quality, professional content.""", +) + +code_agent = Agent( + agent_name="Code-Agent", + agent_description="Expert in programming, code review, and software development", + model_name="anthropic/claude-sonnet-4-5", + max_loops=1, + top_p=None, + dynamic_temperature_enabled=True, + system_prompt="""You are a coding specialist. Your role is to: + 1. Write clean, efficient code + 2. Debug and fix issues + 3. Review and optimize code + 4. Explain programming concepts + 5. Follow best practices and standards + + Always provide working, well-documented code.""", +) + +financial_agent = Agent( + agent_name="Financial-Agent", + agent_description="Expert in financial analysis, market research, and investment insights", + model_name="anthropic/claude-sonnet-4-5", + max_loops=1, + top_p=None, + dynamic_temperature_enabled=True, + system_prompt="""You are a financial specialist. Your role is to: + 1. Analyze financial data and markets + 2. Provide investment insights + 3. Assess risk and opportunities + 4. Create financial reports + 5. Explain complex financial concepts + + Always provide accurate, well-reasoned financial analysis.""", +) + +# Basic usage - individual agent addition +deployer = AOP("MyAgentServer", verbose=True, port=5932) + +agents = [ + research_agent, + analysis_agent, + writing_agent, + code_agent, + financial_agent, +] + +deployer.add_agents_batch(agents) + +deployer.run() +``` + +## Key Components + +### 1. Agent Creation + +Each agent is created with: + +- **agent_name**: Unique identifier for the agent +- **agent_description**: Brief description of the agent's capabilities +- **model_name**: The language model to use +- **system_prompt**: Detailed instructions defining the agent's role and behavior + +### 2. AOP Server Setup + +- **Server Name**: "MyAgentServer" - identifies your server +- **Port**: 5932 - the port where the server will run +- **Verbose**: True - enables detailed logging + +### 3. Agent Registration + +- **add_agents_batch()**: Registers multiple agents at once +- Agents become available for discovery and remote calls + +## Usage + +1. **Start the Server**: Run the script to start the AOP server +2. **Agent Discovery**: Other agents or clients can discover available agents +3. **Remote Calls**: Agents can be called remotely by their names + +## Server Features + +- **Agent Discovery**: Automatically registers agents for network discovery +- **Remote Execution**: Agents can be called from other network nodes +- **Load Balancing**: Distributes requests across available agents +- **Health Monitoring**: Tracks agent status and availability + +## Configuration Options + +- **Port**: Change the port number as needed +- **Verbose**: Set to False for reduced logging +- **Server Name**: Use a descriptive name for your server + +## Next Steps + +- See [AOP Cluster Example](aop_cluster_example.md) for multi-server setups +- Check [AOP Reference](../structs/aop.md) for advanced configuration options +- Explore agent communication patterns in the examples directory diff --git a/pyproject.toml b/pyproject.toml index 9d3c05a1..0f872451 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -5,7 +5,7 @@ build-backend = "poetry.core.masonry.api" [tool.poetry] name = "swarms" -version = "8.4.0" +version = "8.4.1" description = "Swarms - TGSC" license = "MIT" authors = ["Kye Gomez "] diff --git a/swarms/structs/__init__.py b/swarms/structs/__init__.py index e6383155..145a736c 100644 --- a/swarms/structs/__init__.py +++ b/swarms/structs/__init__.py @@ -1,6 +1,7 @@ from swarms.structs.agent import Agent from swarms.structs.agent_loader import AgentLoader from swarms.structs.agent_rearrange import AgentRearrange, rearrange +from swarms.structs.aop import AOP from swarms.structs.auto_swarm_builder import AutoSwarmBuilder from swarms.structs.base_structure import BaseStructure from swarms.structs.base_swarm import BaseSwarm @@ -100,7 +101,6 @@ from swarms.structs.swarming_architectures import ( staircase_swarm, star_swarm, ) -from swarms.structs.aop import AOP __all__ = [ "Agent", diff --git a/swarms/structs/heavy_swarm.py b/swarms/structs/heavy_swarm.py index 1ab3ef92..8b04f8eb 100644 --- a/swarms/structs/heavy_swarm.py +++ b/swarms/structs/heavy_swarm.py @@ -34,15 +34,18 @@ Instructions: - Use evidence hierarchy: peer-reviewed > industry reports > news > social media. Weight by recency and authority. - For each claim, assess: source reliability, data quality, potential bias, methodology validity. - If insufficient evidence, quantify gaps: "Missing: [specific data type] from [timeframe] for [scope]." - -Output (≤400 tokens): -1. Findings (≤8 bullets, 1 sentence each, [Ref N]) -2. Evidence Quality Matrix (Source | Reliability | Recency | Bias Risk | Weight) -3. Confidence (High/Medium/Low + statistical rationale) -4. Data Gaps (≤3 bullets, specific and actionable) -5. References (numbered, titles + URLs + access date) - -Constraints: Systematic verification only. No speculation or analysis. +- Conduct comprehensive literature review and fact-checking protocols. +- Validate information through multiple independent sources when possible. + +Output Structure: +1. Key Findings (comprehensive list with supporting evidence and reference numbers) +2. Evidence Quality Matrix (Source | Reliability | Recency | Bias Risk | Weight | Validation Status) +3. Confidence Assessment (High/Medium/Low with detailed statistical rationale and sample size) +4. Data Gaps Analysis (specific missing information with actionable recommendations for filling gaps) +5. Source Verification (detailed assessment of each source's credibility and methodology) +6. References (comprehensive numbered list with titles, URLs, access dates, and quality scores) + +Constraints: Systematic verification only. No speculation or analysis. Focus on factual accuracy and evidence quality. """ @@ -54,15 +57,19 @@ Instructions: - Use quantitative methods: regression analysis, time series analysis, variance analysis, confidence intervals. - For each insight, calculate: correlation coefficient, statistical significance (p-value), confidence interval, effect size. - State assumptions explicitly and test for validity. Identify confounding variables and control for bias. - -Output (≤400 tokens): -1. Analytical Methods (statistical approach + assumptions + limitations) -2. Quantitative Insights (≤6 items: finding + statistical measure + confidence interval) -3. Statistical Assumptions (≤3 bullets: assumption + validity test + impact if violated) -4. Uncertainty Analysis (≤3 bullets: uncertainty type + magnitude + mitigation) -5. Confidence (High/Medium/Low + statistical rationale + sample size) - -Constraints: Statistical rigor only. No alternatives or implementation. +- Perform robust statistical testing with appropriate corrections for multiple comparisons. +- Conduct sensitivity analysis to test the robustness of findings. + +Output Structure: +1. Analytical Methods (detailed statistical approach, assumptions, limitations, and rationale for method selection) +2. Quantitative Insights (comprehensive findings with statistical measures, confidence intervals, and effect sizes) +3. Statistical Assumptions (detailed assessment of each assumption, validity tests, and impact analysis if violated) +4. Uncertainty Analysis (comprehensive assessment of uncertainty types, magnitudes, and mitigation strategies) +5. Model Validation (goodness-of-fit measures, residual analysis, and model diagnostics) +6. Sensitivity Analysis (robustness testing results and alternative model specifications) +7. Confidence Assessment (High/Medium/Low with detailed statistical rationale, sample size, and power analysis) + +Constraints: Statistical rigor only. No alternatives or implementation. Focus on methodological soundness and analytical depth. """ ALTERNATIVES_AGENT_PROMPT = """ @@ -73,18 +80,24 @@ Instructions: - Use multi-criteria decision analysis (MCDA): weighted scoring, pairwise comparison, sensitivity analysis. - For each option, calculate: NPV/ROI, implementation complexity, resource requirements, timeline, success probability. - Apply scenario analysis: best-case, most-likely, worst-case outcomes with probability distributions. +- Consider stakeholder perspectives and value trade-offs in option evaluation. +- Assess interdependencies and potential synergies between options. -Output (≤500 tokens): -- Options: +Output Structure: +- Strategic Options: - Option Name - - Summary (1 sentence) - - Quantitative Scores: Impact X/5, Effort Y/5, Risk Z/5, ROI %, Timeline (months) - - Pros (≤2), Cons (≤2), Preconditions (≤2) - - Scenario Analysis: Best (probability), Most-likely (probability), Worst (probability) -- Decision Matrix: Option | Impact | Effort | Risk | ROI | Timeline | Weighted Score -- Selection Criteria (≤3 bullets: decision rule + threshold + tie-breaking) - -Constraints: Systematic analysis only. No feasibility verification. + - Executive Summary (comprehensive overview of the option) + - Quantitative Analysis: Impact X/5, Effort Y/5, Risk Z/5, ROI %, Timeline (months), Resource Requirements + - Detailed Pros and Cons (comprehensive advantages and disadvantages) + - Implementation Preconditions (detailed requirements and dependencies) + - Scenario Analysis: Best-case (probability), Most-likely (probability), Worst-case (probability) + - Stakeholder Impact Assessment (who benefits/loses and to what degree) +- Comprehensive Decision Matrix: Option | Impact | Effort | Risk | ROI | Timeline | Resource Efficiency | Weighted Score +- Selection Criteria (detailed decision rules, thresholds, and tie-breaking mechanisms) +- Sensitivity Analysis (how changes in weights or criteria affect rankings) +- Risk-Adjusted Recommendations (options ranked by risk-adjusted value) + +Constraints: Systematic analysis only. No feasibility verification. Focus on comprehensive option evaluation and strategic thinking. """ @@ -96,14 +109,19 @@ Instructions: - Use risk assessment frameworks: probability × impact matrix, failure mode analysis, sensitivity analysis. - For each claim, assess: evidence quality, source credibility, logical consistency, empirical validity. - Identify logical fallacies, cognitive biases, and methodological errors. Flag contradictions with statistical confidence. - -Output (≤400 tokens): -1. Verification Matrix (Claim | Status | Evidence Quality | Source Credibility | Confidence | P-value) -2. Risk Assessment (Risk | Probability | Impact | Mitigation | Residual Risk) -3. Logical Consistency Check (Contradiction | Severity | Resolution | Confidence) -4. Feasibility Analysis (Constraint | Impact | Workaround | Probability of Success) - -Constraints: Systematic validation only. Objective and evidence-based. +- Conduct comprehensive fact-checking using multiple independent verification sources. +- Apply rigorous quality assurance protocols to ensure accuracy and reliability. + +Output Structure: +1. Comprehensive Verification Matrix (Claim | Status | Evidence Quality | Source Credibility | Confidence | P-value | Validation Method) +2. Detailed Risk Assessment (Risk | Probability | Impact | Mitigation Strategy | Residual Risk | Monitoring Requirements) +3. Logical Consistency Analysis (Contradiction | Severity | Resolution Strategy | Confidence Level | Evidence Supporting Resolution) +4. Feasibility Analysis (Constraint | Impact | Workaround Options | Probability of Success | Resource Requirements) +5. Quality Assurance Report (Validation Methods Used | Quality Metrics | Areas of Concern | Recommendations for Improvement) +6. Bias Detection Analysis (Potential Biases | Impact Assessment | Mitigation Strategies | Monitoring Protocols) +7. Evidence Chain Validation (Source Verification | Chain of Custody | Reliability Assessment | Confidence Intervals) + +Constraints: Systematic validation only. Objective and evidence-based. Focus on accuracy, reliability, and comprehensive verification. """ SYNTHESIS_AGENT_PROMPT = """ @@ -114,16 +132,22 @@ Instructions: - Use decision frameworks: multi-criteria decision analysis (MCDA), analytic hierarchy process (AHP), Pareto optimization. - For each recommendation, calculate: expected value, risk-adjusted return, implementation probability, resource efficiency. - Reconcile conflicts using evidence hierarchy: statistical significance > source credibility > recency > sample size. - -Output (≤600 tokens): -1. Executive Summary (≤6 bullets: key findings + confidence + action items) -2. Integrated Analysis (≤8 bullets: insight + statistical measure + agent attribution + confidence) -3. Conflict Resolution Matrix (Contradiction | Evidence Weight | Resolution | Confidence) -4. Optimized Recommendations (table: Recommendation | Expected Value | Risk Score | Implementation Probability | Resource Efficiency | Priority) -5. Risk-Optimized Portfolio (Risk | Probability | Impact | Mitigation | Residual Risk | Cost) -6. Implementation Roadmap (Step | Owner | Timeline | Dependencies | Success Metrics | Probability) - -Constraints: Systematic optimization only. Evidence-based decision support. +- Integrate insights from all agent perspectives into coherent strategic recommendations. +- Apply advanced optimization techniques to maximize value while minimizing risk and resource requirements. + +Output Structure: +1. Executive Summary (comprehensive key findings with confidence levels and prioritized action items) +2. Integrated Analysis (detailed insights with statistical measures, agent attribution, and confidence assessments) +3. Conflict Resolution Matrix (Contradiction | Evidence Weight | Resolution Strategy | Confidence Level | Implementation Plan) +4. Optimized Recommendations (comprehensive table: Recommendation | Expected Value | Risk Score | Implementation Probability | Resource Efficiency | Priority | Timeline) +5. Risk-Optimized Portfolio (Risk | Probability | Impact | Mitigation Strategy | Residual Risk | Cost | Monitoring Requirements) +6. Implementation Roadmap (Step | Owner | Timeline | Dependencies | Success Metrics | Probability | Resource Requirements) +7. Value Optimization Analysis (ROI projections, cost-benefit analysis, and value maximization strategies) +8. Stakeholder Impact Assessment (comprehensive analysis of how recommendations affect different stakeholder groups) +9. Success Metrics and KPIs (detailed measurement framework for tracking implementation success) +10. Contingency Planning (alternative approaches and fallback strategies for high-risk scenarios) + +Constraints: Systematic optimization only. Evidence-based decision support. Focus on practical implementation and measurable outcomes. """ schema = {