### Setup development environment

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/src/praisonai-ts/README.md

Commands to clone the repository, install dependencies, and build the project.

```bash
git clone https://github.com/MervinPraison/PraisonAI.git
cd src/praisonai-ts
```

```bash
npm install
```

```bash
npm run build
```

--------------------------------

### Install Dependencies and Configure Environment

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/python/concepts/CSV_PROCESSING_README.md

Required setup commands for installing the framework, setting API keys, and adding pandas support.

```bash
pip install praisonaiagents
```

```bash
export OPENAI_API_KEY=your_api_key_here
```

```bash
pip install pandas
```

--------------------------------

### Install with All Features

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/src/praisonai-agents/CLAUDE.md

Installs the framework with all available features enabled. This is a comprehensive installation.

```bash
pip install -e .[all]
```

--------------------------------

### Quick Start PraisonAI

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/README.md

Install the package, configure the API key, and execute a simple agent task.

```bash
# Install
pip install praisonaiagents

# Set API key
export OPENAI_API_KEY=your_key_here

# Create a simple agent
python -c "from praisonaiagents import Agent; Agent(instructions='You are a helpful AI assistant').start('Write a haiku about AI')"
```

--------------------------------

### Install and Create a Simple Agent (Python)

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/src/praisonai/README.md

Quick start guide to install the PraisonAI agents package and create a basic AI agent that responds to a prompt.

```bash
pip install praisonaiagents

export OPENAI_API_KEY=your_key_here

python -c "from praisonaiagents import Agent; Agent(instructions='You are a helpful AI assistant').start('Write a haiku about AI')"
```

--------------------------------

### Execute Examples via CLI

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/python/models/googlegemini/README_GEMINI_INTERNAL_TOOLS.md

Commands to run the provided example scripts.

```bash
export GEMINI_API_KEY="your-api-key"
python gemini-google-search.py
python gemini-url-context.py  
python gemini-code-execution.py
python gemini-internal-tools-combined.py
```

--------------------------------

### Run Camera Examples

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/python/camera/README.md

Commands to execute the provided camera integration example scripts.

```bash
python camera-basic.py
```

```bash
python camera-continuous.py
```

```bash
python camera-multi-agent.py
```

```bash
python camera-video-analysis.py
```

--------------------------------

### Start MCP Server Example

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/src/praisonai-agents/CLAUDE.md

Starts an MCP (Model Context Protocol) server using Server-Sent Events (SSE). This is the server-side component for distributed agent execution.

```bash
python tests/mcp-sse-direct-server.py
```

--------------------------------

### Install Python SDK

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/README.md

Install the lightweight SDK or the full framework with CLI support.

```bash
pip install praisonaiagents
```

```bash
pip install praisonai
```

--------------------------------

### Run Basic Agent Usage Example

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/src/praisonai-agents/CLAUDE.md

Executes a script demonstrating the basic usage of a single agent. This is a good starting point for understanding agent instantiation and execution.

```bash
python tests/single-agent.py
```

--------------------------------

### Install Dependencies

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/Research_Knowledge_QA_Agents/Crypto_Research_Agent_Intelligence_Agent.ipynb

Install the required PraisonAI and search packages.

```bash
!pip install -q praisonaiagents openai duckduckgo_search
```

--------------------------------

### Install Dependencies

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/Education_Learning_Agents/Personalized_Learning_Assistant.ipynb

Install the required libraries for the agent framework, OpenAI API, and transformers.

```bash
!pip install praisonaiagents openai transformers
```

--------------------------------

### Install Dependencies

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/Conversational_Chat_Agents/ReAct_agent.ipynb

Install the required packages for the agent framework, OpenAI, and search functionality.

```bash
!pip install openai praisonaiagents duckduckgo-search
```

--------------------------------

### Install Dependencies

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/Research_Knowledge_QA_Agents/Ai_Documentation_Processor.ipynb

Installs the necessary Python packages for the PraisonAI framework and environment setup.

```python
# @title **📦 Install Dependencies**

# Install required packages
!pip install praisonaiagents openai python-dotenv fastapi uvicorn -q

# Basic imports
import os
import json
import re  # FIXED: Added missing import
import base64
import mimetypes
import logging
from typing import Dict, List, Optional, Any, Tuple
from datetime import datetime
import getpass

print("📦 Dependencies installed successfully!")
print("📝 AI Documentation Processor ready!")
print("🤖 Using PraisonAI Multi-Agent Framework")
```

--------------------------------

### Install Dependencies Silently

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/yaml/stock_analysis_agents.ipynb

Installs Python packages using pip without displaying installation output. Useful for automated setups or clean environments.

```bash
%pip install langchain_community > /dev/null
```

```bash
%pip install praisonai[crewai] > /dev/null
```

```bash
%pip install duckduckgo-search > /dev/null
```

```bash
%pip install sec-api > /dev/null
```

```bash
%pip install embedchain > /dev/null
```

```bash
%pip install html2text > /dev/null
```

--------------------------------

### Install Core Package

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/src/praisonai-agents/CLAUDE.md

Installs the core Praison AI Agent Framework package. Use this for basic setup.

```bash
pip install -e .
```

--------------------------------

### Initialize Framework Environment

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/Conversational_Chat_Agents/Multi_Agent_Production_System.ipynb

Import necessary standard libraries and verify the environment setup.

```python
import os
import json
import time
import sqlite3
from pathlib import Path
from typing import Dict, List, Optional, Any, Tuple
from datetime import datetime
import getpass

print("📦 Dependencies installed!")
print("🔄 Using PraisonAI Multi-Agent Framework")
print("🤖 Powered by OpenAI gpt-5-nano")
```

--------------------------------

### Start the Intelligence Analysis

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/SocialMedia_Content_Agents/YouTube_Influencer_Intelligence_Agent.ipynb

Executes the defined task using the `PraisonAIAgents` system. The `start` method takes an input query to guide the analysis.

```python
query = "Study the YouTube channel 'Ali Abdaal'. What makes it grow? Give tips for new productivity YouTubers."
output = yt_intel_system.start(input=query)

```

--------------------------------

### Installation Commands

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/python/usecases/README-secondary-market-research.md

Required packages for running the framework.

```bash
pip install praisonai[crewai]
pip install fastapi uvicorn
```

--------------------------------

### Install with Knowledge Capabilities

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/src/praisonai-agents/CLAUDE.md

Installs the framework with document processing and knowledge retrieval features. Use this when agents need to interact with external documents.

```bash
pip install -e .[knowledge]
```

--------------------------------

### Agent Execution Output

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/yaml/job_profile_matching_agents.ipynb

Example logs showing the agent starting a task and performing file actions.

```text
Output:
 [2024-11-03 18:16:01][DEBUG]: == Working Agent: CV Reader
 [2024-11-03 18:16:01][INFO]: == Starting Task: Extract relevant information from the given CV. Focus on skills, experience, education, and key achievements.
Ensure to capture the candidate's professional summary, technical skills, work history, and educational background.

CV file: /content/cv.md



> Entering new CrewAgentExecutor chain...
Action: Read a file's content  
Action Input: {"file_path": "/content/cv.md"}  
```

--------------------------------

### Execute Monitoring Examples

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/python/monitoring/README.md

Run the provided example scripts to observe performance metrics in action.

```bash
python 01_basic_agent_with_monitoring.py
python 10_comprehensive_dashboard.py
```

--------------------------------

### Configure Agent for CSV URL Analysis

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/python/concepts/CSV_PROCESSING_README.md

Example setup for an agent utilizing CSV tools to analyze specific URL data.

```python
# Your CSV: urls.csv
# url,priority
# https://example.com,high
# https://github.com,medium

agent = Agent(
    name="URLAnalyzer",
    tools=[read_csv, write_csv],
    instructions="Analyze URLs based on priority"
)
```

--------------------------------

### Initialize Sample Document

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/Research_Knowledge_QA_Agents/Local_RAG_Document_QA_Agent.ipynb

Creates a sample document string for testing purposes.

```python
print("\n🧪 Sample Document for Testing")
print("Creating sample document...")

# Create sample document
sample_text = """
```

--------------------------------

### Initialize Financial Coaching Agent

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/Finance_Market_Job_Agents/Financial_Coaching_Agent.ipynb

Sets up dummy financial data and initializes the agent to provide recommendations based on income, expenses, and debt.

```python
dummy_financial_data = {
    "monthly_income": 3000,
    "expenses": {
        "Housing": 1200,
        "Food": 400,
        "Transportation": 200,
        "Entertainment": 150,
        "Savings": 300,
        "Other": 100
    },
    "debts": [
        {"name": "Credit Card", "amount": 2000, "interest_rate": 18.0, "min_payment": 50},
        {"name": "Student Loan", "amount": 8000, "interest_rate": 5.0, "min_payment": 100}
    ]
}

income = dummy_financial_data["monthly_income"]
expenses = dummy_financial_data["expenses"]
debts = dummy_financial_data["debts"]

tool = FinancialSummaryTool(income, expenses, debts)
summary = tool.summary()

if not is_valid_key(OPENAI_API_KEY, "sk"):
    print("API key not set or is a placeholder. Using dummy recommendations for CI/testing.")
    recommendations = """
    - Review your monthly expenses and identify areas to cut back.
    - Increase your monthly savings by at least 10%.
    - Pay off high-interest debts first (e.g., Credit Card).
    - Build an emergency fund covering at least 3-6 months of expenses.
    """
else:
    prompt = f"""
    You are a financial coach. Analyze the following summary and provide actionable recommendations:
    - Monthly income: ${summary['surplus'] + summary['total_expenses']}
    - Total expenses: ${summary['total_expenses']}
    - Surplus: ${summary['surplus']}
    - Total debt: ${summary['total_debt']}
    - Expense breakdown: {summary['expense_breakdown']}
    - Debts: {summary['debts']}
    """
    agent = Agent(
        name="Financial Coaching Agent",
        api_key=OPENAI_API_KEY
    )
    # Use start(prompt) instead of run()
    recommendations = agent.start(prompt)

print("=== Financial Coaching Agent Recommendations ===")
print(recommendations)
```

--------------------------------

### Install uv and Dependencies

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/README.md

Installs the 'uv' package manager and then installs project dependencies from 'pyproject.toml'. Supports installing with extra features like 'crewai' or 'autogen'.

```bash
pip install uv
```

```bash
uv pip install -r pyproject.toml
```

```bash
uv pip install -r pyproject.toml --extra code
```

```bash
uv pip install -r pyproject.toml --extra "crewai,autogen"
```

--------------------------------

### Install with API Server Capabilities

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/src/praisonai-agents/CLAUDE.md

Installs the framework with API server capabilities. This allows agents to be exposed and controlled via an API.

```bash
pip install -e .[api]
```

--------------------------------

### Run Agent with Example Question

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/Vision_Multimodal_Agents/Groq_LPU_Powered_AI_Assistant.ipynb

Executes the agent by building the prompt for a sample user question and then calling the Groq chat completion function. Prints the agent's response.

```python
user_question = "What are the advantages of Groq's LPU-powered models compared to traditional GPUs?"
prompt_messages = build_prompt(user_question)
agent_response = run_groq_chat(prompt_messages, model=config['model'])
print("Agent response:")
print(agent_response)
```

--------------------------------

### Install Dependencies

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/yaml/trip_planner_agents.ipynb

Installs necessary Python packages for the Praison AI Agent Framework, suppressing output during installation.

```bash
%pip install langchain_community > /dev/null
```

```bash
%pip install praisonai[crewai] > /dev/null
```

```bash
%pip install requests > /dev/null
```

```bash
%pip install duckduckgo_search > /dev/null
```

--------------------------------

### Start an Agent with Input

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/Research_Knowledge_QA_Agents/KnowledgeAgent_PraisonAI.ipynb

Use the `agents.start` function to initiate an agent with a specific input query. This is the primary method for interacting with the framework.

```python
result = agents.start(input="Explain how quantum computing differs from classical computing.")\nprint("📄 Output Summary:")\nprint(result)
```

--------------------------------

### Install Dependencies

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/Conversational_Chat_Agents/TinyLlama_1_1B_model_SimpleAIAgent.ipynb

Installs the necessary libraries for running the TinyLlama agent. Ensure you have PyTorch, transformers, and accelerate installed.

```python
!pip install -q transformers accelerate torch
```

--------------------------------

### Install Dependencies

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/Vision_Multimodal_Agents/Pixtral_12B_Vision_Model.ipynb

Installs necessary libraries for using the Pixtral model. Use the Colab-specific installation for Google Colab environments.

```python
!pip install transformers accelerate torch torchvision
```

```python
%%capture
import os
if "COLAB_" not in "".join(os.environ.keys()):
    !pip install unsloth
else:
    # Do this only in Colab notebooks! Otherwise use pip install unsloth
    !pip install --no-deps bitsandbytes accelerate xformers==0.0.29.post3 peft trl triton cut_cross_entropy unsloth_zoo
    !pip install sentencepiece protobuf "datasets>=3.4.1" huggingface_hub hf_transfer
    !pip install --no-deps unsloth
```

--------------------------------

### Initialize and Start the Agent Process

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/SocialMedia_Content_Agents/DuckDuckGo_PraisonAI_Agent_Notebook.ipynb

Sets up the PraisonAIAgents with the defined agents and tasks, specifying a 'sequential' process, and then starts the agent execution.

```python
agents = PraisonAIAgents(\n    agents=[search_agent],\n    tasks=[search_task],\n    process="sequential"\n)\nagents.start()
```

--------------------------------

### Install Dependencies for Trip Planner Agents

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/yaml/surprise_trip_planner_and_itinerary_agents.ipynb

Installs necessary Python packages for the trip planner and itinerary agents. Suppresses output during installation.

```python
# Install dependencies without output
%pip install langchain_community > /dev/null
%pip install praisonai[crewai] > /dev/null
%pip install requests > /dev/null
%pip install duckduckgo_search > /dev/null
```

--------------------------------

### Initialize and Use VectorDatabaseTool

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/Research_Knowledge_QA_Agents/Local_RAG_Document_QA_Agent.ipynb

Demonstrates initializing the VectorDatabaseTool with ChromaDB and adding/searching documents.

```python
import chromadb
import numpy as np
from typing import List, Dict, Any

class VectorDatabaseTool:
    def __init__(self, collection_name: str = "document_qa"):
        self.collection_name = collection_name
        # Use new ChromaDB client configuration
        self.client = chromadb.PersistentClient(path="./chroma_db")
        self.collection = self.client.get_or_create_collection(name=collection_name)

    def add_documents(self, documents: List[str], metadatas: List[Dict] = None, ids: List[str] = None) -> Dict[str, Any]:
        """Add documents to the vector database"""
        try:
            if ids is None:
                ids = [f"doc_{i}" for i in range(len(documents))]
            if metadatas is None:
                metadatas = [{"source": f"document_{i}"} for i in range(len(documents))]

            self.collection.add(
                documents=documents,
                metadatas=metadatas,
                ids=ids
            )

            return {
                "success": True,
                "documents_added": len(documents),
                "collection_name": self.collection_name
            }
        except Exception as e:
            return {"error": f"Error adding documents: {str(e)}"}

    def search_documents(self, query: str, n_results: int = 5) -> Dict[str, Any]:
        """Search for relevant documents"""
        try:
            results = self.collection.query(
                query_texts=[query],
                n_results=n_results
            )

            return {
                "success": True,
                "query": query,
                "results": results,
                "num_results": len(results['documents'][0]) if results['documents'] else 0
            }
        except Exception as e:
            return {"error": f"Error searching documents: {str(e)}"}

    def get_collection_info(self) -> Dict[str, Any]:
        """Get information about the collection"""
        try:
            count = self.collection.count()
            return {
                "success": True,
                "collection_name": self.collection_name,
                "document_count": count
            }
        except Exception as e:
            return {"error": f"Error getting collection info: {str(e)}"}

```

--------------------------------

### Run PraisonAI Examples with ts-node

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/src/praisonai-ts/examples/concepts/README.md

Execute PraisonAI examples using ts-node. Examples include single-agent, multi-agent, and task-based agent scenarios.

```bash
# Run single agent example
npx ts-node examples/concepts/single-agent.ts
```

```bash
# Run multi-agent example
npx ts-node examples/concepts/multi-agent.ts
```

```bash
# Run task-based agent example
npx ts-node examples/concepts/task-based-agent.ts
```

--------------------------------

### Start Documentation Processing Demo

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/Research_Knowledge_QA_Agents/Ai_Documentation_Processor.ipynb

Initiates a demonstration of the documentation processing. This message confirms the start of the demo and specifies the SDK being used.

```text
🚀 Demo: Processing documentation...\n📝 Processing documentation for: TypeScript SDK
```

--------------------------------

### Install Libraries for TTS

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/Vision_Multimodal_Agents/Sesame_CSM_1B_TTS.ipynb

Installs the required libraries for text-to-speech generation using the Sesame CSM model. Ensure these are installed before running the main script.

```python
!pip install -q transformers
!pip install -q torchaudio
!pip install -q soundfile
```

--------------------------------

### Install Dependencies and Initialize Environment

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/Finance_Market_Job_Agents/Ai_Job_Hunting_Assistant.ipynb

Installs necessary Python libraries and imports core modules for the job hunting system.

```python
# @title **📦 Installation & Setup**

# Install required packages
!pip install praisonaiagents openai python-dotenv PyPDF2 pandas numpy -q

# Basic imports
import os
import json
import time
from pathlib import Path
from typing import Dict, List, Optional, Any, Tuple
from datetime import datetime
import getpass
import pandas as pd

print("📦 Dependencies installed!")
print("🎯 Building Job Hunting Agent System")
```

--------------------------------

### Use PraisonAI Tools

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/src/praisonai-agents/examples/plugin_template/README.md

Demonstrates how to initialize an agent with auto-discovered tools or by importing them directly.

```python
from praisonaiagents import Agent

# Use tools by name - they're auto-discovered!
agent = Agent(
    name="Assistant",
    tools=["example_greet", "example_math", "example_reverse"]
)

# Or import and use directly
from praisonai_example_plugin import GreetTool, MathTool, reverse_text

agent = Agent(
    name="Assistant", 
    tools=[GreetTool(), MathTool(), reverse_text]
)
```

--------------------------------

### Install PraisonAI Agents

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/python/agents/MULTI_PROVIDER_README.md

Standard installation command for the framework.

```bash
pip install praisonaiagents
```

--------------------------------

### Run ArXiv Tools Example

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/src/praisonai-ts/examples/tools/README.md

Command to execute the ArXiv tools example script. Downloaded PDFs are saved in the 'examples/downloads' directory.

```bash
npx ts-node examples/tools/arxiv-tools.ts
```

--------------------------------

### Install PraisonAIAgents and Pandas

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/Finance_Market_Job_Agents/Financial_Coaching_Agent.ipynb

Installs the necessary libraries for building the financial coaching agent. Run this command in your environment.

```bash
!pip install praisonaiagents pandas
```

--------------------------------

### Install Dependencies with Pip

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/Conversational_Chat_Agents/Qwen2_5_InstructionAgent.ipynb

Installs the necessary Python packages for using Hugging Face Transformers and accelerate. Use --quiet to suppress verbose output during installation.

```python
!pip install transformers --quiet
!pip install accelerate --quiet

```

--------------------------------

### Setup Agent and Task

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/Programming_Code_Analysis_Agents/Code_Analysis_Agent.ipynb

Configure the agent role and the specific analysis task with expected output schema.

```python
code_analyzer = Agent(
    role="Code Analysis Expert",
    goal="Provide comprehensive code evaluation and recommendations",
    backstory="""Expert code analyst specializing in architecture review,
    best practices, and technical debt assessment.""",
    verbose=True
)

code_analysis_task = Task(
    description="""Analyze code repository and provide structured evaluation:

    1. Overall Quality (0-100)
    2. Core Metrics Analysis:
       - Architecture and Design
       - Code Maintainability
       - Performance Optimization
       - Security Practices
       - Test Coverage
    3. Technical Assessment:
       - Technology Stack Review
       - Code Complexity Analysis
       - Best Practices Adherence
       - Risk Assessment
    4. Recommendations:
       - Key Improvements
       - Architecture Suggestions
       - Security Enhancements""",
    expected_output="Detailed code analysis report with metrics and recommendations",
    agent=code_analyzer,
    output_pydantic=CodeAnalysisReport
)
```

--------------------------------

### Install JavaScript SDK

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/README.md

Install the PraisonAI package using npm.

```bash
npm install praisonai
```

--------------------------------

### Install PraisonAI Dependencies

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/Productivity_Workflow_Agents/Work_Email_Agent.ipynb

Install the required praisonaiagents and openai packages.

```bash
!pip install praisonaiagents openai --quiet
```

--------------------------------

### Complete Workflow YAML Reference

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/src/praisonai-agents/README.md

A comprehensive example showing advanced configuration including LLM settings, agent parameters, and callback hooks.

```yaml
# workflow.yaml - Full feature reference
name: Complete Workflow
description: Demonstrates all workflow.yaml features
framework: praisonai  # praisonai, crewai, autogen
process: workflow     # sequential, hierarchical, workflow

workflow:
  planning: true
  planning_llm: gpt-4o
  reasoning: true
  verbose: true
  memory_config:
    provider: chroma
    persist: true

variables:
  topic: AI trends
  items: [ML, NLP, Vision]

agents:
  researcher:
    name: Researcher
    role: Research Analyst
    goal: Research topics thoroughly
    instructions: "Provide detailed research findings"
    backstory: "Expert researcher with 10 years experience"  # alias for instructions
    llm: gpt-4o-mini
    function_calling_llm: gpt-4o      # For tool calls
    max_rpm: 10                        # Rate limiting
    max_execution_time: 300            # Timeout in seconds
    reflect_llm: gpt-4o               # For self-reflection
    min_reflect: 1
    max_reflect: 3
    system_template: "You are a helpful assistant"
    tools:
      - tavily_search

  writer:
    name: Writer
    role: Content Writer
    goal: Write clear content
    instructions: "Write engaging content"

steps:
  - name: research_step
    agent: researcher
    action: "Research {{topic}}"
    expected_output: "Comprehensive research report"
    output_file: "output/research.md"
    create_directory: true
    
  - name: writing_step
    agent: writer
    action: "Write article based on research"
    context:                          # Task dependencies
      - research_step
    output_json:                      # Structured output
      type: object
      properties:
        title: { type: string }
        content: { type: string }

callbacks:
  on_workflow_start: log_start
  on_step_complete: log_step
  on_workflow_complete: log_complete
```

--------------------------------

### Run Domain Context Solution

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/python/usecases/README-domain-context.md

Example usage demonstrating how to set the target domain and initiate the hierarchical workflow using the PraisonAI framework.

```python
from domain_context_solution import main

# Set your target domain
domain = "your-domain.com"

# Run the hierarchical workflow
main()
```

--------------------------------

### Install dependencies

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/Conversational_Chat_Agents/LangChain_PraisonAI_Agent_Notebook.ipynb

Install the required packages for PraisonAI and LangChain integration.

```bash
!pip install praisonaiagents langchain-community wikipedia youtube-search
```

--------------------------------

### Install Dependencies

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/Research_Knowledge_QA_Agents/ArXiv_agent_notebook_fixed.ipynb

Install the required praisonaiagents and arxiv packages via pip.

```python
!pip install praisonaiagents arxiv
```

--------------------------------

### Install PraisonAI Plugin

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/src/praisonai-agents/examples/plugin_template/README.md

Commands to install the plugin in development mode or from PyPI.

```bash
# Install in development mode
pip install -e .

# Or install from PyPI (after publishing)
pip install praisonai-example-plugin
```

--------------------------------

### Initialize and Run PraisonAI

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/yaml/cli_operation_agents.ipynb

Set up the environment variables and execute the PraisonAI instance.

```python
import os
from praisonai import PraisonAI
from google.colab import userdata

# Create a PraisonAI instance with the agent_yaml content
praisonai = PraisonAI(agent_yaml=agent_yaml, tools=[CLIExecutorTool]) # Add InstagramSearchTool once scripted

# Add OPENAI_API_KEY Secrets to Google Colab on the Left Hand Side 🔑 or Enter Manually Below
os.environ["OPENAI_API_KEY"] = userdata.get('OPENAI_API_KEY') or "ENTER OPENAI_API_KEY HERE"
os.environ["OPENAI_MODEL_NAME"] = "gpt-5-nano"

# Run PraisonAI
result = praisonai.run()
```

--------------------------------

### Install PraisonAI Dependencies

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/yaml/job_hunt_agents.ipynb

Install the required libraries for PraisonAI and CrewAI integration.

```bash
%pip install langchain_community > /dev/null
%pip install praisonai[crewai] > /dev/null
%pip install requests > /dev/null
```

--------------------------------

### Install PraisonAI Dependencies

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/examples/cookbooks/yaml/job_profile_matching_agents.ipynb

Install the necessary libraries for the framework and CrewAI integration.

```python
# Install dependencies without output
%pip install langchain_community > /dev/null
%pip install praisonai[crewai] > /dev/null
```

--------------------------------

### Install with Memory Capabilities

Source: https://github.com/syntax-syndicate/praison-ai-agent-framework/blob/main/src/praisonai-agents/CLAUDE.md

Installs the framework with memory capabilities. Required for agents that need to store and retrieve information over time.

```bash
pip install -e .[memory]
```