Merge pull request #376 from MervinPraison/develop

Enhance train.py CLI configuration handling and bump version to 2.0.71

README.md

@@ -20,7 +20,7 @@
 
 </div>
 
-PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human–agent collaboration.
+PraisonAI is a production-ready Multi-AI Agents framework with self-reflection, designed to create AI Agents to automate and solve problems ranging from simple tasks to complex challenges. By integrating PraisonAI Agents, AutoGen, and CrewAI into a low-code solution, it streamlines the building and management of multi-agent LLM systems, emphasising simplicity, customisation, and effective human-agent collaboration.
 
 <div align="center">
   <a href="https://docs.praison.ai">
@@ -37,35 +37,24 @@ PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application
 - 🧠 Reasoning AI Agents
 - 👁️ Multi Modal AI Agents
 - 🤝 Multi Agent Collaboration
-- ⚡ AI Agent Workflow
-- 🔄 Use CrewAI or AutoGen Framework
+- 🎭 AI Agent Workflow
+- 📚 Add Custom Knowledge
+- 🧠 Agents with Short and Long Term Memory
+- 📄 Chat with PDF Agents
+- 💻 Code Interpreter Agents
+- 📚 RAG Agents
+- 🤔 Async & Parallel Processing
+- 🔄 Auto Agents
+- 🔢 Math Agents
+- 🎯 Structured Output Agents
+- 🔗 LangChain Integrated Agents
+- 📞 Callback Agents
+- 🤏 Mini AI Agents
+- 🛠️ 100+ Custom Tools
+- 📄 YAML Configuration
 - 💯 100+ LLM Support
-- 💻 Chat with ENTIRE Codebase
-- 🎨 Interactive UIs
-- 📄 YAML-based Configuration
-- 🛠️ Custom Tool Integration
-- 🔍 Internet Search Capability (using Crawl4AI and Tavily)
-- 🖼️ Vision Language Model (VLM) Support
-- 🎙️ Real-time Voice Interaction
 
-## Using No Code
-
-### Auto Mode:
-```bash
-pip install praisonai
-export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx
-praisonai --auto create a movie script about Robots in Mars
-```
-
-### Initialise Mode:
-```bash
-pip install praisonai
-export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx
-praisonai --init create a movie script about Robots in Mars
-praisonai
-```
-
-## Using Coding
+## Using Python Code
 
 Light weight package dedicated for coding:
 ```bash
@@ -76,58 +65,13 @@ pip install praisonaiagents
 export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx
 ```
 
+### 1. Single Agent
+
 Create app.py file and add the code below:
 ```python
-from praisonaiagents import Agent, Task, PraisonAIAgents
-
-# 1. Create agents
-researcher = Agent(
-    name="Researcher",
-    role="Senior Research Analyst",
-    goal="Uncover cutting-edge developments in AI and data science",
-    backstory="""You are an expert at a technology research group, 
-    skilled in identifying trends and analyzing complex data.""",
-    verbose=True,
-    llm="gpt-4o",
-    markdown=True
-)
-writer = Agent(
-    name="Writer",
-    role="Tech Content Strategist",
-    goal="Craft compelling content on tech advancements",
-    backstory="""You are a content strategist known for 
-    making complex tech topics interesting and easy to understand.""",
-    llm="gpt-4o",
-    markdown=True
-)
-
-# 2. Define Tasks
-task1 = Task(
-    name="research_task",
-    description="""Analyze 2024's AI advancements. 
-    Find major trends, new technologies, and their effects.""",
-    expected_output="""A detailed report on 2024 AI advancements""",
-    agent=researcher
-)
-
-task2 = Task(
-    name="writing_task",
-    description="""Create a blog post about major AI advancements using the insights you have.
-    Make it interesting, clear, and suited for tech enthusiasts. 
-    It should be at least 4 paragraphs long.""",
-    expected_output="A blog post of at least 4 paragraphs",
-    agent=writer,
-)
-
-agents = PraisonAIAgents(
-    agents=[researcher, writer],
-    tasks=[task1, task2],
-    verbose=False,
-    process="hierarchical",
-    manager_llm="gpt-4o"
-)
-
-result = agents.start()
+from praisonaiagents import Agent
+agent = Agent(instructions="Your are a helpful AI assistant")
+agent.start("Write a movie script about a robot in Mars")
 ```
 
 Run:
@@ -135,6 +79,396 @@ Run:
 python app.py
 ```
 
+### 2. Multi Agents
+
+Create app.py file and add the code below:
+```python
+from praisonaiagents import Agent, PraisonAIAgents
+
+research_agent = Agent(instructions="Research about AI")
+summarise_agent = Agent(instructions="Summarise research agent's findings")
+agents = PraisonAIAgents(agents=[research_agent, summarise_agent])
+agents.start()
+```
+
+Run:
+```bash
+python app.py
+```
+
+## Using No Code
+
+### Auto Mode:
+```bash
+pip install praisonai
+export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx
+praisonai --auto create a movie script about Robots in Mars
+```
+
+## Using JavaScript Code
+
+```bash
+npm install praisonai
+export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx
+```
+
+```javascript
+const { Agent } = require('praisonai');
+const agent = new Agent({ instructions: 'You are a helpful AI assistant' });
+agent.start('Write a movie script about a robot in Mars');
+```
+
+![PraisonAI CLI Demo](docs/demo/praisonai-cli-demo.gif)
+
+## AI Agents Flow
+
+```mermaid
+graph LR
+    %% Define the main flow
+    Start([▶ Start]) --> Agent1
+    Agent1 --> Process[⚙ Process]
+    Process --> Agent2
+    Agent2 --> Output([✓ Output])
+    Process -.-> Agent1
+    
+    %% Define subgraphs for agents and their tasks
+    subgraph Agent1[ ]
+        Task1[📋 Task]
+        AgentIcon1[🤖 AI Agent]
+        Tools1[🔧 Tools]
+        
+        Task1 --- AgentIcon1
+        AgentIcon1 --- Tools1
+    end
+    
+    subgraph Agent2[ ]
+        Task2[📋 Task]
+        AgentIcon2[🤖 AI Agent]
+        Tools2[🔧 Tools]
+        
+        Task2 --- AgentIcon2
+        AgentIcon2 --- Tools2
+    end
+
+    classDef input fill:#8B0000,stroke:#7C90A0,color:#fff
+    classDef process fill:#189AB4,stroke:#7C90A0,color:#fff
+    classDef tools fill:#2E8B57,stroke:#7C90A0,color:#fff
+    classDef transparent fill:none,stroke:none
+
+    class Start,Output,Task1,Task2 input
+    class Process,AgentIcon1,AgentIcon2 process
+    class Tools1,Tools2 tools
+    class Agent1,Agent2 transparent
+```
+
+## AI Agents with Tools
+
+Create AI agents that can use tools to interact with external systems and perform actions.
+
+```mermaid
+flowchart TB
+    subgraph Tools
+        direction TB
+        T3[Internet Search]
+        T1[Code Execution]
+        T2[Formatting]
+    end
+
+    Input[Input] ---> Agents
+    subgraph Agents
+        direction LR
+        A1[Agent 1]
+        A2[Agent 2]
+        A3[Agent 3]
+    end
+    Agents ---> Output[Output]
+
+    T3 --> A1
+    T1 --> A2
+    T2 --> A3
+
+    style Tools fill:#189AB4,color:#fff
+    style Agents fill:#8B0000,color:#fff
+    style Input fill:#8B0000,color:#fff
+    style Output fill:#8B0000,color:#fff
+```
+
+## AI Agents with Memory
+
+Create AI agents with memory capabilities for maintaining context and information across tasks.
+
+```mermaid
+flowchart TB
+    subgraph Memory
+        direction TB
+        STM[Short Term]
+        LTM[Long Term]
+    end
+
+    subgraph Store
+        direction TB
+        DB[(Vector DB)]
+    end
+
+    Input[Input] ---> Agents
+    subgraph Agents
+        direction LR
+        A1[Agent 1]
+        A2[Agent 2]
+        A3[Agent 3]
+    end
+    Agents ---> Output[Output]
+
+    Memory <--> Store
+    Store <--> A1
+    Store <--> A2
+    Store <--> A3
+
+    style Memory fill:#189AB4,color:#fff
+    style Store fill:#2E8B57,color:#fff
+    style Agents fill:#8B0000,color:#fff
+    style Input fill:#8B0000,color:#fff
+    style Output fill:#8B0000,color:#fff
+```
+
+## AI Agents with Different Processes
+
+### Sequential Process
+
+The simplest form of task execution where tasks are performed one after another.
+
+```mermaid
+graph LR
+    Input[Input] --> A1
+    subgraph Agents
+        direction LR
+        A1[Agent 1] --> A2[Agent 2] --> A3[Agent 3]
+    end
+    A3 --> Output[Output]
+
+    classDef input fill:#8B0000,stroke:#7C90A0,color:#fff
+    classDef process fill:#189AB4,stroke:#7C90A0,color:#fff
+    classDef transparent fill:none,stroke:none
+
+    class Input,Output input
+    class A1,A2,A3 process
+    class Agents transparent
+```
+
+### Hierarchical Process
+
+Uses a manager agent to coordinate task execution and agent assignments.
+
+```mermaid
+graph TB
+    Input[Input] --> Manager
+    
+    subgraph Agents
+        Manager[Manager Agent]
+        
+        subgraph Workers
+            direction LR
+            W1[Worker 1]
+            W2[Worker 2]
+            W3[Worker 3]
+        end
+        
+        Manager --> W1
+        Manager --> W2
+        Manager --> W3
+    end
+    
+    W1 --> Manager
+    W2 --> Manager
+    W3 --> Manager
+    Manager --> Output[Output]
+
+    classDef input fill:#8B0000,stroke:#7C90A0,color:#fff
+    classDef process fill:#189AB4,stroke:#7C90A0,color:#fff
+    classDef transparent fill:none,stroke:none
+
+    class Input,Output input
+    class Manager,W1,W2,W3 process
+    class Agents,Workers transparent
+```
+
+### Workflow Process
+
+Advanced process type supporting complex task relationships and conditional execution.
+
+```mermaid
+graph LR
+    Input[Input] --> Start
+    
+    subgraph Workflow
+        direction LR
+        Start[Start] --> C1{Condition}
+        C1 --> |Yes| A1[Agent 1]
+        C1 --> |No| A2[Agent 2]
+        A1 --> Join
+        A2 --> Join
+        Join --> A3[Agent 3]
+    end
+    
+    A3 --> Output[Output]
+
+    classDef input fill:#8B0000,stroke:#7C90A0,color:#fff
+    classDef process fill:#189AB4,stroke:#7C90A0,color:#fff
+    classDef decision fill:#2E8B57,stroke:#7C90A0,color:#fff
+    classDef transparent fill:none,stroke:none
+
+    class Input,Output input
+    class Start,A1,A2,A3,Join process
+    class C1 decision
+    class Workflow transparent
+```
+
+#### Agentic Routing Workflow
+
+Create AI agents that can dynamically route tasks to specialized LLM instances.
+
+```mermaid
+flowchart LR
+    In[In] --> Router[LLM Call Router]
+    Router --> LLM1[LLM Call 1]
+    Router --> LLM2[LLM Call 2]
+    Router --> LLM3[LLM Call 3]
+    LLM1 --> Out[Out]
+    LLM2 --> Out
+    LLM3 --> Out
+    
+    style In fill:#8B0000,color:#fff
+    style Router fill:#2E8B57,color:#fff
+    style LLM1 fill:#2E8B57,color:#fff
+    style LLM2 fill:#2E8B57,color:#fff
+    style LLM3 fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+
+#### Agentic Orchestrator Worker
+
+Create AI agents that orchestrate and distribute tasks among specialized workers.
+
+```mermaid
+flowchart LR
+    In[In] --> Router[LLM Call Router]
+    Router --> LLM1[LLM Call 1]
+    Router --> LLM2[LLM Call 2]
+    Router --> LLM3[LLM Call 3]
+    LLM1 --> Synthesizer[Synthesizer]
+    LLM2 --> Synthesizer
+    LLM3 --> Synthesizer
+    Synthesizer --> Out[Out]
+    
+    style In fill:#8B0000,color:#fff
+    style Router fill:#2E8B57,color:#fff
+    style LLM1 fill:#2E8B57,color:#fff
+    style LLM2 fill:#2E8B57,color:#fff
+    style LLM3 fill:#2E8B57,color:#fff
+    style Synthesizer fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+
+#### Agentic Autonomous Workflow
+
+Create AI agents that can autonomously monitor, act, and adapt based on environment feedback.
+
+```mermaid
+flowchart LR
+    Human[Human] <--> LLM[LLM Call]
+    LLM -->|ACTION| Environment[Environment]
+    Environment -->|FEEDBACK| LLM
+    LLM --> Stop[Stop]
+    
+    style Human fill:#8B0000,color:#fff
+    style LLM fill:#2E8B57,color:#fff
+    style Environment fill:#8B0000,color:#fff
+    style Stop fill:#333,color:#fff
+```
+
+#### Agentic Parallelization
+
+Create AI agents that can execute tasks in parallel for improved performance.
+
+```mermaid
+flowchart LR
+    In[In] --> LLM2[LLM Call 2]
+    In --> LLM1[LLM Call 1]
+    In --> LLM3[LLM Call 3]
+    LLM1 --> Aggregator[Aggregator]
+    LLM2 --> Aggregator
+    LLM3 --> Aggregator
+    Aggregator --> Out[Out]
+    
+    style In fill:#8B0000,color:#fff
+    style LLM1 fill:#2E8B57,color:#fff
+    style LLM2 fill:#2E8B57,color:#fff
+    style LLM3 fill:#2E8B57,color:#fff
+    style Aggregator fill:#fff,color:#000
+    style Out fill:#8B0000,color:#fff
+```
+
+#### Agentic Prompt Chaining
+
+Create AI agents with sequential prompt chaining for complex workflows.
+
+```mermaid
+flowchart LR
+    In[In] --> LLM1[LLM Call 1] --> Gate{Gate}
+    Gate -->|Pass| LLM2[LLM Call 2] -->|Output 2| LLM3[LLM Call 3] --> Out[Out]
+    Gate -->|Fail| Exit[Exit]
+    
+    style In fill:#8B0000,color:#fff
+    style LLM1 fill:#2E8B57,color:#fff
+    style LLM2 fill:#2E8B57,color:#fff
+    style LLM3 fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+    style Exit fill:#8B0000,color:#fff
+```
+
+#### Agentic Evaluator Optimizer
+
+Create AI agents that can generate and optimize solutions through iterative feedback.
+
+```mermaid
+flowchart LR
+    In[In] --> Generator[LLM Call Generator] 
+    Generator -->|SOLUTION| Evaluator[LLM Call Evaluator] -->|ACCEPTED| Out[Out]
+    Evaluator -->|REJECTED + FEEDBACK| Generator
+    
+    style In fill:#8B0000,color:#fff
+    style Generator fill:#2E8B57,color:#fff
+    style Evaluator fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+
+#### Repetitive Agents
+
+Create AI agents that can efficiently handle repetitive tasks through automated loops.
+
+```mermaid
+flowchart LR
+    In[Input] --> LoopAgent[("Looping Agent")]
+    LoopAgent --> Task[Task]
+    Task --> |Next iteration| LoopAgent
+    Task --> |Done| Out[Output]
+    
+    style In fill:#8B0000,color:#fff
+    style LoopAgent fill:#2E8B57,color:#fff,shape:circle
+    style Task fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+
+## Adding Models
+
+<div align="center">
+  <a href="https://docs.praison.ai/models">
+    <p align="center">
+      <img src="https://img.shields.io/badge/%F0%9F%93%9A_Models-Visit_docs.praison.ai-blue?style=for-the-badge&logo=bookstack&logoColor=white" alt="Models" />
+    </p>
+  </a>
+</div>
+
 ## Ollama Integration
 ```bash
 export OPENAI_BASE_URL=http://localhost:11434/v1
@@ -147,267 +481,16 @@ export OPENAI_API_KEY=xxxxxxxxxxx
 export OPENAI_BASE_URL=https://api.groq.com/openai/v1
 ```
 
-## Logging
-```bash
-export LOGLEVEL=info
-```
-
-Advanced logging:
-```bash
-export LOGLEVEL=debug
-```
-
-<div align="center">
-  <picture>
-    <source media="(prefers-color-scheme: dark)" srcset="docs/images/architecture-dark.png" />
-    <source media="(prefers-color-scheme: light)" srcset="docs/images/architecture-light.png" />
-    <img alt="PraisonAI Architecture" src="docs/images/architecture-light.png" />
-  </picture>
-</div>
-
-## Different User Interfaces:
-
-| Interface | Description | URL |
-|---|---|---|
-| **UI** | Multi Agents such as CrewAI or AutoGen | [https://docs.praison.ai/ui/ui](https://docs.praison.ai/ui/ui) |
-| **Chat** | Chat with 100+ LLMs, single AI Agent | [https://docs.praison.ai/ui/chat](https://docs.praison.ai/ui/chat) |
-| **Code** | Chat with entire Codebase, single AI Agent | [https://docs.praison.ai/ui/code](https://docs.praison.ai/ui/code) |
-| **Realtime** | Real-time voice interaction with AI | [https://docs.praison.ai/ui/realtime](https://docs.praison.ai/ui/realtime) |
-
-| Other Features | Description | Docs |
-|---|---|---|
-| **Train** | Fine-tune LLMs using your custom data | [https://docs.praison.ai/train](https://docs.praison.ai/train) |
-
-
-## Google Colab Multi Agents
-
-|               | Cookbook        | Open in Colab                                                                                                                                                                                                                                  |
-| ------------- | --------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| Basic         | PraisonAI       | <a target="_blank" href="https://colab.research.google.com/github/MervinPraison/PraisonAI/blob/main/cookbooks/praisonai-googlecolab.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab" /></a>       |
-| Include Tools | PraisonAI Tools | <a target="_blank" href="https://colab.research.google.com/github/MervinPraison/PraisonAI/blob/main/cookbooks/praisonai-tools-googlecolab.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab" /></a> |
-
-## Installation Options
-
-### Using pip
-```bash
-pip install praisonai
-```
-
-### Framework-specific Installation
-```bash
-# Install with CrewAI support
-pip install "praisonai[crewai]"
-
-# Install with AutoGen support
-pip install "praisonai[autogen]"
-
-# Install with both frameworks
-pip install "praisonai[crewai,autogen]"
-```
-
-### UI and Additional Features
-```bash
-# Install UI support
-pip install "praisonai[ui]"
-
-# Install Chat interface
-pip install "praisonai[chat]"
-
-# Install Code interface
-pip install "praisonai[code]"
-
-# Install Realtime voice interaction
-pip install "praisonai[realtime]"
-
-# Install Call feature
-pip install "praisonai[call]"
-```
-
-## Quick Start
-
-```bash
-# Set your OpenAI API key
-export OPENAI_API_KEY="Enter your API key"
-
-# Initialize with CrewAI (default)
-praisonai --init "create a movie script about dog in moon"
-
-# Or initialize with AutoGen
-praisonai --framework autogen --init "create a movie script about dog in moon"
-
-# Run the agents
-praisonai
-```
-
-## Full Automatic Mode
-
-```bash
-# With CrewAI (default)
-praisonai --auto "create a movie script about Dog in Moon"
-
-# With AutoGen
-praisonai --framework autogen --auto "create a movie script about Dog in Moon"
-```
-
-## Framework-specific Features
-
-### CrewAI
-When installing with `pip install "praisonai[crewai]"`, you get:
-- CrewAI framework support
-- PraisonAI tools integration
-- Task delegation capabilities
-- Sequential and parallel task execution
-
-### AutoGen
-When installing with `pip install "praisonai[autogen]"`, you get:
-- AutoGen framework support
-- PraisonAI tools integration
-- Multi-agent conversation capabilities
-- Code execution environment
-
-
-
-## TL;DR Multi Agents
-
-```bash
-pip install praisonai
-export OPENAI_API_KEY="Enter your API key"
-praisonai --init create a movie script about dog in moon
-praisonai
-```
-
-## Table of Contents
-
-- [Installation](#installation)
-- [Initialise](#initialise)
-- [Run](#run)
-- [Full Automatic Mode](#full-automatic-mode)
-- [User Interface](#user-interface)
-- [Praison AI Chat](#praison-ai-chat)
-- [Create Custom Tools](#create-custom-tools)
-- [Agents Playbook](#agents-playbook)
-- [Include praisonai package in your project](#include-praisonai-package-in-your-project)
-- [Commands to Install Dev Dependencies](#commands-to-install-dependencies)
-- [Other Models](#other-models)
-- [Contributing](#contributing)
-- [Star History](#star-history)
-
-## Installation Multi Agents
-
-```bash
-pip install praisonai
-```
-
-## Initialise
-
-```bash
-export OPENAI_API_KEY="Enter your API key"
-```
-
-Generate your OPENAI API KEY from here: https://platform.openai.com/api-keys
-
-Note: You can use other providers such as Ollama, Mistral ... etc. Details are provided at the bottom.
-
-```bash
-praisonai --init create a movie script about dog in moon
-```
-
-This will automatically create agents.yaml file in the current directory.
-
-### To initialise with a specific agent framework (Optional):
-
-```bash
-praisonai --framework autogen --init create movie script about cat in mars
-```
-
-## Run
-
-```bash
-praisonai
-```
-
-or
-
-```bash
-python -m praisonai
-```
-
-### Specify the agent framework (Optional):
-
-```bash
-praisonai --framework autogen
-```
-
-### Full Automatic Mode
-
-```bash
-praisonai --auto create a movie script about Dog in Moon
-```
-
-## User Interface
-
-## PraisonAI User Interfaces:
-
-| Interface | Description                                | URL                                                                   |
-| --------- | ------------------------------------------ | --------------------------------------------------------------------- |
-| **UI**    | Multi Agents such as CrewAI or AutoGen     | [https://docs.praisonai.com/ui/ui](https://docs.praison.ai/ui/ui)     |
-| **Chat**  | Chat with 100+ LLMs, single AI Agent       | [https://docs.praisonai.com/ui/chat](https://docs.praison.ai/ui/chat) |
-| **Code**  | Chat with entire Codebase, single AI Agent | [https://docs.praisonai.com/ui/code](https://docs.praison.ai/ui/code) |
-
-```bash
-pip install -U "praisonai[ui]"
-export OPENAI_API_KEY="Enter your API key"
-chainlit create-secret
-export CHAINLIT_AUTH_SECRET=xxxxxxxx
-praisonai ui
-```
-
-or
-
-```
-python -m praisonai ui
-```
-
-## Praison AI Chat
-
-- https://docs.praison.ai/chat/
-
-```bash
-pip install "praisonai[chat]"
-export OPENAI_API_KEY="Enter your API key"
-praisonai chat
-```
-
-### Internet Search
-
-Praison AI Chat and Praison AI Code now includes internet search capabilities using Crawl4AI and Tavily, allowing you to retrieve up-to-date information during your conversations.
-
-### Vision Language Model Support
-
-You can now upload images and ask questions based on them using Vision Language Models. This feature enables visual understanding and analysis within your chat sessions.
-
-## Praison AI Code
-
-```bash
-pip install "praisonai[code]"
-export OPENAI_API_KEY="Enter your API key"
-praisonai code
-```
-
-### Internet Search
-
-Praison AI Code also includes internet search functionality, enabling you to find relevant code snippets and programming information online.
-
-## Create Custom Tools
-
-- https://docs.praison.ai/tools/custom/
+## No Code Options
 
 ## Agents Playbook
 
 ### Simple Playbook Example
 
+Create `agents.yaml` file and add the code below:
+
 ```yaml
-framework: crewai
+framework: praisonai
 topic: Artificial Intelligence
 roles:
   screenwriter:
@@ -420,62 +503,25 @@ roles:
         expected_output: "Complete script ready for production."
 ```
 
+*To run the playbook:*
+```bash
+praisonai agents.yaml
+```
+
 ## Use 100+ Models
 
 - https://docs.praison.ai/models/
+<div align="center">
+  <a href="https://docs.praison.ai">
+    <p align="center">
+      <img src="https://img.shields.io/badge/📚_Documentation-Visit_docs.praison.ai-blue?style=for-the-badge&logo=bookstack&logoColor=white" alt="Documentation" />
+    </p>
+  </a>
+</div>
 
-## Include praisonai package in your project
+## Development:
 
-- https://docs.praison.ai/developers/wrapper
-- https://docs.praison.ai/developers/wrapper-tools/
-
-## Option 1: Using RAW YAML
-
-```python
-from praisonai import PraisonAI
-
-# Example agent_yaml content
-agent_yaml = """
-framework: "crewai"
-topic: "Space Exploration"
-
-roles:
-  astronomer:
-    role: "Space Researcher"
-    goal: "Discover new insights about {topic}"
-    backstory: "You are a curious and dedicated astronomer with a passion for unraveling the mysteries of the cosmos."
-    tasks:
-      investigate_exoplanets:
-        description: "Research and compile information about exoplanets discovered in the last decade."
-        expected_output: "A summarized report on exoplanet discoveries, including their size, potential habitability, and distance from Earth."
-"""
-
-# Create a PraisonAI instance with the agent_yaml content
-praisonai = PraisonAI(agent_yaml=agent_yaml)
-
-# Run PraisonAI
-result = praisonai.run()
-
-# Print the result
-print(result)
-```
-
-## Option 2: Using separate agents.yaml file
-
-Note: Please create agents.yaml file before hand.
-
-```python
-from praisonai import PraisonAI
-
-def basic(): # Basic Mode
-    praisonai = PraisonAI(agent_file="agents.yaml")
-    praisonai.run()
-
-if __name__ == "__main__":
-    basic()
-```
-
-## Commands to Install Dependencies:
+Below is used for development only.
 
 ### Using uv
 ```bash
@@ -500,18 +546,34 @@ uv pip install -r pyproject.toml --extra "crewai,autogen"
 - Submit a pull request via GitHub's web interface.
 - Await feedback from project maintainers.
 
+## Other Features
+
+- 🔄 Use CrewAI or AutoGen Framework
+- 💻 Chat with ENTIRE Codebase
+- 🎨 Interactive UIs
+- 📄 YAML-based Configuration
+- 🛠️ Custom Tool Integration
+- 🔍 Internet Search Capability (using Crawl4AI and Tavily)
+- 🖼️ Vision Language Model (VLM) Support
+- 🎙️ Real-time Voice Interaction
+
 ## Star History
 
 [![Star History Chart](https://api.star-history.com/svg?repos=MervinPraison/PraisonAI&type=Date)](https://docs.praison.ai)
 
-## License
-
-Praison AI is an open-sourced software licensed under the **[MIT license](https://opensource.org/licenses/MIT)**.
-
 ## Video Tutorials
 
 | Topic | Video |
 |-------|--------|
+| AI Agents with Self Reflection | [![Self Reflection](https://img.youtube.com/vi/vLXobEN2Vc8/0.jpg)](https://www.youtube.com/watch?v=vLXobEN2Vc8) |
+| Reasoning Data Generating Agent | [![Reasoning Data](https://img.youtube.com/vi/fUT332Y2zA8/0.jpg)](https://www.youtube.com/watch?v=fUT332Y2zA8) |
+| AI Agents with Reasoning | [![Reasoning](https://img.youtube.com/vi/KNDVWGN3TpM/0.jpg)](https://www.youtube.com/watch?v=KNDVWGN3TpM) |
+| Multimodal AI Agents | [![Multimodal](https://img.youtube.com/vi/hjAWmUT1qqY/0.jpg)](https://www.youtube.com/watch?v=hjAWmUT1qqY) |
+| AI Agents Workflow | [![Workflow](https://img.youtube.com/vi/yWTH44QPl2A/0.jpg)](https://www.youtube.com/watch?v=yWTH44QPl2A) |
+| Async AI Agents | [![Async](https://img.youtube.com/vi/VhVQfgo00LE/0.jpg)](https://www.youtube.com/watch?v=VhVQfgo00LE) |
+| Mini AI Agents | [![Mini](https://img.youtube.com/vi/OkvYp5aAGSg/0.jpg)](https://www.youtube.com/watch?v=OkvYp5aAGSg) |
+| AI Agents with Memory | [![Memory](https://img.youtube.com/vi/1hVfVxvPnnQ/0.jpg)](https://www.youtube.com/watch?v=1hVfVxvPnnQ) |
+| Repetitive Agents | [![Repetitive](https://img.youtube.com/vi/dAYGxsjDOPg/0.jpg)](https://www.youtube.com/watch?v=dAYGxsjDOPg) |
 | Introduction | [![Introduction](https://img.youtube.com/vi/Fn1lQjC0GO0/0.jpg)](https://www.youtube.com/watch?v=Fn1lQjC0GO0) |
 | Tools Overview | [![Tools Overview](https://img.youtube.com/vi/XaQRgRpV7jo/0.jpg)](https://www.youtube.com/watch?v=XaQRgRpV7jo) |
 | Custom Tools | [![Custom Tools](https://img.youtube.com/vi/JSU2Rndh06c/0.jpg)](https://www.youtube.com/watch?v=JSU2Rndh06c) |
@@ -524,59 +586,5 @@ Praison AI is an open-sourced software licensed under the **[MIT license](https:
 | Training | [![Training](https://img.youtube.com/vi/aLawE8kwCrI/0.jpg)](https://www.youtube.com/watch?v=aLawE8kwCrI) |
 | Realtime Voice Interface | [![Realtime](https://img.youtube.com/vi/frRHfevTCSw/0.jpg)](https://www.youtube.com/watch?v=frRHfevTCSw) |
 | Call Interface | [![Call](https://img.youtube.com/vi/m1cwrUG2iAk/0.jpg)](https://www.youtube.com/watch?v=m1cwrUG2iAk) |
+| Reasoning Extract Agents | [![Reasoning Extract](https://img.youtube.com/vi/2PPamsADjJA/0.jpg)](https://www.youtube.com/watch?v=2PPamsADjJA) |
 
-## License
-
-Praison AI is an open-sourced software licensed under the **[MIT license](https://opensource.org/licenses/MIT)**.
-
-## Local Docker Development with Live Reload
-
-To facilitate local development with live reload, you can use Docker. Follow the steps below:
-
-1. **Create a `Dockerfile.dev`**:
-    ```dockerfile
-    FROM python:3.11-slim
-
-    WORKDIR /app
-
-    COPY . .
-
-    RUN pip install flask praisonai==2.0.18 watchdog
-
-    EXPOSE 5555
-
-    ENV FLASK_ENV=development
-
-    CMD ["flask", "run", "--host=0.0.0.0"]
-    ```
-
-2. **Create a `docker-compose.yml`**:
-    ```yaml
-    version: '3.8'
-
-    services:
-      app:
-        build:
-          context: .
-          dockerfile: Dockerfile.dev
-        volumes:
-          - .:/app
-        ports:
-          - "5555:5555"
-        environment:
-          FLASK_ENV: development
-        command: flask run --host=0.0.0.0
-
-      watch:
-        image: alpine:latest
-        volumes:
-          - .:/app
-        command: sh -c "apk add --no-cache inotify-tools && while inotifywait -r -e modify,create,delete /app; do kill -HUP 1; done"
-    ```
-
-3. **Run Docker Compose**:
-    ```bash
-    docker-compose up
-    ```
-
-This setup will allow you to develop locally with live reload, making it easier to test and iterate on your code.

agents/.cursorrules

@@ -1,8 +0,0 @@
-1. Make minimal code changes as possible
-2. if you are creating function, make sure to name it in more easy, user friendly , optimised manner. 
-3. Never copy the exact code if presented with a code from other location or file or codebase, just make it optimised
-4. Always Follow the principle LESS IS MORE
-5. Make it minimal change as possible
-6. Firstly try not to make any modification to the existing code as possible
-7. Only modify the existing code if its highly required, without that if it cant be done, then add new code section. 
-8. If you are adding new code, make sure to add it in a way that it can be easily integrated with the existing codebase. 

agents/praisonaiagents/agent/__init__.py

@@ -1,4 +0,0 @@
-"""Agent module for AI agents"""
-from .agent import Agent
-
-__all__ = ['Agent'] 

agents/praisonaiagents/agent/agent.py

@@ -1,834 +0,0 @@
-import os
-import time
-import json
-import logging
-import asyncio
-from typing import List, Optional, Any, Dict, Union, Literal, TYPE_CHECKING
-from rich.console import Console
-from rich.live import Live
-from openai import AsyncOpenAI
-from ..main import (
-    display_error,
-    display_tool_call,
-    display_instruction,
-    display_interaction,
-    display_generating,
-    display_self_reflection,
-    ReflectionOutput,
-    client,
-    error_logs,
-    adisplay_instruction
-)
-import inspect
-import uuid
-
-if TYPE_CHECKING:
-    from ..task.task import Task
-
-class Agent:
-    def _generate_tool_definition(self, function_name):
-        """
-        Generate a tool definition from a function name by inspecting the function.
-        """
-        logging.debug(f"Attempting to generate tool definition for: {function_name}")
-        
-        # First try to get the tool definition if it exists
-        tool_def_name = f"{function_name}_definition"
-        tool_def = globals().get(tool_def_name)
-        logging.debug(f"Looking for {tool_def_name} in globals: {tool_def is not None}")
-        
-        if not tool_def:
-            import __main__
-            tool_def = getattr(__main__, tool_def_name, None)
-            logging.debug(f"Looking for {tool_def_name} in __main__: {tool_def is not None}")
-        
-        if tool_def:
-            logging.debug(f"Found tool definition: {tool_def}")
-            return tool_def
-
-        # Try to find the function in the agent's tools list first
-        func = None
-        for tool in self.tools:
-            if callable(tool) and getattr(tool, '__name__', '') == function_name:
-                func = tool
-                break
-        
-        logging.debug(f"Looking for {function_name} in agent tools: {func is not None}")
-        
-        # If not found in tools, try globals and main
-        if not func:
-            func = globals().get(function_name)
-            logging.debug(f"Looking for {function_name} in globals: {func is not None}")
-            
-            if not func:
-                import __main__
-                func = getattr(__main__, function_name, None)
-                logging.debug(f"Looking for {function_name} in __main__: {func is not None}")
-
-        if not func or not callable(func):
-            logging.debug(f"Function {function_name} not found or not callable")
-            return None
-
-        import inspect
-        # Langchain tools
-        if inspect.isclass(func) and hasattr(func, 'run') and not hasattr(func, '_run'):
-            original_func = func
-            func = func.run
-            function_name = original_func.__name__
-        # CrewAI tools
-        elif inspect.isclass(func) and hasattr(func, '_run'):
-            original_func = func
-            func = func._run
-            function_name = original_func.__name__
-
-        sig = inspect.signature(func)
-        logging.debug(f"Function signature: {sig}")
-        
-        # Skip self, *args, **kwargs, so they don't get passed in arguments
-        parameters_list = []
-        for name, param in sig.parameters.items():
-            if name == "self":
-                continue
-            if param.kind in (inspect.Parameter.VAR_POSITIONAL, inspect.Parameter.VAR_KEYWORD):
-                continue
-            parameters_list.append((name, param))
-
-        parameters = {
-            "type": "object",
-            "properties": {},
-            "required": []
-        }
-        
-        # Parse docstring for parameter descriptions
-        docstring = inspect.getdoc(func)
-        logging.debug(f"Function docstring: {docstring}")
-        
-        param_descriptions = {}
-        if docstring:
-            import re
-            param_section = re.split(r'\s*Args:\s*', docstring)
-            logging.debug(f"Param section split: {param_section}")
-            if len(param_section) > 1:
-                param_lines = param_section[1].split('\n')
-                for line in param_lines:
-                    line = line.strip()
-                    if line and ':' in line:
-                        param_name, param_desc = line.split(':', 1)
-                        param_descriptions[param_name.strip()] = param_desc.strip()
-        
-        logging.debug(f"Parameter descriptions: {param_descriptions}")
-
-        for name, param in parameters_list:
-            param_type = "string"  # Default type
-            if param.annotation != inspect.Parameter.empty:
-                if param.annotation == int:
-                    param_type = "integer"
-                elif param.annotation == float:
-                    param_type = "number"
-                elif param.annotation == bool:
-                    param_type = "boolean"
-                elif param.annotation == list:
-                    param_type = "array"
-                elif param.annotation == dict:
-                    param_type = "object"
-            
-            param_info = {"type": param_type}
-            if name in param_descriptions:
-                param_info["description"] = param_descriptions[name]
-            
-            parameters["properties"][name] = param_info
-            if param.default == inspect.Parameter.empty:
-                parameters["required"].append(name)
-        
-        logging.debug(f"Generated parameters: {parameters}")
-
-        # Extract description from docstring
-        description = docstring.split('\n')[0] if docstring else f"Function {function_name}"
-        
-        tool_def = {
-            "type": "function",
-            "function": {
-                "name": function_name,
-                "description": description,
-                "parameters": parameters
-            }
-        }
-        logging.debug(f"Generated tool definition: {tool_def}")
-        return tool_def
-
-    def __init__(
-        self,
-        name: Optional[str] = None,
-        role: Optional[str] = None,
-        goal: Optional[str] = None,
-        backstory: Optional[str] = None,
-        instructions: Optional[str] = None,
-        llm: Optional[Union[str, Any]] = None,
-        tools: Optional[List[Any]] = None,
-        function_calling_llm: Optional[Any] = None,
-        max_iter: int = 20,
-        max_rpm: Optional[int] = None,
-        max_execution_time: Optional[int] = None,
-        memory: Optional[Any] = None,
-        verbose: bool = True,
-        allow_delegation: bool = False,
-        step_callback: Optional[Any] = None,
-        cache: bool = True,
-        system_template: Optional[str] = None,
-        prompt_template: Optional[str] = None,
-        response_template: Optional[str] = None,
-        allow_code_execution: Optional[bool] = False,
-        max_retry_limit: int = 2,
-        respect_context_window: bool = True,
-        code_execution_mode: Literal["safe", "unsafe"] = "safe",
-        embedder_config: Optional[Dict[str, Any]] = None,
-        knowledge: Optional[List[str]] = None,
-        knowledge_config: Optional[Dict[str, Any]] = None,
-        use_system_prompt: Optional[bool] = True,
-        markdown: bool = True,
-        self_reflect: bool = False,
-        max_reflect: int = 3,
-        min_reflect: int = 1,
-        reflect_llm: Optional[str] = None,
-        user_id: Optional[str] = None
-    ):
-        # Handle backward compatibility for required fields
-        if all(x is None for x in [name, role, goal, backstory, instructions]):
-            raise ValueError("At least one of name, role, goal, backstory, or instructions must be provided")
-
-        # If instructions are provided, use them to set role, goal, and backstory
-        if instructions:
-            self.name = name or "Agent"
-            self.role = role or "Assistant"
-            self.goal = goal or instructions
-            self.backstory = backstory or instructions
-            # Set self_reflect to False by default for instruction-based agents
-            self.self_reflect = False if self_reflect is None else self_reflect
-        else:
-            # Use provided values or defaults
-            self.name = name or "Agent"
-            self.role = role or "Assistant"
-            self.goal = goal or "Help the user with their tasks"
-            self.backstory = backstory or "I am an AI assistant"
-            # Default to True for traditional agents if not specified
-            self.self_reflect = True if self_reflect is None else self_reflect
-        
-        self.instructions = instructions
-        # Check for model name in environment variable if not provided
-        self.llm = llm or os.getenv('OPENAI_MODEL_NAME', 'gpt-4o')
-        self.tools = tools if tools else []  # Store original tools
-        self.function_calling_llm = function_calling_llm
-        self.max_iter = max_iter
-        self.max_rpm = max_rpm
-        self.max_execution_time = max_execution_time
-        self.memory = memory
-        self.verbose = verbose
-        self.allow_delegation = allow_delegation
-        self.step_callback = step_callback
-        self.cache = cache
-        self.system_template = system_template
-        self.prompt_template = prompt_template
-        self.response_template = response_template
-        self.allow_code_execution = allow_code_execution
-        self.max_retry_limit = max_retry_limit
-        self.respect_context_window = respect_context_window
-        self.code_execution_mode = code_execution_mode
-        self.embedder_config = embedder_config
-        self.knowledge = knowledge
-        self.use_system_prompt = use_system_prompt
-        self.chat_history = []
-        self.markdown = markdown
-        self.max_reflect = max_reflect
-        self.min_reflect = min_reflect
-        # Use the same model selection logic for reflect_llm
-        self.reflect_llm = reflect_llm or os.getenv('OPENAI_MODEL_NAME', 'gpt-4o')
-        self.console = Console()  # Create a single console instance for the agent
-        
-        # Initialize system prompt
-        self.system_prompt = f"""{self.backstory}\n
-Your Role: {self.role}\n
-Your Goal: {self.goal}
-        """
-
-        # Generate unique IDs
-        self.agent_id = str(uuid.uuid4())
-
-        # Store user_id
-        self.user_id = user_id
-
-        # Check if knowledge parameter has any values
-        if not knowledge:
-            self.knowledge = None
-        else:
-            # Initialize Knowledge with provided or default config
-            from praisonaiagents.knowledge import Knowledge
-            self.knowledge = Knowledge(knowledge_config or None)
-            
-            # Handle knowledge
-            if knowledge:
-                for source in knowledge:
-                    self._process_knowledge(source)
-
-    def _process_knowledge(self, knowledge_item):
-        """Process and store knowledge from a file path, URL, or string."""
-        try:
-            if os.path.exists(knowledge_item):
-                # It's a file path
-                self.knowledge.add(knowledge_item, user_id=self.user_id, agent_id=self.agent_id)
-            elif knowledge_item.startswith("http://") or knowledge_item.startswith("https://"):
-                # It's a URL
-                pass
-            else:
-                # It's a string content
-                self.knowledge.store(knowledge_item, user_id=self.user_id, agent_id=self.agent_id)
-        except Exception as e:
-            logging.error(f"Error processing knowledge item: {knowledge_item}, error: {e}")
-
-    def generate_task(self) -> 'Task':
-        """Generate a Task object from the agent's instructions"""
-        from ..task.task import Task
-        
-        description = self.instructions if self.instructions else f"Execute task as {self.role} with goal: {self.goal}"
-        expected_output = "Complete the assigned task successfully"
-        
-        return Task(
-            name=self.name,
-            description=description,
-            expected_output=expected_output,
-            agent=self,
-            tools=self.tools
-        )
-
-    def execute_tool(self, function_name, arguments):
-        """
-        Execute a tool dynamically based on the function name and arguments.
-        """
-        logging.debug(f"{self.name} executing tool {function_name} with arguments: {arguments}")
-
-        # Try to find the function in the agent's tools list first
-        func = None
-        for tool in self.tools:
-            if (callable(tool) and getattr(tool, '__name__', '') == function_name) or \
-               (inspect.isclass(tool) and tool.__name__ == function_name):
-                func = tool
-                break
-        
-        if func is None:
-            # If not found in tools, try globals and main
-            func = globals().get(function_name)
-            if not func:
-                import __main__
-                func = getattr(__main__, function_name, None)
-
-        if func:
-            try:
-                # Langchain: If it's a class with run but not _run, instantiate and call run
-                if inspect.isclass(func) and hasattr(func, 'run') and not hasattr(func, '_run'):
-                    instance = func()
-                    run_params = {k: v for k, v in arguments.items() 
-                                  if k in inspect.signature(instance.run).parameters 
-                                  and k != 'self'}
-                    return instance.run(**run_params)
-
-                # CrewAI: If it's a class with an _run method, instantiate and call _run
-                elif inspect.isclass(func) and hasattr(func, '_run'):
-                    instance = func()
-                    run_params = {k: v for k, v in arguments.items() 
-                                  if k in inspect.signature(instance._run).parameters 
-                                  and k != 'self'}
-                    return instance._run(**run_params)
-
-                # Otherwise treat as regular function
-                elif callable(func):
-                    return func(**arguments)
-            except Exception as e:
-                error_msg = str(e)
-                logging.error(f"Error executing tool {function_name}: {error_msg}")
-                return {"error": error_msg}
-        
-        error_msg = f"Tool '{function_name}' is not callable"
-        logging.error(error_msg)
-        return {"error": error_msg}
-
-    def clear_history(self):
-        self.chat_history = []
-
-    def __str__(self):
-        return f"Agent(name='{self.name}', role='{self.role}', goal='{self.goal}')"
-
-    def _chat_completion(self, messages, temperature=0.2, tools=None, stream=True):
-        start_time = time.time()
-        logging.debug(f"{self.name} sending messages to LLM: {messages}")
-
-        formatted_tools = []
-        if tools is None:
-            tools = self.tools
-        if tools:
-            for tool in tools:
-                if isinstance(tool, str):
-                    # Generate tool definition for string tool names
-                    tool_def = self._generate_tool_definition(tool)
-                    if tool_def:
-                        formatted_tools.append(tool_def)
-                    else:
-                        logging.warning(f"Could not generate definition for tool: {tool}")
-                elif isinstance(tool, dict):
-                    formatted_tools.append(tool)
-                elif hasattr(tool, "to_openai_tool"):
-                    formatted_tools.append(tool.to_openai_tool())
-                elif callable(tool):
-                    formatted_tools.append(self._generate_tool_definition(tool.__name__))
-                else:
-                    logging.warning(f"Tool {tool} not recognized")
-
-        try:
-            initial_response = client.chat.completions.create(
-                model=self.llm,
-                messages=messages,
-                temperature=temperature,
-                tools=formatted_tools if formatted_tools else None,
-                stream=False
-            )
-
-            tool_calls = getattr(initial_response.choices[0].message, 'tool_calls', None)
-
-            if tool_calls:
-                messages.append({
-                    "role": "assistant",
-                    "content": initial_response.choices[0].message.content,
-                    "tool_calls": tool_calls
-                })
-
-                for tool_call in tool_calls:
-                    function_name = tool_call.function.name
-                    arguments = json.loads(tool_call.function.arguments)
-
-                    if self.verbose:
-                        display_tool_call(f"Agent {self.name} is calling function '{function_name}' with arguments: {arguments}")
-
-                    tool_result = self.execute_tool(function_name, arguments)
-                    results_str = json.dumps(tool_result) if tool_result else "Function returned an empty output"
-
-                    if self.verbose:
-                        display_tool_call(f"Function '{function_name}' returned: {results_str}")
-
-                    messages.append({
-                        "role": "tool",
-                        "tool_call_id": tool_call.id,
-                        "content": results_str
-                    })
-
-            if stream:
-                response_stream = client.chat.completions.create(
-                    model=self.llm,
-                    messages=messages,
-                    temperature=temperature,
-                    stream=True
-                )
-                full_response_text = ""
-                
-                # Create Live display with proper configuration
-                with Live(
-                    display_generating("", start_time),
-                    console=self.console,
-                    refresh_per_second=4,
-                    transient=True,  # Changed to False to preserve output
-                    vertical_overflow="ellipsis",
-                    auto_refresh=True
-                ) as live:
-                    for chunk in response_stream:
-                        if chunk.choices[0].delta.content:
-                            full_response_text += chunk.choices[0].delta.content
-                            live.update(display_generating(full_response_text, start_time))
-                
-                # Clear the last generating display with a blank line
-                self.console.print()
-                
-                final_response = client.chat.completions.create(
-                    model=self.llm,
-                    messages=messages,
-                    temperature=temperature,
-                    stream=False
-                )
-                return final_response
-            else:
-                if tool_calls:
-                    final_response = client.chat.completions.create(
-                        model=self.llm,
-                        messages=messages,
-                        temperature=temperature,
-                        stream=False
-                    )
-                    return final_response
-                else:
-                    return initial_response
-
-        except Exception as e:
-            display_error(f"Error in chat completion: {e}")
-            return None
-
-    def chat(self, prompt, temperature=0.2, tools=None, output_json=None, output_pydantic=None):
-        # Search for existing knowledge if any knowledge is provided
-        if self.knowledge:
-            search_results = self.knowledge.search(prompt, agent_id=self.agent_id)
-            if search_results:
-                # Check if search_results is a list of dictionaries or strings
-                if isinstance(search_results, dict) and 'results' in search_results:
-                    # Extract memory content from the results
-                    knowledge_content = "\n".join([result['memory'] for result in search_results['results']])
-                else:
-                    # If search_results is a list of strings, join them directly
-                    knowledge_content = "\n".join(search_results)
-                
-                # Append found knowledge to the prompt
-                prompt = f"{prompt}\n\nKnowledge: {knowledge_content}"
-
-        if self.use_system_prompt:
-            system_prompt = f"""{self.backstory}\n
-Your Role: {self.role}\n
-Your Goal: {self.goal}
-            """
-            if output_json:
-                system_prompt += f"\nReturn ONLY a JSON object that matches this Pydantic model: {json.dumps(output_json.model_json_schema())}"
-            elif output_pydantic:
-                system_prompt += f"\nReturn ONLY a JSON object that matches this Pydantic model: {json.dumps(output_pydantic.model_json_schema())}"
-        else:
-            system_prompt = None
-
-        messages = []
-        if system_prompt:
-            messages.append({"role": "system", "content": system_prompt})
-        messages.extend(self.chat_history)
-
-        # Modify prompt if output_json or output_pydantic is specified
-        original_prompt = prompt
-        if output_json or output_pydantic:
-            if isinstance(prompt, str):
-                prompt += "\nReturn ONLY a valid JSON object. No other text or explanation."
-            elif isinstance(prompt, list):
-                # For multimodal prompts, append to the text content
-                for item in prompt:
-                    if item["type"] == "text":
-                        item["text"] += "\nReturn ONLY a valid JSON object. No other text or explanation."
-                        break
-
-        if isinstance(prompt, list):
-            # If we receive a multimodal prompt list, place it directly in the user message
-            messages.append({"role": "user", "content": prompt})
-        else:
-            messages.append({"role": "user", "content": prompt})
-
-        final_response_text = None
-        reflection_count = 0
-        start_time = time.time()
-
-        while True:
-            try:
-                if self.verbose:
-                    # Handle both string and list prompts for instruction display
-                    display_text = prompt
-                    if isinstance(prompt, list):
-                        # Extract text content from multimodal prompt
-                        display_text = next((item["text"] for item in prompt if item["type"] == "text"), "")
-                    
-                    if display_text and str(display_text).strip():
-                        # Pass agent information to display_instruction
-                        agent_tools = [t.__name__ if hasattr(t, '__name__') else str(t) for t in self.tools]
-                        display_instruction(
-                            f"Agent {self.name} is processing prompt: {display_text}", 
-                            console=self.console,
-                            agent_name=self.name,
-                            agent_role=self.role,
-                            agent_tools=agent_tools
-                        )
-
-                response = self._chat_completion(messages, temperature=temperature, tools=tools if tools else None)
-                if not response:
-                    return None
-
-                tool_calls = getattr(response.choices[0].message, 'tool_calls', None)
-                response_text = response.choices[0].message.content.strip()
-
-                if tool_calls:
-                    messages.append({
-                        "role": "assistant",
-                        "content": response_text,
-                        "tool_calls": tool_calls
-                    })
-                    
-                    for tool_call in tool_calls:
-                        function_name = tool_call.function.name
-                        arguments = json.loads(tool_call.function.arguments)
-
-                        if self.verbose:
-                            display_tool_call(f"Agent {self.name} is calling function '{function_name}' with arguments: {arguments}", console=self.console)
-
-                        tool_result = self.execute_tool(function_name, arguments)
-
-                        if tool_result:
-                            if self.verbose:
-                                display_tool_call(f"Function '{function_name}' returned: {tool_result}", console=self.console)
-                            messages.append({
-                                "role": "tool",
-                                "tool_call_id": tool_call.id,
-                                "content": json.dumps(tool_result)
-                            })
-                        else:
-                            messages.append({
-                                "role": "tool",
-                                "tool_call_id": tool_call.id,
-                                "content": "Function returned an empty output"
-                            })
-                        
-                    response = self._chat_completion(messages, temperature=temperature)
-                    if not response:
-                        return None
-                    response_text = response.choices[0].message.content.strip()
-
-                # Handle output_json or output_pydantic if specified
-                if output_json or output_pydantic:
-                    # Add to chat history and return raw response
-                    self.chat_history.append({"role": "user", "content": original_prompt})
-                    self.chat_history.append({"role": "assistant", "content": response_text})
-                    if self.verbose:
-                        display_interaction(original_prompt, response_text, markdown=self.markdown, 
-                                         generation_time=time.time() - start_time, console=self.console)
-                    return response_text
-
-                if not self.self_reflect:
-                    self.chat_history.append({"role": "user", "content": original_prompt})
-                    self.chat_history.append({"role": "assistant", "content": response_text})
-                    if self.verbose:
-                        logging.debug(f"Agent {self.name} final response: {response_text}")
-                    display_interaction(original_prompt, response_text, markdown=self.markdown, generation_time=time.time() - start_time, console=self.console)
-                    return response_text
-
-                reflection_prompt = f"""
-Reflect on your previous response: '{response_text}'.
-Identify any flaws, improvements, or actions.
-Provide a "satisfactory" status ('yes' or 'no').
-Output MUST be JSON with 'reflection' and 'satisfactory'.
-                """
-                logging.debug(f"{self.name} reflection attempt {reflection_count+1}, sending prompt: {reflection_prompt}")
-                messages.append({"role": "user", "content": reflection_prompt})
-
-                try:
-                    reflection_response = client.beta.chat.completions.parse(
-                        model=self.reflect_llm if self.reflect_llm else self.llm,
-                        messages=messages,
-                        temperature=temperature,
-                        response_format=ReflectionOutput
-                    )
-
-                    reflection_output = reflection_response.choices[0].message.parsed
-
-                    if self.verbose:
-                        display_self_reflection(f"Agent {self.name} self reflection (using {self.reflect_llm if self.reflect_llm else self.llm}): reflection='{reflection_output.reflection}' satisfactory='{reflection_output.satisfactory}'", console=self.console)
-
-                    messages.append({"role": "assistant", "content": f"Self Reflection: {reflection_output.reflection} Satisfactory?: {reflection_output.satisfactory}"})
-
-                    # Only consider satisfactory after minimum reflections
-                    if reflection_output.satisfactory == "yes" and reflection_count >= self.min_reflect - 1:
-                        if self.verbose:
-                            display_self_reflection("Agent marked the response as satisfactory after meeting minimum reflections", console=self.console)
-                        self.chat_history.append({"role": "user", "content": prompt})
-                        self.chat_history.append({"role": "assistant", "content": response_text})
-                        display_interaction(prompt, response_text, markdown=self.markdown, generation_time=time.time() - start_time, console=self.console)
-                        return response_text
-
-                    # Check if we've hit max reflections
-                    if reflection_count >= self.max_reflect - 1:
-                        if self.verbose:
-                            display_self_reflection("Maximum reflection count reached, returning current response", console=self.console)
-                        self.chat_history.append({"role": "user", "content": prompt})
-                        self.chat_history.append({"role": "assistant", "content": response_text})
-                        display_interaction(prompt, response_text, markdown=self.markdown, generation_time=time.time() - start_time, console=self.console)
-                        return response_text
-
-                    logging.debug(f"{self.name} reflection count {reflection_count + 1}, continuing reflection process")
-                    messages.append({"role": "user", "content": "Now regenerate your response using the reflection you made"})
-                    response = self._chat_completion(messages, temperature=temperature, tools=None, stream=True)
-                    response_text = response.choices[0].message.content.strip()
-                    reflection_count += 1
-                    continue  # Continue the loop for more reflections
-
-                except Exception as e:
-                    display_error(f"Error in parsing self-reflection json {e}. Retrying", console=self.console)
-                    logging.error("Reflection parsing failed.", exc_info=True)
-                    messages.append({"role": "assistant", "content": f"Self Reflection failed."})
-                    reflection_count += 1
-                    continue  # Continue even after error to try again
-                
-            except Exception as e:
-                display_error(f"Error in chat: {e}", console=self.console)
-                return None 
-
-    def clean_json_output(self, output: str) -> str:
-        """Clean and extract JSON from response text."""
-        cleaned = output.strip()
-        # Remove markdown code blocks if present
-        if cleaned.startswith("```json"):
-            cleaned = cleaned[len("```json"):].strip()
-        if cleaned.startswith("```"):
-            cleaned = cleaned[len("```"):].strip()
-        if cleaned.endswith("```"):
-            cleaned = cleaned[:-3].strip()
-        return cleaned 
-
-    async def achat(self, prompt, temperature=0.2, tools=None, output_json=None, output_pydantic=None):
-        """Async version of chat method"""
-        try:
-            # Build system prompt
-            system_prompt = self.system_prompt
-            if output_json:
-                system_prompt += f"\nReturn ONLY a JSON object that matches this Pydantic model: {json.dumps(output_json.model_json_schema())}"
-            elif output_pydantic:
-                system_prompt += f"\nReturn ONLY a JSON object that matches this Pydantic model: {json.dumps(output_pydantic.model_json_schema())}"
-
-            # Build messages
-            if isinstance(prompt, str):
-                messages = [
-                    {"role": "system", "content": system_prompt},
-                    {"role": "user", "content": prompt + ("\nReturn ONLY a valid JSON object. No other text or explanation." if (output_json or output_pydantic) else "")}
-                ]
-            else:
-                # For multimodal prompts
-                messages = [
-                    {"role": "system", "content": system_prompt},
-                    {"role": "user", "content": prompt}
-                ]
-                if output_json or output_pydantic:
-                    # Add JSON instruction to text content
-                    for item in messages[-1]["content"]:
-                        if item["type"] == "text":
-                            item["text"] += "\nReturn ONLY a valid JSON object. No other text or explanation."
-                            break
-
-            # Display instruction with agent info if verbose
-            if self.verbose:
-                display_text = prompt
-                if isinstance(prompt, list):
-                    display_text = next((item["text"] for item in prompt if item["type"] == "text"), "")
-                
-                if display_text and str(display_text).strip():
-                    agent_tools = [t.__name__ if hasattr(t, '__name__') else str(t) for t in self.tools]
-                    await adisplay_instruction(
-                        f"Agent {self.name} is processing prompt: {display_text}",
-                        console=self.console,
-                        agent_name=self.name,
-                        agent_role=self.role,
-                        agent_tools=agent_tools
-                    )
-
-            # Format tools if provided
-            formatted_tools = []
-            if tools:
-                for tool in tools:
-                    if isinstance(tool, str):
-                        tool_def = self._generate_tool_definition(tool)
-                        if tool_def:
-                            formatted_tools.append(tool_def)
-                    elif isinstance(tool, dict):
-                        formatted_tools.append(tool)
-                    elif hasattr(tool, "to_openai_tool"):
-                        formatted_tools.append(tool.to_openai_tool())
-                    elif callable(tool):
-                        formatted_tools.append(self._generate_tool_definition(tool.__name__))
-
-            # Create async OpenAI client
-            async_client = AsyncOpenAI()
-
-            # Make the API call based on the type of request
-            if tools:
-                response = await async_client.chat.completions.create(
-                    model=self.llm,
-                    messages=messages,
-                    temperature=temperature,
-                    tools=formatted_tools
-                )
-                return await self._achat_completion(response, tools)
-            elif output_json or output_pydantic:
-                response = await async_client.chat.completions.create(
-                    model=self.llm,
-                    messages=messages,
-                    temperature=temperature,
-                    response_format={"type": "json_object"}
-                )
-                # Return the raw response
-                return response.choices[0].message.content
-            else:
-                response = await async_client.chat.completions.create(
-                    model=self.llm,
-                    messages=messages,
-                    temperature=temperature
-                )
-                return response.choices[0].message.content
-        except Exception as e:
-            display_error(f"Error in chat completion: {e}")
-            return None
-
-    async def _achat_completion(self, response, tools):
-        """Async version of _chat_completion method"""
-        try:
-            message = response.choices[0].message
-            if not hasattr(message, 'tool_calls') or not message.tool_calls:
-                return message.content
-
-            results = []
-            for tool_call in message.tool_calls:
-                try:
-                    function_name = tool_call.function.name
-                    arguments = json.loads(tool_call.function.arguments)
-                    
-                    # Find the matching tool
-                    tool = next((t for t in tools if t.__name__ == function_name), None)
-                    if not tool:
-                        display_error(f"Tool {function_name} not found")
-                        continue
-                    
-                    # Check if the tool is async
-                    if asyncio.iscoroutinefunction(tool):
-                        result = await tool(**arguments)
-                    else:
-                        # Run sync function in executor to avoid blocking
-                        loop = asyncio.get_event_loop()
-                        result = await loop.run_in_executor(None, lambda: tool(**arguments))
-                    
-                    results.append(result)
-                except Exception as e:
-                    display_error(f"Error executing tool {function_name}: {e}")
-                    results.append(None)
-
-            # If we have results, format them into a response
-            if results:
-                formatted_results = "\n".join([str(r) for r in results if r is not None])
-                if formatted_results:
-                    messages = [
-                        {"role": "system", "content": self.system_prompt},
-                        {"role": "assistant", "content": "Here are the tool results:"},
-                        {"role": "user", "content": formatted_results + "\nPlease process these results and provide a final response."}
-                    ]
-                    try:
-                        async_client = AsyncOpenAI()
-                        final_response = await async_client.chat.completions.create(
-                            model=self.llm,
-                            messages=messages,
-                            temperature=0.2
-                        )
-                        return final_response.choices[0].message.content
-                    except Exception as e:
-                        display_error(f"Error in final chat completion: {e}")
-                        return formatted_results
-                return formatted_results
-            return None
-        except Exception as e:
-            display_error(f"Error in _achat_completion: {e}")
-            return None 
-
-    def run(self):
-        """Alias for start() method"""
-        return self.start() 
-
-    def start(self, prompt: str, **kwargs):
-        """Start the agent with a prompt. This is a convenience method that wraps chat()."""
-        return self.chat(prompt, **kwargs) 

agents/praisonaiagents/process/process.py

@@ -1,650 +0,0 @@
-import logging
-import asyncio
-from typing import Dict, Optional, List, Any, AsyncGenerator
-from pydantic import BaseModel
-from ..agent.agent import Agent
-from ..task.task import Task
-from ..main import display_error, client
-import csv
-import os
-
-class LoopItems(BaseModel):
-    items: List[Any]
-
-class Process:
-    def __init__(self, tasks: Dict[str, Task], agents: List[Agent], manager_llm: Optional[str] = None, verbose: bool = False, max_iter: int = 10):
-        self.tasks = tasks
-        self.agents = agents
-        self.manager_llm = manager_llm
-        self.verbose = verbose
-        self.max_iter = max_iter
-
-    async def aworkflow(self) -> AsyncGenerator[str, None]:
-        """Async version of workflow method"""
-        current_iter = 0  # Track how many times we've looped
-        # Build workflow relationships first
-        for task in self.tasks.values():
-            if task.next_tasks:
-                for next_task_name in task.next_tasks:
-                    next_task = next((t for t in self.tasks.values() if t.name == next_task_name), None)
-                    if next_task:
-                        next_task.previous_tasks.append(task.name)
-
-        # Find start task
-        start_task = None
-        for task_id, task in self.tasks.items():
-            if task.is_start:
-                start_task = task
-                break
-        
-        if not start_task:
-            start_task = list(self.tasks.values())[0]
-            logging.info("No start task marked, using first task")
-        
-        current_task = start_task
-        visited_tasks = set()
-        loop_data = {}  # Store loop-specific data
-        
-        while current_task:
-            current_iter += 1
-            if current_iter > self.max_iter:
-                logging.info(f"Max iteration limit {self.max_iter} reached, ending workflow.")
-                break
-
-            task_id = current_task.id
-            logging.info(f"Executing workflow task: {current_task.name if current_task.name else task_id}")
-            
-            # Add context from previous tasks to description
-            if current_task.previous_tasks or current_task.context:
-                context = "\nInput data from previous tasks:"
-                
-                # Add data from previous tasks in workflow
-                for prev_name in current_task.previous_tasks:
-                    prev_task = next((t for t in self.tasks.values() if t.name == prev_name), None)
-                    if prev_task and prev_task.result:
-                        # Handle loop data
-                        if current_task.task_type == "loop":
-#                             # create a loop manager Agent
-#                             loop_manager = Agent(
-#                                 name="Loop Manager",
-#                                 role="Loop data processor",
-#                                 goal="Process loop data and convert it to list format",
-#                                 backstory="Expert at handling loop data and converting it to proper format",
-#                                 llm=self.manager_llm,
-#                                 verbose=self.verbose,
-#                                 markdown=True
-#                             )
-
-#                             # get the loop data convert it to list using calling Agent class chat
-#                             loop_prompt = f"""
-# Process this data into a list format:
-# {prev_task.result.raw}
-
-# Return a JSON object with an 'items' array containing the items to process.
-# """
-#                             if current_task.async_execution:
-#                                 loop_data_str = await loop_manager.achat(
-#                                     prompt=loop_prompt,
-#                                     output_json=LoopItems
-#                                 )
-#                             else:
-#                                 loop_data_str = loop_manager.chat(
-#                                     prompt=loop_prompt,
-#                                     output_json=LoopItems
-#                                 )
-                            
-#                             try:
-#                                 # The response will already be parsed into LoopItems model
-#                                 loop_data[f"loop_{current_task.name}"] = {
-#                                     "items": loop_data_str.items,
-#                                     "index": 0,
-#                                     "remaining": len(loop_data_str.items)
-#                                 }
-#                                 context += f"\nCurrent loop item: {loop_data_str.items[0]}"
-#                             except Exception as e:
-#                                 display_error(f"Failed to process loop data: {e}")
-#                                 context += f"\n{prev_name}: {prev_task.result.raw}"
-                            context += f"\n{prev_name}: {prev_task.result.raw}"
-                        else:
-                            context += f"\n{prev_name}: {prev_task.result.raw}"
-                
-                # Add data from context tasks
-                if current_task.context:
-                    for ctx_task in current_task.context:
-                        if ctx_task.result and ctx_task.name != current_task.name:
-                            context += f"\n{ctx_task.name}: {ctx_task.result.raw}"
-                
-                # Update task description with context
-                current_task.description = current_task.description + context
-            
-            # Execute task using existing run_task method
-            yield task_id
-            visited_tasks.add(task_id)
-            
-            # Reset completed task to "not started" so it can run again
-            if self.tasks[task_id].status == "completed":
-                logging.debug(f"Task {task_id} was completed, resetting to 'not started' for next iteration.")
-                self.tasks[task_id].status = "not started"
-            
-            # Handle loop progression
-            if current_task.task_type == "loop":
-                loop_key = f"loop_{current_task.name}"
-                if loop_key in loop_data:
-                    loop_info = loop_data[loop_key]
-                    loop_info["index"] += 1
-                    has_more = loop_info["remaining"] > 0
-                    
-                    # Update result to trigger correct condition
-                    if current_task.result:
-                        result = current_task.result.raw
-                        if has_more:
-                            result += "\nmore"
-                        else:
-                            result += "\ndone"
-                        current_task.result.raw = result
-                    
-            # Determine next task based on result
-            next_task = None
-            if current_task and current_task.result:
-                if current_task.task_type in ["decision", "loop"]:
-                    # MINIMAL CHANGE: use pydantic decision if present
-                    decision_str = current_task.result.raw.lower()
-                    if current_task.result.pydantic and hasattr(current_task.result.pydantic, "decision"):
-                        decision_str = current_task.result.pydantic.decision.lower()
-
-                    # Check conditions
-                    for condition, tasks in current_task.condition.items():
-                        if condition.lower() == decision_str:
-                            # Handle both list and direct string values
-                            task_value = tasks[0] if isinstance(tasks, list) else tasks
-                            if not task_value or task_value == "exit":
-                                logging.info("Workflow exit condition met, ending workflow")
-                                current_task = None
-                                break
-                            next_task_name = task_value
-                            next_task = next((t for t in self.tasks.values() if t.name == next_task_name), None)
-                            # For loops, allow revisiting the same task
-                            if next_task and next_task.id == current_task.id:
-                                visited_tasks.discard(current_task.id)
-                            break
-            
-            if not next_task and current_task and current_task.next_tasks:
-                next_task_name = current_task.next_tasks[0]
-                next_task = next((t for t in self.tasks.values() if t.name == next_task_name), None)
-            
-            current_task = next_task
-            if not current_task:
-                logging.info("Workflow execution completed")
-                break
-
-    async def asequential(self) -> AsyncGenerator[str, None]:
-        """Async version of sequential method"""
-        for task_id in self.tasks:
-            if self.tasks[task_id].status != "completed":
-                yield task_id
-
-    async def ahierarchical(self) -> AsyncGenerator[str, None]:
-        """Async version of hierarchical method"""
-        logging.debug(f"Starting hierarchical task execution with {len(self.tasks)} tasks")
-        manager_agent = Agent(
-            name="Manager",
-            role="Project manager",
-            goal="Manage the entire flow of tasks and delegate them to the right agent",
-            backstory="Expert project manager to coordinate tasks among agents",
-            llm=self.manager_llm,
-            verbose=self.verbose,
-            markdown=True,
-            self_reflect=False
-        )
-
-        class ManagerInstructions(BaseModel):
-            task_id: int
-            agent_name: str
-            action: str
-
-        manager_task = Task(
-            name="manager_task",
-            description="Decide the order of tasks and which agent executes them",
-            expected_output="All tasks completed successfully",
-            agent=manager_agent
-        )
-        manager_task_id = yield manager_task
-        logging.info(f"Created manager task with ID {manager_task_id}")
-
-        completed_count = 0
-        total_tasks = len(self.tasks) - 1
-        logging.info(f"Need to complete {total_tasks} tasks (excluding manager task)")
-
-        while completed_count < total_tasks:
-            tasks_summary = []
-            for tid, tk in self.tasks.items():
-                if tk.name == "manager_task":
-                    continue
-                task_info = {
-                    "task_id": tid,
-                    "name": tk.name,
-                    "description": tk.description,
-                    "status": tk.status if tk.status else "not started",
-                    "agent": tk.agent.name if tk.agent else "No agent"
-                }
-                tasks_summary.append(task_info)
-                logging.info(f"Task {tid} status: {task_info}")
-
-            manager_prompt = f"""
-Here is the current status of all tasks except yours (manager_task):
-{tasks_summary}
-
-Provide a JSON with the structure:
-{{
-   "task_id": <int>,
-   "agent_name": "<string>",
-   "action": "<execute or stop>"
-}}
-"""
-
-            try:
-                logging.info("Requesting manager instructions...")
-                if manager_task.async_execution:
-                    manager_response = await client.beta.chat.completions.parse(
-                        model=self.manager_llm,
-                        messages=[
-                            {"role": "system", "content": manager_task.description},
-                            {"role": "user", "content": manager_prompt}
-                        ],
-                        temperature=0.7,
-                        response_format=ManagerInstructions
-                    )
-                else:
-                    manager_response = client.beta.chat.completions.parse(
-                        model=self.manager_llm,
-                        messages=[
-                            {"role": "system", "content": manager_task.description},
-                            {"role": "user", "content": manager_prompt}
-                        ],
-                        temperature=0.7,
-                        response_format=ManagerInstructions
-                    )
-                parsed_instructions = manager_response.choices[0].message.parsed
-                logging.info(f"Manager instructions: {parsed_instructions}")
-            except Exception as e:
-                display_error(f"Manager parse error: {e}")
-                logging.error(f"Manager parse error: {str(e)}", exc_info=True)
-                break
-
-            selected_task_id = parsed_instructions.task_id
-            selected_agent_name = parsed_instructions.agent_name
-            action = parsed_instructions.action
-
-            logging.info(f"Manager selected task_id={selected_task_id}, agent={selected_agent_name}, action={action}")
-
-            if action.lower() == "stop":
-                logging.info("Manager decided to stop task execution")
-                break
-
-            if selected_task_id not in self.tasks:
-                error_msg = f"Manager selected invalid task id {selected_task_id}"
-                display_error(error_msg)
-                logging.error(error_msg)
-                break
-
-            original_agent = self.tasks[selected_task_id].agent.name if self.tasks[selected_task_id].agent else "None"
-            for a in self.agents:
-                if a.name == selected_agent_name:
-                    self.tasks[selected_task_id].agent = a
-                    logging.info(f"Changed agent for task {selected_task_id} from {original_agent} to {selected_agent_name}")
-                    break
-
-            if self.tasks[selected_task_id].status != "completed":
-                logging.info(f"Starting execution of task {selected_task_id}")
-                yield selected_task_id
-                logging.info(f"Finished execution of task {selected_task_id}, status: {self.tasks[selected_task_id].status}")
-
-            if self.tasks[selected_task_id].status == "completed":
-                completed_count += 1
-                logging.info(f"Task {selected_task_id} completed. Total completed: {completed_count}/{total_tasks}")
-
-        self.tasks[manager_task.id].status = "completed"
-        if self.verbose >= 1:
-            logging.info("All tasks completed under manager supervision.")
-        logging.info("Hierarchical task execution finished") 
-
-    def workflow(self):
-        """Synchronous version of workflow method"""
-        current_iter = 0  # Track how many times we've looped
-        # Build workflow relationships first
-        for task in self.tasks.values():
-            if task.next_tasks:
-                for next_task_name in task.next_tasks:
-                    next_task = next((t for t in self.tasks.values() if t.name == next_task_name), None)
-                    if next_task:
-                        next_task.previous_tasks.append(task.name)
-
-        # Find start task
-        start_task = None
-        for task_id, task in self.tasks.items():
-            if task.is_start:
-                start_task = task
-                break
-        
-        if not start_task:
-            start_task = list(self.tasks.values())[0]
-            logging.info("No start task marked, using first task")
-
-        # If loop type and no input_file, default to tasks.csv 
-        if start_task and start_task.task_type == "loop" and not start_task.input_file:
-            start_task.input_file = "tasks.csv"
-
-        # --- If loop + input_file, read file & create tasks
-        if start_task and start_task.task_type == "loop" and getattr(start_task, "input_file", None):
-            try:
-                file_ext = os.path.splitext(start_task.input_file)[1].lower()
-                new_tasks = []
-                
-                if file_ext == ".csv":
-                    # existing CSV reading logic
-                    with open(start_task.input_file, "r", encoding="utf-8") as f:
-                        # Try as simple CSV first
-                        reader = csv.reader(f)
-                        previous_task = None
-                        for i, row in enumerate(reader):
-                            if row:  # Skip empty rows
-                                task_desc = row[0]  # Take first column
-                                row_task = Task(
-                                    description=task_desc,  # Keep full row as description
-                                    agent=start_task.agent,
-                                    name=task_desc,       # Use first column as name
-                                    is_start=(i == 0),
-                                    task_type="task",
-                                    condition={
-                                        "complete": ["next"],
-                                        "retry": ["current"]
-                                    }
-                                )
-                                self.tasks[row_task.id] = row_task
-                                new_tasks.append(row_task)
-                                
-                                if previous_task:
-                                    previous_task.next_tasks = [row_task.name]
-                                    previous_task.condition["complete"] = [row_task.name]
-                                previous_task = row_task
-                else:
-                    # If not CSV, read lines
-                    with open(start_task.input_file, "r", encoding="utf-8") as f:
-                        lines = f.read().splitlines()
-                        previous_task = None
-                        for i, line in enumerate(lines):
-                            row_task = Task(
-                                description=line.strip(),
-                                agent=start_task.agent,
-                                name=line.strip(),
-                                is_start=(i == 0),
-                                task_type="task",
-                                condition={
-                                    "complete": ["next"],
-                                    "retry": ["current"]
-                                }
-                            )
-                            self.tasks[row_task.id] = row_task
-                            new_tasks.append(row_task)
-                            
-                            if previous_task:
-                                previous_task.next_tasks = [row_task.name]
-                                previous_task.condition["complete"] = [row_task.name]
-                            previous_task = row_task
-
-                if new_tasks:
-                    start_task = new_tasks[0]
-                    logging.info(f"Created {len(new_tasks)} tasks from: {start_task.input_file}")
-            except Exception as e:
-                logging.error(f"Failed to read file tasks: {e}")
-
-        # end of the new block
-        current_task = start_task
-        visited_tasks = set()
-        loop_data = {}  # Store loop-specific data
-        
-        while current_task:
-            current_iter += 1
-            if current_iter > self.max_iter:
-                logging.info(f"Max iteration limit {self.max_iter} reached, ending workflow.")
-                break
-
-            task_id = current_task.id
-            logging.info(f"Executing workflow task: {current_task.name if current_task.name else task_id}")
-            
-            # Add context from previous tasks to description
-            if current_task.previous_tasks or current_task.context:
-                context = "\nInput data from previous tasks:"
-                
-                # Add data from previous tasks in workflow
-                for prev_name in current_task.previous_tasks:
-                    prev_task = next((t for t in self.tasks.values() if t.name == prev_name), None)
-                    if prev_task and prev_task.result:
-                        # Handle loop data
-                        if current_task.task_type == "loop":
-#                             # create a loop manager Agent
-#                             loop_manager = Agent(
-#                                 name="Loop Manager",
-#                                 role="Loop data processor",
-#                                 goal="Process loop data and convert it to list format",
-#                                 backstory="Expert at handling loop data and converting it to proper format",
-#                                 llm=self.manager_llm,
-#                                 verbose=self.verbose,
-#                                 markdown=True
-#                             )
-
-#                             # get the loop data convert it to list using calling Agent class chat
-#                             loop_prompt = f"""
-# Process this data into a list format:
-# {prev_task.result.raw}
-
-# Return a JSON object with an 'items' array containing the items to process.
-# """
-#                             loop_data_str = loop_manager.chat(
-#                                 prompt=loop_prompt,
-#                                 output_json=LoopItems
-#                             )
-                            
-#                             try:
-#                                 # The response will already be parsed into LoopItems model
-#                                 loop_data[f"loop_{current_task.name}"] = {
-#                                     "items": loop_data_str.items,
-#                                     "index": 0,
-#                                     "remaining": len(loop_data_str.items)
-#                                 }
-#                                 context += f"\nCurrent loop item: {loop_data_str.items[0]}"
-#                             except Exception as e:
-#                                 display_error(f"Failed to process loop data: {e}")
-#                                 context += f"\n{prev_name}: {prev_task.result.raw}"
-                            context += f"\n{prev_name}: {prev_task.result.raw}"
-                        else:
-                            context += f"\n{prev_name}: {prev_task.result.raw}"
-                
-                # Add data from context tasks
-                if current_task.context:
-                    for ctx_task in current_task.context:
-                        if ctx_task.result and ctx_task.name != current_task.name:
-                            context += f"\n{ctx_task.name}: {ctx_task.result.raw}"
-                
-                # Update task description with context
-                current_task.description = current_task.description + context
-            
-            # Execute task using existing run_task method
-            yield task_id
-            visited_tasks.add(task_id)
-            
-            # Reset completed task to "not started" so it can run again: Only for workflow because some tasks may be revisited
-            if self.tasks[task_id].status == "completed":
-                logging.debug(f"Task {task_id} was completed, resetting to 'not started' for next iteration.")
-                self.tasks[task_id].status = "not started"
-            
-            # Handle loop progression
-            if current_task.task_type == "loop":
-                loop_key = f"loop_{current_task.name}"
-                if loop_key in loop_data:
-                    loop_info = loop_data[loop_key]
-                    loop_info["index"] += 1
-                    has_more = loop_info["remaining"] > 0
-                    
-                    # Update result to trigger correct condition
-                    if current_task.result:
-                        result = current_task.result.raw
-                        if has_more:
-                            result += "\nmore"
-                        else:
-                            result += "\ndone"
-                        current_task.result.raw = result
-                    
-            # Determine next task based on result
-            next_task = None
-            if current_task and current_task.result:
-                if current_task.task_type in ["decision", "loop"]:
-                    # MINIMAL CHANGE: use pydantic decision if present
-                    decision_str = current_task.result.raw.lower()
-                    if current_task.result.pydantic and hasattr(current_task.result.pydantic, "decision"):
-                        decision_str = current_task.result.pydantic.decision.lower()
-
-                    # Check conditions
-                    for condition, tasks in current_task.condition.items():
-                        if condition.lower() == decision_str:
-                            # Handle both list and direct string values
-                            task_value = tasks[0] if isinstance(tasks, list) else tasks
-                            if not task_value or task_value == "exit":
-                                logging.info("Workflow exit condition met, ending workflow")
-                                current_task = None
-                                break
-                            next_task_name = task_value
-                            next_task = next((t for t in self.tasks.values() if t.name == next_task_name), None)
-                            # For loops, allow revisiting the same task
-                            if next_task and next_task.id == current_task.id:
-                                visited_tasks.discard(current_task.id)
-                            break
-            
-            if not next_task and current_task and current_task.next_tasks:
-                next_task_name = current_task.next_tasks[0]
-                next_task = next((t for t in self.tasks.values() if t.name == next_task_name), None)
-            
-            current_task = next_task
-            if not current_task:
-                logging.info("Workflow execution completed")
-                break
-
-    def sequential(self):
-        """Synchronous version of sequential method"""
-        for task_id in self.tasks:
-            if self.tasks[task_id].status != "completed":
-                yield task_id
-
-    def hierarchical(self):
-        """Synchronous version of hierarchical method"""
-        logging.debug(f"Starting hierarchical task execution with {len(self.tasks)} tasks")
-        manager_agent = Agent(
-            name="Manager",
-            role="Project manager",
-            goal="Manage the entire flow of tasks and delegate them to the right agent",
-            backstory="Expert project manager to coordinate tasks among agents",
-            llm=self.manager_llm,
-            verbose=self.verbose,
-            markdown=True,
-            self_reflect=False
-        )
-
-        class ManagerInstructions(BaseModel):
-            task_id: int
-            agent_name: str
-            action: str
-
-        manager_task = Task(
-            name="manager_task",
-            description="Decide the order of tasks and which agent executes them",
-            expected_output="All tasks completed successfully",
-            agent=manager_agent
-        )
-        manager_task_id = yield manager_task
-        logging.info(f"Created manager task with ID {manager_task_id}")
-
-        completed_count = 0
-        total_tasks = len(self.tasks) - 1
-        logging.info(f"Need to complete {total_tasks} tasks (excluding manager task)")
-
-        while completed_count < total_tasks:
-            tasks_summary = []
-            for tid, tk in self.tasks.items():
-                if tk.name == "manager_task":
-                    continue
-                task_info = {
-                    "task_id": tid,
-                    "name": tk.name,
-                    "description": tk.description,
-                    "status": tk.status if tk.status else "not started",
-                    "agent": tk.agent.name if tk.agent else "No agent"
-                }
-                tasks_summary.append(task_info)
-                logging.info(f"Task {tid} status: {task_info}")
-
-            manager_prompt = f"""
-Here is the current status of all tasks except yours (manager_task):
-{tasks_summary}
-
-Provide a JSON with the structure:
-{{
-   "task_id": <int>,
-   "agent_name": "<string>",
-   "action": "<execute or stop>"
-}}
-"""
-
-            try:
-                logging.info("Requesting manager instructions...")
-                manager_response = client.beta.chat.completions.parse(
-                    model=self.manager_llm,
-                    messages=[
-                        {"role": "system", "content": manager_task.description},
-                        {"role": "user", "content": manager_prompt}
-                    ],
-                    temperature=0.7,
-                    response_format=ManagerInstructions
-                )
-                parsed_instructions = manager_response.choices[0].message.parsed
-                logging.info(f"Manager instructions: {parsed_instructions}")
-            except Exception as e:
-                display_error(f"Manager parse error: {e}")
-                logging.error(f"Manager parse error: {str(e)}", exc_info=True)
-                break
-
-            selected_task_id = parsed_instructions.task_id
-            selected_agent_name = parsed_instructions.agent_name
-            action = parsed_instructions.action
-
-            logging.info(f"Manager selected task_id={selected_task_id}, agent={selected_agent_name}, action={action}")
-
-            if action.lower() == "stop":
-                logging.info("Manager decided to stop task execution")
-                break
-
-            if selected_task_id not in self.tasks:
-                error_msg = f"Manager selected invalid task id {selected_task_id}"
-                display_error(error_msg)
-                logging.error(error_msg)
-                break
-
-            original_agent = self.tasks[selected_task_id].agent.name if self.tasks[selected_task_id].agent else "None"
-            for a in self.agents:
-                if a.name == selected_agent_name:
-                    self.tasks[selected_task_id].agent = a
-                    logging.info(f"Changed agent for task {selected_task_id} from {original_agent} to {selected_agent_name}")
-                    break
-
-            if self.tasks[selected_task_id].status != "completed":
-                logging.info(f"Starting execution of task {selected_task_id}")
-                yield selected_task_id
-                logging.info(f"Finished execution of task {selected_task_id}, status: {self.tasks[selected_task_id].status}")
-
-            if self.tasks[selected_task_id].status == "completed":
-                completed_count += 1
-                logging.info(f"Task {selected_task_id} completed. Total completed: {completed_count}/{total_tasks}")
-
-        self.tasks[manager_task.id].status = "completed"
-        if self.verbose >= 1:
-            logging.info("All tasks completed under manager supervision.")
-        logging.info("Hierarchical task execution finished") 

docker/Dockerfile

@@ -1,6 +1,6 @@
 FROM python:3.11-slim
 WORKDIR /app
 COPY . .
-RUN pip install flask praisonai==2.0.54 gunicorn markdown
+RUN pip install flask praisonai==2.0.71 gunicorn markdown
 EXPOSE 8080
 CMD ["gunicorn", "-b", "0.0.0.0:8080", "api:app"]

docs/api/praisonai/deploy.html

@@ -110,7 +110,7 @@ Loads environment variables from .env file or system and sets them.</p>
             file.write(&#34;FROM python:3.11-slim\n&#34;)
             file.write(&#34;WORKDIR /app\n&#34;)
             file.write(&#34;COPY . .\n&#34;)
-            file.write(&#34;RUN pip install flask praisonai==2.0.54 gunicorn markdown\n&#34;)
+            file.write(&#34;RUN pip install flask praisonai==2.0.71 gunicorn markdown\n&#34;)
             file.write(&#34;EXPOSE 8080\n&#34;)
             file.write(&#39;CMD [&#34;gunicorn&#34;, &#34;-b&#34;, &#34;0.0.0.0:8080&#34;, &#34;api:app&#34;]\n&#39;)
             

docs/concepts/agents.mdx

@@ -112,86 +112,22 @@ graph LR
   <Step title="Create Agent">
     Create `app.py`:
 <CodeGroup>
-  ```python Single Agent
-  from praisonaiagents import Agent, Task, PraisonAIAgents
+```python Single Agent
+from praisonaiagents import Agent
 
-  # Create an agent
-  researcher = Agent(
-      name="Researcher",
-      role="Senior Research Analyst",
-      goal="Uncover cutting-edge developments in AI",
-      backstory="You are an expert at a technology research group",
-      verbose=True,
-      llm="gpt-4o"
-  )
+agent = Agent(instructions="Your are a helpful AI assistant")
+agent.start("Write a movie script about a robot in Mars")
+```
 
-  # Define a task
-  task = Task(
-      name="research_task",
-      description="Analyze 2024's AI advancements",
-      expected_output="A detailed report",
-      agent=researcher
-  )
+```python Multi Agents
+from praisonaiagents import Agent, PraisonAIAgents
 
-  # Run the agents
-  agents = PraisonAIAgents(
-      agents=[researcher],
-      tasks=[task],
-      verbose=False
-  )
+research_agent = Agent(instructions="Research about AI")
+summarise_agent = Agent(instructions="Summarise research agent's findings")
 
-  result = agents.start()
-  ```
-
-  ```python Multiple Agents
-  from praisonaiagents import Agent, Task, PraisonAIAgents
-
-  # Create multiple agents
-  researcher = Agent(
-      name="Researcher",
-      role="Senior Research Analyst",
-      goal="Uncover cutting-edge developments in AI",
-      backstory="You are an expert at a technology research group",
-      verbose=True,
-      llm="gpt-4o",
-      markdown=True
-  )
-
-  writer = Agent(
-      name="Writer",
-      role="Tech Content Strategist",
-      goal="Craft compelling content on tech advancements",
-      backstory="You are a content strategist",
-      llm="gpt-4o",
-      markdown=True
-  )
-
-  # Define multiple tasks
-  task1 = Task(
-      name="research_task",
-      description="Analyze 2024's AI advancements",
-      expected_output="A detailed report",
-      agent=researcher
-  )
-
-  task2 = Task(
-      name="writing_task",
-      description="Create a blog post about AI advancements",
-      expected_output="A blog post",
-      agent=writer
-  )
-
-  # Run with hierarchical process
-  agents = PraisonAIAgents(
-      agents=[researcher, writer],
-      tasks=[task1, task2],
-      verbose=False,
-      process="hierarchical",
-      manager_llm="gpt-4o"
-  )
-
-  result = agents.start()
-  ```
+agents = PraisonAIAgents(agents=[research_agent, summarise_agent])
+agents.start()
+```
 </CodeGroup>
   </Step>
 

docs/developers/local-development.mdx

@@ -0,0 +1,75 @@
+---
+title: 'Local Development'
+description: 'Set up local development environment with Docker and live reload'
+---
+
+## Logging
+```bash
+export LOGLEVEL=info
+```
+
+Advanced logging:
+```bash
+export LOGLEVEL=debug
+```
+
+## Local Docker Development with Live Reload
+
+To facilitate local development with live reload, you can use Docker. Follow the steps below:
+
+### 1. Create Dockerfile.dev
+
+<CodeGroup>
+```dockerfile Dockerfile.dev
+FROM python:3.11-slim
+
+WORKDIR /app
+
+COPY . .
+
+RUN pip install flask praisonai==2.0.18 watchdog
+
+EXPOSE 5555
+
+ENV FLASK_ENV=development
+
+CMD ["flask", "run", "--host=0.0.0.0"]
+```
+</CodeGroup>
+
+### 2. Create docker-compose.yml
+
+<CodeGroup>
+```yaml docker-compose.yml
+version: '3.8'
+
+services:
+  app:
+    build:
+      context: .
+      dockerfile: Dockerfile.dev
+    volumes:
+      - .:/app
+    ports:
+      - "5555:5555"
+    environment:
+      FLASK_ENV: development
+    command: flask run --host=0.0.0.0
+
+  watch:
+    image: alpine:latest
+    volumes:
+      - .:/app
+    command: sh -c "apk add --no-cache inotify-tools && while inotifywait -r -e modify,create,delete /app; do kill -HUP 1; done"
+```
+</CodeGroup>
+
+### 3. Run Docker Compose
+
+<CodeGroup>
+```bash Terminal
+docker-compose up
+```
+</CodeGroup>
+
+This setup will allow you to develop locally with live reload, making it easier to test and iterate on your code.

docs/features/chat-with-pdf.mdx

@@ -0,0 +1,244 @@
+---
+title: "Chat with PDF Agents"
+sidebarTitle: "Chat with PDF"
+description: "Learn how to create AI agents that can intelligently chat with PDF documents using vector databases for efficient information retrieval."
+icon: "file-pdf"
+---
+
+```mermaid
+flowchart LR
+    PDF[PDF Document] --> PDFAgent[("PDF Chat Agent")]
+    VDB[(Vector DB)] --> PDFAgent
+    PDFAgent --> Chat[Chat Interface]
+    Chat --> |Query| VDB
+    Chat --> Out[Response]
+    
+    style PDF fill:#8B0000,color:#fff
+    style PDFAgent fill:#2E8B57,color:#fff,shape:circle
+    style VDB fill:#4169E1,color:#fff,shape:cylinder
+    style Chat fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+
+A PDF-centric workflow where Chat agents interact with vector databases to store and retrieve information from PDF documents, enabling natural conversations and intelligent question-answering capabilities.
+
+## Quick Start
+
+<Steps>
+  <Step title="Install Package">
+    Install PraisonAI Agents with PDF chat support:
+    ```bash
+    pip install "praisonaiagents[knowledge]"
+    ```
+  </Step>
+
+  <Step title="Set API Key">
+    Set your OpenAI API key:
+    ```bash
+    export OPENAI_API_KEY=xxxxx
+    ```
+  </Step>
+
+  <Step title="Create Script">
+    Create a new file `chat_with_pdf.py`:
+```python
+from praisonaiagents import Agent
+
+agent = Agent(
+    name="PDF Chat Agent",
+    instructions="You answer questions based on the provided PDF document.",
+    knowledge=["document.pdf"], # PDF Indexing
+)
+
+agent.start("What is the main topic of this PDF?") # Chat Query
+```
+  </Step>
+</Steps>
+
+## PDF Processing and Chat Agents 
+
+<Note>
+  PDF processing involves indexing the document content for efficient retrieval during chat.
+</Note>
+
+```mermaid
+flowchart LR
+    subgraph In[Input]
+        PDF[PDF Documents]
+    end
+
+    subgraph Router[Vector Store]
+        DB[(Vector DB)]
+    end
+    
+    subgraph Out[Chat Agents]
+        A1[Chat Agent 1]
+        A2[Chat Agent 2]
+        A3[Chat Agent 3]
+    end
+
+    In --> Router
+    Router --> A1
+    Router --> A2
+    Router --> A3
+
+    style In fill:#8B0000,color:#fff
+    style Router fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+
+The simplest way to create a PDF chat agent is without any configuration:
+
+```python
+from praisonaiagents import Agent
+
+agent = Agent(
+    name="PDF Chat Agent",
+    instructions="You answer questions based on the provided PDF document.",
+    knowledge=["document.pdf"] # PDF Indexing
+)
+
+agent.start("What are the key points in this document?") # Chat Query
+```
+
+### Advanced Configuration
+
+For more control over the knowledge base, you can specify a configuration:
+
+```python
+from praisonaiagents import Agent
+
+config = {
+    "vector_store": {
+        "provider": "chroma",
+        "config": {
+            "collection_name": "praison",
+            "path": ".praison",
+        }
+    }
+}
+
+agent = Agent(
+    name="PDF Chat Agent",
+    instructions="You answer questions based on the provided PDF document.",
+    knowledge=["document.pdf"], # PDF Indexing
+    knowledge_config=config # Configuration
+)
+
+agent.start("What is the main topic of this PDF?") # Chat Query
+```
+
+### Multi-Agent Knowledge System
+
+For more complex scenarios, you can create a knowledge-based system with multiple agents:
+
+```python
+from praisonaiagents import Agent, Task, PraisonAIAgents
+import logging
+import os
+
+# Configure logging
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
+logger = logging.getLogger(__name__)
+
+# Define the configuration for the Knowledge instance
+config = {
+    "vector_store": {
+        "provider": "chroma",
+        "config": {
+            "collection_name": "praison",
+            "path": ".praison",
+        }
+    }
+}
+
+# Create an agent with knowledge capabilities
+knowledge_agent = Agent(
+    name="KnowledgeAgent",
+    role="Information Specialist",
+    goal="Store and retrieve knowledge efficiently",
+    backstory="Expert in managing and utilizing stored knowledge",
+    knowledge=["sample.pdf"], # Indexing
+    knowledge_config=config, # Configuration
+    verbose=True
+)
+
+# Define a task for the agent
+knowledge_task = Task(
+    name="knowledge_task",
+    description="Who is Mervin Praison?",
+    expected_output="Answer to the question",
+    agent=knowledge_agent # Agent
+)
+
+# Create and start the agents
+agents = PraisonAIAgents(
+    agents=[knowledge_agent],
+    tasks=[knowledge_task],
+    process="sequential",
+    user_id="user1" # User ID
+)
+
+# Start execution
+result = agents.start() # Retrieval
+```
+
+## Understanding PDF Chat Agents
+
+<Card title="What are PDF Chat Agents?" icon="question">
+  PDF Chat agents enable:
+  - Natural conversation with PDF documents
+  - Intelligent information extraction
+  - Context-aware document understanding
+  - Quick answers to document-specific questions
+</Card>
+
+## Features
+
+<CardGroup cols={2}>
+  <Card title="PDF Processing" icon="file-pdf">
+    Process and index PDF documents efficiently.
+  </Card>
+  <Card title="Natural Chat" icon="comments">
+    Have natural conversations about PDF content.
+  </Card>
+  <Card title="Smart Retrieval" icon="brain">
+    Intelligently retrieve relevant information from PDFs.
+  </Card>
+  <Card title="Context Awareness" icon="layer-group">
+    Maintain context throughout the conversation.
+  </Card>
+</CardGroup>
+
+## Troubleshooting
+
+<CardGroup cols={2}>
+  <Card title="PDF Issues" icon="triangle-exclamation">
+    If PDF processing isn't working:
+    - Check PDF file format and encoding
+    - Verify document accessibility
+    - Enable verbose mode for debugging
+  </Card>
+
+  <Card title="Chat Issues" icon="gauge-high">
+    If chat responses aren't accurate:
+    - Check PDF indexing quality
+    - Verify question clarity
+    - Monitor context retention
+  </Card>
+</CardGroup>
+
+## Next Steps
+
+<CardGroup cols={2}>
+  <Card title="AutoAgents" icon="robot" href="./autoagents">
+    Learn about automatically created and managed AI agents
+  </Card>
+  <Card title="Mini Agents" icon="microchip" href="./mini">
+    Explore lightweight, focused AI agents
+  </Card>
+</CardGroup>
+
+<Note>
+  For optimal chat experience, ensure your PDFs are properly formatted and text-searchable.
+</Note>

docs/features/cli.mdx

@@ -0,0 +1,117 @@
+---
+title: "Command Line Interface"
+sidebarTitle: "CLI"
+description: "Use PraisonAI directly from your terminal with simple commands"
+icon: "terminal"
+---
+
+```mermaid
+flowchart LR
+    Start((🚀)) --> CLI[CLI Command]
+    CLI --> Agent[AI Agent]
+    Agent --> Config[Config/YAML]
+    Config --> Out((🏁))
+    
+    style Start fill:#8B0000,color:#fff,stroke:#8B0000
+    style CLI fill:#2E8B57,color:#fff
+    style Agent fill:#2E8B57,color:#fff
+    style Config fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff,stroke:#8B0000
+```
+
+PraisonAI CLI provides a simple way to interact with AI agents directly from your terminal. You can run quick commands, specify LLM options, or use YAML configuration files for more complex scenarios.
+
+<Frame>
+  <img src="../demo/praisonai-cli-demo.gif" alt="PraisonAI CLI Demo" />
+</Frame>
+
+## Quick Start
+
+<Steps>
+  <Step title="Install Package">
+    Install the PraisonAI package:
+    ```bash
+    pip install praisonai
+    ```
+  </Step>
+
+  <Step title="Set API Key">
+    Set your OpenAI API key as an environment variable:
+    ```bash
+    export OPENAI_API_KEY=your_api_key_here
+    ```
+  </Step>
+</Steps>
+
+## Usage Examples
+
+<AccordionGroup>
+  <Accordion title="Simple Command" icon="terminal" defaultOpen>
+    Run a simple command directly:
+    ```bash
+    praisonai "write a movie script in 3 lines"
+    ```
+  </Accordion>
+
+  <Accordion title="With LLM Option" icon="wand-magic-sparkles" defaultOpen>
+    Specify a different LLM model:
+    ```bash
+    praisonai "write a movie script in 3 lines" --llm gpt-4o-mini
+    ```
+  </Accordion>
+
+  <Accordion title="Using YAML Config" icon="file-code" defaultOpen>
+    Run agents defined in a YAML file:
+    ```bash
+    praisonai agents.yaml
+    ```
+  </Accordion>
+</AccordionGroup>
+
+## Configuration
+
+<Tabs>
+  <Tab title="Create Config">
+    Initialize a new agents.yaml file for your project:
+    ```bash
+    praisonai --init "Create a movie script about AI"
+    ```
+    This will create an `agents.yaml` file with predefined configuration for your task.
+  </Tab>
+
+  <Tab title="Auto Mode">
+    Let PraisonAI automatically create and configure agents:
+    ```bash
+    praisonai --auto "Create a movie script about AI"
+    ```
+    This mode will analyze your task and set up appropriate agents automatically.
+  </Tab>
+</Tabs>
+
+## Features
+
+<CardGroup cols={2}>
+  <Card title="Simple Commands" icon="terminal">
+    Run AI tasks directly from your terminal with simple commands.
+  </Card>
+  <Card title="LLM Options" icon="wand-magic-sparkles">
+    Choose from different LLM models for your specific needs.
+  </Card>
+  <Card title="YAML Support" icon="file-code">
+    Use YAML files for complex agent configurations and workflows.
+  </Card>
+  <Card title="Auto Configuration" icon="robot">
+    Automatic agent setup based on task requirements.
+  </Card>
+</CardGroup>
+
+## Next Steps
+
+<CardGroup>
+  <Card title="YAML Configuration" icon="file-code" href="/config">
+    Learn more about YAML configuration options
+  </Card>
+  <Card title="API Reference" icon="code" href="/api-reference">
+    View the complete API documentation
+  </Card>
+</CardGroup>

docs/features/generate-reasoning.mdx

@@ -0,0 +1,298 @@
+---
+title: "Generate Synthetic Reasoning Data Agents"
+sidebarTitle: "Generate Reasoning Data"
+description: "Learn how to generate chain-of-thought reasoning data using PraisonAI Agents."
+icon: "brain"
+---
+
+```mermaid
+flowchart TD
+    Start[Start] --> Generator[Question Answer Generator Agent]
+    Generator --> Evaluator[Evaluator Agent]
+    Evaluator --> COT[Reasoning Steps / COT Generator Agent]
+    COT --> COT
+    COT --> Upload[HuggingFace Uploader Agent]
+    Upload --> End[End]
+    
+    style Start fill:#8B0000,color:#fff
+    style Generator fill:#2E8B57,color:#fff
+    style Evaluator fill:#2E8B57,color:#fff
+    style COT fill:#2E8B57,color:#fff
+    style Upload fill:#2E8B57,color:#fff
+    style End fill:#8B0000,color:#fff
+```
+
+## What is Chain-of-Thought Generation?
+
+Chain-of-Thought (CoT) Generation is a process where AI agents create detailed, step-by-step reasoning paths for solving problems. This involves generating questions, evaluating them, producing detailed solution steps, and making the data available for training and analysis.
+
+## Quick Start
+
+<Steps>
+    <Step title="Install Package">
+        First, install the PraisonAI Agents package:
+        ```bash
+        pip install "praisonaiagents[llm]" datasets huggingface-hub pandas
+        ```
+    </Step>
+
+    <Step title="Set API Key">
+        Set your OpenAI API key as an environment variable in your terminal:
+        ```bash
+        export OPENAI_API_KEY=your_api_key_here
+        export HF_TOKEN=your_huggingface_token_here
+        ```
+    </Step>
+
+    <Step title="Create a file">
+        Create a new file `app.py` with the basic setup:
+```python
+from praisonaiagents import Agent, Task, PraisonAIAgents
+from praisonaiagents.tools import cot_save, cot_upload_to_huggingface
+from pydantic import BaseModel
+import os
+
+# Define Pydantic model for structured output
+class DecisionModel(BaseModel):
+    response: str
+    decision: str
+
+def write_csv(file_path, data):
+    """Write data to CSV file."""
+    if not os.path.exists(file_path):
+        with open(file_path, 'w') as file:
+            file.write(data + '\n')
+    else:
+        with open(file_path, 'a') as file:
+            file.write(data + '\n')
+    return f"Data appended to {file_path}"
+
+def count_questions(file_path):
+    """Count lines in file."""
+    with open(file_path, 'r') as file:
+        return sum(1 for _ in file)
+
+# Create specialized agents
+qa_generator = Agent(
+    name="Generator",
+    role="Question Creator",
+    goal="Create challenging math and logic questions",
+    backstory="Expert in educational content creation",
+    llm="gpt-4o-mini",
+    tools=[write_csv, count_questions]
+)
+
+total_questions_evaluator = Agent(
+    name="TotalQuestionsEvaluator",
+    role="Total Questions Evaluator",
+    goal="Evaluate the total number of questions in qa_pairs.csv file",
+    backstory="Expert in evaluating the total number of questions in a file",
+    llm="gpt-4o-mini",
+    tools=[count_questions],
+    verbose=False
+)
+
+cot_generator = Agent(
+    name="COTGenerator",
+    role="Chain of Thought Specialist",
+    goal="Generate and manage chain of thought solutions for Q&A pairs",
+    backstory="Expert in breaking down problems and generating detailed solution steps",
+    tools=[cot_save],
+    llm="gpt-4o-mini",
+    verbose=False
+)
+
+upload_to_huggingface = Agent(
+    name="UploadToHuggingface",
+    role="Upload to Huggingface",
+    goal="Upload the generated chain of thought solutions to a Huggingface dataset",
+    backstory="Expert in saving data to Huggingface",
+    tools=[cot_upload_to_huggingface],
+    llm="gpt-4o-mini",
+    verbose=False
+)
+
+# Define tasks with workflow
+generate_task = Task(
+    description="""Generate question and answer in csv format without headers: question, answer and append to qa_pairs.csv file
+generate 10 unique questions and answers and don't repeat on the same question and answer. Reponse with 'done' when done
+with append mode as 'a'
+Example question and answer:
+question, answer
+What is the sum of numbers from 1 to 10?, 55
+Number of r's in the word strawberry, 3
+""",
+    expected_output="append to qa_pairs.csv file with questions and answers and move to next task",
+    agent=qa_generator,
+    name="generate_task",
+    is_start=True,
+    next_tasks=["evaluate_total_questions"],
+    task_type="decision",
+    condition={
+        "more": "generate_task",
+        "done": "evaluate_total_questions"
+    }
+)
+
+evaluate_total_questions_task = Task(
+    description="Evaluate the total number of questions in qa_pairs.csv file is 1",
+    expected_output="Total number of questions in qa_pairs.csv file",
+    agent=total_questions_evaluator,
+    task_type="decision",
+    name="evaluate_total_questions",
+    condition={
+        "more": "generate_task",
+        "done": "generate_cot"
+    }
+)
+
+generate_cot_task = Task(
+    name="generate_cot",
+    description="""Generate chain of thought solutions for each question in the input file. 
+Save to cot_solutions.csv file
+Don't generate chain of thought solutions again after receiving the response from Tool Call
+After calling the tool, respond with a JSON object:
+{
+    "response": "done",
+    "decision": "done"
+}
+""",
+    expected_output="done",
+    agent=cot_generator,
+    input_file="qa_pairs.csv",
+    task_type="loop",
+    next_tasks=["upload_to_huggingface"],
+    condition={
+        "done": ["upload_to_huggingface"],
+        "exit": [],
+    },
+    output_pydantic=DecisionModel  # Use Pydantic model for output validation
+)
+
+upload_to_huggingface_task = Task(
+    name="upload_to_huggingface",
+    description="""Upload to Huggingface:
+    1. Save to cot_solutions.csv
+    2. Upload to mervinpraison/cot-dataset""",
+    expected_output="Dataset published successfully",
+    agent=upload_to_huggingface,
+    tools=[cot_upload_to_huggingface]
+)
+
+# Initialize workflow
+agents = PraisonAIAgents(
+    agents=[qa_generator, total_questions_evaluator, cot_generator, upload_to_huggingface],
+    tasks=[generate_task, evaluate_total_questions_task, generate_cot_task, upload_to_huggingface_task],
+    process="workflow",
+    max_iter=30,
+    verbose=False
+)
+
+agents.start()
+```
+    </Step>
+
+    <Step title="Run the application">
+        Execute the Python script to start generating chain-of-thought data:
+        ```bash
+        python app.py
+        ```
+    </Step>
+
+</Steps>
+
+
+## Features
+
+<CardGroup cols={2}>
+  <Card title="Question Generation" icon="question">
+    Create challenging math and logic questions with answers.
+  </Card>
+  <Card title="Question Evaluation" icon="check-double">
+    Evaluate and validate generated questions for quality.
+  </Card>
+  <Card title="CoT Solutions" icon="diagram-project">
+    Generate detailed chain-of-thought solutions for each question.
+  </Card>
+  <Card title="Data Management" icon="database">
+    Save and manage generated data in structured formats.
+  </Card>
+  <Card title="HuggingFace Integration" icon="cloud-arrow-up">
+    Upload datasets directly to HuggingFace for sharing.
+  </Card>
+</CardGroup>
+
+## Understanding the Workflow
+
+<AccordionGroup>
+  <Accordion title="Key Components">
+    <CardGroup cols={2}>
+      <Card title="Question Generator" icon="robot">
+        Creates unique math and logic questions with answers. Uses `write_csv` and `count_questions` tools.
+      </Card>
+      <Card title="Questions Evaluator" icon="magnifying-glass-chart">
+        Validates the total number of generated questions. Uses `count_questions` tool.
+      </Card>
+      <Card title="CoT Generator" icon="diagram-project">
+        Produces detailed step-by-step solutions. Uses `cot_save` tool for solution management.
+      </Card>
+      <Card title="HuggingFace Uploader" icon="cloud-arrow-up">
+        Publishes datasets to HuggingFace. Uses `cot_upload_to_huggingface` tool.
+      </Card>
+    </CardGroup>
+  </Accordion>
+
+  <Accordion title="Task Types and Flow Control">
+    <Tabs>
+      <Tab title="Decision Tasks">
+        Used in question generation and evaluation phases.
+        
+        ```python Decision Task Example
+        generate_task = Task(
+            task_type="decision",
+            condition={
+                "more": "generate_task",
+                "done": "evaluate_total_questions"
+            }
+        )
+        ```
+
+        <Note>
+          Conditions determine whether to continue generating or move forward. The task can loop back to itself or proceed to the next task.
+        </Note>
+      </Tab>
+      <Tab title="Loop Tasks">
+        Used in Chain-of-Thought generation phase.
+        
+        ```python Loop Task Example
+        generate_cot_task = Task(
+            task_type="loop",
+            input_file="qa_pairs.csv",
+            output_pydantic=DecisionModel
+        )
+        ```
+
+        <Warning>
+          Always use Pydantic models for output validation in loop tasks to ensure data consistency.
+        </Warning>
+      </Tab>
+    </Tabs>
+
+    <Info>
+      Each task type serves a specific purpose in the workflow:
+      - **Decision Tasks**: Control flow and branching logic
+      - **Loop Tasks**: Process data iteratively with validation
+    </Info>
+  </Accordion>
+</AccordionGroup>
+
+## Next Steps
+
+<CardGroup>
+  <Card title="Introduction" icon="book" href="/introduction">
+    Learn more about PraisonAI and its core concepts
+  </Card>
+  <Card title="Quick Start" icon="bolt" href="/quickstart">
+    Get started with the basics of PraisonAI
+  </Card>
+</CardGroup>

docs/features/image-generation.mdx

@@ -0,0 +1,126 @@
+---
+title: "Image Generation AI Agents"
+sidebarTitle: "Image Generation"
+description: "Generate high-quality images using PraisonAI Image Agents with both synchronous and asynchronous capabilities."
+icon: "image"
+---
+
+```mermaid
+flowchart LR
+    In[Start] --> Process[Image Description]
+    Process --> Agent[Image Agent]
+    Agent --> Out[Image URL]
+    
+    style In fill:#8B0000,color:#fff
+    style Process fill:#2E8B57,color:#fff
+    style Agent fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+
+Image Generation in PraisonAI allows you to create high-quality images using natural language descriptions. The Image Agent supports both synchronous and asynchronous operations, making it flexible for various use cases.
+
+## Quick Start
+
+<Tabs>
+  <Tab title="Code">
+    <Steps>
+      <Step title="Install Package">
+        First, install the PraisonAI Agents package with LLM support:
+        ```bash
+        pip install "praisonaiagents[llm]"
+        ```
+      </Step>
+
+      <Step title="Set API Key">
+        Set your OpenAI API key as an environment variable:
+        ```bash
+        export OPENAI_API_KEY=your_api_key_here
+        ```
+      </Step>
+
+      <Step title="Create Agent">
+        Create a new file `image_gen.py` with the basic setup:
+        ```python
+        from praisonaiagents.agent.image_agent import ImageAgent
+
+        # Create an image agent
+        agent = ImageAgent(
+            llm="dall-e-3",
+            verbose=True
+        )
+
+        # Generate an image
+        result = agent.chat("A cute baby sea otter playing with a laptop")
+        print("Image generation result:", result)
+        ```
+      </Step>
+    </Steps>
+  </Tab>
+
+  <Tab title="Async">
+    <Steps>
+      <Step title="Install Package">
+        First, install the PraisonAI Agents package with LLM support:
+        ```bash
+        pip install "praisonaiagents[llm]"
+        ```
+      </Step>
+
+      <Step title="Set API Key">
+        Set your OpenAI API key as an environment variable:
+        ```bash
+        export OPENAI_API_KEY=your_api_key_here
+        ```
+      </Step>
+
+      <Step title="Create Async Agent">
+        Create a new file `image_gen_async.py` with the async setup:
+        ```python
+        import asyncio
+        from praisonaiagents import ImageAgent
+
+        async def main():
+            agent = ImageAgent(
+                name="ImageCreator",
+                llm="dall-e-3",
+                style="natural"
+            )
+
+            result = await agent.achat("A cute baby sea otter playing with a laptop")
+            print(f"Image generation result: {result}")
+
+        if __name__ == "__main__":
+            asyncio.run(main())
+        ```
+      </Step>
+    </Steps>
+  </Tab>
+</Tabs>
+
+## Features
+
+<CardGroup cols={2}>
+  <Card title="DALL-E Integration" icon="image">
+    Seamless integration with DALL-E for high-quality image generation.
+  </Card>
+  <Card title="Async Support" icon="bolt">
+    Asynchronous operations for better performance in concurrent environments.
+  </Card>
+  <Card title="Natural Style" icon="paintbrush">
+    Generate images with natural, realistic styling options.
+  </Card>
+  <Card title="Verbose Mode" icon="message">
+    Detailed output logging for better debugging and monitoring.
+  </Card>
+</CardGroup>
+
+## Next Steps
+
+<CardGroup>
+  <Card title="Agents Overview" icon="robot" href="/agents">
+    Learn more about PraisonAI Agents and their capabilities
+  </Card>
+  <Card title="API Reference" icon="code" href="/api-reference">
+    View the complete API documentation
+  </Card>
+</CardGroup>

docs/features/reasoning-extract.mdx

@@ -0,0 +1,137 @@
+---
+title: "Reasoning Extract Agents"
+description: "Learn how to create AI agents that can perform step-by-step reasoning and extract information"
+icon: "brain-circuit"
+---
+
+```mermaid
+flowchart LR
+    In[Input] --> RA[("Reasoning Agent")]
+    RA --> Steps[Reasoning Steps]
+    Steps --> SA[("Small Agent")]
+    SA --> Out[Output]
+    
+    style In fill:#8B0000,color:#fff
+    style RA fill:#2E8B57,color:#fff,shape:circle
+    style Steps fill:#4169E1,color:#fff
+    style SA fill:#2E8B57,color:#fff,shape:circle
+    style Out fill:#8B0000,color:#fff
+```
+
+A workflow where a reasoning agent breaks down complex problems into steps, followed by a smaller agent that processes these steps to provide concise answers.
+
+## Prerequisites
+
+<Steps>
+    <Step title="Install Package">
+        Install required packages:
+        ```bash
+        pip install "praisonaiagents[llm]"
+        ```
+
+        <Note>
+        praisonaiagents[llm] includes all necessary dependencies for reasoning agents
+        </Note>
+    </Step>
+
+    <Step title="Set API Key">
+        Configure your API key:
+        ```bash
+        export OPENAI_API_KEY=your_api_key_here
+        ```
+    </Step>
+
+    <Step title="Create File">
+        Create a new file called `app.py` and add the following code:
+    </Step>
+
+    <Step title="Run Application">
+        Execute the script:
+        ```bash
+        python app.py
+        ```
+    </Step>
+</Steps>
+
+## Code
+
+```python
+from praisonaiagents import Agent, Task, PraisonAIAgents
+
+reasoning_agent = Agent(
+    role="Helpful Assistant", 
+    reasoning_steps=True, 
+    llm="deepseek/deepseek-reasoner"
+)
+
+small_agent = Agent(
+    role="Helpful Assistant", 
+    llm="gpt-3.5-turbo"
+)
+
+reasoning_task = Task(
+    description="How many r's in the word 'Strawberry'?", 
+    agent=reasoning_agent
+)
+
+small_task = Task(
+    description="With the provided reasoning tell me how many r's in the word 'Strawberry'?", 
+    agent=small_agent
+)
+
+agents = PraisonAIAgents(
+    agents=[reasoning_agent, small_agent],
+    tasks=[reasoning_task, small_task]
+)
+
+agents.start()
+```
+
+## Features
+
+<CardGroup cols={2}>
+  <Card title="Step-by-Step Reasoning" icon="list-check">
+    Break down complex problems into logical steps.
+  </Card>
+  <Card title="Multi-Agent Collaboration" icon="users">
+    Combine reasoning and processing agents.
+  </Card>
+  <Card title="Flexible Models" icon="arrows-split-up-and-left">
+    Use different models for reasoning and processing.
+  </Card>
+  <Card title="Task Chaining" icon="link">
+    Connect reasoning output to processing tasks.
+  </Card>
+</CardGroup>
+
+## Understanding Reasoning Agents
+
+<Card title="What are Reasoning Agents?" icon="question">
+  Reasoning agents enable:
+  - Detailed step-by-step analysis
+  - Logical problem decomposition
+  - Clear reasoning paths
+  - Enhanced decision making
+</Card>
+
+## Troubleshooting
+
+<CardGroup cols={2}>
+  <Card title="Reasoning Issues" icon="triangle-exclamation">
+    If reasoning steps aren't clear:
+    - Check reasoning_steps parameter
+    - Verify model compatibility
+    - Review task descriptions
+  </Card>
+
+  <Card title="Agent Communication" icon="messages">
+    If agents aren't coordinating:
+    - Ensure task order is correct
+    - Check task dependencies
+    - Verify agent configurations
+  </Card>
+</CardGroup>
+
+<Note>
+  The reasoning agent uses a specialized model (deepseek-reasoner) optimized for step-by-step analysis, while the small agent can use a more general-purpose model for processing the reasoning output.
+</Note>

docs/index.mdx

@@ -1,7 +1,7 @@
 ---
 title: "Praison AI"
 sidebarTitle: "Home"
-description: "Comprehensive guide to PraisonAI - an AI Agents Framework with Self Reflection, combining PraisonAI Agents, AutoGen, and CrewAI for building multi-agent LLM systems"
+description: "PraisonAI is a production-ready Multi-AI Agents framework with self-reflection, designed to create AI Agents to automate and solve problems ranging from simple tasks to complex challenges. By integrating PraisonAI Agents, AutoGen, and CrewAI into a low-code solution, it streamlines the building and management of multi-agent LLM systems, emphasising simplicity, customisation, and effective human-agent collaboration."
 icon: "house"
 openGraph:
   url: "/"
@@ -66,24 +66,53 @@ seo:
     Internet search using Crawl4AI and Tavily
   </Card>
 </CardGroup>
-<br />
-<div className="relative w-full aspect-video overflow-hidden rounded-lg shadow-lg mb-8">
-  <iframe
-    className="absolute top-0 left-0 w-full h-full border-0"
-    src="https://www.youtube.com/embed/Fn1lQjC0GO0"
-    title="YouTube video player"
-    allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture"
-    allowFullScreen
-    style={{
-      maxWidth: '100vw',
-      margin: '0 auto'
-    }}
-  ></iframe>
-</div>
 
-## Installation Options
+## Install
 
 <Tabs>
+  <Tab title="Code">
+    <Steps>
+      <Step title="Install Package">
+        ```bash
+        pip install praisonaiagents
+        ```
+      </Step>
+      <Step title="Set API Key">
+        ```bash
+        export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx
+        ```
+      </Step>
+      <Step title="Create File">
+        Create `app.py` file
+
+        ## Code Example
+
+<CodeGroup>
+```python Single Agent
+from praisonaiagents import Agent
+
+agent = Agent(instructions="Your are a helpful AI assistant")
+agent.start("Write a movie script about a robot in Mars")
+```
+
+```python Multi Agents
+from praisonaiagents import Agent, PraisonAIAgents
+
+research_agent = Agent(instructions="Research about AI")
+summarise_agent = Agent(instructions="Summarise research agent's findings")
+
+agents = PraisonAIAgents(agents=[research_agent, summarise_agent])
+agents.start()
+```
+</CodeGroup>
+      </Step>
+      <Step title="Run Script">
+        ```bash
+        python app.py
+        ```
+      </Step>
+    </Steps>
+  </Tab>
   <Tab title="No Code">
     <Tip>
         PraisonAI combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customization, and efficient human-agent collaboration.
@@ -109,11 +138,11 @@ seo:
       </Step>
     </Steps>
   </Tab>
-  <Tab title="Code">
+  <Tab title="JavaScript">
     <Steps>
       <Step title="Install Package">
         ```bash
-        pip install praisonaiagents
+        npm install praisonai
         ```
       </Step>
       <Step title="Set API Key">
@@ -122,102 +151,390 @@ seo:
         ```
       </Step>
       <Step title="Create File">
-        Create `app.py` file
+        Create `app.js` file
 
         ## Code Example
 
 <CodeGroup>
-  ```python Basic
-  from praisonaiagents import Agent, Task, PraisonAIAgents
+```javascript Single Agent
+const { Agent } = require('praisonai');
+const agent = new Agent({ instructions: 'You are a helpful AI assistant' });
+agent.start('Write a movie script about a robot in Mars');
+```
 
-  # Create an agent
-  researcher = Agent(
-      name="Researcher",
-      role="Senior Research Analyst",
-      goal="Uncover cutting-edge developments in AI",
-      backstory="You are an expert at a technology research group",
-      verbose=True,
-      llm="gpt-4o"
-  )
+```javascript Multi Agents
+const { Agent, PraisonAIAgents } = require('praisonai');
 
-  # Define a task
-  task = Task(
-      name="research_task",
-      description="Analyze 2024's AI advancements",
-      expected_output="A detailed report",
-      agent=researcher
-  )
+const researchAgent = new Agent({ instructions: 'Research about AI' });
+const summariseAgent = new Agent({ instructions: 'Summarise research agent\'s findings' });
 
-  # Run the agents
-  agents = PraisonAIAgents(
-      agents=[researcher],
-      tasks=[task],
-      verbose=False
-  )
-
-  result = agents.start()
-  ```
-
-  ```python Advanced
-  from praisonaiagents import Agent, Task, PraisonAIAgents
-
-  # Create multiple agents
-  researcher = Agent(
-      name="Researcher",
-      role="Senior Research Analyst",
-      goal="Uncover cutting-edge developments in AI",
-      backstory="You are an expert at a technology research group",
-      verbose=True,
-      llm="gpt-4o",
-      markdown=True
-  )
-
-  writer = Agent(
-      name="Writer",
-      role="Tech Content Strategist",
-      goal="Craft compelling content on tech advancements",
-      backstory="You are a content strategist",
-      llm="gpt-4o",
-      markdown=True
-  )
-
-  # Define multiple tasks
-  task1 = Task(
-      name="research_task",
-      description="Analyze 2024's AI advancements",
-      expected_output="A detailed report",
-      agent=researcher
-  )
-
-  task2 = Task(
-      name="writing_task",
-      description="Create a blog post about AI advancements",
-      expected_output="A blog post",
-      agent=writer
-  )
-
-  # Run with hierarchical process
-  agents = PraisonAIAgents(
-      agents=[researcher, writer],
-      tasks=[task1, task2],
-      verbose=False,
-      process="hierarchical",
-      manager_llm="gpt-4o"
-  )
-
-  result = agents.start()
-  ```
+const agents = new PraisonAIAgents({ agents: [researchAgent, summariseAgent] });
+agents.start();
+```
 </CodeGroup>
       </Step>
       <Step title="Run Script">
         ```bash
-        python app.py
+        node app.js
         ```
       </Step>
     </Steps>
   </Tab>
 </Tabs>
 
+## AI Agents Flow
+
+```mermaid
+graph LR
+    %% Define the main flow
+    Start([▶ Start]) --> Agent1
+    Agent1 --> Process[⚙ Process]
+    Process --> Agent2
+    Agent2 --> Output([✓ Output])
+    Process -.-> Agent1
+    
+    %% Define subgraphs for agents and their tasks
+    subgraph Agent1[ ]
+        Task1[📋 Task]
+        AgentIcon1[🤖 AI Agent]
+        Tools1[🔧 Tools]
+        
+        Task1 --- AgentIcon1
+        AgentIcon1 --- Tools1
+    end
+    
+    subgraph Agent2[ ]
+        Task2[📋 Task]
+        AgentIcon2[🤖 AI Agent]
+        Tools2[🔧 Tools]
+        
+        Task2 --- AgentIcon2
+        AgentIcon2 --- Tools2
+    end
+
+    classDef input fill:#8B0000,stroke:#7C90A0,color:#fff
+    classDef process fill:#189AB4,stroke:#7C90A0,color:#fff
+    classDef tools fill:#2E8B57,stroke:#7C90A0,color:#fff
+    classDef transparent fill:none,stroke:none
+
+    class Start,Output,Task1,Task2 input
+    class Process,AgentIcon1,AgentIcon2 process
+    class Tools1,Tools2 tools
+    class Agent1,Agent2 transparent
+```
+
+## AI Agents with Tools
+
+Create AI agents that can use tools to interact with external systems and perform actions.
+
+```mermaid
+flowchart TB
+    subgraph Tools
+        direction TB
+        T3[Internet Search]
+        T1[Code Execution]
+        T2[Formatting]
+    end
+
+    Input[Input] ---> Agents
+    subgraph Agents
+        direction LR
+        A1[Agent 1]
+        A2[Agent 2]
+        A3[Agent 3]
+    end
+    Agents ---> Output[Output]
+
+    T3 --> A1
+    T1 --> A2
+    T2 --> A3
+
+    style Tools fill:#189AB4,color:#fff
+    style Agents fill:#8B0000,color:#fff
+    style Input fill:#8B0000,color:#fff
+    style Output fill:#8B0000,color:#fff
+```
+
+## AI Agents with Memory
+
+Create AI agents with memory capabilities for maintaining context and information across tasks.
+
+```mermaid
+flowchart TB
+    subgraph Memory
+        direction TB
+        STM[Short Term]
+        LTM[Long Term]
+    end
+
+    subgraph Store
+        direction TB
+        DB[(Vector DB)]
+    end
+
+    Input[Input] ---> Agents
+    subgraph Agents
+        direction LR
+        A1[Agent 1]
+        A2[Agent 2]
+        A3[Agent 3]
+    end
+    Agents ---> Output[Output]
+
+    Memory <--> Store
+    Store <--> A1
+    Store <--> A2
+    Store <--> A3
+
+    style Memory fill:#189AB4,color:#fff
+    style Store fill:#2E8B57,color:#fff
+    style Agents fill:#8B0000,color:#fff
+    style Input fill:#8B0000,color:#fff
+    style Output fill:#8B0000,color:#fff
+```
+
+## AI Agents with Different Processes
+
+### Sequential Process
+
+The simplest form of task execution where tasks are performed one after another.
+
+```mermaid
+graph LR
+    Input[Input] --> A1
+    subgraph Agents
+        direction LR
+        A1[Agent 1] --> A2[Agent 2] --> A3[Agent 3]
+    end
+    A3 --> Output[Output]
+
+    classDef input fill:#8B0000,stroke:#7C90A0,color:#fff
+    classDef process fill:#189AB4,stroke:#7C90A0,color:#fff
+    classDef transparent fill:none,stroke:none
+
+    class Input,Output input
+    class A1,A2,A3 process
+    class Agents transparent
+```
+
+### Hierarchical Process
+
+Uses a manager agent to coordinate task execution and agent assignments.
+
+```mermaid
+graph TB
+    Input[Input] --> Manager
+    
+    subgraph Agents
+        Manager[Manager Agent]
+        
+        subgraph Workers
+            direction LR
+            W1[Worker 1]
+            W2[Worker 2]
+            W3[Worker 3]
+        end
+        
+        Manager --> W1
+        Manager --> W2
+        Manager --> W3
+    end
+    
+    W1 --> Manager
+    W2 --> Manager
+    W3 --> Manager
+    Manager --> Output[Output]
+
+    classDef input fill:#8B0000,stroke:#7C90A0,color:#fff
+    classDef process fill:#189AB4,stroke:#7C90A0,color:#fff
+    classDef transparent fill:none,stroke:none
+
+    class Input,Output input
+    class Manager,W1,W2,W3 process
+    class Agents,Workers transparent
+```
+
+### Workflow Process
+
+Advanced process type supporting complex task relationships and conditional execution.
+
+```mermaid
+graph LR
+    Input[Input] --> Start
+    
+    subgraph Workflow
+        direction LR
+        Start[Start] --> C1{Condition}
+        C1 --> |Yes| A1[Agent 1]
+        C1 --> |No| A2[Agent 2]
+        A1 --> Join
+        A2 --> Join
+        Join --> A3[Agent 3]
+    end
+    
+    A3 --> Output[Output]
+
+    classDef input fill:#8B0000,stroke:#7C90A0,color:#fff
+    classDef process fill:#189AB4,stroke:#7C90A0,color:#fff
+    classDef decision fill:#2E8B57,stroke:#7C90A0,color:#fff
+    classDef transparent fill:none,stroke:none
+
+    class Input,Output input
+    class Start,A1,A2,A3,Join process
+    class C1 decision
+    class Workflow transparent
+```
+
+#### Agentic Routing Workflow
+
+Create AI agents that can dynamically route tasks to specialized LLM instances.
+
+```mermaid
+flowchart LR
+    In[In] --> Router[LLM Call Router]
+    Router --> LLM1[LLM Call 1]
+    Router --> LLM2[LLM Call 2]
+    Router --> LLM3[LLM Call 3]
+    LLM1 --> Out[Out]
+    LLM2 --> Out
+    LLM3 --> Out
+    
+    style In fill:#8B0000,color:#fff
+    style Router fill:#2E8B57,color:#fff
+    style LLM1 fill:#2E8B57,color:#fff
+    style LLM2 fill:#2E8B57,color:#fff
+    style LLM3 fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+
+#### Agentic Orchestrator Worker
+
+Create AI agents that orchestrate and distribute tasks among specialized workers.
+
+```mermaid
+flowchart LR
+    In[In] --> Router[LLM Call Router]
+    Router --> LLM1[LLM Call 1]
+    Router --> LLM2[LLM Call 2]
+    Router --> LLM3[LLM Call 3]
+    LLM1 --> Synthesizer[Synthesizer]
+    LLM2 --> Synthesizer
+    LLM3 --> Synthesizer
+    Synthesizer --> Out[Out]
+    
+    style In fill:#8B0000,color:#fff
+    style Router fill:#2E8B57,color:#fff
+    style LLM1 fill:#2E8B57,color:#fff
+    style LLM2 fill:#2E8B57,color:#fff
+    style LLM3 fill:#2E8B57,color:#fff
+    style Synthesizer fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+
+#### Agentic Autonomous Workflow
+
+Create AI agents that can autonomously monitor, act, and adapt based on environment feedback.
+
+```mermaid
+flowchart LR
+    Human[Human] <--> LLM[LLM Call]
+    LLM -->|ACTION| Environment[Environment]
+    Environment -->|FEEDBACK| LLM
+    LLM --> Stop[Stop]
+    
+    style Human fill:#8B0000,color:#fff
+    style LLM fill:#2E8B57,color:#fff
+    style Environment fill:#8B0000,color:#fff
+    style Stop fill:#333,color:#fff
+```
+
+#### Agentic Parallelization
+
+Create AI agents that can execute tasks in parallel for improved performance.
+
+```mermaid
+flowchart LR
+    In[In] --> LLM2[LLM Call 2]
+    In --> LLM1[LLM Call 1]
+    In --> LLM3[LLM Call 3]
+    LLM1 --> Aggregator[Aggregator]
+    LLM2 --> Aggregator
+    LLM3 --> Aggregator
+    Aggregator --> Out[Out]
+    
+    style In fill:#8B0000,color:#fff
+    style LLM1 fill:#2E8B57,color:#fff
+    style LLM2 fill:#2E8B57,color:#fff
+    style LLM3 fill:#2E8B57,color:#fff
+    style Aggregator fill:#fff,color:#000
+    style Out fill:#8B0000,color:#fff
+```
+
+#### Agentic Prompt Chaining
+
+Create AI agents with sequential prompt chaining for complex workflows.
+
+```mermaid
+flowchart LR
+    In[In] --> LLM1[LLM Call 1] --> Gate{Gate}
+    Gate -->|Pass| LLM2[LLM Call 2] -->|Output 2| LLM3[LLM Call 3] --> Out[Out]
+    Gate -->|Fail| Exit[Exit]
+    
+    style In fill:#8B0000,color:#fff
+    style LLM1 fill:#2E8B57,color:#fff
+    style LLM2 fill:#2E8B57,color:#fff
+    style LLM3 fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+    style Exit fill:#8B0000,color:#fff
+```
+
+#### Agentic Evaluator Optimizer
+
+Create AI agents that can generate and optimize solutions through iterative feedback.
+
+```mermaid
+flowchart LR
+    In[In] --> Generator[LLM Call Generator] 
+    Generator -->|SOLUTION| Evaluator[LLM Call Evaluator] -->|ACCEPTED| Out[Out]
+    Evaluator -->|REJECTED + FEEDBACK| Generator
+    
+    style In fill:#8B0000,color:#fff
+    style Generator fill:#2E8B57,color:#fff
+    style Evaluator fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+
+#### Repetitive Agents
+
+Create AI agents that can efficiently handle repetitive tasks through automated loops.
+
+```mermaid
+flowchart LR
+    In[Input] --> LoopAgent[("Looping Agent")]
+    LoopAgent --> Task[Task]
+    Task --> |Next iteration| LoopAgent
+    Task --> |Done| Out[Output]
+    
+    style In fill:#8B0000,color:#fff
+    style LoopAgent fill:#2E8B57,color:#fff,shape:circle
+    style Task fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+<br />
+<div className="relative w-full aspect-video overflow-hidden rounded-lg shadow-lg mb-8">
+  <iframe
+    className="absolute top-0 left-0 w-full h-full border-0"
+    src="https://www.youtube.com/embed/Fn1lQjC0GO0"
+    title="YouTube video player"
+    allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture"
+    allowFullScreen
+    style={{
+      maxWidth: '100vw',
+      margin: '0 auto'
+    }}
+  ></iframe>
+</div>
+
 ## Integration Options
 
 <AccordionGroup>
@@ -338,4 +655,31 @@ seo:
   <div className="hover:opacity-80 transition-opacity">
     <img src="https://img.shields.io/github/forks/MervinPraison/PraisonAI?style=social" alt="GitHub Forks" />
   </div>
-</div>
+</div>
+
+## Video Tutorials
+
+| Topic | Video |
+|-------|--------|
+| AI Agents with Self Reflection | [![Self Reflection](https://img.youtube.com/vi/vLXobEN2Vc8/0.jpg)](https://www.youtube.com/watch?v=vLXobEN2Vc8) |
+| Reasoning Data Generating Agent | [![Reasoning Data](https://img.youtube.com/vi/fUT332Y2zA8/0.jpg)](https://www.youtube.com/watch?v=fUT332Y2zA8) |
+| AI Agents with Reasoning | [![Reasoning](https://img.youtube.com/vi/KNDVWGN3TpM/0.jpg)](https://www.youtube.com/watch?v=KNDVWGN3TpM) |
+| Multimodal AI Agents | [![Multimodal](https://img.youtube.com/vi/hjAWmUT1qqY/0.jpg)](https://www.youtube.com/watch?v=hjAWmUT1qqY) |
+| AI Agents Workflow | [![Workflow](https://img.youtube.com/vi/yWTH44QPl2A/0.jpg)](https://www.youtube.com/watch?v=yWTH44QPl2A) |
+| Async AI Agents | [![Async](https://img.youtube.com/vi/VhVQfgo00LE/0.jpg)](https://www.youtube.com/watch?v=VhVQfgo00LE) |
+| Mini AI Agents | [![Mini](https://img.youtube.com/vi/OkvYp5aAGSg/0.jpg)](https://www.youtube.com/watch?v=OkvYp5aAGSg) |
+| AI Agents with Memory | [![Memory](https://img.youtube.com/vi/1hVfVxvPnnQ/0.jpg)](https://www.youtube.com/watch?v=1hVfVxvPnnQ) |
+| Repetitive Agents | [![Repetitive](https://img.youtube.com/vi/dAYGxsjDOPg/0.jpg)](https://www.youtube.com/watch?v=dAYGxsjDOPg) |
+| Introduction | [![Introduction](https://img.youtube.com/vi/Fn1lQjC0GO0/0.jpg)](https://www.youtube.com/watch?v=Fn1lQjC0GO0) |
+| Tools Overview | [![Tools Overview](https://img.youtube.com/vi/XaQRgRpV7jo/0.jpg)](https://www.youtube.com/watch?v=XaQRgRpV7jo) |
+| Custom Tools | [![Custom Tools](https://img.youtube.com/vi/JSU2Rndh06c/0.jpg)](https://www.youtube.com/watch?v=JSU2Rndh06c) |
+| Firecrawl Integration | [![Firecrawl](https://img.youtube.com/vi/UoqUDcLcOYo/0.jpg)](https://www.youtube.com/watch?v=UoqUDcLcOYo) |
+| User Interface | [![UI](https://img.youtube.com/vi/tg-ZjNl3OCg/0.jpg)](https://www.youtube.com/watch?v=tg-ZjNl3OCg) |
+| Crawl4AI Integration | [![Crawl4AI](https://img.youtube.com/vi/KAvuVUh0XU8/0.jpg)](https://www.youtube.com/watch?v=KAvuVUh0XU8) |
+| Chat Interface | [![Chat](https://img.youtube.com/vi/sw3uDqn2h1Y/0.jpg)](https://www.youtube.com/watch?v=sw3uDqn2h1Y) |
+| Code Interface | [![Code](https://img.youtube.com/vi/_5jQayO-MQY/0.jpg)](https://www.youtube.com/watch?v=_5jQayO-MQY) |
+| Mem0 Integration | [![Mem0](https://img.youtube.com/vi/KIGSgRxf1cY/0.jpg)](https://www.youtube.com/watch?v=KIGSgRxf1cY) |
+| Training | [![Training](https://img.youtube.com/vi/aLawE8kwCrI/0.jpg)](https://www.youtube.com/watch?v=aLawE8kwCrI) |
+| Realtime Voice Interface | [![Realtime](https://img.youtube.com/vi/frRHfevTCSw/0.jpg)](https://www.youtube.com/watch?v=frRHfevTCSw) |
+| Call Interface | [![Call](https://img.youtube.com/vi/m1cwrUG2iAk/0.jpg)](https://www.youtube.com/watch?v=m1cwrUG2iAk) |
+| Reasoning Extract Agents | [![Reasoning Extract](https://img.youtube.com/vi/2PPamsADjJA/0.jpg)](https://www.youtube.com/watch?v=2PPamsADjJA) |

docs/installation.mdx

@@ -11,6 +11,9 @@ pip install praisonaiagents
 ```bash No Code
 pip install praisonai
 ```
+```bash JavaScript
+npm install praisonai
+```
 </RequestExample>
 
 <Note>
@@ -90,6 +93,22 @@ Follow these steps to set up PraisonAI in your development environment.
         </Step>
     </Steps>
   </Tab>
+  <Tab title="JavaScript">
+    <Steps>
+        <Step title="Install PraisonAI">
+            Install the PraisonAI package:
+            ```bash
+            npm install praisonai
+            ```
+        </Step>
+        <Step title="Set API Key">
+            Set your OpenAI API key as an environment variable in your terminal:
+            ```bash
+            export OPENAI_API_KEY=your_openai_key
+            ```
+        </Step>
+    </Steps>
+  </Tab>
 </Tabs>
 
 Generate your OpenAI API key from [OpenAI](https://platform.openai.com/api-keys)

docs/introduction.mdx

@@ -89,143 +89,163 @@ graph LR
 ## Getting Started is Easy
 <Tabs>
   <Tab title="Code">
-<Steps>
+    <Steps>
+      <Step title="Install Package">
+        Install the PraisonAI Agents package:
+        ```bash
+        pip install praisonaiagents
+        ```
+      </Step>
 
-  <Step title="Install PraisonAI">
-    Install the core package:
-    ```bash Terminal
-    pip install praisonaiagents
-    ```
-  </Step>
+      <Step title="Set API Key">
+        ```bash
+        export OPENAI_API_KEY=your_openai_key
+        ```
+        Generate your OpenAI API key from [OpenAI](https://platform.openai.com/api-keys).
+        Use other LLM providers like Ollama, Anthropic, Groq, Google, etc. Please refer to the [Models](/models) for more information.
+      </Step>
 
-  <Step title="Configure Environment">
-    ```bash Terminal
-    export OPENAI_API_KEY=your_openai_key
-    ```
-    Generate your OpenAI API key from [OpenAI](https://platform.openai.com/api-keys)
-    Use other LLM providers like Ollama, Anthropic, Groq, Google, etc. Please refer to the [Models](/models) for more information.
-  </Step>
+      <Step title="Create Agents">
+        Create `app.py`:
+    <CodeGroup>
+      ```python Single Agent
+      from praisonaiagents import Agent, PraisonAIAgents
 
-  <Step title="Create Agent">
-    Create `app.py`:
-<CodeGroup>
-  ```python Single Agent
-  from praisonaiagents import Agent, Task, PraisonAIAgents
+      # Create a simple agent
+      summarise_agent = Agent(instructions="Summarise Photosynthesis")
 
-  # Create an agent
-  researcher = Agent(
-      name="Researcher",
-      role="Senior Research Analyst",
-      goal="Uncover cutting-edge developments in AI",
-      backstory="You are an expert at a technology research group",
-      verbose=True,
-      llm="gpt-4o"
-  )
+      # Run the agent
+      agents = PraisonAIAgents(agents=[summarise_agent])
+      agents.start()
+      ```
 
-  # Define a task
-  task = Task(
-      name="research_task",
-      description="Analyze 2024's AI advancements",
-      expected_output="A detailed report",
-      agent=researcher
-  )
+      ```python Multiple Agents
+      from praisonaiagents import Agent, PraisonAIAgents
 
-  # Run the agents
-  agents = PraisonAIAgents(
-      agents=[researcher],
-      tasks=[task],
-      verbose=False
-  )
+      # Create agents with specific roles
+      diet_agent = Agent(
+          instructions="Give me 5 healthy food recipes",
+      )
 
-  result = agents.start()
-  ```
+      blog_agent = Agent(
+          instructions="Write a blog post about the food recipes",
+      )
 
-  ```python Multiple Agents
-  from praisonaiagents import Agent, Task, PraisonAIAgents
+      # Run multiple agents
+      agents = PraisonAIAgents(agents=[diet_agent, blog_agent])
+      agents.start()
+      ```
+    </CodeGroup>
+      </Step>
 
-  # Create multiple agents
-  researcher = Agent(
-      name="Researcher",
-      role="Senior Research Analyst",
-      goal="Uncover cutting-edge developments in AI",
-      backstory="You are an expert at a technology research group",
-      verbose=True,
-      llm="gpt-4o",
-      markdown=True
-  )
+      <Step title="Run Agents">
+        Execute your script:
+        ```bash
+        python app.py
+        ```
 
-  writer = Agent(
-      name="Writer",
-      role="Tech Content Strategist",
-      goal="Craft compelling content on tech advancements",
-      backstory="You are a content strategist",
-      llm="gpt-4o",
-      markdown=True
-  )
-
-  # Define multiple tasks
-  task1 = Task(
-      name="research_task",
-      description="Analyze 2024's AI advancements",
-      expected_output="A detailed report",
-      agent=researcher
-  )
-
-  task2 = Task(
-      name="writing_task",
-      description="Create a blog post about AI advancements",
-      expected_output="A blog post",
-      agent=writer
-  )
-
-  # Run with hierarchical process
-  agents = PraisonAIAgents(
-      agents=[researcher, writer],
-      tasks=[task1, task2],
-      verbose=False,
-      process="hierarchical",
-      manager_llm="gpt-4o"
-  )
-
-  result = agents.start()
-  ```
-</CodeGroup>
-  </Step>
-
-  <Step title="Start Agents">
-    Execute your script:
-    ```bash Terminal
-    python app.py
-    ```
-  </Step>
-</Steps>
-</Tab>
+        You'll see:
+        - Agent initialization
+        - Task execution progress
+        - Final results
 
+        <Tip>
+        You have successfully CreatedAI Agents and made them work for you!
+        </Tip>
+      </Step>
+    </Steps>
+  </Tab>
   <Tab title="No Code">
     <Steps>
+      <Step title="Install Package">
+        Install the No Code PraisonAI Package:
+        ```bash
+        pip install praisonaiagents
+        ```
+      </Step>
 
-        <Step title="Install PraisonAI">
-            Install the PraisonAI package:
-            ```bash
-            pip install praisonai
-            ```
-        </Step>
+      <Step title="Set API Key">
+        ```bash
+        export OPENAI_API_KEY=your_openai_key
+        ```
+      </Step>
 
-        <Step title="Set API Key">
-            Set your OpenAI API key as an environment variable in your terminal:
-            ```bash Terminal
-            export OPENAI_API_KEY=your_openai_key
-            ```
-            Generate your OpenAI API key from [OpenAI](https://platform.openai.com/api-keys)
-            Use other LLM providers like Ollama, Anthropic, Groq, Google, etc. Please refer to the [Models](/models) for more information.
-        </Step>
+      <Step title="Create Config">
+        Create `agents.yaml`:
 
-        <Step title="Start AutoAgents">    
-            Run your AutoAgents:
-            ```bash
-            praisonai --auto "Create a movie script about a robot in Mars"
-            ```
-        </Step>
+    <CodeGroup>
+      ```yaml Single Agent
+      roles:
+        summarise_agent:
+          instructions: Summarise Photosynthesis
+      ```
+
+      ```yaml Multiple Agents
+      roles:
+        diet_agent:
+          instructions: Give me 5 healthy food recipes
+        blog_agent:
+          instructions: Write a blog post about the food recipes
+      ```
+    </CodeGroup>
+
+<Note>
+You can automatically create `agents.yaml` using:
+```bash
+praisonai --init "your task description"
+```
+</Note>
+
+      </Step>
+
+      <Step title="Run Agents">
+        Execute your config:
+        ```bash
+        praisonai agents.yaml
+        ```
+      </Step>
+    </Steps>
+  </Tab>
+  <Tab title="JavaScript">
+    <Steps>
+      <Step title="Install Package">
+        ```bash
+        npm install praisonai
+        ```
+      </Step>
+      <Step title="Set API Key">
+        ```bash
+        export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx
+        ```
+      </Step>
+      <Step title="Create File">
+        Create `app.js` file
+
+        ## Code Example
+
+<CodeGroup>
+```javascript Single Agent
+const { Agent } = require('praisonai');
+const agent = new Agent({ instructions: 'You are a helpful AI assistant' });
+agent.start('Write a movie script about a robot in Mars');
+```
+
+```javascript Multi Agents
+const { Agent, PraisonAIAgents } = require('praisonai');
+
+const researchAgent = new Agent({ instructions: 'Research about AI' });
+const summariseAgent = new Agent({ instructions: 'Summarise research agent\'s findings' });
+
+const agents = new PraisonAIAgents({ agents: [researchAgent, summariseAgent] });
+agents.start();
+```
+</CodeGroup>
+      </Step>
+      <Step title="Run Script">
+        ```bash
+        node app.js
+        ```
+      </Step>
     </Steps>
   </Tab>
 </Tabs>

docs/js/development.mdx

@@ -0,0 +1,38 @@
+---
+title: "Development Setup"
+sidebarTitle: "Development"
+description: "Set up your development environment for PraisonAI JavaScript framework"
+icon: "code"
+---
+
+## Development Setup
+
+<Steps>
+  <Step title="Clone Repository">
+    ```bash
+    git clone https://github.com/MervinPraison/PraisonAI.git
+    cd src/praisonai-ts
+    ```
+  </Step>
+
+  <Step title="Install Dependencies">
+    ```bash
+    npm install
+    ```
+  </Step>
+
+  <Step title="Build Package">
+    ```bash
+    npm run build
+    ```
+  </Step>
+</Steps>
+
+## Package Structure
+
+```
+src/
+├── agent/         # Agent-related interfaces and implementations
+├── task/          # Task management and execution
+├── utils/         # Utility functions and helpers
+└── types/         # TypeScript type definitions

docs/js/js.mdx

@@ -0,0 +1,214 @@
+---
+title: "JavaScript AI Agents Framework"
+sidebarTitle: "JavaScript Agents"
+description: "A production-ready Multi AI Agents framework for JavaScript"
+icon: "js"
+---
+
+PraisonAI is a production-ready Multi AI Agents framework for JavaScript, designed to create AI Agents to automate and solve problems ranging from simple tasks to complex challenges. It provides a low-code solution to streamline the building and management of multi-agent LLM systems, emphasising simplicity, customisation, and effective human-agent collaboration.
+
+```mermaid
+graph LR
+    %% Define the main flow
+    Start([▶ Start]) --> Agent1
+    Agent1 --> Process[⚙ Process]
+    Process --> Agent2
+    Agent2 --> Output([✓ Output])
+    Process -.-> Agent1
+    
+    %% Define subgraphs for agents and their tasks
+    subgraph Agent1[ ]
+        Task1[📋 Task]
+        AgentIcon1[🤖 AI Agent]
+        Tools1[🔧 Tools]
+        
+        Task1 --- AgentIcon1
+        AgentIcon1 --- Tools1
+    end
+    
+    subgraph Agent2[ ]
+        Task2[📋 Task]
+        AgentIcon2[🤖 AI Agent]
+        Tools2[🔧 Tools]
+        
+        Task2 --- AgentIcon2
+        AgentIcon2 --- Tools2
+    end
+
+    classDef input fill:#8B0000,stroke:#7C90A0,color:#fff
+    classDef process fill:#189AB4,stroke:#7C90A0,color:#fff
+    classDef tools fill:#2E8B57,stroke:#7C90A0,color:#fff
+    classDef transparent fill:none,stroke:none
+
+    class Start,Output,Task1,Task2 input
+    class Process,AgentIcon1,AgentIcon2 process
+    class Tools1,Tools2 tools
+    class Agent1,Agent2 transparent
+```
+
+<Tabs>
+<Tab title="JavaScript">
+    <Steps>
+      <Step title="Install Package">
+        <CodeGroup>
+        ```bash npm
+        npm install praisonai
+        ```
+        ```bash yarn
+        yarn add praisonai
+        ```
+        </CodeGroup>
+      </Step>
+      <Step title="Set API Key">
+        ```bash
+        export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx
+        ```
+      </Step>
+      <Step title="Create File">
+        Create `app.js` file
+
+        ## Code Example
+
+<CodeGroup>
+```javascript Single Agent
+const { Agent } = require('praisonai');
+const agent = new Agent({ instructions: 'You are a helpful AI assistant' });
+agent.start('Write a movie script about a robot in Mars');
+```
+
+```javascript Multi Agents
+const { Agent, PraisonAIAgents } = require('praisonai');
+
+const researchAgent = new Agent({ instructions: 'Research about AI' });
+const summariseAgent = new Agent({ instructions: 'Summarise research agent\'s findings' });
+
+const agents = new PraisonAIAgents({ agents: [researchAgent, summariseAgent] });
+agents.start();
+```
+</CodeGroup>
+      </Step>
+      <Step title="Run Script">
+        ```bash
+        node app.js
+        ```
+      </Step>
+    </Steps>
+  </Tab>
+</Tabs>
+## Usage Examples
+
+<AccordionGroup>
+  <Accordion title="Single Agent Example" icon="user" defaultOpen>
+    Create and run a single agent to perform a specific task:
+
+```javascript
+const { Agent } = require('praisonai');
+
+// Create a simple science explainer agent
+const agent = new Agent({
+  instructions: "You are a science expert who explains complex phenomena in simple terms.",
+  name: "ScienceExplainer",
+  verbose: true
+});
+
+// Ask a question
+agent.start("Why is the sky blue?")
+  .then(response => {
+    console.log('\nExplanation:');
+    console.log(response);
+  })
+  .catch(error => console.error('Error:', error));
+
+```
+  </Accordion>
+
+  <Accordion title="Multi-Agent Example" icon="users" defaultOpen>
+    Create and run multiple agents working together:
+
+```javascript
+const { PraisonAIAgents, Agent } = require('praisonai');
+
+// Create a story agent and a summary agent
+const storyAgent = new Agent({
+  instructions: "You are a creative storyteller. Create engaging stories.",
+  name: "Storyteller"
+});
+
+const summaryAgent = new Agent({
+  instructions: "You summarize stories into brief, engaging summaries.",
+  name: "Summarizer"
+});
+
+// Create multi-agent system
+const agents = new PraisonAIAgents({
+  agents: [storyAgent, summaryAgent],
+  tasks: [
+    "Create a short story about a magical forest",
+    "Summarize the story in 2 sentences"
+  ]
+});
+
+// Run the agents
+agents.start()
+  .then(responses => {
+    console.log('\nStory:');
+    console.log(responses[0]);
+    console.log('\nSummary:');
+    console.log(responses[1]);
+  })
+  .catch(error => console.error('Error:', error));
+```
+  </Accordion>
+
+  <Accordion title="Task-Based Agent Example" icon="list-check" defaultOpen>
+    Create agents with specific tasks and dependencies:
+
+```javascript
+const { Agent, Task } = require('praisonai');
+
+// Create a task-based agent
+const agent = new Agent({
+  name: "TaskMaster",
+  role: "Assistant",
+  goal: "Complete tasks efficiently",
+  backstory: "You are an AI assistant that helps complete tasks step by step."
+});
+
+// Create a task with dependencies
+const mainTask = new Task({
+  name: "Write Blog Post",
+  description: "Write a blog post about artificial intelligence",
+  expected_output: "A complete blog post",
+  dependencies: []
+});
+
+// Execute the task
+agent.execute(mainTask)
+  .then(response => {
+    console.log('\nBlog Post:');
+    console.log(response);
+  })
+  .catch(error => console.error('Error:', error));
+```
+  </Accordion>
+</AccordionGroup>
+
+## Running the Examples
+
+<Steps>
+  <Step title="Set Environment Variables">
+    ```bash
+    export OPENAI_API_KEY='your-api-key'
+    ```
+  </Step>
+
+  <Step title="Create Example File">
+    Create a new JavaScript file (e.g., `app.js`) with any of the above examples.
+  </Step>
+
+  <Step title="Run the Example">
+    ```bash
+    node app.js
+    ```
+  </Step>
+</Steps>

docs/js/nodejs.mdx

@@ -0,0 +1,251 @@
+---
+title: "Node.js AI Agents Framework"
+sidebarTitle: "Node.js Agents"
+description: "A production-ready Multi AI Agents framework for Node.js"
+icon: "node-js"
+---
+
+PraisonAI is a production-ready Multi AI Agents framework for Node.js, designed to create AI Agents to automate and solve problems ranging from simple tasks to complex challenges. It provides a low-code solution to streamline the building and management of multi-agent LLM systems, emphasising simplicity, customisation, and effective human-agent collaboration.
+
+```mermaid
+graph LR
+    %% Define the main flow
+    Start([▶ Start]) --> Agent1
+    Agent1 --> Process[⚙ Process]
+    Process --> Agent2
+    Agent2 --> Output([✓ Output])
+    Process -.-> Agent1
+    
+    %% Define subgraphs for agents and their tasks
+    subgraph Agent1[ ]
+        Task1[📋 Task]
+        AgentIcon1[🤖 AI Agent]
+        Tools1[🔧 Tools]
+        
+        Task1 --- AgentIcon1
+        AgentIcon1 --- Tools1
+    end
+    
+    subgraph Agent2[ ]
+        Task2[📋 Task]
+        AgentIcon2[🤖 AI Agent]
+        Tools2[🔧 Tools]
+        
+        Task2 --- AgentIcon2
+        AgentIcon2 --- Tools2
+    end
+
+    classDef input fill:#8B0000,stroke:#7C90A0,color:#fff
+    classDef process fill:#189AB4,stroke:#7C90A0,color:#fff
+    classDef tools fill:#2E8B57,stroke:#7C90A0,color:#fff
+    classDef transparent fill:none,stroke:none
+
+    class Start,Output,Task1,Task2 input
+    class Process,AgentIcon1,AgentIcon2 process
+    class Tools1,Tools2 tools
+    class Agent1,Agent2 transparent
+```
+
+<Tabs>
+<Tab title="Node.js">
+    <Steps>
+      <Step title="Install Package">
+        <CodeGroup>
+        ```bash npm
+        npm install praisonai
+        ```
+        ```bash yarn
+        yarn add praisonai
+        ```
+        </CodeGroup>
+      </Step>
+      <Step title="Set API Key">
+        ```bash
+        export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx
+        ```
+      </Step>
+      <Step title="Create File">
+        Create `app.js` file
+
+        ## Code Example
+
+<CodeGroup>
+```javascript Single Agent
+const { Agent } = require('praisonai');
+const agent = new Agent({ instructions: 'You are a helpful AI assistant' });
+agent.start('Write a movie script about a robot in Mars');
+```
+
+```javascript Multi Agents
+const { Agent, PraisonAIAgents } = require('praisonai');
+
+const researchAgent = new Agent({ instructions: 'Research about AI' });
+const summariseAgent = new Agent({ instructions: 'Summarise research agent\'s findings' });
+
+const agents = new PraisonAIAgents({ agents: [researchAgent, summariseAgent] });
+agents.start();
+```
+</CodeGroup>
+      </Step>
+      <Step title="Run Script">
+        ```bash
+        node app.js
+        ```
+      </Step>
+    </Steps>
+  </Tab>
+</Tabs>
+
+## Usage Examples
+
+<AccordionGroup>
+  <Accordion title="Single Agent Example" icon="user" defaultOpen>
+    Create and run a single agent to perform a specific task:
+
+```typescript
+import { Agent } from 'praisonai';
+
+// Single agent example - Science Explainer
+const agent = new Agent({ 
+  instructions: `You are a science expert who explains complex phenomena in simple terms.
+Provide clear, accurate, and easy-to-understand explanations.`,
+  name: "ScienceExplainer",
+  verbose: true
+});
+
+agent.start("Why is the sky blue?")
+  .then(response => {
+    console.log('\nExplanation:');
+    console.log(response);
+  })
+  .catch(error => {
+    console.error('Error:', error);
+  });
+
+```
+  </Accordion>
+
+  <Accordion title="Multi-Agent Example" icon="users" defaultOpen>
+    Create and run multiple agents working together:
+
+```typescript
+import { Agent, PraisonAIAgents } from 'praisonai';
+
+// Create story agent
+const storyAgent = new Agent({
+  instructions: "You are a storyteller. Write a very short story (2-3 sentences) about a given topic.",
+  name: "StoryAgent",
+  verbose: true
+});
+
+// Create summary agent
+const summaryAgent = new Agent({
+  instructions: "You are an editor. Create a one-sentence summary of the given story.",
+  name: "SummaryAgent",
+  verbose: true
+});
+
+// Create and start agents
+const agents = new PraisonAIAgents({
+  agents: [storyAgent, summaryAgent],
+  tasks: [
+    "Write a short story about a cat",
+    "{previous_result}"  // This will be replaced with the story
+  ],
+  verbose: true
+});
+
+agents.start()
+  .then(results => {
+    console.log('\nStory:', results[0]);
+    console.log('\nSummary:', results[1]);
+  })
+  .catch(error => console.error('Error:', error));
+```
+  </Accordion>
+
+  <Accordion title="Task-Based Agent Example" icon="list-check" defaultOpen>
+    Create agents with specific tasks and dependencies:
+
+```typescript
+import { Agent, PraisonAIAgents } from 'praisonai';
+
+// Create recipe agent
+const recipeAgent = new Agent({
+  instructions: `You are a professional chef and nutritionist. Create 5 healthy food recipes that are both nutritious and delicious.
+Each recipe should include:
+1. Recipe name
+2. List of ingredients with quantities
+3. Step-by-step cooking instructions
+4. Nutritional information
+5. Health benefits
+
+Format your response in markdown.`,
+  name: "RecipeAgent",
+  verbose: true
+});
+
+// Create blog agent
+const blogAgent = new Agent({
+  instructions: `You are a food and health blogger. Write an engaging blog post about the provided recipes.
+The blog post should:
+1. Have an engaging title
+2. Include an introduction about healthy eating
+3. Discuss each recipe and its unique health benefits
+4. Include tips for meal planning and preparation
+5. End with a conclusion encouraging healthy eating habits
+
+Here are the recipes to write about:
+{previous_result}
+
+Format your response in markdown.`,
+  name: "BlogAgent",
+  verbose: true
+});
+
+// Create PraisonAIAgents instance with tasks
+const agents = new PraisonAIAgents({
+  agents: [recipeAgent, blogAgent],
+  tasks: [
+    "Create 5 healthy and delicious recipes",
+    "Write a blog post about the recipes"
+  ],
+  verbose: true
+});
+
+// Start the agents
+agents.start()
+  .then(results => {
+    console.log('\nFinal Results:');
+    console.log('\nRecipe Task Results:');
+    console.log(results[0]);
+    console.log('\nBlog Task Results:');
+    console.log(results[1]);
+  })
+  .catch(error => {
+    console.error('Error:', error);
+  });
+
+```
+  </Accordion>
+</AccordionGroup>
+
+## Running the Examples
+
+<Steps>
+  <Step title="Set Environment Variables">
+    ```bash
+    export OPENAI_API_KEY='your-api-key'
+    ```
+  </Step>
+
+  <Step title="Create Example File">
+    Create a new TypeScript file (e.g., `app.ts`) with any of the above examples.
+  </Step>
+
+  <Step title="Run the Example">
+    ```bash
+    npx ts-node app.ts
+    ```
+  </Step>
+</Steps>

docs/js/typescript-async.mdx

@@ -0,0 +1,198 @@
+---
+title: "TypeScript Async AI Agents"
+sidebarTitle: "TypeScript Async"
+description: "A production-ready Multi AI Agents framework for TypeScript Async"
+icon: "rotate"
+---
+
+PraisonAI is a production-ready Multi AI Agents framework for TypeScript Async, designed to create AI Agents to automate and solve problems ranging from simple tasks to complex challenges. It provides a low-code solution to streamline the building and management of multi-agent LLM systems, emphasising simplicity, customisation, and effective human-agent collaboration.
+
+## Installation
+
+<CodeGroup>
+```bash npm
+npm install praisonai
+```
+
+```bash yarn
+yarn add praisonai
+```
+</CodeGroup>
+
+## Usage Examples
+
+<AccordionGroup>
+  <Accordion title="Single Agent Example" icon="user" defaultOpen>
+    Create and run a single agent to perform a specific task:
+
+    ```typescript
+    import { Agent, PraisonAIAgents } from 'praisonai';
+
+    async function main() {
+        // Create a simple agent (no task specified)
+        const agent = new Agent({
+            name: "BiologyExpert",
+            instructions: "Explain the process of photosynthesis in detail.",
+            verbose: true
+        });
+
+        // Run the agent
+        const praisonAI = new PraisonAIAgents({
+            agents: [agent],
+            tasks: ["Explain the process of photosynthesis in detail."],
+            verbose: true
+        });
+
+        try {
+            console.log('Starting single agent example...');
+            const results = await praisonAI.start();
+            console.log('\nFinal Results:', results);
+        } catch (error) {
+            console.error('Error:', error);
+        }
+    }
+
+    main();
+    ```
+  </Accordion>
+
+  <Accordion title="Multi-Agent Example" icon="users" defaultOpen>
+    Create and run multiple agents working together:
+
+    ```typescript
+    import { Agent, PraisonAIAgents } from 'praisonai';
+
+    async function main() {
+        // Create multiple agents with different roles
+        const researchAgent = new Agent({
+            name: "ResearchAgent",
+            instructions: "Research and provide detailed information about renewable energy sources.",
+            verbose: true
+        });
+
+        const summaryAgent = new Agent({
+            name: "SummaryAgent",
+            instructions: "Create a concise summary of the research findings about renewable energy sources. Use {previous_result} as input.",
+            verbose: true
+        });
+
+        const recommendationAgent = new Agent({
+            name: "RecommendationAgent",
+            instructions: "Based on the summary in {previous_result}, provide specific recommendations for implementing renewable energy solutions.",
+            verbose: true
+        });
+
+        // Run the agents in sequence
+        const praisonAI = new PraisonAIAgents({
+            agents: [researchAgent, summaryAgent, recommendationAgent],
+            tasks: [
+                "Research and analyze current renewable energy technologies and their implementation.",
+                "Summarize the key findings from the research.",
+                "Provide actionable recommendations based on the summary."
+            ],
+            verbose: true
+        });
+
+        try {
+            console.log('Starting multi-agent example...');
+            const results = await praisonAI.start();
+            console.log('\nFinal Results:', results);
+        } catch (error) {
+            console.error('Error:', error);
+        }
+    }
+
+    main();
+    ```
+  </Accordion>
+
+  <Accordion title="Task-Based Agent Example" icon="list-check" defaultOpen>
+    Create agents with specific tasks and dependencies:
+
+    ```typescript
+    import { Agent, Task, PraisonAIAgents } from 'praisonai';
+
+    async function main() {
+        // Create agents first
+        const dietAgent = new Agent({
+            name: "DietAgent",
+            role: "Nutrition Expert",
+            goal: "Create healthy and delicious recipes",
+            backstory: "You are a certified nutritionist with years of experience in creating balanced meal plans.",
+            verbose: true,
+            instructions: `You are a professional chef and nutritionist. Create 5 healthy food recipes that are both nutritious and delicious.
+    Each recipe should include:
+    1. Recipe name
+    2. List of ingredients with quantities
+    3. Step-by-step cooking instructions
+    4. Nutritional information
+    5. Health benefits
+
+    Format your response in markdown.`
+        });
+
+        const blogAgent = new Agent({
+            name: "BlogAgent",
+            role: "Food Blogger",
+            goal: "Write engaging blog posts about food and recipes",
+            backstory: "You are a successful food blogger known for your ability to make recipes sound delicious and approachable.",
+            verbose: true,
+            instructions: `You are a food and health blogger. Write an engaging blog post about the provided recipes.
+    The blog post should:
+    1. Have an engaging title
+    2. Include an introduction about healthy eating`
+        });
+
+        // Create tasks
+        const createRecipesTask = new Task({
+            name: "Create Recipes",
+            description: "Create 5 healthy and delicious recipes",
+            agent: dietAgent
+        });
+
+        const writeBlogTask = new Task({
+            name: "Write Blog",
+            description: "Write a blog post about the recipes",
+            agent: blogAgent,
+            dependencies: [createRecipesTask]  // This task depends on the recipes being created first
+        });
+
+        // Run the tasks
+        const praisonAI = new PraisonAIAgents({
+            tasks: [createRecipesTask, writeBlogTask],
+            verbose: true
+        });
+
+        try {
+            console.log('Starting task-based example...');
+            const results = await praisonAI.start();
+            console.log('\nFinal Results:', results);
+        } catch (error) {
+            console.error('Error:', error);
+        }
+    }
+
+    main();
+    ```
+  </Accordion>
+</AccordionGroup>
+
+## Running the Examples
+
+<Steps>
+  <Step title="Set Environment Variables">
+    ```bash
+    export OPENAI_API_KEY='your-api-key'
+    ```
+  </Step>
+
+  <Step title="Create Example File">
+    Create a new TypeScript file (e.g., `app.ts`) with any of the above examples.
+  </Step>
+
+  <Step title="Run the Example">
+    ```bash
+    npx ts-node app.ts
+    ```
+  </Step>
+</Steps>

docs/js/typescript.mdx

@@ -0,0 +1,266 @@
+---
+title: "TypeScript AI Agents Framework"
+sidebarTitle: "TypeScript Agents"
+description: "A production-ready Multi AI Agents framework for TypeScript"
+icon: "scroll"
+---
+
+PraisonAI is a production-ready Multi AI Agents framework for TypeScript, designed to create AI Agents to automate and solve problems ranging from simple tasks to complex challenges. It provides a low-code solution to streamline the building and management of multi-agent LLM systems, emphasising simplicity, customisation, and effective human-agent collaboration.
+
+```mermaid
+graph LR
+    %% Define the main flow
+    Start([▶ Start]) --> Agent1
+    Agent1 --> Process[⚙ Process]
+    Process --> Agent2
+    Agent2 --> Output([✓ Output])
+    Process -.-> Agent1
+    
+    %% Define subgraphs for agents and their tasks
+    subgraph Agent1[ ]
+        Task1[📋 Task]
+        AgentIcon1[🤖 AI Agent]
+        Tools1[🔧 Tools]
+        
+        Task1 --- AgentIcon1
+        AgentIcon1 --- Tools1
+    end
+    
+    subgraph Agent2[ ]
+        Task2[📋 Task]
+        AgentIcon2[🤖 AI Agent]
+        Tools2[🔧 Tools]
+        
+        Task2 --- AgentIcon2
+        AgentIcon2 --- Tools2
+    end
+
+    classDef input fill:#8B0000,stroke:#7C90A0,color:#fff
+    classDef process fill:#189AB4,stroke:#7C90A0,color:#fff
+    classDef tools fill:#2E8B57,stroke:#7C90A0,color:#fff
+    classDef transparent fill:none,stroke:none
+
+    class Start,Output,Task1,Task2 input
+    class Process,AgentIcon1,AgentIcon2 process
+    class Tools1,Tools2 tools
+    class Agent1,Agent2 transparent
+```
+
+<Tabs>
+<Tab title="TypeScript">
+    <Steps>
+      <Step title="Install Package">
+        <CodeGroup>
+        ```bash npm
+        npm install praisonai
+        ```
+        ```bash yarn
+        yarn add praisonai
+        ```
+        </CodeGroup>
+      </Step>
+      <Step title="Set API Key">
+        ```bash
+        export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx
+        ```
+      </Step>
+      <Step title="Create File">
+        Create `app.ts` file
+
+        ## Code Example
+
+<CodeGroup>
+```javascript Single Agent
+import { Agent } from 'praisonai';
+
+const agent = new Agent({ 
+  instructions: `You are a creative writer who writes short stories with emojis.`,
+  name: "StoryWriter"
+});
+
+agent.start("Write a story about a time traveler")
+```
+
+```javascript Multi Agents
+import { Agent, PraisonAIAgents } from 'praisonai';
+
+const storyAgent = new Agent({
+  instructions: "Generate a very short story (2-3 sentences) about artificial intelligence with emojis.",
+  name: "StoryAgent"
+});
+
+const summaryAgent = new Agent({
+  instructions: "Summarize the provided AI story in one sentence with emojis.",
+  name: "SummaryAgent"
+});
+
+const agents = new PraisonAIAgents({
+  agents: [storyAgent, summaryAgent]
+});
+
+agents.start()
+```
+</CodeGroup>
+      </Step>
+      <Step title="Run Script">
+        ```bash
+        npx ts-node app.ts
+        ```
+      </Step>
+    </Steps>
+  </Tab>
+</Tabs>
+
+## Usage Examples
+
+<AccordionGroup>
+  <Accordion title="Single Agent Example" icon="user" defaultOpen>
+    Create and run a single agent to perform a specific task:
+
+```typescript
+import { Agent } from 'praisonai';
+
+// Single agent example - Science Explainer
+const agent = new Agent({ 
+  instructions: `You are a science expert who explains complex phenomena in simple terms.
+Provide clear, accurate, and easy-to-understand explanations.`,
+  name: "ScienceExplainer",
+  verbose: true
+});
+
+agent.start("Why is the sky blue?")
+  .then(response => {
+    console.log('\nExplanation:');
+    console.log(response);
+  })
+  .catch(error => {
+    console.error('Error:', error);
+  });
+
+```
+  </Accordion>
+
+  <Accordion title="Multi-Agent Example" icon="users" defaultOpen>
+    Create and run multiple agents working together:
+
+```typescript
+import { Agent, PraisonAIAgents } from 'praisonai';
+
+// Create story agent
+const storyAgent = new Agent({
+  instructions: "You are a storyteller. Write a very short story (2-3 sentences) about a given topic.",
+  name: "StoryAgent",
+  verbose: true
+});
+
+// Create summary agent
+const summaryAgent = new Agent({
+  instructions: "You are an editor. Create a one-sentence summary of the given story.",
+  name: "SummaryAgent",
+  verbose: true
+});
+
+// Create and start agents
+const agents = new PraisonAIAgents({
+  agents: [storyAgent, summaryAgent],
+  tasks: [
+    "Write a short story about a cat",
+    "{previous_result}"  // This will be replaced with the story
+  ],
+  verbose: true
+});
+
+agents.start()
+  .then(results => {
+    console.log('\nStory:', results[0]);
+    console.log('\nSummary:', results[1]);
+  })
+  .catch(error => console.error('Error:', error));
+```
+  </Accordion>
+
+  <Accordion title="Task-Based Agent Example" icon="list-check" defaultOpen>
+    Create agents with specific tasks and dependencies:
+
+```typescript
+import { Agent, PraisonAIAgents } from 'praisonai';
+
+// Create recipe agent
+const recipeAgent = new Agent({
+  instructions: `You are a professional chef and nutritionist. Create 5 healthy food recipes that are both nutritious and delicious.
+Each recipe should include:
+1. Recipe name
+2. List of ingredients with quantities
+3. Step-by-step cooking instructions
+4. Nutritional information
+5. Health benefits
+
+Format your response in markdown.`,
+  name: "RecipeAgent",
+  verbose: true
+});
+
+// Create blog agent
+const blogAgent = new Agent({
+  instructions: `You are a food and health blogger. Write an engaging blog post about the provided recipes.
+The blog post should:
+1. Have an engaging title
+2. Include an introduction about healthy eating
+3. Discuss each recipe and its unique health benefits
+4. Include tips for meal planning and preparation
+5. End with a conclusion encouraging healthy eating habits
+
+Here are the recipes to write about:
+{previous_result}
+
+Format your response in markdown.`,
+  name: "BlogAgent",
+  verbose: true
+});
+
+// Create PraisonAIAgents instance with tasks
+const agents = new PraisonAIAgents({
+  agents: [recipeAgent, blogAgent],
+  tasks: [
+    "Create 5 healthy and delicious recipes",
+    "Write a blog post about the recipes"
+  ],
+  verbose: true
+});
+
+// Start the agents
+agents.start()
+  .then(results => {
+    console.log('\nFinal Results:');
+    console.log('\nRecipe Task Results:');
+    console.log(results[0]);
+    console.log('\nBlog Task Results:');
+    console.log(results[1]);
+  })
+  .catch(error => {
+    console.error('Error:', error);
+  });
+
+```
+  </Accordion>
+</AccordionGroup>
+
+## Running the Examples
+
+<Steps>
+  <Step title="Set Environment Variables">
+    ```bash
+    export OPENAI_API_KEY='your-api-key'
+    ```
+  </Step>
+
+  <Step title="Create Example File">
+    Create a new TypeScript file (e.g., `app.ts`) with any of the above examples.
+  </Step>
+
+  <Step title="Run the Example">
+    ```bash
+    npx ts-node app.ts
+    ```
+  </Step>
+</Steps>

docs/mint.json

@@ -74,6 +74,10 @@
     {
         "name": "Tools",
         "url": "/tools"
+    },
+    {
+        "name": "JS",
+        "url": "/js"
     }
   ],
   "navigation": [
@@ -115,18 +119,23 @@
     {
       "group": "Features",
       "pages": [
+        "features/cli",
         "features/autoagents",
+        "features/image-generation",
         "features/selfreflection",
         "features/rag",
+        "features/reasoning-extract",
         "features/reasoning",
         "features/multimodal",
         "features/langchain",
         "features/async",
         "features/mini",
+        "features/generate-reasoning",
         "features/codeagent",
         "features/mathagent",
         "features/structured",
-        "features/callbacks"
+        "features/callbacks",
+        "features/chat-with-pdf"
       ]
     },
     {
@@ -141,6 +150,7 @@
         "models/anthropic",
         "models/cohere",
         "models/mistral",
+        "models/deepseek",
         "models/other"
       ]
     },
@@ -230,6 +240,16 @@
         "tools/googlecalendar"
       ]
     },
+    {
+      "group": "JavaScript",
+      "pages": [
+        "js/js",
+        "js/typescript",
+        "js/nodejs",
+        "js/typescript-async",
+        "js/development"
+      ]
+    },
     {
       "group": "Other Features",
       "pages": [
@@ -250,7 +270,10 @@
           "pages": [
             "ui/streamlit",
             "ui/streamlit/code-analysis-streamlit",
-            "ui/streamlit/hackathon-judge-streamlit"
+            "ui/streamlit/hackathon-judge-streamlit",
+            "ui/streamlit/ollama-streamlit",
+            "ui/streamlit/deepseek-streamlit",
+            "ui/streamlit/gemini-streamlit"
           ]
         },
         "ui/ui",
@@ -271,6 +294,7 @@
         "developers/wrapper-tools",
         "developers/googlecolab",
         "developers/googlecolab-tools",
+        "developers/local-development",
         "deploy"
       ]
     },

docs/models.mdx

@@ -4,7 +4,184 @@ description: "Overview of supported language models in PraisonAI, including Open
 icon: "brain"
 ---
 
-## Supported Models for Code
+# Code
+
+## Set model by 3 ways
+
+### 1. OpenAI Compatible Endpoints
+
+<Note>By Default it uses OPENAI_BASE_URL https://api.openai.com/v1 </Note>
+Example Groq Implementation:
+
+```bash
+export OPENAI_API_KEY=groq-api-key
+export OPENAI_BASE_URL=https://api.groq.com/openai/v1
+```
+
+```python
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a helpful assistant",
+    llm="llama-3.1-8b-instant",
+)
+
+agent.start("Why sky is Blue?")
+```
+
+### 2. Litellm Compatible model names (eg: gemini/gemini-1.5-flash-8b)
+
+```bash
+pip install "praisonaiagents[llm]"
+```
+
+```python
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a helpful assistant",
+    llm="gemini/gemini-1.5-flash-8b",
+    self_reflect=True,
+    verbose=True
+)
+
+agent.start("Why sky is Blue?")
+```
+
+### 3. Litellm Compatible Configuration
+
+```bash
+pip install "praisonaiagents[llm]"
+```
+
+```python 
+from praisonaiagents import Agent
+
+llm_config = {
+    "model": "gemini/gemini-1.5-flash-latest",  # Model name without provider prefix
+    
+    # Core settings
+    "temperature": 0.7,                # Controls randomness (like temperature)
+    "timeout": 30,                 # Timeout in seconds
+    "top_p": 0.9,                    # Nucleus sampling parameter
+    "max_tokens": 1000,               # Max tokens in response
+    
+    # Advanced parameters
+    "presence_penalty": 0.1,         # Penalize repetition of topics (-2.0 to 2.0)
+    "frequency_penalty": 0.1,        # Penalize token repetition (-2.0 to 2.0)
+    
+    # API settings (optional)
+    "api_key": None,                 # Your API key (or use environment variable)
+    "base_url": None,                # Custom API endpoint if needed
+    
+    # Response formatting
+    "response_format": {             # Force specific response format
+        "type": "text"               # Options: "text", "json_object"
+    },
+    
+    # Additional controls
+    "seed": 42,                      # For reproducible responses
+    "stop_phrases": ["##", "END"],   # Custom stop sequences
+}
+
+agent = Agent(
+    instructions="You are a helpful Assistant."
+    llm=llm_config
+)
+agent.start()
+```
+
+## Advanced Configuration (Litellm Support)
+
+<Note>This uses Litellm</Note>
+<Steps>
+  <Step title="Install Package">
+    Install required packages:
+    ```bash
+    pip install "praisonaiagents[llm]"
+    ```
+  </Step>
+
+  <Step title="Setup Environment">
+    Configure environment:
+    ```bash
+    export GOOGLE_API_KEY=your-api-key
+    ```
+    
+    <Note>
+    Get your API key from [Google AI Studio](https://makersuite.google.com/app/apikey)
+    </Note>
+  </Step>
+
+  <Step title="Create Agent">
+    Create `app.py`:
+
+<CodeGroup>
+
+```python Basic
+# if json_object is supported by the model
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a helpful assistant",
+    llm="gemini/gemini-1.5-flash-8b",
+    self_reflect=True,
+    verbose=True
+)
+
+agent.start("Why sky is Blue?")
+```
+
+```python Advanced 
+# if json_object is not supported by the model
+from praisonaiagents import Agent
+
+# Detailed LLM configuration
+llm_config = {
+    "model": "gemini/gemini-1.5-flash-latest",  # Model name without provider prefix
+    
+    # Core settings
+    "temperature": 0.7,                # Controls randomness (like temperature)
+    "timeout": 30,                 # Timeout in seconds
+    "top_p": 0.9,                    # Nucleus sampling parameter
+    "max_tokens": 1000,               # Max tokens in response
+    
+    # Advanced parameters
+    "presence_penalty": 0.1,         # Penalize repetition of topics (-2.0 to 2.0)
+    "frequency_penalty": 0.1,        # Penalize token repetition (-2.0 to 2.0)
+    
+    # API settings (optional)
+    "api_key": None,                 # Your API key (or use environment variable)
+    "base_url": None,                # Custom API endpoint if needed
+    
+    # Response formatting
+    "response_format": {             # Force specific response format
+        "type": "text"               # Options: "text", "json_object"
+    },
+    
+    # Additional controls
+    "seed": 42,                      # For reproducible responses
+    "stop_phrases": ["##", "END"],   # Custom stop sequences
+}
+
+agent = Agent(
+    instructions="You are a helpful Assistant specialized in scientific explanations. "
+                "Provide clear, accurate, and engaging responses.",
+    llm=llm_config,                  # Pass the detailed configuration
+    verbose=True,                    # Enable detailed output
+    markdown=True,                   # Format responses in markdown
+    self_reflect=True,              # Enable self-reflection
+    max_reflect=3,                  # Maximum reflection iterations
+    min_reflect=1                   # Minimum reflection iterations
+)
+
+# Test the agent
+response = agent.start("Why is the sky blue? Please explain in simple terms.")
+
+```
+</CodeGroup>
+</Step>
+</Steps>
 
 <AccordionGroup>
   <Accordion title="Ollama Integration" defaultOpen>

docs/models/deepseek.mdx

@@ -0,0 +1,253 @@
+---
+title: "DeepSeek Agents"
+
+description: "Learn how to use Deepseek models with PraisonAI Agents for various applications."
+icon: "brain"
+---
+
+```mermaid
+flowchart LR
+    In[Input] --> Ollama[("Ollama")]
+    Ollama --> DS[("Deepseek")]
+    DS --> Basic[Basic Agent]
+    DS --> RAG[RAG Agent]
+    DS --> UI[UI Agent]
+    Basic --> Out1[Output]
+    RAG --> Out2[Output]
+    UI --> Out3[Output]
+    
+    style In fill:#8B0000,color:#fff
+    style Ollama fill:#4169E1,color:#fff,shape:circle
+    style DS fill:#2E8B57,color:#fff,shape:circle
+    style Basic fill:#2E8B57,color:#fff
+    style RAG fill:#2E8B57,color:#fff
+    style UI fill:#2E8B57,color:#fff
+    style Out1 fill:#8B0000,color:#fff
+    style Out2 fill:#8B0000,color:#fff
+    style Out3 fill:#8B0000,color:#fff
+```
+
+Learn how to use Deepseek models with PraisonAI Agents through Ollama integration for basic queries, RAG applications, and interactive UI implementations.
+
+## Prerequisites
+
+<Steps>
+    <Step title="Install Ollama">
+        First, install Ollama on your system:
+        ```bash
+        curl -fsSL https://ollama.com/install.sh | sh
+        ```
+    </Step>
+
+    <Step title="Pull Deepseek Model">
+        Pull the Deepseek model from Ollama:
+        ```bash
+        ollama pull deepseek-r1
+        ```
+    </Step>
+
+    <Step title="Install Package">
+        Install PraisonAI Agents:
+        ```bash
+        pip install "praisonaiagents[knowledge]" ollama streamlit
+        ```
+
+        <Note> 
+        Streamlit for UI is optional.
+        Ollama is required for Local RAG Agents.
+        praisonaiagents[knowledge] is for RAG Agents. praisonaiagents is for Basic Agents.
+        </Note>
+    </Step>
+
+    <Step title="Set Environment">
+        Set Ollama as your base URL:
+        ```bash
+        export OPENAI_BASE_URL=http://localhost:11434/v1
+        export OPENAI_API_KEY=fake-key
+        ```
+    </Step>
+</Steps>
+
+## Basic Usage
+
+The simplest way to use Deepseek with PraisonAI Agents:
+
+```python
+from praisonaiagents import Agent
+
+agent = Agent(instructions="You are helpful Assisant", llm="deepseek-r1")
+
+agent.start("Why sky is Blue?")
+```
+
+## RAG Implementation
+
+Use Deepseek with RAG capabilities for knowledge-based interactions:
+
+```python
+from praisonaiagents import Agent
+
+config = {
+    "vector_store": {
+        "provider": "chroma",
+        "config": {
+            "collection_name": "praison",
+            "path": ".praison"
+        }
+    },
+    "llm": {
+        "provider": "ollama",
+        "config": {
+            "model": "deepseek-r1:latest",
+            "temperature": 0,
+            "max_tokens": 8000,
+            "ollama_base_url": "http://localhost:11434",
+        },
+    },
+    "embedder": {
+        "provider": "ollama",
+        "config": {
+            "model": "nomic-embed-text:latest",
+            "ollama_base_url": "http://localhost:11434",
+            "embedding_dims": 1536
+        },
+    },
+}
+
+agent = Agent(
+    name="Knowledge Agent",
+    instructions="You answer questions based on the provided knowledge.",
+    knowledge=["kag-research-paper.pdf"], # Indexing
+    knowledge_config=config,
+    user_id="user1",
+    llm="deepseek-r1"
+)
+
+agent.start("What is KAG in one line?") # Retrieval
+```
+
+## Interactive UI with Streamlit
+
+Create an interactive chat interface using Streamlit:
+
+```python
+import streamlit as st
+from praisonaiagents import Agent
+
+def init_agent():
+    config = {
+        "vector_store": {
+            "provider": "chroma",
+            "config": {
+                "collection_name": "praison",
+                "path": ".praison"
+            }
+        },
+        "llm": {
+            "provider": "ollama",
+            "config": {
+                "model": "deepseek-r1:latest",
+                "temperature": 0,
+                "max_tokens": 8000,
+                "ollama_base_url": "http://localhost:11434",
+            },
+        },
+        "embedder": {
+            "provider": "ollama",
+            "config": {
+                "model": "nomic-embed-text:latest",
+                "ollama_base_url": "http://localhost:11434",
+                "embedding_dims": 1536
+            },
+        },
+    }
+    
+    return Agent(
+        name="Knowledge Agent",
+        instructions="You answer questions based on the provided knowledge.",
+        knowledge=["kag-research-paper.pdf"],
+        knowledge_config=config,
+        user_id="user1",
+        llm="deepseek-r1"
+    )
+
+st.title("Knowledge Agent Chat")
+
+if "agent" not in st.session_state:
+    st.session_state.agent = init_agent()
+    st.session_state.messages = []
+
+if "messages" in st.session_state:
+    for message in st.session_state.messages:
+        with st.chat_message(message["role"]):
+            st.markdown(message["content"])
+
+prompt = st.chat_input("Ask a question...")
+
+if prompt:
+    st.session_state.messages.append({"role": "user", "content": prompt})
+    with st.chat_message("user"):
+        st.markdown(prompt)
+
+    with st.chat_message("assistant"):
+        response = st.session_state.agent.start(prompt)
+        st.markdown(response)
+        st.session_state.messages.append({"role": "assistant", "content": response}) 
+```
+
+## Running the UI
+
+<Steps>
+    <Step title="Install Streamlit">
+        Install Streamlit if you haven't already:
+        ```bash
+        pip install streamlit
+        ```
+    </Step>
+
+    <Step title="Save and Run">
+        Save the UI code in a file (e.g., `app.py`) and run:
+        ```bash
+        streamlit run app.py
+        ```
+    </Step>
+</Steps>
+
+## Features
+
+<CardGroup cols={2}>
+  <Card title="Local Deployment" icon="server">
+    Run Deepseek models locally through Ollama.
+  </Card>
+  <Card title="RAG Capabilities" icon="database">
+    Integrate with vector databases for knowledge retrieval.
+  </Card>
+  <Card title="Interactive UI" icon="desktop">
+    Create chat interfaces with Streamlit integration.
+  </Card>
+  <Card title="Custom Configuration" icon="gear">
+    Configure model parameters and embedding settings.
+  </Card>
+</CardGroup>
+
+## Troubleshooting
+
+<CardGroup cols={2}>
+  <Card title="Ollama Issues" icon="triangle-exclamation">
+    If Ollama isn't working:
+    - Check if Ollama is running
+    - Verify model is downloaded
+    - Check port availability
+  </Card>
+
+  <Card title="Performance Issues" icon="gauge-high">
+    If responses are slow:
+    - Check system resources
+    - Adjust max_tokens
+    - Monitor memory usage
+  </Card>
+</CardGroup>
+
+<Note>
+  For optimal performance, ensure your system meets the minimum requirements for running Deepseek models locally through Ollama.
+</Note>

docs/models/google.mdx

@@ -1,12 +1,166 @@
 ---
-title: "Google Gemini"
+title: "Google Gemini Agents"
+sidebarTitle: "Google Gemini"
 description: "Instructions for integrating Google's Gemini models with PraisonAI, including API setup and configuration details"
 icon: "google"
 ---
 
-# Add Google Gemini to Praison AI
+```mermaid
+flowchart LR
+    In[Input] --> API[("Google API")]
+    API --> Gemini[("Gemini")]
+    Gemini --> Basic[Basic Agent]
+    Gemini --> Multi[Multi-Agents]
+    Gemini --> YAML[No-Code]
+    Basic --> Out1[Output]
+    Multi --> Out2[Output]
+    YAML --> Out3[Output]
+    
+    style In fill:#8B0000,color:#fff
+    style API fill:#4169E1,color:#fff,shape:circle
+    style Gemini fill:#2E8B57,color:#fff,shape:circle
+    style Basic fill:#2E8B57,color:#fff
+    style Multi fill:#2E8B57,color:#fff
+    style YAML fill:#2E8B57,color:#fff
+    style Out1 fill:#8B0000,color:#fff
+    style Out2 fill:#8B0000,color:#fff
+    style Out3 fill:#8B0000,color:#fff
+```
 
-## Code
+## Prerequisites
+
+<Steps>
+    <Step title="Install Package">
+        First, install PraisonAI Agents:
+        ```bash
+        pip install "praisonaiagents[llm]"
+        ```
+
+        <Note>
+        praisonaiagents[llm] includes all Google Gemini dependencies.
+        For No-Code implementation, also install: pip install langchain-google-genai
+        </Note>
+    </Step>
+
+    <Step title="Set API Key">
+        Set your Gemini API key:
+        ```bash
+        export GEMINI_API_KEY=xxxxxxxxxxx
+        ```
+    </Step>
+
+    <Step title="Code">
+```python
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a helpful assistant",
+    llm="gemini/gemini-1.5-flash-8b",
+    self_reflect=True,
+    verbose=True
+)
+
+agent.start("Why sky is Blue?")
+```
+    </Step>
+</Steps>
+
+## Code Implementation
+
+### Basic Usage
+
+The simplest way to use Gemini with PraisonAI Agents:
+
+```python
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a helpful assistant",
+    llm="gemini/gemini-1.5-flash-8b",
+    self_reflect=True,
+    verbose=True
+)
+
+agent.start("Why sky is Blue?")
+```
+
+### Multi-Agent Setup
+
+Create multiple agents working together:
+
+```python
+from praisonaiagents import Agent, Task, PraisonAIAgents
+
+agent = Agent(
+    instructions="You are a helpful assistant",
+    llm="gemini/gemini-1.5-flash-8b",
+    self_reflect=True,
+    verbose=True
+)
+
+task = Task(
+    description="Why sky is Blue?",
+    agent=agent,
+)
+
+agents = PraisonAIAgents(
+  agents=[agent],
+  tasks=[task],
+)
+
+agents.start()
+```
+
+<Note>
+  This uses Litellm to connect to Google Gemini.
+</Note>
+
+## Gemini 2.0 Flash Thinking
+
+### LLM Configuration
+```python
+llm_config = {
+  "model": "gemini/gemini-2.0-flash-thinking-exp-01-21",
+  "response_format": {"type": "text"} # type is text, because json_object is not supported
+}
+```
+
+<Steps>
+    <Step title="Install Package">
+        Install required packages:
+        ```bash
+        pip install "praisonaiagents[llm]"
+        ```
+    </Step>
+
+    <Step title="Set API Key">
+        Set your Gemini API key:
+        ```bash
+        export GEMINI_API_KEY=xxxxxxxxxxx
+        ```
+    </Step>
+
+    <Step title="Code">
+
+```python
+from praisonaiagents import Agent
+
+llm_config = {"model": "gemini/gemini-2.0-flash-thinking-exp-01-21","response_format": {"type": "text"}}
+
+agent = Agent(
+    instructions="You are a helpful assistant",
+    llm=llm_config
+)
+
+result = agent.start("Why sky is Blue?")
+print(result)
+```
+    </Step>
+</Steps>
+
+## Alternative Setup
+
+### Using Environment Variables
 
 <AccordionGroup>
   <Accordion title="Google Gemini" defaultOpen> 
@@ -16,16 +170,18 @@ icon: "google"
     ```
   </Accordion>
 </AccordionGroup>
-## No Code
 
+## No-Code Implementation
+
+### Setup
 ```bash
 pip install langchain-google-genai
-```
-```bash
 export GOOGLE_API_KEY=xxxxxxxxxx
 ```
 
-### agents.yaml file
+### YAML Configuration
+
+Create an `agents.yaml` file:
 
 ```yaml
 framework: crewai
@@ -48,6 +204,8 @@ roles:
     - ''
 ```
 
+## Additional Resources
+
 | PraisonAI Chat | PraisonAI Code | PraisonAI (Multi-Agents) |
 | --- | --- | --- |
 | [Litellm](https://litellm.vercel.app/docs/providers) | [Litellm](https://litellm.vercel.app/docs/providers) | [Models](../models.md) |

docs/quickstart.mdx

@@ -125,6 +125,48 @@ praisonai --init "your task description"
       </Step>
     </Steps>
   </Tab>
+  <Tab title="JavaScript">
+    <Steps>
+      <Step title="Install Package">
+        ```bash
+        npm install praisonai
+        ```
+      </Step>
+      <Step title="Set API Key">
+        ```bash
+        export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx
+        ```
+      </Step>
+      <Step title="Create File">
+        Create `app.js` file
+
+        ## Code Example
+
+<CodeGroup>
+```javascript Single Agent
+const { Agent } = require('praisonai');
+const agent = new Agent({ instructions: 'You are a helpful AI assistant' });
+agent.start('Write a movie script about a robot in Mars');
+```
+
+```javascript Multi Agents
+const { Agent, PraisonAIAgents } = require('praisonai');
+
+const researchAgent = new Agent({ instructions: 'Research about AI' });
+const summariseAgent = new Agent({ instructions: 'Summarise research agent\'s findings' });
+
+const agents = new PraisonAIAgents({ agents: [researchAgent, summariseAgent] });
+agents.start();
+```
+</CodeGroup>
+      </Step>
+      <Step title="Run Script">
+        ```bash
+        node app.js
+        ```
+      </Step>
+    </Steps>
+  </Tab>
 </Tabs>
 
 <Note>

docs/train.mdx

@@ -20,6 +20,20 @@ icon: "dumbbell"
 export HF_TOKEN=xxxxxxxxxxxxxx
 ```
 
+## Initilise praisonai train
+
+```bash
+praisonai train init
+```
+
+## Required
+
+1. Huggingface token
+2. Base model to train on (e.g. unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit)
+3. Dataset to train on (e.g. yahma/alpaca-cleaned)
+4. Huggingface model name to upload to (e.g. mervinpraison/llama3.1-instruct) (Optional)
+5. Ollama model name to upload to (e.g. mervinpraison/llama3.1-instruct) (Optional)
+
 ## To upload to ollama.com (Linux)
 
 ```bash
@@ -108,4 +122,21 @@ quantization_method:
 
 ```bash
 praisonai train
+```
+
+## wandb
+
+```bash
+wandb login
+```
+
+<Note>
+Get the key from [here](https://wandb.ai/site/login)
+</Note>
+
+```bash
+export PRAISON_WANDB=True
+export WANDB_LOG_MODEL=checkpoint
+export WANDB_PROJECT=praisonai-test
+export PRAISON_WANDB_RUN_NAME=praisonai-train  
 ```

docs/ui/streamlit/deepseek-streamlit.mdx

@@ -0,0 +1,158 @@
+---
+title: "Deepseek Streamlit UI"
+description: "Create interactive chat interfaces with Deepseek models using Streamlit"
+icon: "window"
+---
+
+```mermaid
+flowchart LR
+    In[Input] --> UI[("Streamlit UI")]
+    VDB[(Vector DB)] --> Agent
+    DS[("Deepseek")] --> Agent
+    UI --> Agent[("Knowledge Agent")]
+    Agent --> |Query| VDB
+    Agent --> Out[Output]
+    Out --> UI
+    
+    style In fill:#8B0000,color:#fff
+    style UI fill:#FF4B4B,color:#fff,shape:circle
+    style DS fill:#4169E1,color:#fff,shape:circle
+    style Agent fill:#2E8B57,color:#fff,shape:circle
+    style VDB fill:#4169E1,color:#fff,shape:cylinder
+    style Out fill:#8B0000,color:#fff
+```
+
+## Prerequisites
+
+<Steps>
+    <Step title="Install Package">
+        Install required packages:
+        ```bash
+        pip install "praisonaiagents[knowledge]" streamlit ollama
+        ```
+
+        <Note>
+        streamlit for UI
+        ollama for Deepseek model hosting
+        praisonaiagents[knowledge] for RAG capabilities
+        </Note>
+    </Step>
+
+    <Step title="Setup Model">
+        Pull Deepseek model:
+        ```bash
+        # Large Language Model
+        ollama pull deepseek-r1
+        
+        # Embedding Model
+        ollama pull nomic-embed-text
+        ```
+    </Step>
+
+    <Step title="Setup Environment">
+        Configure environment:
+        ```bash
+        export OPENAI_BASE_URL=http://localhost:11434/v1
+        export OPENAI_API_KEY=fake-key
+        ```
+    </Step>
+
+    <Step title="Create File">
+        Create a new file called `app.py` and add the following code:
+    </Step>
+
+    <Step title="Run Application">
+        Start the Streamlit application:
+        ```bash
+        streamlit run app.py
+        ```
+    </Step>
+</Steps>
+
+## Code
+
+```python
+import streamlit as st
+from praisonaiagents import Agent
+
+def init_agent():
+    config = {
+        "vector_store": {
+            "provider": "chroma",
+            "config": {
+                "collection_name": "praison",
+                "path": ".praison"
+            }
+        },
+        "llm": {
+            "provider": "ollama",
+            "config": {
+                "model": "deepseek-r1:latest",
+                "temperature": 0,
+                "max_tokens": 8000,
+                "ollama_base_url": "http://localhost:11434",
+            },
+        },
+        "embedder": {
+            "provider": "ollama",
+            "config": {
+                "model": "nomic-embed-text:latest",
+                "ollama_base_url": "http://localhost:11434",
+                "embedding_dims": 1536
+            },
+        },
+    }
+    
+    return Agent(
+        name="Knowledge Agent",
+        instructions="You answer questions based on the provided knowledge.",
+        knowledge=["kag-research-paper.pdf"],
+        knowledge_config=config,
+        user_id="user1",
+        llm="deepseek-r1"
+    )
+
+st.title("Knowledge Agent Chat")
+
+if "agent" not in st.session_state:
+    st.session_state.agent = init_agent()
+    st.session_state.messages = []
+
+if "messages" in st.session_state:
+    for message in st.session_state.messages:
+        with st.chat_message(message["role"]):
+            st.markdown(message["content"])
+
+prompt = st.chat_input("Ask a question...")
+
+if prompt:
+    st.session_state.messages.append({"role": "user", "content": prompt})
+    with st.chat_message("user"):
+        st.markdown(prompt)
+
+    with st.chat_message("assistant"):
+        response = st.session_state.agent.start(prompt)
+        st.markdown(response)
+        st.session_state.messages.append({"role": "assistant", "content": response}) 
+```
+
+## Features
+
+<CardGroup cols={2}>
+  <Card title="Interactive Chat" icon="comments">
+    Real-time chat interface with message history.
+  </Card>
+  <Card title="Knowledge Base" icon="database">
+    RAG capabilities with ChromaDB integration.
+  </Card>
+  <Card title="Model Integration" icon="server">
+    Uses Deepseek through Ollama.
+  </Card>
+  <Card title="Session Management" icon="clock-rotate-left">
+    Maintains chat history in session state.
+  </Card>
+</CardGroup>
+
+<Note>
+  Make sure your system meets the requirements for running Deepseek models locally through Ollama.
+</Note>

docs/ui/streamlit/gemini-streamlit.mdx

@@ -0,0 +1,119 @@
+---
+title: "Gemini Streamlit UI"
+description: "Create interactive chat interfaces with Google's Gemini models using Streamlit"
+icon: "window"
+---
+
+```mermaid
+flowchart LR
+    In[Input] --> UI[("Streamlit UI")]
+    VDB[(Vector DB)] --> Agent
+    Gemini[("Gemini")] --> Agent
+    UI --> Agent[("Knowledge Agent")]
+    Agent --> |Query| VDB
+    Agent --> Out[Output]
+    Out --> UI
+    
+    style In fill:#8B0000,color:#fff
+    style UI fill:#FF4B4B,color:#fff,shape:circle
+    style Gemini fill:#4169E1,color:#fff,shape:circle
+    style Agent fill:#2E8B57,color:#fff,shape:circle
+    style VDB fill:#4169E1,color:#fff,shape:cylinder
+    style Out fill:#8B0000,color:#fff
+```
+
+## Prerequisites
+
+<Steps>
+    <Step title="Install Package">
+        Install required packages:
+        ```bash
+        pip install "praisonaiagents[llm]" streamlit
+        ```
+
+        <Note>
+        streamlit for UI<br />
+        praisonaiagents[llm] for Gemini model access (It uses Litellm)
+        </Note>
+    </Step>
+
+    <Step title="Setup Environment">
+        Configure environment:
+        ```bash
+        export GOOGLE_API_KEY=your-api-key
+        ```
+        
+        <Note>
+        Get your API key from [Google AI Studio](https://makersuite.google.com/app/apikey)
+        </Note>
+    </Step>
+
+    <Step title="Create File">
+        Create a new file called `app.py` and add the following code:
+    </Step>
+
+    <Step title="Run Application">
+        Start the Streamlit application:
+        ```bash
+        streamlit run app.py
+        ```
+    </Step>
+</Steps>
+
+## Code
+
+```python
+import streamlit as st
+from praisonaiagents import Agent
+
+st.title("Gemini 2.0 Thinking AI Agent")
+
+# Initialize the agent
+@st.cache_resource
+def get_agent():
+    llm_config = {
+        "model": "gemini/gemini-2.0-flash-thinking-exp-01-21",
+        "response_format": {"type": "text"}
+    }
+    
+    return Agent(
+        instructions="You are a helpful assistant",
+        llm=llm_config
+    )
+
+agent = get_agent()
+
+# Create text area input field
+user_question = st.text_area("Ask your question:", height=150)
+
+# Add ask button
+if st.button("Ask"):
+    if user_question:
+        with st.spinner('Thinking...'):
+            result = agent.start(user_question)
+            st.write("### Answer")
+            st.write(result)
+    else:
+        st.warning("Please enter a question") 
+```
+
+## Features
+
+<CardGroup cols={2}>
+  <Card title="Interactive Chat" icon="comments">
+    Real-time chat interface with message history.
+  </Card>
+  <Card title="Knowledge Base" icon="database">
+    RAG capabilities with ChromaDB integration.
+  </Card>
+  <Card title="Model Integration" icon="server">
+    Uses Google's Gemini Pro model.
+  </Card>
+  <Card title="Session Management" icon="clock-rotate-left">
+    Maintains chat history in session state.
+  </Card>
+</CardGroup>
+
+<Note>
+  Make sure you have a valid Google API key and sufficient quota for using Gemini models.
+</Note>

docs/ui/streamlit/ollama-streamlit.mdx

@@ -0,0 +1,158 @@
+---
+title: "Ollama Streamlit UI"
+description: "Create interactive chat interfaces with Ollama models using Streamlit"
+icon: "window"
+---
+
+```mermaid
+flowchart LR
+    In[Input] --> UI[("Streamlit UI")]
+    VDB[(Vector DB)] --> Agent
+    Ollama[("Ollama")] --> Agent
+    UI --> Agent[("Knowledge Agent")]
+    Agent --> |Query| VDB
+    Agent --> Out[Output]
+    Out --> UI
+    
+    style In fill:#8B0000,color:#fff
+    style UI fill:#FF4B4B,color:#fff,shape:circle
+    style Ollama fill:#4169E1,color:#fff,shape:circle
+    style Agent fill:#2E8B57,color:#fff,shape:circle
+    style VDB fill:#4169E1,color:#fff,shape:cylinder
+    style Out fill:#8B0000,color:#fff
+```
+
+## Prerequisites
+
+<Steps>
+    <Step title="Install Package">
+        Install required packages:
+        ```bash
+        pip install "praisonaiagents[knowledge]" streamlit ollama
+        ```
+
+        <Note>
+        streamlit for UI
+        ollama for model hosting
+        praisonaiagents[knowledge] for RAG capabilities
+        </Note>
+    </Step>
+
+    <Step title="Setup Model">
+        Pull Ollama models:
+        ```bash
+        # Large Language Model
+        ollama pull deepseek-r1
+        
+        # Embedding Model
+        ollama pull nomic-embed-text
+        ```
+    </Step>
+
+    <Step title="Setup Environment">
+        Configure environment:
+        ```bash
+        export OPENAI_BASE_URL=http://localhost:11434/v1
+        export OPENAI_API_KEY=fake-key
+        ```
+    </Step>
+
+    <Step title="Create File">
+        Create a new file called `app.py` and add the following code:
+    </Step>
+
+    <Step title="Run Application">
+        Start the Streamlit application:
+        ```bash
+        streamlit run app.py
+        ```
+    </Step>
+</Steps>
+
+## Code
+
+```python
+import streamlit as st
+from praisonaiagents import Agent
+
+def init_agent():
+    config = {
+        "vector_store": {
+            "provider": "chroma",
+            "config": {
+                "collection_name": "praison",
+                "path": ".praison"
+            }
+        },
+        "llm": {
+            "provider": "ollama",
+            "config": {
+                "model": "deepseek-r1:latest",
+                "temperature": 0,
+                "max_tokens": 8000,
+                "ollama_base_url": "http://localhost:11434",
+            },
+        },
+        "embedder": {
+            "provider": "ollama",
+            "config": {
+                "model": "nomic-embed-text:latest",
+                "ollama_base_url": "http://localhost:11434",
+                "embedding_dims": 1536
+            },
+        },
+    }
+    
+    return Agent(
+        name="Knowledge Agent",
+        instructions="You answer questions based on the provided knowledge.",
+        knowledge=["kag-research-paper.pdf"],
+        knowledge_config=config,
+        user_id="user1",
+        llm="deepseek-r1"
+    )
+
+st.title("Knowledge Agent Chat")
+
+if "agent" not in st.session_state:
+    st.session_state.agent = init_agent()
+    st.session_state.messages = []
+
+if "messages" in st.session_state:
+    for message in st.session_state.messages:
+        with st.chat_message(message["role"]):
+            st.markdown(message["content"])
+
+prompt = st.chat_input("Ask a question...")
+
+if prompt:
+    st.session_state.messages.append({"role": "user", "content": prompt})
+    with st.chat_message("user"):
+        st.markdown(prompt)
+
+    with st.chat_message("assistant"):
+        response = st.session_state.agent.start(prompt)
+        st.markdown(response)
+        st.session_state.messages.append({"role": "assistant", "content": response}) 
+```
+
+## Features
+
+<CardGroup cols={2}>
+  <Card title="Interactive Chat" icon="comments">
+    Real-time chat interface with message history.
+  </Card>
+  <Card title="Knowledge Base" icon="database">
+    RAG capabilities with ChromaDB integration.
+  </Card>
+  <Card title="Model Integration" icon="server">
+    Uses Ollama for local model hosting.
+  </Card>
+  <Card title="Session Management" icon="clock-rotate-left">
+    Maintains chat history in session state.
+  </Card>
+</CardGroup>
+
+<Note>
+  Make sure your system meets the requirements for running models locally through Ollama.
+</Note>

examples/data/cot-agents.py

@@ -0,0 +1,142 @@
+from praisonaiagents import Agent, Task, PraisonAIAgents
+from praisonaiagents.tools import cot_save, cot_upload_to_huggingface
+from pydantic import BaseModel
+import os
+
+# Define Pydantic model for structured output
+class DecisionModel(BaseModel):
+    response: str
+    decision: str
+
+def write_csv(file_path, data):
+    """Write data to CSV file."""
+    if not os.path.exists(file_path):
+        with open(file_path, 'w') as file:
+            file.write(data + '\n')
+    else:
+        with open(file_path, 'a') as file:
+            file.write(data + '\n')
+    return f"Data appended to {file_path}"
+
+def count_questions(file_path):
+    """Count lines in file."""
+    with open(file_path, 'r') as file:
+        return sum(1 for _ in file)
+
+# Keep existing agents with minimal changes
+qa_generator = Agent(
+    name="Generator",
+    role="Question Creator",
+    goal="Create challenging math and logic questions",
+    backstory="Expert in educational content creation",
+    llm="gpt-4o-mini",
+    tools=[write_csv, count_questions]
+)
+
+total_questions_evaluator = Agent(
+    name="TotalQuestionsEvaluator",
+    role="Total Questions Evaluator",
+    goal="Evaluate the total number of questions in qa_pairs.csv file",
+    backstory="Expert in evaluating the total number of questions in a file",
+    llm="gpt-4o-mini",
+    tools=[count_questions],
+    verbose=False
+)
+
+cot_generator = Agent(
+    name="COTGenerator",
+    role="Chain of Thought Specialist",
+    goal="Generate and manage chain of thought solutions for Q&A pairs",
+    backstory="Expert in breaking down problems and generating detailed solution steps",
+    tools=[cot_save],
+    llm="gpt-4o-mini",
+    verbose=False
+)
+
+upload_to_huggingface = Agent(
+    name="UploadToHuggingface",
+    role="Upload to Huggingface",
+    goal="Upload the generated chain of thought solutions to a Huggingface dataset",
+    backstory="Expert in saving data to Huggingface",
+    tools=[cot_upload_to_huggingface],
+    llm="gpt-4o-mini",
+    verbose=False
+)
+
+# Define tasks with workflow improvements
+generate_task = Task(
+    description="""Generate question and answer in csv format without headers: question, answer and append to qa_pairs.csv file
+generate 10 unique questions and answers and don't repeat on the same question and answer. Reponse with 'done' when done
+with append mode as 'a'
+Example question and answer:
+question, answer
+What is the sum of numbers from 1 to 10?, 55
+Number of r's in the word strawberry, 3
+""",
+    expected_output="append to qa_pairs.csv file with questions and answers and move to next task",
+    agent=qa_generator,
+    name="generate_task",
+    is_start=True,
+    next_tasks=["evaluate_total_questions"],
+    task_type="decision",
+    condition={
+        "more": "generate_task",
+        "done": "evaluate_total_questions"
+    }
+)
+
+evaluate_total_questions_task = Task(
+    description="Evaluate the total number of questions in qa_pairs.csv file is 1",
+    expected_output="Total number of questions in qa_pairs.csv file",
+    agent=total_questions_evaluator,
+    task_type="decision",
+    name="evaluate_total_questions",
+    condition={
+        "more": "generate_task",
+        "done": "generate_cot"
+    }
+)
+
+generate_cot_task = Task(
+    name="generate_cot",
+    description="""Generate chain of thought solutions for each question in the input file. 
+Save to cot_solutions.csv file
+Don't generate chain of thought solutions again after receiving the response from Tool Call
+After calling the tool, respond with a JSON object:
+{
+    "response": "done",
+    "decision": "done"
+}
+""",
+    expected_output="done",
+    agent=cot_generator,
+    input_file="qa_pairs.csv",
+    task_type="loop",
+    next_tasks=["upload_to_huggingface"],
+    condition={
+        "done": ["upload_to_huggingface"],
+        "exit": [],
+    },
+    output_pydantic=DecisionModel  # Use Pydantic model for output validation
+)
+
+upload_to_huggingface_task = Task(
+    name="upload_to_huggingface",
+    description="""Upload to Huggingface:
+    1. Save to cot_solutions.csv
+    2. Upload to mervinpraison/cot-dataset""",
+    expected_output="Dataset published successfully",
+    agent=upload_to_huggingface,
+    tools=[cot_upload_to_huggingface]
+)
+
+# Initialize workflow
+agents = PraisonAIAgents(
+    agents=[qa_generator, total_questions_evaluator, cot_generator, upload_to_huggingface],
+    tasks=[generate_task, evaluate_total_questions_task, generate_cot_task, upload_to_huggingface_task],
+    process="workflow",
+    max_iter=30,
+    verbose=False
+)
+
+agents.start()

examples/image/image-agent-async.py

@@ -0,0 +1,15 @@
+import asyncio
+from praisonaiagents import ImageAgent
+
+async def main():
+    agent = ImageAgent(
+        name="ImageCreator",
+        llm="dall-e-3",
+        style="natural"
+    )
+
+    result = await agent.achat("A cute baby sea otter playing with a laptop")
+    print(f"Image generation result: {result}")
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/image/image-agent.py

@@ -0,0 +1,8 @@
+from praisonaiagents.agent.image_agent import ImageAgent
+
+# Create an image agent with normal mode
+agent = ImageAgent(llm="dall-e-3")
+
+# Generate an image
+result = agent.chat("A cute baby sea otter playing with a laptop")
+print("Image generation result:", result)

examples/models/deepseek/deepseek-agents.py

@@ -0,0 +1,9 @@
+# pip install praisonaiagents
+# export OPENAI_BASE_URL=http://localhost:11434/v1
+# ollama pull deepseek-r1
+
+from praisonaiagents import Agent
+
+agent = Agent(instructions="You are helpful Assisant", llm="deepseek-r1")
+
+agent.start("Why sky is Blue?")

examples/models/deepseek/deepseek-rag-agents-streamlit.py

@@ -0,0 +1,62 @@
+import streamlit as st
+from praisonaiagents import Agent
+
+def init_agent():
+    config = {
+        "vector_store": {
+            "provider": "chroma",
+            "config": {
+                "collection_name": "praison",
+                "path": ".praison"
+            }
+        },
+        "llm": {
+            "provider": "ollama",
+            "config": {
+                "model": "deepseek-r1:latest",
+                "temperature": 0,
+                "max_tokens": 8000,
+                "ollama_base_url": "http://localhost:11434",
+            },
+        },
+        "embedder": {
+            "provider": "ollama",
+            "config": {
+                "model": "nomic-embed-text:latest",
+                "ollama_base_url": "http://localhost:11434",
+                "embedding_dims": 1536
+            },
+        },
+    }
+    
+    return Agent(
+        name="Knowledge Agent",
+        instructions="You answer questions based on the provided knowledge.",
+        knowledge=["kag-research-paper.pdf"],
+        knowledge_config=config,
+        user_id="user1",
+        llm="deepseek-r1"
+    )
+
+st.title("Knowledge Agent Chat")
+
+if "agent" not in st.session_state:
+    st.session_state.agent = init_agent()
+    st.session_state.messages = []
+
+if "messages" in st.session_state:
+    for message in st.session_state.messages:
+        with st.chat_message(message["role"]):
+            st.markdown(message["content"])
+
+prompt = st.chat_input("Ask a question...")
+
+if prompt:
+    st.session_state.messages.append({"role": "user", "content": prompt})
+    with st.chat_message("user"):
+        st.markdown(prompt)
+
+    with st.chat_message("assistant"):
+        response = st.session_state.agent.start(prompt)
+        st.markdown(response)
+        st.session_state.messages.append({"role": "assistant", "content": response}) 

examples/models/deepseek/deepseek-rag-agents.py

@@ -0,0 +1,39 @@
+from praisonaiagents import Agent
+
+config = {
+    "vector_store": {
+        "provider": "chroma",
+        "config": {
+            "collection_name": "praison",
+            "path": ".praison"
+        }
+    },
+    "llm": {
+        "provider": "ollama",
+        "config": {
+            "model": "deepseek-r1:latest",
+            "temperature": 0,
+            "max_tokens": 8000,
+            "ollama_base_url": "http://localhost:11434",
+        },
+    },
+    "embedder": {
+        "provider": "ollama",
+        "config": {
+            "model": "nomic-embed-text:latest",
+            "ollama_base_url": "http://localhost:11434",
+            "embedding_dims": 1536
+        },
+    },
+}
+
+agent = Agent(
+    name="Knowledge Agent",
+    instructions="You answer questions based on the provided knowledge.",
+    knowledge=["kag-research-paper.pdf"], # Indexing
+    knowledge_config=config,
+    user_id="user1",
+    llm="deepseek-r1"
+)
+
+agent.start("What is KAG in one line?") # Retrieval

examples/models/googlegemini/any-llm-agents-advanced.py

@@ -0,0 +1,45 @@
+from praisonaiagents import Agent
+
+# Detailed LLM configuration
+llm_config = {
+    "model": "gemini/gemini-1.5-flash-latest",  # Model name without provider prefix
+    
+    # Core settings
+    "temperature": 0.7,                # Controls randomness (like temperature)
+    "timeout": 30,                 # Timeout in seconds
+    "top_p": 0.9,                    # Nucleus sampling parameter
+    "max_tokens": 1000,               # Max tokens in response
+    
+    # Advanced parameters
+    "presence_penalty": 0.1,         # Penalize repetition of topics (-2.0 to 2.0)
+    "frequency_penalty": 0.1,        # Penalize token repetition (-2.0 to 2.0)
+    
+    # API settings (optional)
+    "api_key": None,                 # Your API key (or use environment variable)
+    "base_url": None,                # Custom API endpoint if needed
+    
+    # Response formatting
+    "response_format": {             # Force specific response format
+        "type": "text"               # Options: "text", "json_object"
+    },
+    
+    # Additional controls
+    "seed": 42,                      # For reproducible responses
+    "stop_phrases": ["##", "END"],   # Custom stop sequences
+}
+
+agent = Agent(
+    instructions="You are a helpful Assistant specialized in scientific explanations. "
+                "Provide clear, accurate, and engaging responses.",
+    llm=llm_config,                  # Pass the detailed configuration
+    verbose=True,                    # Enable detailed output
+    markdown=True,                   # Format responses in markdown
+    self_reflect=True,              # Enable self-reflection
+    max_reflect=3,                  # Maximum reflection iterations
+    min_reflect=1                   # Minimum reflection iterations
+)
+
+# Test the agent
+response = agent.start("Why is the sky blue? Please explain in simple terms.")
+
+print(response)

examples/models/googlegemini/any-llm-agents-async.py

@@ -0,0 +1,18 @@
+import asyncio
+from praisonaiagents import Agent
+
+async def main():
+    agent = Agent(
+        instructions="You are a helpful assistant",
+        llm="gemini/gemini-1.5-flash-8b",
+        self_reflect=True,
+        verbose=True
+    )
+
+    # Use achat instead of start/chat for async operation
+    response = await agent.achat("Why sky is Blue in 1000 words?")
+    print(response)
+
+if __name__ == "__main__":
+    # Run the async main function
+    asyncio.run(main())

examples/models/googlegemini/any-llm-agents.py

@@ -0,0 +1,10 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a helpful assistant",
+    llm="gemini/gemini-1.5-flash-8b",
+    self_reflect=True,
+    verbose=True
+)
+
+agent.start("Why sky is Blue?")

examples/providers/ollama/ollama-agents.py

@@ -0,0 +1,9 @@
+# pip install praisonaiagents
+# export OPENAI_BASE_URL=http://localhost:11434/v1
+# ollama pull deepseek-r1
+
+from praisonaiagents import Agent
+
+agent = Agent(instructions="You are helpful Assisant", llm="deepseek-r1")
+
+agent.start("Why sky is Blue?")

examples/ui/gemini-streamlit.py

@@ -0,0 +1,32 @@
+import streamlit as st
+from praisonaiagents import Agent
+
+st.title("Gemini 2.0 Thinking AI Agent")
+
+# Initialize the agent
+@st.cache_resource
+def get_agent():
+    llm_config = {
+        "model": "gemini/gemini-2.0-flash-thinking-exp-01-21",
+        "response_format": {"type": "text"}
+    }
+    
+    return Agent(
+        instructions="You are a helpful assistant",
+        llm=llm_config
+    )
+
+agent = get_agent()
+
+# Create text area input field
+user_question = st.text_area("Ask your question:", height=150)
+
+# Add ask button
+if st.button("Ask"):
+    if user_question:
+        with st.spinner('Thinking...'):
+            result = agent.start(user_question)
+            st.write("### Answer")
+            st.write(result)
+    else:
+        st.warning("Please enter a question") 

examples/ui/ollama-rag-agents-streamlit.py

@@ -0,0 +1,62 @@
+import streamlit as st
+from praisonaiagents import Agent
+
+def init_agent():
+    config = {
+        "vector_store": {
+            "provider": "chroma",
+            "config": {
+                "collection_name": "praison",
+                "path": ".praison"
+            }
+        },
+        "llm": {
+            "provider": "ollama",
+            "config": {
+                "model": "deepseek-r1:latest",
+                "temperature": 0,
+                "max_tokens": 8000,
+                "ollama_base_url": "http://localhost:11434",
+            },
+        },
+        "embedder": {
+            "provider": "ollama",
+            "config": {
+                "model": "nomic-embed-text:latest",
+                "ollama_base_url": "http://localhost:11434",
+                "embedding_dims": 1536
+            },
+        },
+    }
+    
+    return Agent(
+        name="Knowledge Agent",
+        instructions="You answer questions based on the provided knowledge.",
+        knowledge=["kag-research-paper.pdf"],
+        knowledge_config=config,
+        user_id="user1",
+        llm="deepseek-r1"
+    )
+
+st.title("Knowledge Agent Chat")
+
+if "agent" not in st.session_state:
+    st.session_state.agent = init_agent()
+    st.session_state.messages = []
+
+if "messages" in st.session_state:
+    for message in st.session_state.messages:
+        with st.chat_message(message["role"]):
+            st.markdown(message["content"])
+
+prompt = st.chat_input("Ask a question...")
+
+if prompt:
+    st.session_state.messages.append({"role": "user", "content": prompt})
+    with st.chat_message("user"):
+        st.markdown(prompt)
+
+    with st.chat_message("assistant"):
+        response = st.session_state.agent.start(prompt)
+        st.markdown(response)
+        st.session_state.messages.append({"role": "assistant", "content": response}) 

praisonai.rb

@@ -3,7 +3,7 @@ class Praisonai < Formula
   
     desc "AI tools for various AI applications"
     homepage "https://github.com/MervinPraison/PraisonAI"
-    url "https://github.com/MervinPraison/PraisonAI/archive/refs/tags/2.0.54.tar.gz"
+    url "https://github.com/MervinPraison/PraisonAI/archive/refs/tags/2.0.71.tar.gz"
     sha256 "1828fb9227d10f991522c3f24f061943a254b667196b40b1a3e4a54a8d30ce32"  # Replace with actual SHA256 checksum
     license "MIT"
   

praisonai/cli.py

@@ -25,7 +25,6 @@ CALL_MODULE_AVAILABLE = False
 CREWAI_AVAILABLE = False
 AUTOGEN_AVAILABLE = False
 PRAISONAI_AVAILABLE = False
-
 try:
     # Create necessary directories and set CHAINLIT_APP_ROOT
     if "CHAINLIT_APP_ROOT" not in os.environ:
@@ -140,6 +139,8 @@ class PraisonAI:
         provided arguments.
         """
         args = self.parse_args()
+        # Store args for use in handle_direct_prompt
+        self.args = args
         invocation_cmd = "praisonai"
         version_string = f"PraisonAI version {__version__}"
 
@@ -148,8 +149,16 @@ class PraisonAI:
         if args.command:
             if args.command.startswith("tests.test"):  # Argument used for testing purposes
                 print("test")
+                return "test"
             else:
                 self.agent_file = args.command
+        elif hasattr(args, 'direct_prompt') and args.direct_prompt:
+            result = self.handle_direct_prompt(args.direct_prompt)
+            print(result)
+            return result
+        else:
+            # Default to agents.yaml if no command provided
+            self.agent_file = "agents.yaml"
 
         if args.deploy:
             from .deploy import CloudDeployer
@@ -192,6 +201,10 @@ class PraisonAI:
                 )
                 with open('config.yaml', 'w') as f:
                     yaml.dump(config, f, default_flow_style=False, indent=2)
+            else:
+                # Load existing config
+                with open(config_yaml_destination, 'r') as f:
+                    config = yaml.safe_load(f)
 
             # Overwrite huggingface_save and ollama_save if --hf or --ollama are provided
             if args.hf:
@@ -285,14 +298,18 @@ class PraisonAI:
         """
         Parse the command-line arguments for the PraisonAI CLI.
         """
+        # Define special commands
+        special_commands = ['chat', 'code', 'call', 'realtime', 'train', 'ui']
+        
         parser = argparse.ArgumentParser(prog="praisonai", description="praisonAI command-line interface")
         parser.add_argument("--framework", choices=["crewai", "autogen", "praisonai"], help="Specify the framework")
         parser.add_argument("--ui", choices=["chainlit", "gradio"], help="Specify the UI framework (gradio or chainlit).")
         parser.add_argument("--auto", nargs=argparse.REMAINDER, help="Enable auto mode and pass arguments for it")
         parser.add_argument("--init", nargs=argparse.REMAINDER, help="Initialize agents with optional topic")
-        parser.add_argument("command", nargs="?", help="Command to run")
+        parser.add_argument("command", nargs="?", help="Command to run or direct prompt")
         parser.add_argument("--deploy", action="store_true", help="Deploy the application")
         parser.add_argument("--model", type=str, help="Model name")
+        parser.add_argument("--llm", type=str, help="LLM model to use for direct prompts")
         parser.add_argument("--hf", type=str, help="Hugging Face model name")
         parser.add_argument("--ollama", type=str, help="Ollama model name")
         parser.add_argument("--dataset", type=str, help="Dataset name for training", default="yahma/alpaca-cleaned")
@@ -301,6 +318,7 @@ class PraisonAI:
         parser.add_argument("--public", action="store_true", help="Use ngrok to expose the server publicly (only with --call)")
         args, unknown_args = parser.parse_known_args()
 
+        # Handle special cases first
         if unknown_args and unknown_args[0] == '-b' and unknown_args[1] == 'api:app':
             args.command = 'agents.yaml'
         if args.command == 'api:app' or args.command == '/app/api:app':
@@ -331,9 +349,7 @@ class PraisonAI:
             call_module.main(call_args)
             sys.exit(0)
 
-        # Handle special commands first
-        special_commands = ['chat', 'code', 'call', 'realtime', 'train', 'ui']
-
+        # Handle special commands
         if args.command in special_commands:
             if args.command == 'chat':
                 if not CHAINLIT_AVAILABLE:
@@ -380,9 +396,8 @@ class PraisonAI:
                 sys.exit(0)
 
             elif args.command == 'train':
-                print("[red]ERROR: Train feature is not installed. Install with:[/red]")
-                print("\npip install \"praisonai[train]\"\n")
-                sys.exit(1)
+                package_root = os.path.dirname(os.path.abspath(__file__))
+                config_yaml_destination = os.path.join(os.getcwd(), 'config.yaml')
 
             elif args.command == 'ui':
                 if not CHAINLIT_AVAILABLE:
@@ -402,8 +417,78 @@ class PraisonAI:
                 print("pip install praisonaiagents # For PraisonAIAgents\n")  
                 sys.exit(1)
 
+        # Handle direct prompt if command is not a special command or file
+        if args.command and not args.command.endswith('.yaml') and args.command not in special_commands:
+            args.direct_prompt = args.command
+            args.command = None
+
         return args
 
+    def handle_direct_prompt(self, prompt):
+        """
+        Handle direct prompt by creating a single agent and running it.
+        """
+        if PRAISONAI_AVAILABLE:
+            agent_config = {
+                "name": "DirectAgent",
+                "role": "Assistant",
+                "goal": "Complete the given task",
+                "backstory": "You are a helpful AI assistant"
+            }
+            
+            # Add llm if specified
+            if hasattr(self, 'args') and self.args.llm:
+                agent_config["llm"] = self.args.llm
+            
+            agent = PraisonAgent(**agent_config)
+            result = agent.start(prompt)
+            return ""
+        elif CREWAI_AVAILABLE:
+            agent_config = {
+                "name": "DirectAgent",
+                "role": "Assistant",
+                "goal": "Complete the given task",
+                "backstory": "You are a helpful AI assistant"
+            }
+            
+            # Add llm if specified
+            if hasattr(self, 'args') and self.args.llm:
+                agent_config["llm"] = self.args.llm
+            
+            agent = Agent(**agent_config)
+            task = Task(
+                description=prompt,
+                agent=agent
+            )
+            crew = Crew(
+                agents=[agent],
+                tasks=[task]
+            )
+            return crew.kickoff()
+        elif AUTOGEN_AVAILABLE:
+            config_list = self.config_list
+            # Add llm if specified
+            if hasattr(self, 'args') and self.args.llm:
+                config_list[0]['model'] = self.args.llm
+                
+            assistant = autogen.AssistantAgent(
+                name="DirectAgent",
+                llm_config={"config_list": config_list}
+            )
+            user_proxy = autogen.UserProxyAgent(
+                name="UserProxy",
+                code_execution_config={"work_dir": "coding"}
+            )
+            user_proxy.initiate_chat(assistant, message=prompt)
+            return "Task completed"
+        else:
+            print("[red]ERROR: No framework is installed. Please install at least one framework:[/red]")
+            print("\npip install \"praisonai\\[crewai]\"  # For CrewAI")
+            print("pip install \"praisonai\\[autogen]\"  # For AutoGen")
+            print("pip install \"praisonai\\[crewai,autogen]\"  # For both frameworks\n")
+            print("pip install praisonaiagents # For PraisonAIAgents\n")  
+            sys.exit(1)
+
     def create_chainlit_chat_interface(self):
         """
         Create a Chainlit interface for the chat application.

praisonai/deploy.py

@@ -56,7 +56,7 @@ class CloudDeployer:
             file.write("FROM python:3.11-slim\n")
             file.write("WORKDIR /app\n")
             file.write("COPY . .\n")
-            file.write("RUN pip install flask praisonai==2.0.54 gunicorn markdown\n")
+            file.write("RUN pip install flask praisonai==2.0.71 gunicorn markdown\n")
             file.write("EXPOSE 8080\n")
             file.write('CMD ["gunicorn", "-b", "0.0.0.0:8080", "api:app"]\n')
             

praisonai/setup/setup_conda_env.sh

@@ -11,6 +11,38 @@ if [[ "$OSTYPE" == "darwin"* ]]; then
 elif [[ "$OSTYPE" == "linux-gnu"* ]]; then
     # Linux
     MINICONDA_URL="https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh"
+    
+    # Install libcurl development package if not present (Debian based)
+    if command -v dpkg &> /dev/null; then
+        if ! dpkg -s libcurl4-openssl-dev &> /dev/null; then
+            echo "libcurl4-openssl-dev is not installed. Installing..."
+            sudo apt-get update
+            sudo apt-get install -y libcurl4-openssl-dev
+        else
+            echo "libcurl4-openssl-dev is already installed."
+        fi
+    else
+        echo "Non-Debian based Linux detected. Please ensure libcurl development libraries are installed."
+    fi
+
+    # Check if ollama is installed and executable; if not, install it
+    if ! command -v ollama &> /dev/null; then
+        echo "Ollama is not installed. Installing Ollama..."
+        curl -fsSL https://ollama.com/install.sh | sh
+        
+        # Generate SSH key non-interactively only if it doesn't already exist
+        if [ ! -f ~/.ssh/id_ed25519 ]; then
+            echo "Generating SSH key for Ollama..."
+            ssh-keygen -t ed25519 -N "" -f ~/.ssh/id_ed25519 -q
+        else
+            echo "SSH key ~/.ssh/id_ed25519 already exists. Skipping generation."
+        fi
+        echo "Copying SSH key to /usr/share/ollama/.ollama..."
+        sudo cp ~/.ssh/id_ed25519 /usr/share/ollama/.ollama
+    else
+        echo "Ollama is already installed."
+    fi
+
 elif [[ "$OSTYPE" == "msys" || "$OSTYPE" == "win32" ]]; then
     # Windows
     MINICONDA_URL="https://repo.anaconda.com/miniconda/Miniconda3-latest-Windows-x86_64.exe"
@@ -21,12 +53,12 @@ else
     exit 1
 fi
 
-# Check if conda is already installed
+# Check if conda is installed
 if ! command -v conda &> /dev/null; then
     echo "Conda is not installed. Installing Miniconda..."
-    wget $MINICONDA_URL -O ~/miniconda.sh
-    bash ~/miniconda.sh -b -p $HOME/miniconda
-    source $HOME/miniconda/bin/activate
+    wget "$MINICONDA_URL" -O ~/miniconda.sh
+    bash ~/miniconda.sh -b -p "$HOME/miniconda"
+    source "$HOME/miniconda/bin/activate"
     conda init
 else
     echo "Conda is already installed."
@@ -34,39 +66,40 @@ fi
 
 # Create and activate the Conda environment
 ENV_NAME="praison_env"
-if conda info --envs | grep -q $ENV_NAME; then
+if conda info --envs | grep -q "$ENV_NAME"; then
     echo "Environment $ENV_NAME already exists. Recreating..."
-    conda env remove -y -n $ENV_NAME  # Remove existing environment
+    conda env remove -y -n "$ENV_NAME"
     if [[ "$OSTYPE" == "darwin"* ]]; then
-        # macOS (both Intel and M1/M2)
-        conda create --name $ENV_NAME python=3.10 pytorch=2.3.0 -c pytorch -y
+        conda create --name "$ENV_NAME" python=3.10 pytorch=2.3.0 -c pytorch -y
     elif [[ "$OSTYPE" == "linux-gnu"* ]]; then
-        # Linux
-        conda create --name $ENV_NAME python=3.10 pytorch=2.3.0 cudatoolkit=11.8 -c pytorch -c nvidia -y
+        conda create --name "$ENV_NAME" python=3.10 pytorch=2.3.0 cudatoolkit=11.8 -c pytorch -c nvidia -y
     fi
-    # conda activate $ENV_NAME
 else
     echo "Creating new environment $ENV_NAME..."
     if [[ "$OSTYPE" == "darwin"* ]]; then
-        # macOS (both Intel and M1/M2)
-        conda create --name $ENV_NAME python=3.10 pytorch=2.3.0 -c pytorch -y
+        conda create --name "$ENV_NAME" python=3.10 pytorch=2.3.0 -c pytorch -y
     elif [[ "$OSTYPE" == "linux-gnu"* ]]; then
-        # Linux
-        conda create --name $ENV_NAME python=3.10 pytorch=2.3.0 cudatoolkit=11.8 -c pytorch -c nvidia -y
+        conda create --name "$ENV_NAME" python=3.10 pytorch=2.3.0 cudatoolkit=11.8 -c pytorch -c nvidia -y
     fi
-    # conda activate $ENV_NAME
 fi
 
-# source $HOME/miniconda/bin/activate $ENV_NAME
+# Activate the environment
+source "$HOME/miniconda/bin/activate" "$ENV_NAME"
 
-# Get full path of pip
-PIP_FULL_PATH=$(conda run -n $ENV_NAME which pip)
+# Install cmake via conda
+echo "Installing cmake..."
+conda install -y cmake
 
-# Install other packages within the activated environment
-# Use PIP_FULL_PATH to run pip commands
+# Get full path of pip within the activated environment
+PIP_FULL_PATH=$(conda run -n "$ENV_NAME" which pip)
+
+# Install other packages using pip
 $PIP_FULL_PATH install --upgrade pip 
 $PIP_FULL_PATH install "xformers==0.0.26.post1"
-$PIP_FULL_PATH install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git@4e570be9ae4ced8cdc64e498125708e34942befc"
+$PIP_FULL_PATH install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git@038e6d4c8d40207a87297ab3aaf787c19b1006d1"
 $PIP_FULL_PATH install --no-deps "trl<0.9.0" peft accelerate bitsandbytes 
+$PIP_FULL_PATH install unsloth_zoo
+$PIP_FULL_PATH install cut_cross_entropy
+$PIP_FULL_PATH install sentencepiece protobuf datasets huggingface_hub hf_transfer wandb
 
 echo "Setup completed successfully!"

praisonai/train.py

@@ -1,168 +1,283 @@
-import subprocess
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+"""
+This script finetunes a model using Unsloth’s fast training framework.
+It supports both ShareGPT and Alpaca‑style datasets by converting raw conversation
+data into plain-text prompts using a chat template, then pre‑tokenizing the prompts.
+Extra debug logging is added to help trace the root cause of errors.
+"""
+
 import os
 import sys
 import yaml
 import torch
 import shutil
+import subprocess
 from transformers import TextStreamer
 from unsloth import FastLanguageModel, is_bfloat16_supported
 from trl import SFTTrainer
 from transformers import TrainingArguments
-from datasets import load_dataset, concatenate_datasets, Dataset
+from datasets import load_dataset, concatenate_datasets
 from psutil import virtual_memory
+from unsloth.chat_templates import standardize_sharegpt, get_chat_template
+from functools import partial
 
-class train:
+#####################################
+# Step 1: Formatting Raw Conversations
+#####################################
+def formatting_prompts_func(examples, tokenizer):
+    """
+    Converts each example’s conversation into a single plain-text prompt.
+    If the example has a "conversations" field, process it as ShareGPT-style.
+    Otherwise, assume Alpaca-style data with "instruction", "input", and "output" fields.
+    """
+    print("DEBUG: formatting_prompts_func() received batch with keys:", list(examples.keys()))
+    texts = []
+    # Check if the example has a "conversations" field.
+    if "conversations" in examples:
+        for convo in examples["conversations"]:
+            try:
+                formatted = tokenizer.apply_chat_template(
+                    convo,
+                    tokenize=False,  # Return a plain string
+                    add_generation_prompt=False
+                )
+            except Exception as e:
+                print(f"ERROR in apply_chat_template (conversations): {e}")
+                formatted = ""
+            # Flatten list if necessary
+            if isinstance(formatted, list):
+                formatted = formatted[0] if len(formatted) == 1 else "\n".join(formatted)
+            texts.append(formatted)
+    else:
+        # Assume Alpaca format: use "instruction", "input", and "output" keys.
+        instructions = examples.get("instruction", [])
+        inputs_list = examples.get("input", [])
+        outputs_list = examples.get("output", [])
+        # If any field is missing, replace with empty string.
+        for ins, inp, out in zip(instructions, inputs_list, outputs_list):
+            # Create a conversation-like structure.
+            convo = [
+                {"role": "user", "content": ins + (f"\nInput: {inp}" if inp.strip() != "" else "")},
+                {"role": "assistant", "content": out}
+            ]
+            try:
+                formatted = tokenizer.apply_chat_template(
+                    convo,
+                    tokenize=False,
+                    add_generation_prompt=False
+                )
+            except Exception as e:
+                print(f"ERROR in apply_chat_template (alpaca): {e}")
+                formatted = ""
+            if isinstance(formatted, list):
+                formatted = formatted[0] if len(formatted) == 1 else "\n".join(formatted)
+            texts.append(formatted)
+    if texts:
+        print("DEBUG: Raw texts sample (first 200 chars):", texts[0][:200])
+    return {"text": texts}
+
+#####################################
+# Step 2: Tokenizing the Prompts
+#####################################
+def tokenize_function(examples, hf_tokenizer, max_length):
+    """
+    Tokenizes a batch of text prompts with padding and truncation enabled.
+    """
+    flat_texts = []
+    for t in examples["text"]:
+        if isinstance(t, list):
+            t = t[0] if len(t) == 1 else " ".join(t)
+        flat_texts.append(t)
+    print("DEBUG: Tokenizing a batch of size:", len(flat_texts))
+    tokenized = hf_tokenizer(
+        flat_texts,
+        padding="max_length",
+        truncation=True,
+        max_length=max_length,
+        return_tensors="pt",
+    )
+    tokenized = {key: value.tolist() for key, value in tokenized.items()}
+    sample_key = list(tokenized.keys())[0]
+    print("DEBUG: Tokenized sample (first 10 tokens of", sample_key, "):", tokenized[sample_key][0][:10])
+    return tokenized
+
+#####################################
+# Main Training Class
+#####################################
+class TrainModel:
     def __init__(self, config_path="config.yaml"):
         self.load_config(config_path)
         self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-        self.model, self.tokenizer = None, None
+        self.model = None
+        self.hf_tokenizer = None   # The underlying HF tokenizer
+        self.chat_tokenizer = None # Chat wrapper for formatting
 
     def load_config(self, path):
         with open(path, "r") as file:
             self.config = yaml.safe_load(file)
+        print("DEBUG: Loaded config:", self.config)
 
     def print_system_info(self):
-        print(f"PyTorch version: {torch.__version__}")
-        print(f"CUDA version: {torch.version.cuda}")
+        print("DEBUG: PyTorch version:", torch.__version__)
+        print("DEBUG: CUDA version:", torch.version.cuda)
         if torch.cuda.is_available():
-            device_capability = torch.cuda.get_device_capability()
-            print(f"CUDA Device Capability: {device_capability}")
+            print("DEBUG: CUDA Device Capability:", torch.cuda.get_device_capability())
         else:
-            print("CUDA is not available")
-
-        python_version = sys.version
-        pip_version = subprocess.check_output(['pip', '--version']).decode().strip()
-        python_path = sys.executable
-        pip_path = subprocess.check_output(['which', 'pip']).decode().strip()
-        print(f"Python Version: {python_version}")
-        print(f"Pip Version: {pip_version}")
-        print(f"Python Path: {python_path}")
-        print(f"Pip Path: {pip_path}")
+            print("DEBUG: CUDA is not available")
+        print("DEBUG: Python Version:", sys.version)
+        print("DEBUG: Python Path:", sys.executable)
 
     def check_gpu(self):
         gpu_stats = torch.cuda.get_device_properties(0)
-        print(f"GPU = {gpu_stats.name}. Max memory = {round(gpu_stats.total_memory / 1024 / 1024 / 1024, 3)} GB.")
+        print(f"DEBUG: GPU = {gpu_stats.name}. Max memory = {round(gpu_stats.total_memory/(1024**3),3)} GB.")
 
     def check_ram(self):
         ram_gb = virtual_memory().total / 1e9
-        print('Your runtime has {:.1f} gigabytes of available RAM\n'.format(ram_gb))
+        print(f"DEBUG: Your runtime has {ram_gb:.1f} gigabytes of available RAM")
         if ram_gb < 20:
-            print('Not using a high-RAM runtime')
+            print("DEBUG: Not using a high-RAM runtime")
         else:
-            print('You are using a high-RAM runtime!')
-
-    # def install_packages(self):
-    #     subprocess.run(["pip", "install", "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git@4e570be9ae4ced8cdc64e498125708e34942befc"])
-    #     subprocess.run(["pip", "install", "--no-deps", "trl<0.9.0", "peft==0.12.0", "accelerate==0.33.0", "bitsandbytes==0.43.3"])
+            print("DEBUG: You are using a high-RAM runtime!")
 
     def prepare_model(self):
-        self.model, self.tokenizer = FastLanguageModel.from_pretrained(
+        print("DEBUG: Preparing model and tokenizer...")
+        self.model, original_tokenizer = FastLanguageModel.from_pretrained(
             model_name=self.config["model_name"],
             max_seq_length=self.config["max_seq_length"],
             dtype=None,
-            load_in_4bit=self.config["load_in_4bit"]
+            load_in_4bit=self.config["load_in_4bit"],
         )
+        print("DEBUG: Model and original tokenizer loaded.")
+        if original_tokenizer.pad_token is None:
+            original_tokenizer.pad_token = original_tokenizer.eos_token
+        original_tokenizer.model_max_length = self.config["max_seq_length"]
+        self.chat_tokenizer = get_chat_template(original_tokenizer, chat_template="llama-3.1")
+        self.hf_tokenizer = original_tokenizer
+        print("DEBUG: Chat tokenizer created; HF tokenizer saved.")
         self.model = FastLanguageModel.get_peft_model(
             self.model,
-            r=self.config["lora_r"],
-            target_modules=self.config["lora_target_modules"],
-            lora_alpha=self.config["lora_alpha"],
-            lora_dropout=self.config["lora_dropout"],
-            bias=self.config["lora_bias"],
-            use_gradient_checkpointing=self.config["use_gradient_checkpointing"],
-            random_state=self.config["random_state"],
-            use_rslora=self.config["use_rslora"],
-            loftq_config=self.config["loftq_config"],
+            r=16,
+            target_modules=["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"],
+            lora_alpha=16,
+            lora_dropout=0,
+            bias="none",
+            use_gradient_checkpointing="unsloth",
+            random_state=3407,
+            use_rslora=False,
+            loftq_config=None,
         )
+        print("DEBUG: LoRA adapters added.")
 
     def process_dataset(self, dataset_info):
         dataset_name = dataset_info["name"]
         split_type = dataset_info.get("split_type", "train")
-        processing_func = getattr(self, dataset_info.get("processing_func", "format_prompts"))
-        rename = dataset_info.get("rename", {})
-        filter_data = dataset_info.get("filter_data", False)
-        filter_column_value = dataset_info.get("filter_column_value", "id")
-        filter_value = dataset_info.get("filter_value", "alpaca")
-        num_samples = dataset_info.get("num_samples", 20000)
-
+        print(f"DEBUG: Loading dataset '{dataset_name}' split '{split_type}'...")
         dataset = load_dataset(dataset_name, split=split_type)
-
-        if rename:
-            dataset = dataset.rename_columns(rename)
-        if filter_data:
-            dataset = dataset.filter(lambda example: filter_value in example[filter_column_value]).shuffle(seed=42).select(range(num_samples))
-        dataset = dataset.map(processing_func, batched=True)
+        print("DEBUG: Dataset columns:", dataset.column_names)
+        if "conversations" in dataset.column_names:
+            print("DEBUG: Standardizing dataset (ShareGPT style)...")
+            dataset = standardize_sharegpt(dataset)
+        else:
+            print("DEBUG: Dataset does not have 'conversations'; assuming Alpaca format.")
+        print("DEBUG: Applying formatting function to dataset...")
+        format_func = partial(formatting_prompts_func, tokenizer=self.chat_tokenizer)
+        dataset = dataset.map(format_func, batched=True, remove_columns=dataset.column_names)
+        sample = dataset[0]
+        print("DEBUG: Sample processed example keys:", list(sample.keys()))
+        if "text" in sample:
+            print("DEBUG: Sample processed 'text' type:", type(sample["text"]))
+            print("DEBUG: Sample processed 'text' content (first 200 chars):", sample["text"][:200])
+        else:
+            print("DEBUG: Processed sample does not contain 'text'.")
         return dataset
 
-    def format_prompts(self, examples):
-        alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
-
-        ### Instruction:
-        {}
-
-        ### Input:
-        {}
-
-        ### Response:
-        {}"""
-        texts = [alpaca_prompt.format(ins, inp, out) + self.tokenizer.eos_token for ins, inp, out in zip(examples["instruction"], examples["input"], examples["output"])]
-        return {"text": texts}
+    def tokenize_dataset(self, dataset):
+        print("DEBUG: Tokenizing the entire dataset...")
+        tokenized_dataset = dataset.map(
+            lambda examples: tokenize_function(examples, self.hf_tokenizer, self.config["max_seq_length"]),
+            batched=True
+        )
+        tokenized_dataset = tokenized_dataset.remove_columns(["text"])
+        print("DEBUG: Tokenized dataset sample keys:", tokenized_dataset[0].keys())
+        return tokenized_dataset
 
     def load_datasets(self):
         datasets = []
         for dataset_info in self.config["dataset"]:
+            print("DEBUG: Processing dataset info:", dataset_info)
             datasets.append(self.process_dataset(dataset_info))
-        return concatenate_datasets(datasets)
+        combined = concatenate_datasets(datasets)
+        print("DEBUG: Combined dataset has", len(combined), "examples.")
+        return combined
 
     def train_model(self):
-        dataset = self.load_datasets()
+        print("DEBUG: Starting training...")
+        raw_dataset = self.load_datasets()
+        tokenized_dataset = self.tokenize_dataset(raw_dataset)
+        print("DEBUG: Dataset tokenization complete.")
+        training_args = TrainingArguments(
+            per_device_train_batch_size=2,
+            gradient_accumulation_steps=4,
+            warmup_steps=5,
+            max_steps=60,
+            learning_rate=2e-4,
+            fp16=not is_bfloat16_supported(),
+            bf16=is_bfloat16_supported(),
+            logging_steps=1,
+            optim="adamw_8bit",
+            weight_decay=0.01,
+            lr_scheduler_type="linear",
+            seed=3407,
+            output_dir="outputs",
+            report_to="none" if not os.getenv("PRAISON_WANDB") else "wandb",
+            save_steps=100 if os.getenv("PRAISON_WANDB") else None,
+            run_name=os.getenv("PRAISON_WANDB_RUN_NAME", "praisonai-train") if os.getenv("PRAISON_WANDB") else None,
+            remove_unused_columns=False,
+        )
+        # Since the dataset is pre-tokenized, we supply a dummy dataset_text_field.
         trainer = SFTTrainer(
             model=self.model,
-            tokenizer=self.tokenizer,
-            train_dataset=dataset,
-            dataset_text_field=self.config["dataset_text_field"],
+            tokenizer=self.hf_tokenizer,
+            train_dataset=tokenized_dataset,
+            dataset_text_field="input_ids",  # Dummy field since data is numeric
             max_seq_length=self.config["max_seq_length"],
-            dataset_num_proc=self.config["dataset_num_proc"],
-            packing=self.config["packing"],
-            args=TrainingArguments(
-                per_device_train_batch_size=self.config["per_device_train_batch_size"],
-                gradient_accumulation_steps=self.config["gradient_accumulation_steps"],
-                warmup_steps=self.config["warmup_steps"],
-                num_train_epochs=self.config["num_train_epochs"],
-                max_steps=self.config["max_steps"],
-                learning_rate=self.config["learning_rate"],
-                fp16=not is_bfloat16_supported(),
-                bf16=is_bfloat16_supported(),
-                logging_steps=self.config["logging_steps"],
-                optim=self.config["optim"],
-                weight_decay=self.config["weight_decay"],
-                lr_scheduler_type=self.config["lr_scheduler_type"],
-                seed=self.config["seed"],
-                output_dir=self.config["output_dir"],
-            ),
+            dataset_num_proc=1,  # Use a single process to avoid pickling issues
+            packing=False,
+            args=training_args,
         )
+        from unsloth.chat_templates import train_on_responses_only
+        trainer = train_on_responses_only(
+            trainer,
+            instruction_part="<|start_header_id|>user<|end_header_id|>\n\n",
+            response_part="<|start_header_id|>assistant<|end_header_id|>\n\n",
+        )
+        print("DEBUG: Beginning trainer.train() ...")
         trainer.train()
-        self.model.save_pretrained("lora_model") # Local saving
-        self.tokenizer.save_pretrained("lora_model")
+        print("DEBUG: Training complete. Saving model and tokenizer locally...")
+        self.model.save_pretrained("lora_model")
+        self.hf_tokenizer.save_pretrained("lora_model")
+        print("DEBUG: Saved model and tokenizer to 'lora_model'.")
 
     def inference(self, instruction, input_text):
         FastLanguageModel.for_inference(self.model)
-        alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
+        messages = [{"role": "user", "content": f"{instruction}\n\nInput: {input_text}"}]
+        inputs = self.hf_tokenizer.apply_chat_template(
+            messages,
+            tokenize=True,
+            add_generation_prompt=True,
+            return_tensors="pt"
+        ).to("cuda")
+        outputs = self.model.generate(
+            input_ids=inputs,
+            max_new_tokens=64,
+            use_cache=True,
+            temperature=1.5,
+            min_p=0.1
+        )
+        print("DEBUG: Inference output:", self.hf_tokenizer.batch_decode(outputs))
 
-        ### Instruction:
-        {}
-
-        ### Input:
-        {}
-
-        ### Response:
-        {}"""
-        inputs = self.tokenizer([alpaca_prompt.format(instruction, input_text, "")], return_tensors="pt").to("cuda")
-        outputs = self.model.generate(**inputs, max_new_tokens=64, use_cache=True)
-        print(self.tokenizer.batch_decode(outputs))
-        
     def load_model(self):
-        """Loads the model and tokenizer using the FastLanguageModel library."""
         from unsloth import FastLanguageModel
         model, tokenizer = FastLanguageModel.from_pretrained(
             model_name=self.config["output_dir"],
@@ -177,56 +292,233 @@ class train:
             shutil.rmtree(self.config["hf_model_name"])
         self.model.push_to_hub_merged(
             self.config["hf_model_name"],
-            self.tokenizer,
+            self.hf_tokenizer,
             save_method="merged_16bit",
-            token=os.getenv('HF_TOKEN')
+            token=os.getenv("HF_TOKEN")
         )
 
     def push_model_gguf(self):
         self.model.push_to_hub_gguf(
             self.config["hf_model_name"],
-            self.tokenizer,
+            self.hf_tokenizer,
             quantization_method=self.config["quantization_method"],
-            token=os.getenv('HF_TOKEN')
+            token=os.getenv("HF_TOKEN")
         )
-    
+
     def save_model_gguf(self):
         self.model.save_pretrained_gguf(
             self.config["hf_model_name"],
-            self.tokenizer,
+            self.hf_tokenizer,
             quantization_method="q4_k_m"
         )
 
     def prepare_modelfile_content(self):
         output_model = self.config["hf_model_name"]
-        gguf_path = f"{output_model}/unsloth.Q4_K_M.gguf"
+        model_name = self.config["model_name"].lower()
+        # Mapping from model name keywords to their default TEMPLATE and stop tokens (and optional SYSTEM/num_ctx)
+        mapping = {
+            "llama": {
+                "template": """<|start_header_id|>system<|end_header_id|>
+    Cutting Knowledge Date: December 2023
+    {{ if .System }}{{ .System }}
+    {{- end }}
+    {{- if .Tools }}When you receive a tool call response, use the output to format an answer to the orginal user question.
+    You are a helpful assistant with tool calling capabilities.
+    {{- end }}<|eot_id|>
+    {{- range $i, $_ := .Messages }}
+    {{- $last := eq (len (slice $.Messages $i)) 1 }}
+    {{- if eq .Role "user" }}<|start_header_id|>user<|end_header_id|>
+    {{- if and $.Tools $last }}
+    Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt.
+    Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. Do not use variables.
+    {{ range $.Tools }}
+    {{- . }}
+    {{ end }}
+    {{ .Content }}<|eot_id|>
+    {{- else }}
+    {{ .Content }}<|eot_id|>
+    {{- end }}{{ if $last }}<|start_header_id|>assistant<|end_header_id|>
+    {{ end }}
+    {{- else if eq .Role "assistant" }}<|start_header_id|>assistant<|end_header_id|>
+    {{- if .ToolCalls }}
+    {{ range .ToolCalls }}
+    {"name": "{{ .Function.Name }}", "parameters": {{ .Function.Arguments }}}{{ end }}
+    {{- else }}
+    {{ .Content }}
+    {{- end }}{{ if not $last }}<|eot_id|>{{ end }}
+    {{- else if eq .Role "tool" }}<|start_header_id|>ipython<|end_header_id|>
+    {{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|>
+    {{ end }}
+    {{- end }}
+    {{- end }}""",
+                "stop_tokens": ["<|start_header_id|>", "<|end_header_id|>", "<|eot_id|>"]
+            },
+            "qwen": {
+                "template": """{{- if .Suffix }}<|fim_prefix|>{{ .Prompt }}<|fim_suffix|>{{ .Suffix }}<|fim_middle|>
+    {{- else if .Messages }}
+    {{- if or .System .Tools }}<|im_start|>system
+    {{- if .System }}
+    {{ .System }}
+    {{- end }}
+    {{- if .Tools }}
+    # Tools
+    You may call one or more functions to assist with the user query.
+    You are provided with function signatures within <tools></tools> XML tags:
+    <tools>
+    {{- range .Tools }}
+    {"type": "function", "function": {{ .Function }}}
+    {{- end }}
+    </tools>
+    For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
+    <tool_call>
+    {"name": <function-name>, "arguments": <args-json-object>}
+    </tool_call>
+    {{- end }}<|im_end|>
+    {{ end }}
+    {{- range $i, $_ := .Messages }}
+    {{- $last := eq (len (slice $.Messages $i)) 1 -}}
+    {{- if eq .Role "user" }}<|im_start|>user
+    {{ .Content }}<|im_end|>
+    {{ else if eq .Role "assistant" }}<|im_start|>assistant
+    {{ if .Content }}{{ .Content }}
+    {{- else if .ToolCalls }}<tool_call>
+    {{ range .ToolCalls }}{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}}
+    {{ end }}</tool_call>
+    {{- end }}{{ if not $last }}<|im_end|>
+    {{ end }}
+    {{- else if eq .Role "tool" }}<|im_start|>user
+    <tool_response>
+    {{ .Content }}
+    </tool_response><|im_end|>
+    {{ end }}
+    {{- if and (ne .Role "assistant") $last }}<|im_start|>assistant
+    {{ end }}
+    {{- end }}
+    {{- else }}
+    {{- if .System }}<|im_start|>system
+    {{ .System }}<|im_end|>
+    {{ end }}{{ if .Prompt }}<|im_start|>user
+    {{ .Prompt }}<|im_end|>
+    {{ end }}<|im_start|>assistant
+    {{ end }}{{ .Response }}{{ if .Response }}<|im_end|>{{ end }}""",
+                "system": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant.",
+                "num_ctx": 32768,
+                "stop_tokens": ["<|endoftext|>"]
+            },
+            "mistral": {
+                "template": "[INST] {{ if .System }}{{ .System }} {{ end }}{{ .Prompt }} [/INST]",
+                "stop_tokens": ["[INST]", "[/INST]"]
+            },
+            "phi": {
+                "template": """{{- range $i, $_ := .Messages }}
+    {{- $last := eq (len (slice $.Messages $i)) 1 -}}
+    <|im_start|>{{ .Role }}<|im_sep|>
+    {{ .Content }}{{ if not $last }}<|im_end|>
+    {{ end }}
+    {{- if and (ne .Role "assistant") $last }}<|im_end|>
+    <|im_start|>assistant<|im_sep|>
+    {{ end }}
+    {{- end }}""",
+                "stop_tokens": ["<|im_start|>", "<|im_end|>", "<|im_sep|>"]
+            },
+            "deepseek": {
+                "template": """{{- if .System }}{{ .System }}{{ end }}
+    {{- range $i, $_ := .Messages }}
+    {{- $last := eq (len (slice $.Messages $i)) 1}}
+    {{- if eq .Role "user" }}<｜User｜>{{ .Content }}
+    {{- else if eq .Role "assistant" }}<｜Assistant｜>{{ .Content }}{{- if not $last }}<｜end▁of▁sentence｜>{{- end }}
+    {{- end }}
+    {{- if and $last (ne .Role "assistant") }}<｜Assistant｜>{{- end }}
+    {{- end }}""",
+                "stop_tokens": ["<｜begin▁of▁sentence｜>", "<｜end▁of▁sentence｜>", "<｜User｜>", "<｜Assistant｜>"]
+            },
+            "llava": {
+                "template": """{{- if .Suffix }}<|fim_prefix|>{{ .Prompt }}<|fim_suffix|>{{ .Suffix }}<|fim_middle|>
+    {{- else if .Messages }}
+    {{- if or .System .Tools }}<|im_start|>system
+    {{- if .System }}
+    {{ .System }}
+    {{- end }}
+    {{- if .Tools }}
+    # Tools
+    You may call one or more functions to assist with the user query.
+    You are provided with function signatures within <tools></tools> XML tags:
+    <tools>
+    {{- range .Tools }}
+    {"type": "function", "function": {{ .Function }}}
+    {{- end }}
+    </tools>
+    For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
+    <tool_call>
+    {"name": <function-name>, "arguments": <args-json-object>}
+    </tool_call>
+    {{- end }}<|im_end|>
+    {{ end }}
+    {{- range $i, $_ := .Messages }}
+    {{- $last := eq (len (slice $.Messages $i)) 1 -}}
+    {{- if eq .Role "user" }}<|im_start|>user
+    {{ .Content }}<|im_end|>
+    {{ else if eq .Role "assistant" }}<|im_start|>assistant
+    {{ if .Content }}{{ .Content }}
+    {{- else if .ToolCalls }}<tool_call>
+    {{ range .ToolCalls }}{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}}
+    {{ end }}</tool_call>
+    {{- end }}{{ if not $last }}<|im_end|>
+    {{ end }}
+    {{- else if eq .Role "tool" }}<|im_start|>user
+    <tool_response>
+    {{ .Content }}
+    </tool_response><|im_end|>
+    {{ end }}
+    {{- if and (ne .Role "assistant") $last }}<|im_start|>assistant
+    {{ end }}
+    {{- end }}
+    {{- else }}
+    {{- if .System }}<|im_start|>system
+    {{ .System }}<|im_end|>
+    {{ end }}{{ if .Prompt }}<|im_start|>user
+    {{ .Prompt }}<|im_end|>
+    {{ end }}<|im_start|>assistant
+    {{ end }}{{ .Response }}{{ if .Response }}<|im_end|>{{ end }}""",
+                "stop_tokens": ["</s>", "USER:", "ASSSISTANT:"]
+            }
+        }
+        # Select mapping by checking if any key is in the model_name.
+        chosen = None
+        for key, settings in mapping.items():
+            if key in model_name:
+                chosen = settings
+                break
+        if chosen is None:
+            # Fallback default
+            chosen = {
+                "template": """{{ if .System }}<|start_header_id|>system<|end_header_id|>
+    {{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>
+    {{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>
+    {{ .Response }}<|eot_id|>""",
+                "stop_tokens": ["<|start_header_id|>", "<|end_header_id|>", "<|eot_id|>"]
+            }
+        # Build the stop parameter lines.
+        stop_params = "\n".join([f"PARAMETER stop {token}" for token in chosen["stop_tokens"]])
+        # Optionally include a SYSTEM line and num_ctx if defined in the mapping.
+        system_line = ""
+        if "system" in chosen:
+            system_line = f"SYSTEM {chosen['system']}\n"
+        num_ctx_line = ""
+        if "num_ctx" in chosen:
+            num_ctx_line = f"PARAMETER num_ctx {chosen['num_ctx']}\n"
+        # Assemble and return the modelfile content.
+        return f"""FROM {output_model}
+    TEMPLATE \"\"\"{chosen['template']}\"\"\"
+    {system_line}{num_ctx_line}{stop_params}
+    """
 
-        # Check if the GGUF file exists. If not, generate it ## TODO Multiple Quantisation other than Q4_K_M.gguf
-        if not os.path.exists(gguf_path):
-            self.model, self.tokenizer = self.load_model()
-            self.save_model_gguf()
-        return f"""FROM {output_model}/unsloth.Q4_K_M.gguf
 
-TEMPLATE \"\"\"Below are some instructions that describe some tasks. Write responses that appropriately complete each request.{{{{ if .Prompt }}}}
-
-### Instruction:
-{{{{ .Prompt }}}}
-
-{{{{ end }}}}### Response:
-{{{{ .Response }}}}\"\"\"
-
-PARAMETER stop ""
-PARAMETER stop ""
-PARAMETER stop ""
-PARAMETER stop ""
-PARAMETER stop "<|reserved_special_token_"
-"""
 
     def create_and_push_ollama_model(self):
         modelfile_content = self.prepare_modelfile_content()
-        with open('Modelfile', 'w') as file:
+        with open("Modelfile", "w") as file:
             file.write(modelfile_content)
-
         subprocess.run(["ollama", "serve"])
         subprocess.run(["ollama", "create", f"{self.config['ollama_model']}:{self.config['model_parameters']}", "-f", "Modelfile"])
         subprocess.run(["ollama", "push", f"{self.config['ollama_model']}:{self.config['model_parameters']}"])
@@ -235,42 +527,36 @@ PARAMETER stop "<|reserved_special_token_"
         self.print_system_info()
         self.check_gpu()
         self.check_ram()
-        # self.install_packages()
         if self.config.get("train", "true").lower() == "true":
             self.prepare_model()
             self.train_model()
-
         if self.config.get("huggingface_save", "true").lower() == "true":
-            # self.model, self.tokenizer = self.load_model()
             self.save_model_merged()
-
         if self.config.get("huggingface_save_gguf", "true").lower() == "true":
-            # self.model, self.tokenizer = self.load_model()
             self.push_model_gguf()
-            
-        # if self.config.get("save_gguf", "true").lower() == "true": ## TODO
-        #     self.model, self.tokenizer = self.load_model()
-        #     self.save_model_gguf()
-        
-        # if self.config.get("save_merged", "true").lower() == "true": ## TODO
-        #     self.model, self.tokenizer = self.load_model()
-        #     self.save_model_merged()
-
         if self.config.get("ollama_save", "true").lower() == "true":
             self.create_and_push_ollama_model()
 
-
 def main():
     import argparse
-    parser = argparse.ArgumentParser(description='PraisonAI Training Script')
-    parser.add_argument('command', choices=['train'], help='Command to execute')
-    parser.add_argument('--config', default='config.yaml', help='Path to configuration file')
+    parser = argparse.ArgumentParser(description="PraisonAI Training Script")
+    parser.add_argument("command", choices=["train"], help="Command to execute")
+    parser.add_argument("--config", default="config.yaml", help="Path to configuration file")
+    parser.add_argument("--model", type=str, help="Model name")
+    parser.add_argument("--hf", type=str, help="Hugging Face model name")
+    parser.add_argument("--ollama", type=str, help="Ollama model name")
+    parser.add_argument("--dataset", type=str, help="Dataset name for training")
     args = parser.parse_args()
 
-    if args.command == 'train':
-        ai = train(config_path=args.config)
-        ai.run()
+    if args.command == "train":
+        # Check if any command line args are provided that would override config
+        if any([args.model, args.hf, args.ollama, args.dataset]):
+            # Use CLI provided arguments
+            trainer_obj = TrainModel(config_path=args.config)
+        else:
+            # Use existing config.yaml without modification
+            trainer_obj = TrainModel("config.yaml")
+        trainer_obj.run()
 
-
-if __name__ == '__main__':
+if __name__ == "__main__":
     main()

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "PraisonAI"
-version = "2.0.54"
+version = "2.0.71"
 description = "PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent collaboration."
 readme = "README.md"
 license = ""
@@ -12,7 +12,7 @@ dependencies = [
     "rich>=13.7",
     "markdown>=3.5",
     "pyparsing>=3.0.0",
-    "praisonaiagents>=0.0.45",
+    "praisonaiagents>=0.0.61",
     "python-dotenv>=0.19.0",
     "instructor>=1.3.3",
     "PyYAML>=6.0",
@@ -84,7 +84,7 @@ autogen = ["pyautogen>=0.2.19", "praisonai-tools>=0.0.7", "crewai"]
 
 [tool.poetry]
 name = "PraisonAI"
-version = "2.0.54"
+version = "2.0.71"
 description = "PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human–agent collaboration."
 authors = ["Mervin Praison"]
 license = ""
@@ -102,7 +102,7 @@ python = ">=3.10,<3.13"
 rich = ">=13.7"
 markdown = ">=3.5"
 pyparsing = ">=3.0.0"
-praisonaiagents = ">=0.0.45"
+praisonaiagents = ">=0.0.61"
 python-dotenv = ">=0.19.0"
 instructor = ">=1.3.3"
 PyYAML = ">=6.0"

src/praisonai-agents/.cursorrules

@@ -0,0 +1,150 @@
+1. Make minimal code changes as possible
+2. if you are creating function, make sure to name it in more easy, user friendly , optimised manner. 
+3. Never copy the exact code if presented with a code from other location or file or codebase, just make it optimised
+4. Always Follow the principle LESS IS MORE
+5. Make it minimal change as possible
+6. Firstly try not to make any modification to the existing code as possible
+7. Only modify the existing code if its highly required, without that if it cant be done, then add new code section. 
+8. If you are adding new code, make sure to add it in a way that it can be easily integrated with the existing codebase. 
+
+
+Below is a **detailed technical overview** of the issues that have been coming up in the workflow execution (specifically around loops, resetting tasks, and continuing on to subsequent tasks). It includes:
+
+1. **How the workflow currently flows**  
+2. **What logic marks a task as “completed”**  
+3. **What issues arose in `loop` tasks**  
+4. **Why the workflow can end up “stuck” or “looping indefinitely”**  
+
+---
+
+## 1. Overall Workflow Flow
+
+### a. Building relationships among tasks
+
+- At startup, the code iterates through all `tasks`.  
+- For each `task`:
+  - It looks at `task.next_tasks`, and for each `next_task_name`:
+    - Finds the corresponding `Task` object
+    - Appends the current task’s name to the found `next_task`'s `previous_tasks` list.  
+- This means if Task A has `next_tasks=["B"]`, then Task B’s `previous_tasks` will include `"A"`.
+
+### b. Finding and starting with a “start task”
+
+- The workflow code tries to locate a task with `is_start=True`.  
+- If no such task is found, it uses the first item in the tasks dictionary instead.  
+- That “start task” is what the workflow tries to run first.
+
+### c. Execution loop in the method (e.g., `workflow()` or `aworkflow()`)
+
+- There is a `while current_task:` loop that processes tasks in sequence, or conditionally, based on `task.condition`.
+- Each time a task runs (if non-loop), it yields the `task_id` or triggers an agent to run. Once the agent finishes (with or without a final result), the workflow picks up again to see what to do next:
+  - If the `task` is a `loop` type, the code tries to create or manage sub-tasks for each row/line in an “input_file.”
+  - If the `task` is a normal (“decision” or “task” or “some-other-type”), it just executes once, sets `status="completed"`, and the code moves on.
+
+### d. Condition-based branching
+
+- If a task has a result that includes a “decision” (like `{"decision":"more"}` or `"done"`), the code checks `task.condition`. For example:
+  ```python
+  condition = {
+    "more": "generate_task",
+    "done": "evaluate_total_questions"
+  }
+  ```
+- If the result’s decision is `"done"`, it jumps to the task named `"evaluate_total_questions"`.  
+- If the result’s decision is `"more"`, it jumps right back to `"generate_task"`.  
+- If no condition matches, it can fallback to the first item in `task.next_tasks`.
+
+### e. Marking tasks as “completed”
+
+- After a task’s execution (like a typical “non-loop” task), the code sets `task.status = "completed"`.
+- Then the code has a snippet that says:
+  ```python
+  if self.tasks[task_id].status == "completed":
+      # Possibly reset to "not started" so we can re-run if needed
+  ```
+- By default, the system tries to “reset” tasks to `"not started"`, **unless** it is a loop task or a subtask of a loop.  
+
+---
+
+## 2. How a “completed” task is marked
+
+Generally, tasks are marked `status="completed"` in two primary ways:
+
+1. **Non-Loop Execution**  
+   A normal task (like a “decision” or “task”) is executed once the code calls the agent, the agent returns a final result, and the system sets `task.status = "completed"`.
+2. **Loop Execution**  
+   A loop-type task is *programmatically* set to `status="completed"` when all of its sub-tasks have finished. That is:
+   - The code checks: “Have all child tasks of this loop finished?”  
+   - If `True`, the loop task is set to `completed`.
+
+---
+
+## 3. Issues Specifically in `loop` Tasks
+
+### a. Re-Entering the Loop
+
+- Before, the same snippet that “resets completed tasks to ‘not started’ so they can re-run if needed” **also** tried to reset loop tasks or their subtasks.  
+- If a loop task got reset to `"not started"`, the code would eventually pick it back up again, leading to repeated creation of sub-tasks (or repeated attempts to re-run them).
+- This caused an **infinite loop** or repeating the same steps in the workflow, never truly exiting the loop stage.
+
+### b. Subtasks Not Marked or Overwritten
+
+- Another tricky scenario: If sub-tasks themselves got reset, the parent loop would see them as “not started” again, and might wait for them to “complete,” or might re-run them. That can lead to indefinite re-running of sub-tasks.
+
+### c. Not Proceeding to Next (e.g., “upload_to_huggingface”)
+
+- If the loop kept “restarting,” the workflow never ended up hitting the next tasks. For example, if your workflow is:
+  1. `generate_task`  
+  2. `evaluate_total_questions`  
+  3. `generate_cot` (loop)  
+  4. `upload_to_huggingface`
+- The system might get stuck in step #3 indefinitely (the sub-tasks keep getting reset, so it never actually transitions to step #4).
+
+### d. Condition Logic vs. Next Tasks
+
+- Another subtlety: If the loop tasks had a `condition` that pointed them back to a prior step, it might cause unintentional re-entry. Typically, you only want loop tasks to proceed once, **unless** you explicitly want to re-visit. But if it’s a data ingestion process, you usually want to do it once, then move on to the next step.
+
+---
+
+## 4. Why the System Can End Up Stuck or “Looping Indefinitely”
+
+1. **Reset Mechanism**  
+   - The code tries to “reset tasks to ‘not started’ once they complete,” so they can be re-run in some dynamic multi-run scenario.  
+   - But that same logic can cause loop tasks to revert back to “not started” the moment they end. The system sees “Oh, a task is ‘not started’? Let’s run it!” and you’re in a cycle.
+
+2. **No Condition for Exit**  
+   - If the loop has a condition that leads back to a prior step (like `"more" -> generate_cot`), it can keep re-running.
+
+3. **Subtasks Not Marked**  
+   - If the subtask or the loop tries to “reactivate” each other, it never exits.
+
+---
+
+## Summary of the “Core Problem”
+
+1. We want to keep the resetting mechanism for **non-loop tasks** – because in some advanced workflows, we like re-running them from a different path or after some condition.  
+2. But we want **loop tasks** to remain `"completed"` once all sub-tasks are done, so the code can seamlessly proceed to the next major step.  
+3. Before the fix, loop tasks or their sub-tasks got reset. This triggered the system to re-enter the loop, re-run the sub-tasks, etc., causing an infinite loop and preventing the workflow from reaching tasks like “upload_to_huggingface.”
+
+---
+
+## Technical Highlights to Pass On
+
+- **In the reset snippet**:  
+  ```python
+  if self.tasks[task_id].status == "completed":
+      # never reset if loop or subtask-of-loop
+      # else reset to "not started"
+  ```
+  This is crucial to skipping re-runs on loop tasks.  
+- **Ensure** that once a loop’s sub-tasks are all “completed,” the loop’s status is set to “completed,” and it transitions to the next major tasks (like `upload_to_huggingface`).  
+- **Check** if the loop’s condition is correct. If you want a single pass, do not implement a condition that leads back to the same loop.  
+- Also, you can check you do not have “overlapping conditions” that cause re-entry.
+
+---
+
+### Conclusion
+
+**Hence,** the main challenge is that the reset logic (meant to let normal tasks be re-run) conflicts with a loop task’s one-pass usage. Once you avoid resetting the loop tasks or sub-tasks, you can finish them once, mark them “completed,” and properly proceed to the next stage.
+
+Dont remove any logging or debug statements, as it will help you to understand the flow of the code.