Merge pull request #333 from MervinPraison/develop

2.0.59

README.md

@@ -71,7 +71,7 @@ Create app.py file and add the code below:
 ```python
 from praisonaiagents import Agent
 agent = Agent(instructions="Your are a helpful AI assistant")
-agent.chat("Write a movie script about a robot in Mars")
+agent.start("Write a movie script about a robot in Mars")
 ```
 
 Run:
@@ -472,6 +472,8 @@ export OPENAI_BASE_URL=https://api.groq.com/openai/v1
 
 ### Simple Playbook Example
 
+Create `agents.yaml` file and add the code below:
+
 ```yaml
 framework: praisonai
 topic: Artificial Intelligence
@@ -544,14 +546,18 @@ uv pip install -r pyproject.toml --extra "crewai,autogen"
 
 [![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) |
+| 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) |

agents/deepseek-reasoning-agents.py

@@ -0,0 +1,6 @@
+from praisonaiagents import Agent
+
+agent = Agent(instructions="You are helpful Assisant", llm="deepseek-reasoner", reasoning_steps=True)
+
+result = agent.start("Why sky is Blue?")
+print(result)

agents/deepseek-reasoning-multi-agents.py

@@ -0,0 +1,14 @@
+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()

agents/deepseek-reasoning-output-tokens.py

@@ -0,0 +1,19 @@
+from praisonaiagents import Agent, Task, PraisonAIAgents
+
+llm_config = {
+    "model": "deepseek/deepseek-reasoner",
+    "max_tokens": 1
+}
+
+reasoning_agent = Agent(role="Helpful Assistant", llm=llm_config, reasoning_steps=True)
+small_agent = Agent(role="Helpful Assistant", llm="openai/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()

agents/deepseek-think.py

@@ -0,0 +1,18 @@
+from openai import OpenAI
+
+client = OpenAI()
+
+response = client.chat.completions.create(
+    model="deepseek-reasoner",
+    messages=[
+        {"role": "system", "content": "You are a helpful assistant"},
+        {"role": "user", "content": "Why sky is Blue?"},
+    ],
+    stream=True
+)
+
+for chunk in response:
+    if chunk.choices[0].delta.content is not None:
+        print(chunk.choices[0].delta.content, end="", flush=True)
+    if chunk.choices[0].delta.reasoning_content is not None:
+        print(chunk.choices[0].delta.reasoning_content, end="", flush=True)

agents/litellm-reasoning.py

@@ -0,0 +1,14 @@
+from litellm import completion
+
+messages = [{"role": "user", "content": "What is 1+1?"}]
+resp = completion(
+    model="deepseek/deepseek-reasoner",
+    messages=messages,
+    stream=False
+)
+
+reasoning_content = resp.choices[0].message.provider_specific_fields["reasoning_content"]
+content = resp.choices[0].message.content
+
+print(reasoning_content)
+print(content)

agents/llm-deepseek-agents.py

@@ -0,0 +1,9 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are helpful Assisant", 
+    llm="deepseek/deepseek-reasoner"
+)
+
+result = agent.start("Why sky is Blue?")
+print(result)

agents/llm-deepseek-reasoning-agents.py

@@ -0,0 +1,10 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are helpful Assisant", 
+    llm="deepseek/deepseek-reasoner", 
+    reasoning_steps=True
+)
+
+result = agent.start("Why sky is Blue?")
+print(result)

agents/llm-deepseek-reasoning-steps.py

@@ -0,0 +1,14 @@
+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="openai/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()

agents/llm-langchain-toolcall.py

@@ -0,0 +1,30 @@
+from praisonaiagents import Agent, Task, PraisonAIAgents
+from langchain_community.tools import YouTubeSearchTool
+from langchain_community.utilities import WikipediaAPIWrapper
+
+# Create an agent with both tools
+agent = Agent(
+    name="SearchAgent",
+    role="Research Assistant",
+    goal="Search for information from multiple sources",
+    backstory="I am an AI assistant that can search YouTube and Wikipedia.",
+    tools=[YouTubeSearchTool, WikipediaAPIWrapper],
+    llm="openai/gpt-4o-mini"
+)
+
+# Create tasks to demonstrate both tools
+task = Task(
+    name="search_task",
+    description="Search for information about 'AI advancements' on both YouTube and Wikipedia",
+    expected_output="Combined information from YouTube videos and Wikipedia articles",
+    agent=agent
+)
+
+# Create and start the workflow
+agents = PraisonAIAgents(
+    agents=[agent],
+    tasks=[task],
+    verbose=True
+)
+
+agents.start()

agents/praisonaiagents/agent/agent.py

@@ -21,10 +21,180 @@ from ..main import (
 )
 import inspect
 import uuid
+from dataclasses import dataclass
 
 if TYPE_CHECKING:
     from ..task.task import Task
 
+@dataclass
+class ChatCompletionMessage:
+    content: str
+    role: str = "assistant"
+    refusal: Optional[str] = None
+    audio: Optional[str] = None
+    function_call: Optional[dict] = None
+    tool_calls: Optional[List] = None
+    reasoning_content: Optional[str] = None
+
+@dataclass
+class Choice:
+    finish_reason: Optional[str]
+    index: int
+    message: ChatCompletionMessage
+    logprobs: Optional[dict] = None
+
+@dataclass
+class CompletionTokensDetails:
+    accepted_prediction_tokens: Optional[int] = None
+    audio_tokens: Optional[int] = None
+    reasoning_tokens: Optional[int] = None
+    rejected_prediction_tokens: Optional[int] = None
+
+@dataclass
+class PromptTokensDetails:
+    audio_tokens: Optional[int] = None
+    cached_tokens: int = 0
+
+@dataclass
+class CompletionUsage:
+    completion_tokens: int = 0
+    prompt_tokens: int = 0
+    total_tokens: int = 0
+    completion_tokens_details: Optional[CompletionTokensDetails] = None
+    prompt_tokens_details: Optional[PromptTokensDetails] = None
+    prompt_cache_hit_tokens: int = 0
+    prompt_cache_miss_tokens: int = 0
+
+@dataclass
+class ChatCompletion:
+    id: str
+    choices: List[Choice]
+    created: int
+    model: str
+    object: str = "chat.completion"
+    system_fingerprint: Optional[str] = None
+    service_tier: Optional[str] = None
+    usage: Optional[CompletionUsage] = None
+
+def process_stream_chunks(chunks):
+    """Process streaming chunks into combined response"""
+    if not chunks:
+        return None
+    
+    try:
+        first_chunk = chunks[0]
+        last_chunk = chunks[-1]
+        
+        # Basic metadata
+        id = getattr(first_chunk, "id", None) 
+        created = getattr(first_chunk, "created", None)
+        model = getattr(first_chunk, "model", None)
+        system_fingerprint = getattr(first_chunk, "system_fingerprint", None)
+        
+        # Track usage
+        completion_tokens = 0
+        prompt_tokens = 0
+        
+        content_list = []
+        reasoning_list = []
+        tool_calls = []
+        current_tool_call = None
+
+        # First pass: Get initial tool call data
+        for chunk in chunks:
+            if not hasattr(chunk, "choices") or not chunk.choices:
+                continue
+            
+            delta = getattr(chunk.choices[0], "delta", None)
+            if not delta:
+                continue
+
+            # Handle content and reasoning
+            if hasattr(delta, "content") and delta.content:
+                content_list.append(delta.content)
+            if hasattr(delta, "reasoning_content") and delta.reasoning_content:
+                reasoning_list.append(delta.reasoning_content)
+            
+            # Handle tool calls
+            if hasattr(delta, "tool_calls") and delta.tool_calls:
+                for tool_call_delta in delta.tool_calls:
+                    if tool_call_delta.index is not None and tool_call_delta.id:
+                        # Found the initial tool call
+                        current_tool_call = {
+                            "id": tool_call_delta.id,
+                            "type": "function",
+                            "function": {
+                                "name": tool_call_delta.function.name,
+                                "arguments": ""
+                            }
+                        }
+                        while len(tool_calls) <= tool_call_delta.index:
+                            tool_calls.append(None)
+                        tool_calls[tool_call_delta.index] = current_tool_call
+                        current_tool_call = tool_calls[tool_call_delta.index]
+                    elif current_tool_call is not None and hasattr(tool_call_delta.function, "arguments"):
+                        if tool_call_delta.function.arguments:
+                            current_tool_call["function"]["arguments"] += tool_call_delta.function.arguments
+
+        # Remove any None values and empty tool calls
+        tool_calls = [tc for tc in tool_calls if tc and tc["id"] and tc["function"]["name"]]
+
+        combined_content = "".join(content_list) if content_list else ""
+        combined_reasoning = "".join(reasoning_list) if reasoning_list else None
+        finish_reason = getattr(last_chunk.choices[0], "finish_reason", None) if hasattr(last_chunk, "choices") and last_chunk.choices else None
+
+        # Create ToolCall objects
+        processed_tool_calls = []
+        if tool_calls:
+            try:
+                from openai.types.chat import ChatCompletionMessageToolCall
+                for tc in tool_calls:
+                    tool_call = ChatCompletionMessageToolCall(
+                        id=tc["id"],
+                        type=tc["type"],
+                        function={
+                            "name": tc["function"]["name"],
+                            "arguments": tc["function"]["arguments"]
+                        }
+                    )
+                    processed_tool_calls.append(tool_call)
+            except Exception as e:
+                print(f"Error processing tool call: {e}")
+
+        message = ChatCompletionMessage(
+            content=combined_content,
+            role="assistant",
+            reasoning_content=combined_reasoning,
+            tool_calls=processed_tool_calls if processed_tool_calls else None
+        )
+        
+        choice = Choice(
+            finish_reason=finish_reason or "tool_calls" if processed_tool_calls else None,
+            index=0,
+            message=message
+        )
+
+        usage = CompletionUsage(
+            completion_tokens=completion_tokens,
+            prompt_tokens=prompt_tokens,
+            total_tokens=completion_tokens + prompt_tokens,
+            completion_tokens_details=CompletionTokensDetails(),
+            prompt_tokens_details=PromptTokensDetails()
+        )
+        
+        return ChatCompletion(
+            id=id,
+            choices=[choice],
+            created=created,
+            model=model,
+            system_fingerprint=system_fingerprint,
+            usage=usage
+        )
+        
+    except Exception as e:
+        print(f"Error processing chunks: {e}")
+        return None
+
 class Agent:
     def _generate_tool_definition(self, function_name):
         """
@@ -190,7 +360,8 @@ class Agent:
         max_reflect: int = 3,
         min_reflect: int = 1,
         reflect_llm: Optional[str] = None,
-        user_id: Optional[str] = None
+        user_id: Optional[str] = None,
+        reasoning_steps: bool = False
     ):
         # Add check at start if memory is requested
         if memory is not None:
@@ -298,6 +469,7 @@ Your Goal: {self.goal}
 
         # Store user_id
         self.user_id = user_id or "praison"
+        self.reasoning_steps = reasoning_steps
 
         # Check if knowledge parameter has any values
         if not knowledge:
@@ -399,7 +571,54 @@ Your Goal: {self.goal}
     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):
+    def _process_stream_response(self, messages, temperature, start_time, formatted_tools=None, reasoning_steps=False):
+        """Process streaming response and return final response"""
+        try:
+            # Create the response stream
+            response_stream = client.chat.completions.create(
+                model=self.llm,
+                messages=messages,
+                temperature=temperature,
+                tools=formatted_tools if formatted_tools else None,
+                stream=True
+            )
+            
+            full_response_text = ""
+            reasoning_content = ""
+            chunks = []
+            
+            # Create Live display with proper configuration
+            with Live(
+                display_generating("", start_time),
+                console=self.console,
+                refresh_per_second=4,
+                transient=True,
+                vertical_overflow="ellipsis",
+                auto_refresh=True
+            ) as live:
+                for chunk in response_stream:
+                    chunks.append(chunk)
+                    if chunk.choices[0].delta.content:
+                        full_response_text += chunk.choices[0].delta.content
+                        live.update(display_generating(full_response_text, start_time))
+                    
+                    # Update live display with reasoning content if enabled
+                    if reasoning_steps and hasattr(chunk.choices[0].delta, "reasoning_content"):
+                        rc = chunk.choices[0].delta.reasoning_content
+                        if rc:
+                            reasoning_content += rc
+                            live.update(display_generating(f"{full_response_text}\n[Reasoning: {reasoning_content}]", start_time))
+            
+            # Clear the last generating display with a blank line
+            self.console.print()
+            final_response = process_stream_chunks(chunks)
+            return final_response
+            
+        except Exception as e:
+            display_error(f"Error in stream processing: {e}")
+            return None
+
+    def _chat_completion(self, messages, temperature=0.2, tools=None, stream=True, reasoning_steps=False):
         start_time = time.time()
         logging.debug(f"{self.name} sending messages to LLM: {messages}")
 
@@ -425,20 +644,31 @@ Your Goal: {self.goal}
                     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
-            )
+            if stream:
+                # Process as streaming response with formatted tools
+                final_response = self._process_stream_response(
+                    messages, 
+                    temperature, 
+                    start_time, 
+                    formatted_tools=formatted_tools if formatted_tools else None,
+                    reasoning_steps=reasoning_steps
+                )
+            else:
+                # Process as regular non-streaming response
+                final_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)
+            tool_calls = getattr(final_response.choices[0].message, 'tool_calls', None)
 
             if tool_calls:
                 messages.append({
-                    "role": "assistant",
-                    "content": initial_response.choices[0].message.content,
+                    "role": "assistant", 
+                    "content": final_response.choices[0].message.content,
                     "tool_calls": tool_calls
                 })
 
@@ -461,56 +691,31 @@ Your Goal: {self.goal}
                         "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:
+                # Get final response after tool calls
+                if stream:
+                    final_response = self._process_stream_response(
+                        messages, 
+                        temperature, 
+                        start_time,
+                        formatted_tools=formatted_tools if formatted_tools else None,
+                        reasoning_steps=reasoning_steps
+                    )
+                else:
                     final_response = client.chat.completions.create(
                         model=self.llm,
                         messages=messages,
                         temperature=temperature,
                         stream=False
                     )
-                    return final_response
-                else:
-                    return initial_response
+
+            return final_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):
+    def chat(self, prompt, temperature=0.2, tools=None, output_json=None, output_pydantic=None, reasoning_steps=False):
+        reasoning_steps = reasoning_steps or self.reasoning_steps
         # Search for existing knowledge if any knowledge is provided
         if self.knowledge:
             search_results = self.knowledge.search(prompt, agent_id=self.agent_id)
@@ -546,7 +751,8 @@ Your Goal: {self.goal}
                     agent_name=self.name,
                     agent_role=self.role,
                     agent_tools=[t.__name__ if hasattr(t, '__name__') else str(t) for t in self.tools],
-                    execute_tool_fn=self.execute_tool  # Pass tool execution function
+                    execute_tool_fn=self.execute_tool,  # Pass tool execution function
+                    reasoning_steps=reasoning_steps
                 )
 
                 self.chat_history.append({"role": "user", "content": prompt})
@@ -616,14 +822,13 @@ Your Goal: {self.goal}
                                 agent_tools=agent_tools
                             )
 
-                    response = self._chat_completion(messages, temperature=temperature, tools=tools if tools else None)
+                    response = self._chat_completion(messages, temperature=temperature, tools=tools if tools else None, reasoning_steps=reasoning_steps)
                     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:
+                    if tool_calls: ## TODO: Most likely this tool call is already called in _chat_completion, so maybe we can remove this.
                         messages.append({
                             "role": "assistant",
                             "content": response_text,
@@ -675,6 +880,9 @@ Your Goal: {self.goal}
                         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 only reasoning content if reasoning_steps is True
+                        if reasoning_steps and hasattr(response.choices[0].message, 'reasoning_content'):
+                            return response.choices[0].message.reasoning_content
                         return response_text
 
                     reflection_prompt = f"""
@@ -749,8 +957,9 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
             cleaned = cleaned[:-3].strip()
         return cleaned  
 
-    async def achat(self, prompt: str, temperature=0.2, tools=None, output_json=None, output_pydantic=None):
+    async def achat(self, prompt: str, temperature=0.2, tools=None, output_json=None, output_pydantic=None, reasoning_steps=False):
         """Async version of chat method. TODO: Requires Syncing with chat method.""" 
+        reasoning_steps = reasoning_steps or self.reasoning_steps
         try:
             # Search for existing knowledge if any knowledge is provided
             if self.knowledge:
@@ -781,7 +990,8 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                         agent_name=self.name,
                         agent_role=self.role,
                         agent_tools=[t.__name__ if hasattr(t, '__name__') else str(t) for t in self.tools],
-                        execute_tool_fn=self.execute_tool_async
+                        execute_tool_fn=self.execute_tool_async,
+                        reasoning_steps=reasoning_steps
                     )
 
                     self.chat_history.append({"role": "user", "content": prompt})
@@ -847,48 +1057,48 @@ Your Goal: {self.goal}
                             )
 
                     # 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__))
+                    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()
+                    # 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
+                    # 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
@@ -896,7 +1106,7 @@ Your Goal: {self.goal}
             display_error(f"Error in achat: {e}")
             return None
 
-    async def _achat_completion(self, response, tools):
+    async def _achat_completion(self, response, tools, reasoning_steps=False):
         """Async version of _chat_completion method"""
         try:
             message = response.choices[0].message
@@ -942,9 +1152,42 @@ Your Goal: {self.goal}
                         final_response = await async_client.chat.completions.create(
                             model=self.llm,
                             messages=messages,
-                            temperature=0.2
+                            temperature=0.2,
+                            stream=True
                         )
-                        return final_response.choices[0].message.content
+                        full_response_text = ""
+                        reasoning_content = ""
+                        chunks = []
+                        start_time = time.time()
+                        
+                        with Live(
+                            display_generating("", start_time),
+                            console=self.console,
+                            refresh_per_second=4,
+                            transient=True,
+                            vertical_overflow="ellipsis",
+                            auto_refresh=True
+                        ) as live:
+                            async for chunk in final_response:
+                                chunks.append(chunk)
+                                if chunk.choices[0].delta.content:
+                                    full_response_text += chunk.choices[0].delta.content
+                                    live.update(display_generating(full_response_text, start_time))
+                                
+                                if reasoning_steps and hasattr(chunk.choices[0].delta, "reasoning_content"):
+                                    rc = chunk.choices[0].delta.reasoning_content
+                                    if rc:
+                                        reasoning_content += rc
+                                        live.update(display_generating(f"{full_response_text}\n[Reasoning: {reasoning_content}]", start_time))
+                        
+                        self.console.print()
+                        
+                        final_response = process_stream_chunks(chunks)
+                        # Return only reasoning content if reasoning_steps is True
+                        if reasoning_steps and hasattr(final_response.choices[0].message, 'reasoning_content'):
+                            return final_response.choices[0].message.reasoning_content
+                        return final_response.choices[0].message.content if final_response else full_response_text
+
                     except Exception as e:
                         display_error(f"Error in final chat completion: {e}")
                         return formatted_results
@@ -952,7 +1195,7 @@ Your Goal: {self.goal}
             return None
         except Exception as e:
             display_error(f"Error in _achat_completion: {e}")
-            return None 
+            return None
 
     async def astart(self, prompt: str, **kwargs):
         """Async version of start method"""

agents/praisonaiagents/agents/agents.py

@@ -390,15 +390,8 @@ Context:
                     task.status = "completed"
                     # Run execute_callback for memory operations
                     try:
-                        try:
-                            # If a loop is already running, just create the task
-                            loop = asyncio.get_running_loop()
-                            loop.create_task(task.execute_callback(task_output))
-                        except RuntimeError:
-                            # Otherwise, create and set a new loop, and run the callback
-                            loop = asyncio.new_event_loop()
-                            asyncio.set_event_loop(loop)
-                            loop.create_task(task.execute_callback(task_output))
+                        # Use the new sync wrapper to avoid pending coroutine issues
+                        task.execute_callback_sync(task_output)
                     except Exception as e:
                         logger.error(f"Error executing memory callback for task {task_id}: {e}")
                         logger.exception(e)
@@ -720,15 +713,8 @@ Context:
                     task.status = "completed"
                     # Run execute_callback for memory operations
                     try:
-                        try:
-                            # If a loop is already running, just create the task
-                            loop = asyncio.get_running_loop()
-                            loop.create_task(task.execute_callback(task_output))
-                        except RuntimeError:
-                            # Otherwise, create and set a new loop, and run the callback
-                            loop = asyncio.new_event_loop()
-                            asyncio.set_event_loop(loop)
-                            loop.create_task(task.execute_callback(task_output))
+                        # Use the new sync wrapper to avoid pending coroutine issues
+                        task.execute_callback_sync(task_output)
                     except Exception as e:
                         logger.error(f"Error executing memory callback for task {task_id}: {e}")
                         logger.exception(e)

agents/praisonaiagents/llm/llm.py

@@ -17,6 +17,8 @@ from ..main import (
 from rich.console import Console
 from rich.live import Live
 
+# TODO: Include in-build tool calling in LLM class
+# TODO: Restructure so that duplicate calls are not made (Sync with agent.py)
 class LLMContextLengthExceededException(Exception):
     """Raised when LLM context length is exceeded"""
     def __init__(self, message: str):
@@ -113,6 +115,7 @@ class LLM:
             litellm.callbacks = []
             # Additional logging suppression
             litellm.suppress_debug_messages = True
+            litellm._logging._disable_debugging()
             logging.getLogger("litellm.utils").setLevel(logging.WARNING)
             logging.getLogger("litellm.main").setLevel(logging.WARNING)
         except ImportError:
@@ -147,6 +150,7 @@ class LLM:
         self.self_reflect = extra_settings.get('self_reflect', False)
         self.max_reflect = extra_settings.get('max_reflect', 3)
         self.min_reflect = extra_settings.get('min_reflect', 1)
+        self.reasoning_steps = extra_settings.get('reasoning_steps', False)
         
         # Enable error dropping for cleaner output
         litellm.drop_params = True
@@ -176,7 +180,8 @@ class LLM:
         """Enhanced get_response with all OpenAI-like features"""
         try:
             import litellm
-            
+            # This below **kwargs** is passed to .completion() directly. so reasoning_steps has to be popped. OR find alternate best way of handling this.
+            reasoning_steps = kwargs.pop('reasoning_steps', self.reasoning_steps) 
             # Disable litellm debug messages
             litellm.set_verbose = False
             
@@ -230,8 +235,55 @@ class LLM:
 
                     # Get response from LiteLLM
                     start_time = time.time()
-                    if verbose:
-                        with Live(display_generating("", start_time), console=console, refresh_per_second=4) as live:
+
+                    # If reasoning_steps is True, do a single non-streaming call
+                    if reasoning_steps:
+                        resp = litellm.completion(
+                            model=self.model,
+                            messages=messages,
+                            temperature=temperature,
+                            stream=False,  # force non-streaming
+                            **{k:v for k,v in kwargs.items() if k != 'reasoning_steps'}
+                        )
+                        reasoning_content = resp["choices"][0]["message"].get("provider_specific_fields", {}).get("reasoning_content")
+                        response_text = resp["choices"][0]["message"]["content"]
+                        
+                        # Optionally display reasoning if present
+                        if verbose and reasoning_content:
+                            display_interaction(
+                                original_prompt,
+                                f"Reasoning:\n{reasoning_content}\n\nAnswer:\n{response_text}",
+                                markdown=markdown,
+                                generation_time=time.time() - start_time,
+                                console=console
+                            )
+                        else:
+                            display_interaction(
+                                original_prompt,
+                                response_text,
+                                markdown=markdown,
+                                generation_time=time.time() - start_time,
+                                console=console
+                            )
+                    
+                    # Otherwise do the existing streaming approach
+                    else:
+                        if verbose:
+                            with Live(display_generating("", start_time), console=console, refresh_per_second=4) as live:
+                                response_text = ""
+                                for chunk in litellm.completion(
+                                    model=self.model,
+                                    messages=messages,
+                                    temperature=temperature,
+                                    stream=True,
+                                    **kwargs
+                                ):
+                                    if chunk and chunk.choices and chunk.choices[0].delta.content:
+                                        content = chunk.choices[0].delta.content
+                                        response_text += content
+                                        live.update(display_generating(response_text, start_time))
+                        else:
+                            # Non-verbose mode, just collect the response
                             response_text = ""
                             for chunk in litellm.completion(
                                 model=self.model,
@@ -241,23 +293,9 @@ class LLM:
                                 **kwargs
                             ):
                                 if chunk and chunk.choices and chunk.choices[0].delta.content:
-                                    content = chunk.choices[0].delta.content
-                                    response_text += content
-                                    live.update(display_generating(response_text, start_time))
-                    else:
-                        # Non-verbose mode, just collect the response
-                        response_text = ""
-                        for chunk in litellm.completion(
-                            model=self.model,
-                            messages=messages,
-                            temperature=temperature,
-                            stream=True,
-                            **kwargs
-                        ):
-                            if chunk and chunk.choices and chunk.choices[0].delta.content:
-                                response_text += chunk.choices[0].delta.content
+                                    response_text += chunk.choices[0].delta.content
 
-                    response_text = response_text.strip()
+                        response_text = response_text.strip()
 
                     # Get final completion to check for tool calls
                     final_response = litellm.completion(
@@ -302,9 +340,53 @@ class LLM:
                                     "content": "Function returned an empty output"
                                 })
 
-                        # Get response after tool calls with streaming
-                        if verbose:
-                            with Live(display_generating("", start_time), console=console, refresh_per_second=4) as live:
+                        # If reasoning_steps is True, do a single non-streaming call
+                        if reasoning_steps:
+                            resp = litellm.completion(
+                                model=self.model,
+                                messages=messages,
+                                temperature=temperature,
+                                stream=False,  # force non-streaming
+                                **{k:v for k,v in kwargs.items() if k != 'reasoning_steps'}
+                            )
+                            reasoning_content = resp["choices"][0]["message"].get("provider_specific_fields", {}).get("reasoning_content")
+                            response_text = resp["choices"][0]["message"]["content"]
+                            
+                            # Optionally display reasoning if present
+                            if verbose and reasoning_content:
+                                display_interaction(
+                                    original_prompt,
+                                    f"Reasoning:\n{reasoning_content}\n\nAnswer:\n{response_text}",
+                                    markdown=markdown,
+                                    generation_time=time.time() - start_time,
+                                    console=console
+                                )
+                            else:
+                                display_interaction(
+                                    original_prompt,
+                                    response_text,
+                                    markdown=markdown,
+                                    generation_time=time.time() - start_time,
+                                    console=console
+                                )
+                        
+                        # Otherwise do the existing streaming approach
+                        else:
+                            # Get response after tool calls with streaming
+                            if verbose:
+                                with Live(display_generating("", start_time), console=console, refresh_per_second=4) as live:
+                                    response_text = ""
+                                    for chunk in litellm.completion(
+                                        model=self.model,
+                                        messages=messages,
+                                        temperature=temperature,
+                                        stream=True
+                                    ):
+                                        if chunk and chunk.choices and chunk.choices[0].delta.content:
+                                            content = chunk.choices[0].delta.content
+                                            response_text += content
+                                            live.update(display_generating(response_text, start_time))
+                            else:
                                 response_text = ""
                                 for chunk in litellm.completion(
                                     model=self.model,
@@ -313,21 +395,9 @@ class LLM:
                                     stream=True
                                 ):
                                     if chunk and chunk.choices and chunk.choices[0].delta.content:
-                                        content = chunk.choices[0].delta.content
-                                        response_text += content
-                                        live.update(display_generating(response_text, start_time))
-                        else:
-                            response_text = ""
-                            for chunk in litellm.completion(
-                                model=self.model,
-                                messages=messages,
-                                temperature=temperature,
-                                stream=True
-                            ):
-                                if chunk and chunk.choices and chunk.choices[0].delta.content:
-                                    response_text += chunk.choices[0].delta.content
+                                        response_text += chunk.choices[0].delta.content
 
-                        response_text = response_text.strip()
+                            response_text = response_text.strip()
 
                     # Handle output formatting
                     if output_json or output_pydantic:
@@ -342,6 +412,9 @@ class LLM:
                         if verbose:
                             display_interaction(original_prompt, response_text, markdown=markdown,
                                              generation_time=time.time() - start_time, console=console)
+                        # Return reasoning content if reasoning_steps is True
+                        if reasoning_steps and reasoning_content:
+                            return reasoning_content
                         return response_text
 
                     # Handle self-reflection
@@ -357,32 +430,66 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                         {"role": "user", "content": reflection_prompt}
                     ]
 
-                    # Get reflection response with streaming
-                    if verbose:
-                        with Live(display_generating("", start_time), console=console, refresh_per_second=4) as live:
+                    # If reasoning_steps is True, do a single non-streaming call to capture reasoning
+                    if reasoning_steps:
+                        reflection_resp = litellm.completion(
+                            model=self.model,
+                            messages=reflection_messages,
+                            temperature=temperature,
+                            stream=False,  # Force non-streaming
+                            response_format={"type": "json_object"},
+                            **{k:v for k,v in kwargs.items() if k != 'reasoning_steps'}
+                        )
+                        # Grab reflection text and optional reasoning
+                        reasoning_content = reflection_resp["choices"][0]["message"].get("provider_specific_fields", {}).get("reasoning_content")
+                        reflection_text = reflection_resp["choices"][0]["message"]["content"]
+
+                        # Optionally display reasoning if present
+                        if verbose and reasoning_content:
+                            display_interaction(
+                                "Reflection reasoning:",
+                                f"{reasoning_content}\n\nReflection result:\n{reflection_text}",
+                                markdown=markdown,
+                                generation_time=time.time() - start_time,
+                                console=console
+                            )
+                        elif verbose:
+                            display_interaction(
+                                "Self-reflection (non-streaming):",
+                                reflection_text,
+                                markdown=markdown,
+                                generation_time=time.time() - start_time,
+                                console=console
+                            )
+                    else:
+                        # Existing streaming approach
+                        if verbose:
+                            with Live(display_generating("", start_time), console=console, refresh_per_second=4) as live:
+                                reflection_text = ""
+                                for chunk in litellm.completion(
+                                    model=self.model,
+                                    messages=reflection_messages,
+                                    temperature=temperature,
+                                    stream=True,
+                                    response_format={"type": "json_object"},
+                                    **{k:v for k,v in kwargs.items() if k != 'reasoning_steps'}
+                                ):
+                                    if chunk and chunk.choices and chunk.choices[0].delta.content:
+                                        content = chunk.choices[0].delta.content
+                                        reflection_text += content
+                                        live.update(display_generating(reflection_text, start_time))
+                        else:
                             reflection_text = ""
                             for chunk in litellm.completion(
                                 model=self.model,
                                 messages=reflection_messages,
                                 temperature=temperature,
                                 stream=True,
-                                response_format={"type": "json_object"}
+                                response_format={"type": "json_object"},
+                                **{k:v for k,v in kwargs.items() if k != 'reasoning_steps'}
                             ):
                                 if chunk and chunk.choices and chunk.choices[0].delta.content:
-                                    content = chunk.choices[0].delta.content
-                                    reflection_text += content
-                                    live.update(display_generating(reflection_text, start_time))
-                    else:
-                        reflection_text = ""
-                        for chunk in litellm.completion(
-                            model=self.model,
-                            messages=reflection_messages,
-                            temperature=temperature,
-                            stream=True,
-                            response_format={"type": "json_object"}
-                        ):
-                            if chunk and chunk.choices and chunk.choices[0].delta.content:
-                                reflection_text += chunk.choices[0].delta.content
+                                    reflection_text += chunk.choices[0].delta.content
 
                     try:
                         reflection_data = json.loads(reflection_text)
@@ -453,6 +560,7 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
         """Async version of get_response with identical functionality."""
         try:
             import litellm
+            reasoning_steps = kwargs.pop('reasoning_steps', self.reasoning_steps)
             litellm.set_verbose = False
 
             # Build messages list
@@ -490,10 +598,10 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
             # Format tools for LiteLLM
             formatted_tools = None
             if tools:
-                logging.info(f"Starting tool formatting for {len(tools)} tools")
+                logging.debug(f"Starting tool formatting for {len(tools)} tools")
                 formatted_tools = []
                 for tool in tools:
-                    logging.info(f"Processing tool: {tool.__name__ if hasattr(tool, '__name__') else str(tool)}")
+                    logging.debug(f"Processing tool: {tool.__name__ if hasattr(tool, '__name__') else str(tool)}")
                     if hasattr(tool, '__name__'):
                         tool_name = tool.__name__
                         tool_doc = tool.__doc__ or "No description available"
@@ -539,10 +647,9 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                             }
                         }
                         # Ensure tool definition is JSON serializable
-                        print(f"Generated tool definition: {tool_def}")
                         try:
                             json.dumps(tool_def)  # Test serialization
-                            logging.info(f"Generated tool definition: {tool_def}")
+                            logging.debug(f"Generated tool definition: {tool_def}")
                             formatted_tools.append(tool_def)
                         except TypeError as e:
                             logging.error(f"Tool definition not JSON serializable: {e}")
@@ -552,38 +659,67 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
             if formatted_tools:
                 try:
                     json.dumps(formatted_tools)  # Final serialization check
-                    logging.info(f"Final formatted tools: {json.dumps(formatted_tools, indent=2)}")
+                    logging.debug(f"Final formatted tools: {json.dumps(formatted_tools, indent=2)}")
                 except TypeError as e:
                     logging.error(f"Final tools list not JSON serializable: {e}")
                     formatted_tools = None
 
             response_text = ""
-            if verbose:
-                # ----------------------------------------------------
-                # 1) Make the streaming call WITHOUT tools
-                # ----------------------------------------------------
-                async for chunk in await litellm.acompletion(
+            if reasoning_steps:
+                # Non-streaming call to capture reasoning
+                resp = await litellm.acompletion(
                     model=self.model,
                     messages=messages,
                     temperature=temperature,
-                    stream=True,
-                    **kwargs
-                ):
-                    if chunk and chunk.choices and chunk.choices[0].delta.content:
-                        response_text += chunk.choices[0].delta.content
-                        print("\033[K", end="\r")  
-                        print(f"Generating... {time.time() - start_time:.1f}s", end="\r")
+                    stream=False,  # force non-streaming
+                    **{k:v for k,v in kwargs.items() if k != 'reasoning_steps'}
+                )
+                reasoning_content = resp["choices"][0]["message"].get("provider_specific_fields", {}).get("reasoning_content")
+                response_text = resp["choices"][0]["message"]["content"]
+                
+                if verbose and reasoning_content:
+                    display_interaction(
+                        "Initial reasoning:",
+                        f"Reasoning:\n{reasoning_content}\n\nAnswer:\n{response_text}",
+                        markdown=markdown,
+                        generation_time=time.time() - start_time,
+                        console=console
+                    )
+                elif verbose:
+                    display_interaction(
+                        "Initial response:",
+                        response_text,
+                        markdown=markdown,
+                        generation_time=time.time() - start_time,
+                        console=console
+                    )
             else:
-                # Non-verbose streaming call, still no tools
-                async for chunk in await litellm.acompletion(
-                    model=self.model,
-                    messages=messages,
-                    temperature=temperature,
-                    stream=True,
-                    **kwargs
-                ):
-                    if chunk and chunk.choices and chunk.choices[0].delta.content:
-                        response_text += chunk.choices[0].delta.content
+                if verbose:
+                    # ----------------------------------------------------
+                    # 1) Make the streaming call WITHOUT tools
+                    # ----------------------------------------------------
+                    async for chunk in await litellm.acompletion(
+                        model=self.model,
+                        messages=messages,
+                        temperature=temperature,
+                        stream=True,
+                        **kwargs
+                    ):
+                        if chunk and chunk.choices and chunk.choices[0].delta.content:
+                            response_text += chunk.choices[0].delta.content
+                            print("\033[K", end="\r")  
+                            print(f"Generating... {time.time() - start_time:.1f}s", end="\r")
+                else:
+                    # Non-verbose streaming call, still no tools
+                    async for chunk in await litellm.acompletion(
+                        model=self.model,
+                        messages=messages,
+                        temperature=temperature,
+                        stream=True,
+                        **kwargs
+                    ):
+                        if chunk and chunk.choices and chunk.choices[0].delta.content:
+                            response_text += chunk.choices[0].delta.content
 
             response_text = response_text.strip()
 
@@ -598,7 +734,7 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                     temperature=temperature,
                     stream=False,
                     tools=formatted_tools,  # We safely pass tools here
-                    **kwargs
+                    **{k:v for k,v in kwargs.items() if k != 'reasoning_steps'}
                 )
                 # handle tool_calls from tool_response as usual...
                 tool_calls = tool_response.choices[0].message.get("tool_calls")
@@ -634,35 +770,66 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                                 "content": "Function returned an empty output"
                             })
 
-                    # Get response after tool calls with streaming
+                    # Get response after tool calls
                     response_text = ""
-                    if verbose:
-                        async for chunk in await litellm.acompletion(
+                    if reasoning_steps:
+                        # Non-streaming call to capture reasoning
+                        resp = await litellm.acompletion(
                             model=self.model,
                             messages=messages,
                             temperature=temperature,
-                            stream=True,
-                            tools=formatted_tools,
-                            **kwargs
-                        ):
-                            if chunk and chunk.choices and chunk.choices[0].delta.content:
-                                content = chunk.choices[0].delta.content
-                                response_text += content
-                                print("\033[K", end="\r")
-                                print(f"Reflecting... {time.time() - start_time:.1f}s", end="\r")
-            else:
-                response_text = ""
-                for chunk in litellm.completion(
-                    model=self.model,
-                    messages=messages,
-                    temperature=temperature,
-                    stream=True,
-                    **kwargs
-                ):
-                    if chunk and chunk.choices and chunk.choices[0].delta.content:
-                        response_text += chunk.choices[0].delta.content
+                            stream=False,  # force non-streaming
+                            tools=formatted_tools,  # Include tools
+                            **{k:v for k,v in kwargs.items() if k != 'reasoning_steps'}
+                        )
+                        reasoning_content = resp["choices"][0]["message"].get("provider_specific_fields", {}).get("reasoning_content")
+                        response_text = resp["choices"][0]["message"]["content"]
+                        
+                        if verbose and reasoning_content:
+                            display_interaction(
+                                "Tool response reasoning:",
+                                f"Reasoning:\n{reasoning_content}\n\nAnswer:\n{response_text}",
+                                markdown=markdown,
+                                generation_time=time.time() - start_time,
+                                console=console
+                            )
+                        elif verbose:
+                            display_interaction(
+                                "Tool response:",
+                                response_text,
+                                markdown=markdown,
+                                generation_time=time.time() - start_time,
+                                console=console
+                            )
+                    else:
+                        # Get response after tool calls with streaming
+                        if verbose:
+                            async for chunk in await litellm.acompletion(
+                                model=self.model,
+                                messages=messages,
+                                temperature=temperature,
+                                stream=True,
+                                tools=formatted_tools,
+                                **{k:v for k,v in kwargs.items() if k != 'reasoning_steps'}
+                            ):
+                                if chunk and chunk.choices and chunk.choices[0].delta.content:
+                                    content = chunk.choices[0].delta.content
+                                    response_text += content
+                                    print("\033[K", end="\r")
+                                    print(f"Reflecting... {time.time() - start_time:.1f}s", end="\r")
+                        else:
+                            response_text = ""
+                            for chunk in litellm.completion(
+                                model=self.model,
+                                messages=messages,
+                                temperature=temperature,
+                                stream=True,
+                                **{k:v for k,v in kwargs.items() if k != 'reasoning_steps'}
+                            ):
+                                if chunk and chunk.choices and chunk.choices[0].delta.content:
+                                    response_text += chunk.choices[0].delta.content
 
-            response_text = response_text.strip()
+                    response_text = response_text.strip()
 
             # Handle output formatting
             if output_json or output_pydantic:
@@ -677,6 +844,9 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                 if verbose:
                     display_interaction(original_prompt, response_text, markdown=markdown,
                                      generation_time=time.time() - start_time, console=console)
+                # Return reasoning content if reasoning_steps is True
+                if reasoning_steps and reasoning_content:
+                    return reasoning_content
                 return response_text
 
             # Handle self-reflection
@@ -692,33 +862,66 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                 {"role": "user", "content": reflection_prompt}
             ]
 
-            # Get reflection response
-            reflection_text = ""
-            if verbose:
-                async for chunk in await litellm.acompletion(
+            # If reasoning_steps is True, do a single non-streaming call to capture reasoning
+            if reasoning_steps:
+                reflection_resp = litellm.completion(
                     model=self.model,
                     messages=reflection_messages,
                     temperature=temperature,
-                    stream=True,
+                    stream=False,  # Force non-streaming
                     response_format={"type": "json_object"},
-                    **kwargs
-                ):
-                    if chunk and chunk.choices and chunk.choices[0].delta.content:
-                        content = chunk.choices[0].delta.content
-                        reflection_text += content
-                        print("\033[K", end="\r")
-                        print(f"Reflecting... {time.time() - start_time:.1f}s", end="\r")
+                    **{k:v for k,v in kwargs.items() if k != 'reasoning_steps'}
+                )
+                # Grab reflection text and optional reasoning
+                reasoning_content = reflection_resp["choices"][0]["message"].get("provider_specific_fields", {}).get("reasoning_content")
+                reflection_text = reflection_resp["choices"][0]["message"]["content"]
+
+                # Optionally display reasoning if present
+                if verbose and reasoning_content:
+                    display_interaction(
+                        "Reflection reasoning:",
+                        f"{reasoning_content}\n\nReflection result:\n{reflection_text}",
+                        markdown=markdown,
+                        generation_time=time.time() - start_time,
+                        console=console
+                    )
+                elif verbose:
+                    display_interaction(
+                        "Self-reflection (non-streaming):",
+                        reflection_text,
+                        markdown=markdown,
+                        generation_time=time.time() - start_time,
+                        console=console
+                    )
             else:
-                async for chunk in await litellm.acompletion(
-                    model=self.model,
-                    messages=reflection_messages,
-                    temperature=temperature,
-                    stream=True,
-                    response_format={"type": "json_object"},
-                    **kwargs
-                ):
-                    if chunk and chunk.choices and chunk.choices[0].delta.content:
-                        reflection_text += chunk.choices[0].delta.content
+                # Existing streaming approach
+                if verbose:
+                    with Live(display_generating("", start_time), console=console, refresh_per_second=4) as live:
+                        reflection_text = ""
+                        for chunk in litellm.completion(
+                            model=self.model,
+                            messages=reflection_messages,
+                            temperature=temperature,
+                            stream=True,
+                            response_format={"type": "json_object"},
+                            **{k:v for k,v in kwargs.items() if k != 'reasoning_steps'}
+                        ):
+                            if chunk and chunk.choices and chunk.choices[0].delta.content:
+                                content = chunk.choices[0].delta.content
+                                reflection_text += content
+                                live.update(display_generating(reflection_text, start_time))
+                else:
+                    reflection_text = ""
+                    for chunk in litellm.completion(
+                        model=self.model,
+                        messages=reflection_messages,
+                        temperature=temperature,
+                        stream=True,
+                        response_format={"type": "json_object"},
+                        **{k:v for k,v in kwargs.items() if k != 'reasoning_steps'}
+                    ):
+                        if chunk and chunk.choices and chunk.choices[0].delta.content:
+                            reflection_text += chunk.choices[0].delta.content
 
             while True:  # Add loop for reflection handling
                 try:

agents/praisonaiagents/process/process.py

@@ -44,6 +44,8 @@ class Process:
         current_task = start_task
         visited_tasks = set()
         loop_data = {}  # Store loop-specific data
+
+        # TODO: start task with loop feature is not available in aworkflow method
         
         while current_task:
             current_iter += 1
@@ -350,9 +352,10 @@ Provide a JSON with the structure:
                             if row:  # Skip empty rows
                                 task_desc = row[0]  # Take first column
                                 row_task = Task(
-                                    description=task_desc,  # Keep full row as description
+                                    description=f"{start_task.description}\n{task_desc}" if start_task.description else task_desc,
                                     agent=start_task.agent,
-                                    name=task_desc,       # Use first column as name
+                                    name=f"{start_task.name}_{i+1}" if start_task.name else task_desc,
+                                    expected_output=getattr(start_task, 'expected_output', None),
                                     is_start=(i == 0),
                                     task_type="task",
                                     condition={
@@ -374,9 +377,10 @@ Provide a JSON with the structure:
                         previous_task = None
                         for i, line in enumerate(lines):
                             row_task = Task(
-                                description=line.strip(),
+                                description=f"{start_task.description}\n{line.strip()}" if start_task.description else line.strip(),
                                 agent=start_task.agent,
-                                name=line.strip(),
+                                name=f"{start_task.name}_{i+1}" if start_task.name else line.strip(),
+                                expected_output=getattr(start_task, 'expected_output', None),
                                 is_start=(i == 0),
                                 task_type="task",
                                 condition={

agents/praisonaiagents/task/task.py

@@ -302,4 +302,21 @@ Expected Output: {self.expected_output}.
 Context:
 
 {'  '.join(unique_contexts)}
-"""
+"""
+
+    def execute_callback_sync(self, task_output: TaskOutput) -> None:
+        """
+        Synchronous wrapper to ensure that execute_callback is awaited,
+        preventing 'Task was destroyed but pending!' warnings if called 
+        from non-async code.
+        """
+        import asyncio
+        try:
+            loop = asyncio.get_running_loop()
+            if loop.is_running():
+                loop.create_task(self.execute_callback(task_output))
+            else:
+                loop.run_until_complete(self.execute_callback(task_output))
+        except RuntimeError:
+            # If no loop is running in this context
+            asyncio.run(self.execute_callback(task_output))

agents/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "praisonaiagents"
-version = "0.0.50"
+version = "0.0.56"
 description = "Praison AI agents for completing complex tasks with Self Reflection Agents"
 authors = [
     { name="Mervin Praison" }

agents/repetitive-agents.py

@@ -6,7 +6,8 @@ agent = Agent(
 )
 
 task = Task(
-    description="Create the list of tasks to be looped through.",
+    description="complete the task",
+    expected_output="task completed",
     agent=agent,
     task_type="loop",
     input_file="tasks.csv"

agents/uv.lock

@@ -1868,7 +1868,7 @@ wheels = [
 
 [[package]]
 name = "praisonaiagents"
-version = "0.0.50"
+version = "0.0.56"
 source = { editable = "." }
 dependencies = [
     { name = "openai" },

agents/wikipedia-agent.py

@@ -7,6 +7,7 @@ agent = Agent(
     self_reflect=True,
     min_reflect=3,
     max_reflect=5,
+    llm="gpt-4o-mini"
 )
 agent.start(
     "What is the history of AI?"

docker/Dockerfile

@@ -1,6 +1,6 @@
 FROM python:3.11-slim
 WORKDIR /app
 COPY . .
-RUN pip install flask praisonai==2.0.57 gunicorn markdown
+RUN pip install flask praisonai==2.0.59 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==2.0.57 gunicorn markdown\n&#34;)
+            file.write(&#34;RUN pip install flask praisonai==2.0.59 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/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.
@@ -109,115 +138,361 @@ seo:
       </Step>
     </Steps>
   </Tab>
-  <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 Basic
-  from praisonaiagents import Agent, Task, PraisonAIAgents
-
-  # 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"
-  )
-
-  # Define a task
-  task = Task(
-      name="research_task",
-      description="Analyze 2024's AI advancements",
-      expected_output="A detailed report",
-      agent=researcher
-  )
-
-  # 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()
-  ```
-</CodeGroup>
-      </Step>
-      <Step title="Run Script">
-        ```bash
-        python app.py
-        ```
-      </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 +613,29 @@ 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) |
+| 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) |

docs/introduction.mdx

@@ -89,143 +89,121 @@ 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>
 </Tabs>

docs/mint.json

@@ -118,6 +118,7 @@
         "features/autoagents",
         "features/selfreflection",
         "features/rag",
+        "features/reasoning-extract",
         "features/reasoning",
         "features/multimodal",
         "features/langchain",

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/2.0.57.tar.gz"
+    url "https://github.com/MervinPraison/PraisonAI/archive/refs/tags/2.0.59.tar.gz"
     sha256 "1828fb9227d10f991522c3f24f061943a254b667196b40b1a3e4a54a8d30ce32"  # Replace with actual SHA256 checksum
     license "MIT"
   

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==2.0.57 gunicorn markdown\n")
+            file.write("RUN pip install flask praisonai==2.0.59 gunicorn markdown\n")
             file.write("EXPOSE 8080\n")
             file.write('CMD ["gunicorn", "-b", "0.0.0.0:8080", "api:app"]\n')
             

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "PraisonAI"
-version = "2.0.57"
+version = "2.0.59"
 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>=0.0.50",
+    "praisonaiagents>=0.0.56",
     "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 = "2.0.57"
+version = "2.0.59"
 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 = ">=0.0.50"
+praisonaiagents = ">=0.0.56"
 python-dotenv = ">=0.19.0"
 instructor = ">=1.3.3"
 PyYAML = ">=6.0"

uv.lock

@@ -3060,7 +3060,7 @@ wheels = [
 
 [[package]]
 name = "praisonai"
-version = "2.0.57"
+version = "2.0.59"
 source = { editable = "." }
 dependencies = [
     { name = "instructor" },
@@ -3197,7 +3197,7 @@ requires-dist = [
     { name = "plotly", marker = "extra == 'realtime'", specifier = ">=5.24.0" },
     { name = "praisonai-tools", marker = "extra == 'autogen'", specifier = ">=0.0.7" },
     { name = "praisonai-tools", marker = "extra == 'crewai'", specifier = ">=0.0.7" },
-    { name = "praisonaiagents", specifier = ">=0.0.50" },
+    { name = "praisonaiagents", specifier = ">=0.0.56" },
     { name = "pyautogen", marker = "extra == 'autogen'", specifier = ">=0.2.19" },
     { name = "pydantic", marker = "extra == 'chat'", specifier = "<=2.10.1" },
     { name = "pydantic", marker = "extra == 'code'", specifier = "<=2.10.1" },
@@ -3250,16 +3250,16 @@ wheels = [
 
 [[package]]
 name = "praisonaiagents"
-version = "0.0.50"
+version = "0.0.56"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "openai" },
     { name = "pydantic" },
     { name = "rich" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/e9/44/52c6e7a0c8bef2cc861e35206c0a5fee350b07134d0c4745dfb62ddfc09d/praisonaiagents-0.0.50.tar.gz", hash = "sha256:3cb6447422a76aff6846df6047e885c7552516ec6a36321bb0c0f663dfcffa24", size = 85120 }
+sdist = { url = "https://files.pythonhosted.org/packages/1f/d0/5b3ee6832c4797cb6dd47496485789e13113014d501856c2b5b286e7108c/praisonaiagents-0.0.56.tar.gz", hash = "sha256:148b6400403a7ad05b105084640e7140799e4e3bfb23a844bb79e10ea98bf859", size = 88236 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/96/b5/5433a5611a0798063fd1e3fdbd74f90171f2a9b593adfe448865b30b8c8b/praisonaiagents-0.0.50-py3-none-any.whl", hash = "sha256:3a0657d4bfd1ad70d319ab741b87e9b81b0ffd7aa57499afdc9bd914bdf7f4cd", size = 103242 },
+    { url = "https://files.pythonhosted.org/packages/1a/7e/1da42b51510d3bef28f4d450824d7d14fdd2358981adf7c5b8251e586526/praisonaiagents-0.0.56-py3-none-any.whl", hash = "sha256:b198c60a8909c39b2ced09e0c7cc1ad6224af15b8c743f6890ef3985fae4d036", size = 106340 },
 ]
 
 [[package]]