diff --git a/src/praisonai-agents/praisonaiagents/agent/agent.py b/src/praisonai-agents/praisonaiagents/agent/agent.py
index 261fc61f..cdd75e34 100644
--- a/src/praisonai-agents/praisonaiagents/agent/agent.py
+++ b/src/praisonai-agents/praisonaiagents/agent/agent.py
@@ -713,7 +713,7 @@ def _chat_completion(self, messages, temperature=0.2, tools=None, stream=True, r
             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, reasoning_steps=False):
+    def chat(self, prompt, temperature=0.2, tools=None, output_json=None, output_pydantic=None, reasoning_steps=False, stream=None):
         # Log all parameter values when in debug mode
         if logging.getLogger().getEffectiveLevel() == logging.DEBUG:
             param_info = {
@@ -842,7 +842,7 @@ def chat(self, prompt, temperature=0.2, tools=None, output_json=None, output_pyd
                                 agent_tools=agent_tools
                             )
 
-                    response = self._chat_completion(messages, temperature=temperature, tools=tools if tools else None, reasoning_steps=reasoning_steps)
+                    response = self._chat_completion(messages, temperature=temperature, tools=tools if tools else None, reasoning_steps=reasoning_steps, stream=stream)
                     if not response:
                         return None
 
@@ -879,7 +879,7 @@ def chat(self, prompt, temperature=0.2, tools=None, output_json=None, output_pyd
                                     "content": "Function returned an empty output"
                                 })
                             
-                        response = self._chat_completion(messages, temperature=temperature)
+                        response = self._chat_completion(messages, temperature=temperature, stream=stream)
                         if not response:
                             return None
                         response_text = response.choices[0].message.content.strip()
@@ -949,7 +949,7 @@ def chat(self, prompt, temperature=0.2, tools=None, output_json=None, output_pyd
 
                         logging.debug(f"{self.name} reflection count {reflection_count + 1}, continuing reflection process")
                         messages.append({"role": "user", "content": "Now regenerate your response using the reflection you made"})
-                        response = self._chat_completion(messages, temperature=temperature, tools=None, stream=True)
+                        response = self._chat_completion(messages, temperature=temperature, tools=None, stream=stream)
                         response_text = response.choices[0].message.content.strip()
                         reflection_count += 1
                         continue  # Continue the loop for more reflections
@@ -1129,7 +1129,7 @@ async def achat(self, prompt: str, temperature=0.2, tools=None, output_json=None
                             model=self.llm,
                             messages=messages,
                             temperature=temperature,
-                            tools=formatted_tools
+                            tools=formatted_tools,
                         )
                         result = await self._achat_completion(response, tools)
                         if logging.getLogger().getEffectiveLevel() == logging.DEBUG:
diff --git a/src/praisonai-agents/praisonaiagents/agents/agents.py b/src/praisonai-agents/praisonaiagents/agents/agents.py
index 3aeec8a6..9587eb7a 100644
--- a/src/praisonai-agents/praisonaiagents/agents/agents.py
+++ b/src/praisonai-agents/praisonaiagents/agents/agents.py
@@ -45,7 +45,7 @@ def process_video(video_path: str, seconds_per_frame=2):
     return base64_frames
 
 class PraisonAIAgents:
-    def __init__(self, agents, tasks=None, verbose=0, completion_checker=None, max_retries=5, process="sequential", manager_llm=None, memory=False, memory_config=None, embedder=None, user_id=None, max_iter=10):
+    def __init__(self, agents, tasks=None, verbose=0, completion_checker=None, max_retries=5, process="sequential", manager_llm=None, memory=False, memory_config=None, embedder=None, user_id=None, max_iter=10, stream=None):
         # Add check at the start if memory is requested
         if memory:
             try:
@@ -68,8 +68,8 @@ def __init__(self, agents, tasks=None, verbose=0, completion_checker=None, max_r
         for agent in agents:
             agent.user_id = self.user_id
 
-        self.agents = agents
-        self.tasks = {}
+        self.agents: List[Agent] = agents
+        self.tasks: Dict[int, Task] = {}
         if max_retries < 3:
             max_retries = 3
         self.completion_checker = completion_checker if completion_checker else self.default_completion_checker
@@ -77,6 +77,7 @@ def __init__(self, agents, tasks=None, verbose=0, completion_checker=None, max_r
         self.verbose = verbose
         self.max_retries = max_retries
         self.process = process
+        self.stream = stream
         
         # Check for manager_llm in environment variable if not provided
         self.manager_llm = manager_llm or os.getenv('OPENAI_MODEL_NAME', 'gpt-4o')
@@ -665,7 +666,8 @@ def _get_multimodal_message(text_prompt, images):
                 task_prompt,
                 tools=task.tools,
                 output_json=task.output_json,
-                output_pydantic=task.output_pydantic
+                output_pydantic=task.output_pydantic,
+                stream=self.stream,
             )
 
         if agent_output: