Repetitive Agents

from praisonaiagents import Agent, Task, PraisonAIAgents

# Create agent for processing questions
qa_agent = Agent(
    name="QA Bot",
    role="Answer questions",
    goal="Provide accurate answers to user questions"
)

# Create loop task that processes questions from CSV
loop_task = Task(
    name="process_questions",
    description="Answer each question",
    expected_output="Answer for each question",
    agent=qa_agent,
    task_type="loop",
    input_file="questions.csv"  # Each row becomes a subtask
)

# Create workflow
agents = PraisonAIAgents(
    agents=[qa_agent],
    tasks=[loop_task],
    process="workflow"  # Use workflow for loop tasks
)

# Run the batch processing
result = agents.start()

question,context,priority
"What is Python?","Programming language context","high"
"Explain machine learning","AI and ML context","medium"
"How does Docker work?","Container technology context","high"

# Agent that uses multiple CSV columns
analyzer = Agent(
    name="Data Analyzer",
    role="Analyze data entries",
    goal="Process and analyze each data entry"
)

# Task that uses multiple columns from CSV
analysis_task = Task(
    name="analyze_entries",
    description="Analyze data: {title} with context: {context}",
    expected_output="Analysis report for each entry",
    agent=analyzer,
    task_type="loop",
    input_file="data_entries.csv",
    # Map CSV columns to task parameters
    column_mapping={
        "title": "title",
        "context": "context",
        "category": "metadata.category"
    }
)

# Define the processor agent
processor = Agent(
    name="DataProcessor",
    role="Data processing specialist",
    goal="Process various data formats efficiently"
)

# JSON file processing
json_task = Task(
    name="process_json_data",
    description="Process JSON entries",
    expected_output="Processed results",
    agent=processor,
    task_type="loop",
    input_file="data.json",
    file_format="json"  # Specify file format
)

# Text file processing (one task per line)
text_task = Task(
    name="process_lines",
    description="Process text: {line}",
    expected_output="Processed line",
    agent=processor,
    task_type="loop",
    input_file="tasks.txt",
    file_format="text"
)

# Configure parallel processing for better performance
agents = PraisonAIAgents(
    agents=[qa_agent],
    tasks=[loop_task],
    process="workflow",
    max_workers=5,  # Process 5 items in parallel
    batch_size=10   # Process in batches of 10
)

# Define the required agents
extractor = Agent(
    name="DataExtractor",
    role="Data extraction specialist",
    goal="Extract data from various sources"
)

transformer = Agent(
    name="DataTransformer",
    role="Data transformation expert",
    goal="Transform data to required format"
)

# First loop task processes data
extract_task = Task(
    name="extract_data",
    description="Extract data from {source}",
    expected_output="Extracted data",
    agent=extractor,
    task_type="loop",
    input_file="sources.csv"
)

# Second loop task uses results from first
transform_task = Task(
    name="transform_data",
    description="Transform extracted data",
    expected_output="Transformed data",
    agent=transformer,
    task_type="loop",
    depends_on=["extract_data"]  # Uses output from extract_data
)

# Define processor agent
processor = Agent(
    name="SafeProcessor",
    role="Error-tolerant processor",
    goal="Process items with error recovery"
)

# Configure error handling for batch processing
loop_task = Task(
    name="process_with_recovery",
    description="Process item safely",
    expected_output="Processed result",
    agent=processor,
    task_type="loop",
    input_file="items.csv",
    error_handling={
        "continue_on_error": True,  # Don't stop on errors
        "max_retries": 3,          # Retry failed items
        "log_errors": True         # Log all errors
    }
)

from praisonaiagents.callbacks import Callback

class BatchProgressTracker(Callback):
    def __init__(self):
        self.processed = 0
        self.total = 0
        
    def on_task_start(self, task, **kwargs):
        if task.task_type == "loop" and self.total == 0:
            # Count total items
            import csv
            try:
                with open(task.input_file, 'r', encoding='utf-8') as f:
                    # More efficient for counting lines in a CSV
                    self.total = sum(1 for _ in f) - 1
            except FileNotFoundError:
                print(f"Warning: Input file not found at {task.input_file}. Progress will not be shown.")
                self.total = 0
    
    def on_subtask_complete(self, subtask, result, **kwargs):
        self.processed += 1
        print(f"Progress: {self.processed}/{self.total} ({self.processed/self.total*100:.1f}%)")

# Use progress tracker
agents = PraisonAIAgents(
    agents=[qa_agent],
    tasks=[loop_task],
    callbacks=[BatchProgressTracker()]
)

# Define the summarizer agent
summarizer = Agent(
    name="Summarizer",
    role="Results aggregator",
    goal="Create comprehensive summaries from processed data"
)

# Task that aggregates all loop results
summary_task = Task(
    name="summarize_results",
    description="Create summary of all processed items",
    expected_output="Comprehensive summary report",
    agent=summarizer,
    depends_on=["process_questions"],  # Depends on loop task
    aggregate_results=True  # Receives all loop results
)

# Complete workflow
# Note: Assuming qa_agent and loop_task are defined from previous examples
agents = PraisonAIAgents(
    agents=[qa_agent, summarizer],
    tasks=[loop_task, summary_task],
    process="workflow"
)

import os
import csv

def validate_input_file(filepath):
    if not os.path.exists(filepath):
        raise FileNotFoundError(f"Input file not found: {filepath}")
    
    with open(filepath, 'r') as f:
        reader = csv.reader(f)
        headers = next(reader, None)
        if not headers:
            raise ValueError("CSV file is empty or has no headers")
    
    return True

loop_task = Task(
    name="process_large_file",
    description="Process item",
    expected_output="Result",
    agent=processor,
    task_type="loop",
    input_file="large_data.csv",
    streaming=True,  # Process one item at a time
    chunk_size=100   # Read 100 rows at a time
)

loop_task = Task(
    name="process_and_save",
    description="Process and save",
    expected_output="Saved result",
    agent=processor,
    task_type="loop",
    input_file="data.csv",
    output_file="results.csv",  # Save results to file
    append_mode=True  # Append results as processed
)