praisonaiagents 0.0.16__tar.gz → 0.0.18__tar.gz

{praisonaiagents-0.0.16 → praisonaiagents-0.0.18}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: praisonaiagents
-Version: 0.0.16
+Version: 0.0.18
 Summary: Praison AI agents for completing complex tasks with Self Reflection Agents
 Author: Mervin Praison
 Requires-Dist: pydantic

{praisonaiagents-0.0.16 → praisonaiagents-0.0.18}/praisonaiagents/__init__.py

@@ -16,6 +16,8 @@ from .main import (
     display_generating,
     clean_triple_backticks,
     error_logs,
+    register_display_callback,
+    display_callbacks,
 )
 
 __all__ = [
@@ -32,4 +34,6 @@ __all__ = [
     'display_generating',
     'clean_triple_backticks',
     'error_logs',
+    'register_display_callback',
+    'display_callbacks',
 ] 

{praisonaiagents-0.0.16 → praisonaiagents-0.0.18}/praisonaiagents/agent/agent.py

@@ -1,9 +1,12 @@
-import logging
-import json
+import os
 import time
+import json
+import logging
+import asyncio
 from typing import List, Optional, Any, Dict, Union, Literal
 from rich.console import Console
 from rich.live import Live
+from openai import AsyncOpenAI
 from ..main import (
     display_error,
     display_tool_call,
@@ -192,6 +195,12 @@ class Agent:
         self.min_reflect = min_reflect
         self.reflect_llm = reflect_llm
         self.console = Console()  # Create a single console instance for the agent
+        
+        # Initialize system prompt
+        self.system_prompt = f"""{self.backstory}\n
+Your Role: {self.role}\n
+Your Goal: {self.goal}
+        """
 
     def execute_tool(self, function_name, arguments):
         """
@@ -536,4 +545,143 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
             cleaned = cleaned[len("```"):].strip()
         if cleaned.endswith("```"):
             cleaned = cleaned[:-3].strip()
-        return cleaned 
+        return cleaned 
+
+    async def achat(self, prompt, temperature=0.2, tools=None, output_json=None):
+        """Async version of chat method"""
+        try:
+            # Build system prompt
+            system_prompt = self.system_prompt
+            if output_json:
+                system_prompt += f"\nReturn ONLY a JSON object that matches this Pydantic model: {output_json.schema_json()}"
+
+            # Build messages
+            if isinstance(prompt, str):
+                messages = [
+                    {"role": "system", "content": system_prompt},
+                    {"role": "user", "content": prompt + ("\nReturn ONLY a valid JSON object. No other text or explanation." if output_json else "")}
+                ]
+            else:
+                # For multimodal prompts
+                messages = [
+                    {"role": "system", "content": system_prompt},
+                    {"role": "user", "content": prompt}
+                ]
+                if output_json:
+                    # Add JSON instruction to text content
+                    for item in messages[-1]["content"]:
+                        if item["type"] == "text":
+                            item["text"] += "\nReturn ONLY a valid JSON object. No other text or explanation."
+                            break
+
+            # Format tools if provided
+            formatted_tools = []
+            if tools:
+                for tool in tools:
+                    if isinstance(tool, str):
+                        tool_def = self._generate_tool_definition(tool)
+                        if tool_def:
+                            formatted_tools.append(tool_def)
+                    elif isinstance(tool, dict):
+                        formatted_tools.append(tool)
+                    elif hasattr(tool, "to_openai_tool"):
+                        formatted_tools.append(tool.to_openai_tool())
+                    elif callable(tool):
+                        formatted_tools.append(self._generate_tool_definition(tool.__name__))
+
+            # Create async OpenAI client
+            async_client = AsyncOpenAI()
+
+            # Make the API call based on the type of request
+            if tools:
+                response = await async_client.chat.completions.create(
+                    model=self.llm,
+                    messages=messages,
+                    temperature=temperature,
+                    tools=formatted_tools
+                )
+                return await self._achat_completion(response, tools)
+            elif output_json:
+                response = await async_client.chat.completions.create(
+                    model=self.llm,
+                    messages=messages,
+                    temperature=temperature,
+                    response_format={"type": "json_object"}
+                )
+                result = response.choices[0].message.content
+                # Clean and parse the JSON response
+                cleaned_json = self.clean_json_output(result)
+                try:
+                    parsed = json.loads(cleaned_json)
+                    return output_json(**parsed)
+                except Exception as e:
+                    display_error(f"Error parsing JSON response: {e}")
+                    return None
+            else:
+                response = await async_client.chat.completions.create(
+                    model=self.llm,
+                    messages=messages,
+                    temperature=temperature
+                )
+                return response.choices[0].message.content
+        except Exception as e:
+            display_error(f"Error in chat completion: {e}")
+            return None
+
+    async def _achat_completion(self, response, tools):
+        """Async version of _chat_completion method"""
+        try:
+            message = response.choices[0].message
+            if not hasattr(message, 'tool_calls') or not message.tool_calls:
+                return message.content
+
+            results = []
+            for tool_call in message.tool_calls:
+                try:
+                    function_name = tool_call.function.name
+                    arguments = json.loads(tool_call.function.arguments)
+                    
+                    # Find the matching tool
+                    tool = next((t for t in tools if t.__name__ == function_name), None)
+                    if not tool:
+                        display_error(f"Tool {function_name} not found")
+                        continue
+                    
+                    # Check if the tool is async
+                    if asyncio.iscoroutinefunction(tool):
+                        result = await tool(**arguments)
+                    else:
+                        # Run sync function in executor to avoid blocking
+                        loop = asyncio.get_event_loop()
+                        result = await loop.run_in_executor(None, lambda: tool(**arguments))
+                    
+                    results.append(result)
+                except Exception as e:
+                    display_error(f"Error executing tool {function_name}: {e}")
+                    results.append(None)
+
+            # If we have results, format them into a response
+            if results:
+                formatted_results = "\n".join([str(r) for r in results if r is not None])
+                if formatted_results:
+                    messages = [
+                        {"role": "system", "content": self.system_prompt},
+                        {"role": "assistant", "content": "Here are the tool results:"},
+                        {"role": "user", "content": formatted_results + "\nPlease process these results and provide a final response."}
+                    ]
+                    try:
+                        async_client = AsyncOpenAI()
+                        final_response = await async_client.chat.completions.create(
+                            model=self.llm,
+                            messages=messages,
+                            temperature=0.2
+                        )
+                        return final_response.choices[0].message.content
+                    except Exception as e:
+                        display_error(f"Error in final chat completion: {e}")
+                        return formatted_results
+                return formatted_results
+            return None
+        except Exception as e:
+            display_error(f"Error in _achat_completion: {e}")
+            return None 

{praisonaiagents-0.0.16 → praisonaiagents-0.0.18}/praisonaiagents/agents/agents.py

@@ -11,6 +11,7 @@ from ..main import display_error, TaskOutput, error_logs, client
 from ..agent.agent import Agent
 from ..task.task import Task
 from ..process.process import Process, LoopItems
+import asyncio
 
 def encode_file_to_base64(file_path: str) -> str:
     """Base64-encode a file."""
@@ -82,7 +83,8 @@ class PraisonAIAgents:
             return True
         return len(agent_output.strip()) > 0
 
-    def execute_task(self, task_id):
+    async def aexecute_task(self, task_id):
+        """Async version of execute_task method"""
         if task_id not in self.tasks:
             display_error(f"Error: Task with ID {task_id} does not exist")
             return
@@ -159,12 +161,12 @@ Expected Output: {task.expected_output}.
                         })
                 return content
 
-            agent_output = executor_agent.chat(
+            agent_output = await executor_agent.achat(
                 _get_multimodal_message(task_prompt, task.images),
                 tools=task.tools
             )
         else:
-            agent_output = executor_agent.chat(task_prompt, tools=task.tools)
+            agent_output = await executor_agent.achat(task_prompt, tools=task.tools)
 
         if agent_output:
             task_output = TaskOutput(
@@ -202,6 +204,83 @@ Expected Output: {task.expected_output}.
             task.status = "failed"
             return None
 
+    async def arun_task(self, task_id):
+        """Async version of run_task method"""
+        if task_id not in self.tasks:
+            display_error(f"Error: Task with ID {task_id} does not exist")
+            return
+        task = self.tasks[task_id]
+        if task.status == "completed":
+            logging.info(f"Task with ID {task_id} is already completed")
+            return
+
+        retries = 0
+        while task.status != "completed" and retries < self.max_retries:
+            logging.debug(f"Attempt {retries+1} for task {task_id}")
+            if task.status in ["not started", "in progress"]:
+                task_output = await self.aexecute_task(task_id)
+                if task_output and self.completion_checker(task, task_output.raw):
+                    task.status = "completed"
+                    if task.callback:
+                        await task.execute_callback(task_output)
+                    self.save_output_to_file(task, task_output)
+                    if self.verbose >= 1:
+                        logging.info(f"Task {task_id} completed successfully.")
+                else:
+                    task.status = "in progress"
+                    if self.verbose >= 1:
+                        logging.info(f"Task {task_id} not completed, retrying")
+                    await asyncio.sleep(1)
+                    retries += 1
+            else:
+                if task.status == "failed":
+                    logging.info("Task is failed, resetting to in-progress for another try...")
+                    task.status = "in progress"
+                else:
+                    logging.info("Invalid Task status")
+                    break
+
+        if retries == self.max_retries and task.status != "completed":
+            logging.info(f"Task {task_id} failed after {self.max_retries} retries.")
+
+    async def arun_all_tasks(self):
+        """Async version of run_all_tasks method"""
+        process = Process(
+            tasks=self.tasks,
+            agents=self.agents,
+            manager_llm=self.manager_llm,
+            verbose=self.verbose
+        )
+        
+        if self.process == "workflow":
+            async for task_id in process.aworkflow():
+                if self.tasks[task_id].async_execution:
+                    await self.arun_task(task_id)
+                else:
+                    self.run_task(task_id)
+        elif self.process == "sequential":
+            async for task_id in process.asequential():
+                if self.tasks[task_id].async_execution:
+                    await self.arun_task(task_id)
+                else:
+                    self.run_task(task_id)
+        elif self.process == "hierarchical":
+            async for task_id in process.ahierarchical():
+                if isinstance(task_id, Task):
+                    task_id = self.add_task(task_id)
+                if self.tasks[task_id].async_execution:
+                    await self.arun_task(task_id)
+                else:
+                    self.run_task(task_id)
+
+    async def astart(self):
+        """Async version of start method"""
+        await self.arun_all_tasks()
+        return {
+            "task_status": self.get_all_tasks_status(),
+            "task_results": {task_id: self.get_task_result(task_id) for task_id in self.tasks}
+        }
+
     def save_output_to_file(self, task, task_output):
         if task.output_file:
             try:
@@ -214,7 +293,129 @@ Expected Output: {task.expected_output}.
             except Exception as e:
                 display_error(f"Error saving task output to file: {e}")
 
+    def execute_task(self, task_id):
+        """Synchronous version of execute_task method"""
+        if task_id not in self.tasks:
+            display_error(f"Error: Task with ID {task_id} does not exist")
+            return
+        task = self.tasks[task_id]
+        
+        # Only import multimodal dependencies if task has images
+        if task.images and task.status == "not started":
+            try:
+                import cv2
+                import base64
+                from moviepy import VideoFileClip
+            except ImportError as e:
+                display_error(f"Error: Missing required dependencies for image/video processing: {e}")
+                display_error("Please install with: pip install opencv-python moviepy")
+                task.status = "failed"
+                return None
+
+        if task.status == "not started":
+            task.status = "in progress"
+
+        executor_agent = task.agent
+
+        task_prompt = f"""
+You need to do the following task: {task.description}.
+Expected Output: {task.expected_output}.
+        """
+        if task.context:
+            context_results = ""
+            for context_task in task.context:
+                if context_task.result:
+                    context_results += f"Result of previous task {context_task.name if context_task.name else context_task.description}: {context_task.result.raw}\n"
+                else:
+                    context_results += f"Previous task {context_task.name if context_task.name else context_task.description} had no result.\n"
+            task_prompt += f"""
+            Here are the results of previous tasks that might be useful:\n
+            {context_results}
+            """
+        task_prompt += "Please provide only the final result of your work. Do not add any conversation or extra explanation."
+
+        if self.verbose >= 2:
+            logging.info(f"Executing task {task_id}: {task.description} using {executor_agent.name}")
+        logging.debug(f"Starting execution of task {task_id} with prompt:\n{task_prompt}")
+
+        if task.images:
+            def _get_multimodal_message(text_prompt, images):
+                content = [{"type": "text", "text": text_prompt}]
+
+                for img in images:
+                    # If local file path for a valid image
+                    if os.path.exists(img):
+                        ext = os.path.splitext(img)[1].lower()
+                        # If it's a .mp4, convert to frames
+                        if ext == ".mp4":
+                            frames = process_video(img, seconds_per_frame=1)
+                            content.append({"type": "text", "text": "These are frames from the video."})
+                            for f in frames:
+                                content.append({
+                                    "type": "image_url",
+                                    "image_url": {"url": f"data:image/jpg;base64,{f}"}
+                                })
+                        else:
+                            encoded = encode_file_to_base64(img)
+                            content.append({
+                                "type": "image_url",
+                                "image_url": {
+                                    "url": f"data:image/{ext.lstrip('.')};base64,{encoded}"
+                                }
+                            })
+                    else:
+                        # Treat as a remote URL
+                        content.append({
+                            "type": "image_url",
+                            "image_url": {"url": img}
+                        })
+                return content
+
+            agent_output = executor_agent.chat(
+                _get_multimodal_message(task_prompt, task.images),
+                tools=task.tools
+            )
+        else:
+            agent_output = executor_agent.chat(task_prompt, tools=task.tools)
+
+        if agent_output:
+            task_output = TaskOutput(
+                description=task.description,
+                summary=task.description[:10],
+                raw=agent_output,
+                agent=executor_agent.name,
+                output_format="RAW"
+            )
+
+            if task.output_json:
+                cleaned = self.clean_json_output(agent_output)
+                try:
+                    parsed = json.loads(cleaned)
+                    task_output.json_dict = parsed
+                    task_output.output_format = "JSON"
+                except:
+                    logging.warning(f"Warning: Could not parse output of task {task_id} as JSON")
+                    logging.debug(f"Output that failed JSON parsing: {agent_output}")
+
+            if task.output_pydantic:
+                cleaned = self.clean_json_output(agent_output)
+                try:
+                    parsed = json.loads(cleaned)
+                    pyd_obj = task.output_pydantic(**parsed)
+                    task_output.pydantic = pyd_obj
+                    task_output.output_format = "Pydantic"
+                except:
+                    logging.warning(f"Warning: Could not parse output of task {task_id} as Pydantic Model")
+                    logging.debug(f"Output that failed Pydantic parsing: {agent_output}")
+
+            task.result = task_output
+            return task_output
+        else:
+            task.status = "failed"
+            return None
+
     def run_task(self, task_id):
+        """Synchronous version of run_task method"""
         if task_id not in self.tasks:
             display_error(f"Error: Task with ID {task_id} does not exist")
             return
@@ -253,7 +454,7 @@ Expected Output: {task.expected_output}.
             logging.info(f"Task {task_id} failed after {self.max_retries} retries.")
 
     def run_all_tasks(self):
-        """Execute tasks based on execution mode"""
+        """Synchronous version of run_all_tasks method"""
         process = Process(
             tasks=self.tasks,
             agents=self.agents,

{praisonaiagents-0.0.16 → praisonaiagents-0.0.18}/praisonaiagents/main.py

@@ -25,6 +25,13 @@ logging.basicConfig(
 # Global list to store error logs
 error_logs = []
 
+# Global callback registry
+display_callbacks = {}
+
+def register_display_callback(display_type: str, callback_fn):
+    """Register a callback function for a specific display type."""
+    display_callbacks[display_type] = callback_fn
+
 def _clean_display_content(content: str, max_length: int = 20000) -> str:
     """Helper function to clean and truncate content for display."""
     if not content or not str(content).strip():
@@ -49,18 +56,28 @@ def display_interaction(message, response, markdown=True, generation_time=None,
     """Display the interaction between user and assistant."""
     if console is None:
         console = Console()
-    if generation_time:
-        console.print(Text(f"Response generated in {generation_time:.1f}s", style="dim"))
-
+    
     # Handle multimodal content (list)
     if isinstance(message, list):
-        # Extract just the text content from the multimodal message
         text_content = next((item["text"] for item in message if item["type"] == "text"), "")
         message = text_content
 
     message = _clean_display_content(str(message))
     response = _clean_display_content(str(response))
 
+    # Execute callback if registered
+    if 'interaction' in display_callbacks:
+        display_callbacks['interaction'](
+            message=message,
+            response=response,
+            markdown=markdown,
+            generation_time=generation_time
+        )
+
+    # Existing display logic...
+    if generation_time:
+        console.print(Text(f"Response generated in {generation_time:.1f}s", style="dim"))
+
     if markdown:
         console.print(Panel.fit(Markdown(message), title="Message", border_style="cyan"))
         console.print(Panel.fit(Markdown(response), title="Response", border_style="cyan"))
@@ -74,6 +91,11 @@ def display_self_reflection(message: str, console=None):
     if console is None:
         console = Console()
     message = _clean_display_content(str(message))
+    
+    # Execute callback if registered
+    if 'self_reflection' in display_callbacks:
+        display_callbacks['self_reflection'](message=message)
+    
     console.print(Panel.fit(Text(message, style="bold yellow"), title="Self Reflection", border_style="magenta"))
 
 def display_instruction(message: str, console=None):
@@ -82,6 +104,11 @@ def display_instruction(message: str, console=None):
     if console is None:
         console = Console()
     message = _clean_display_content(str(message))
+    
+    # Execute callback if registered
+    if 'instruction' in display_callbacks:
+        display_callbacks['instruction'](message=message)
+    
     console.print(Panel.fit(Text(message, style="bold blue"), title="Instruction", border_style="cyan"))
 
 def display_tool_call(message: str, console=None):
@@ -90,6 +117,11 @@ def display_tool_call(message: str, console=None):
     if console is None:
         console = Console()
     message = _clean_display_content(str(message))
+    
+    # Execute callback if registered
+    if 'tool_call' in display_callbacks:
+        display_callbacks['tool_call'](message=message)
+    
     console.print(Panel.fit(Text(message, style="bold cyan"), title="Tool Call", border_style="green"))
 
 def display_error(message: str, console=None):
@@ -98,19 +130,32 @@ def display_error(message: str, console=None):
     if console is None:
         console = Console()
     message = _clean_display_content(str(message))
+    
+    # Execute callback if registered
+    if 'error' in display_callbacks:
+        display_callbacks['error'](message=message)
+    
     console.print(Panel.fit(Text(message, style="bold red"), title="Error", border_style="red"))
-    # Store errors
     error_logs.append(message)
 
 def display_generating(content: str = "", start_time: Optional[float] = None):
     if not content or not str(content).strip():
-        return Panel("", title="", border_style="green")  # Return empty panel when no content
+        return Panel("", title="", border_style="green")
+    
     elapsed_str = ""
     if start_time is not None:
         elapsed = time.time() - start_time
         elapsed_str = f" {elapsed:.1f}s"
     
     content = _clean_display_content(str(content))
+    
+    # Execute callback if registered
+    if 'generating' in display_callbacks:
+        display_callbacks['generating'](
+            content=content,
+            elapsed_time=elapsed_str.strip() if elapsed_str else None
+        )
+    
     return Panel(Markdown(content), title=f"Generating...{elapsed_str}", border_style="green")
 
 def clean_triple_backticks(text: str) -> str: