AI Governance Lexicon Agent

ai_lexicon/
├── main.py                    # Entry point with async main() function
├── agent.py                   # Agent configuration and system prompts
├── tools.py                   # Search tool configuration
├── schemas.py                 # Pydantic output schemas
├── upsonic_configs.json       # Upsonic CLI configuration
└── README.md                  # Quick start guide

# Required: Set OpenAI API key
export OPENAI_API_KEY="your-api-key"

# Install dependencies from upsonic_configs.json
upsonic install

# Add a package
upsonic add <package> <section>
upsonic add pandas api

# Remove a package
upsonic remove <package> <section>
upsonic remove streamlit api

uv run main.py

upsonic run

curl -X POST http://localhost:8000/call \
  -H "Content-Type: application/json" \
  -d '{
    "inputs": {
      "term": "Gap analysis for AI governance"
    }
  }'

{
  "term": "Gap analysis for AI governance"
}

{
  "term": "Gap analysis for AI governance",
  "brief_explanation": "Gap analysis for AI governance is a systematic process...",
  "faqs": [
    {
      "question": "What is the purpose of gap analysis in AI governance?",
      "answer": "Gap analysis helps organizations identify..."
    }
  ]
}

"""
Main entry point for AI Governance Lexicon Agent.

This module provides the entry point that coordinates the research 
and explanation generation for AI governance terms.
"""

from __future__ import annotations

from typing import Dict, Any

from upsonic import Task

try:
    from .agent import create_lexicon_agent
    from .schemas import LexiconEntry
except ImportError:
    from agent import create_lexicon_agent
    from schemas import LexiconEntry


async def main(inputs: Dict[str, Any]) -> Dict[str, Any]:
    """
    Main function for AI Lexicon agent.
    
    Args:
        inputs: Dictionary containing:
            - term: The AI governance term to explain (required)
            - model: Optional model identifier (default: "openai/gpt-4o")
            - max_search_results: Optional max search results (default: 10)
    
    Returns:
        Dictionary containing the detailed explanation and FAQs
    """
    term = inputs.get("term")
    if not term:
        # Fallback for "keyword" if "term" is not provided
        term = inputs.get("keyword")
        
    if not term:
        raise ValueError("term or keyword is required in inputs")
    
    model = inputs.get("model", "openai/gpt-4o")
    max_search_results_input = inputs.get("max_search_results", 10)
    max_search_results: int = int(max_search_results_input) if max_search_results_input is not None else 10
    
    # Initialize the agent
    agent = create_lexicon_agent(
        model=model,
        max_search_results=max_search_results
    )
    
    # Define the task
    task_description = f"""
    Research and explain the AI governance term: "{term}"
    
    1. Search for current definitions, frameworks, and best practices.
    2. Provide a brief but comprehensive explanation.
    3. Generate 3-5 relevant FAQs with answers.
    """
    
    task = Task(task_description, response_format=LexiconEntry)
    
    # Execute the agent
    result = await agent.do_async(task)
    
    # Return result as dictionary
    return result.model_dump(mode='json')


if __name__ == "__main__":
    import asyncio
    import json
    import sys
    
    test_inputs = {
        "term": "Gap analysis for AI governance",
        "model": "openai/gpt-4o",
    }
    
    if len(sys.argv) > 1:
        try:
            with open(sys.argv[1], "r") as f:
                file_inputs = json.load(f)
                if file_inputs:
                    test_inputs = file_inputs
        except Exception as e:
            print(f"Error loading JSON file: {e}")
            print("Using default test inputs")
    
    async def run_main():
        try:
            print(f"Researching term: {test_inputs.get('term') or test_inputs.get('keyword')}...")
            result = await main(test_inputs)
            
            print("\n" + "=" * 80)
            print("LEXICON ENTRY GENERATED")
            print("=" * 80)
            
            print(f"\n{result.get('term')}:")
            print(f"\n{result.get('brief_explanation')}")
            
            print("\nFAQs:")
            for i, faq in enumerate(result.get('faqs', []), 1):
                print(f"\nQ{i}: {faq.get('question')}")
                print(f"A{i}: {faq.get('answer')}")
                
        except Exception as e:
            print(f"\n❌ Error during execution: {e}")
            import traceback
            traceback.print_exc()
            sys.exit(1)
    
    asyncio.run(run_main())

"""
Agent configuration for the AI Lexicon Agent.

This module creates and configures the Upsonic Agent with 
appropriate tools and system prompts for AI governance term explanations.
"""

from __future__ import annotations

from typing import Optional

from upsonic import Agent

try:
    from .tools import get_all_tools
except ImportError:
    from tools import get_all_tools


LEXICON_SYSTEM_PROMPT = """You are an AI Governance Lexicon Expert. Your role is to provide comprehensive, 
accurate, and educational explanations of AI-related governance terms and concepts.

When given an AI governance term or concept, you must:

1. RESEARCH: Use the web search tool to find current, authoritative information about the term.
   Search for definitions, frameworks, best practices, and real-world applications.

2. EXPLAIN: Provide a detailed but accessible explanation that covers:
   - Clear definition of the term
   - Why it matters in AI governance
   - Key components or aspects
   - Practical applications and examples
   - Relationship to other governance concepts

3. FAQs: Generate 3-5 frequently asked questions that someone learning about this term 
   would likely have, along with comprehensive answers.

Your explanations should be:
- Accurate and well-researched (use search tools to verify information)
- Educational and accessible to both technical and non-technical audiences
- Practical with real-world examples when possible
- Current and up-to-date with latest industry practices

Always search the internet first to ensure your explanations are based on current 
best practices and authoritative sources."""


def create_lexicon_agent(
    model: str = "openai/gpt-4o",
    max_search_results: int = 10,
) -> Agent:
    """
    Create and configure the AI Lexicon agent.
    
    Args:
        model: The LLM model identifier to use
        max_search_results: Maximum search results per query
        
    Returns:
        Configured Agent instance ready for lexicon tasks
    """
    tools = get_all_tools(max_search_results=max_search_results)
    
    agent = Agent(
        name="AI Governance Lexicon Agent",
        model=model,
        system_prompt=LEXICON_SYSTEM_PROMPT,
    )
    
    agent.add_tools(tools)
    
    return agent

"""
Tools for the AI Lexicon Agent.

This module provides web search tools for researching AI governance terms
and retrieving comprehensive information from the internet.
"""

from __future__ import annotations

from typing import Callable


def get_search_tool(max_results: int = 10) -> Callable:
    """
    Get the DuckDuckGo search tool for researching AI terms.
    
    Args:
        max_results: Maximum number of search results to return
        
    Returns:
        A configured search tool function
    """
    from upsonic.tools.common_tools.duckduckgo import duckduckgo_search_tool
    
    return duckduckgo_search_tool(
        duckduckgo_client=None,
        max_results=max_results
    )


def get_all_tools(max_search_results: int = 10) -> list:
    """
    Get all tools configured for the AI Lexicon agent.
    
    Args:
        max_search_results: Maximum search results per query
        
    Returns:
        List of all configured tools
    """
    return [
        get_search_tool(max_results=max_search_results),
    ]

"""
Output schemas for the AI Lexicon Agent.

This module defines the Pydantic models for structured output
from the AI governance lexicon explanations.
"""

from __future__ import annotations

from typing import List
from pydantic import BaseModel, Field


class FAQ(BaseModel):
    """A single frequently asked question with its answer."""
    
    question: str = Field(
        description="A common question about the AI governance term"
    )
    answer: str = Field(
        description="A comprehensive answer to the question"
    )


class LexiconEntry(BaseModel):
    """
    Complete lexicon entry for an AI governance term.
    
    This represents the full output of the AI Lexicon agent,
    containing a brief explanation and FAQs for the given term.
    """
    
    term: str = Field(
        description="The AI governance term being explained"
    )
    brief_explanation: str = Field(
        description="A detailed but concise explanation of the term, covering its definition, importance, and practical applications in AI governance"
    )
    faqs: List[FAQ] = Field(
        default_factory=list,
        description="List of frequently asked questions and their answers about the term"
    )
    
    def format_output(self) -> str:
        """Format the lexicon entry as a readable string."""
        output_lines = [
            f"{self.term}:",
            "",
            self.brief_explanation,
            "",
            "FAQs:",
            ""
        ]
        
        for i, faq in enumerate(self.faqs, 1):
            output_lines.append(f"Q{i}: {faq.question}")
            output_lines.append(f"A{i}: {faq.answer}")
            output_lines.append("")
        
        return "\n".join(output_lines)

{
    "envinroment_variables": {
        "UPSONIC_WORKERS_AMOUNT": {
            "type": "number",
            "description": "The number of workers for the Upsonic API",
            "default": 1
        },
        "API_WORKERS": {
            "type": "number",
            "description": "The number of workers for the Upsonic API",
            "default": 1
        },
        "RUNNER_CONCURRENCY": {
            "type": "number",
            "description": "The number of runners for the Upsonic API",
            "default": 1
        }
    },
    "machine_spec": {
        "cpu": 2,
        "memory": 4096,
        "storage": 1024
    },
    "agent_name": "AI Governance Lexicon Agent",
    "description": "An educational AI agent that takes an AI governance term as input, researches it using web tools, and provides a detailed explanation along with frequently asked questions.",
    "icon": "book-open",
    "language": "python",
    "streamlit": false,
    "proxy_agent": false,
    "dependencies": {
        "api": [
            "upsonic",
            "upsonic[tools]"
        ],
        "development": [
            "python-dotenv",
            "pytest"
        ]
    },
    "entrypoints": {
        "api_file": "main.py",
        "streamlit_file": "streamlit_app.py"
    },
    "input_schema": {
        "inputs": {
            "term": {
                "type": "string",
                "description": "The AI governance term to research and explain (e.g., 'Gap analysis for AI governance')",
                "required": true,
                "default": null
            },
            "model": {
                "type": "string",
                "description": "Optional model identifier",
                "required": false,
                "default": "openai/gpt-4o"
            },
            "max_search_results": {
                "type": "number",
                "description": "Maximum number of search results to use for research",
                "required": false,
                "default": 10
            }
        }
    },
    "output_schema": {
        "term": {
            "type": "string",
            "description": "The AI governance term being explained"
        },
        "brief_explanation": {
            "type": "string",
            "description": "A detailed but concise explanation of the term"
        },
        "faqs": {
            "type": "array",
            "description": "List of frequently asked questions and their answers",
            "items": {
                "type": "object",
                "properties": {
                    "question": {
                        "type": "string",
                        "description": "The question"
                    },
                    "answer": {
                        "type": "string",
                        "description": "The answer"
                    }
                }
            }
        }
    }
}