chore: update PraisonAI and related package versions to 2.2.45 and 0.0.118

- Updated PraisonAI version in Dockerfiles and README to 2.2.45
- Updated version in pyproject.toml and uv.lock for PraisonAI and PraisonAI agents to 0.0.118
- Adjusted deployment script to reflect the new PraisonAI version

docker/Dockerfile

@@ -16,7 +16,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
     flask \
-    "praisonai>=2.2.44" \
+    "praisonai>=2.2.45" \
     "praisonai[api]" \
     gunicorn \
     markdown

docker/Dockerfile.chat

@@ -16,7 +16,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
     praisonai_tools \
-    "praisonai>=2.2.44" \
+    "praisonai>=2.2.45" \
     "praisonai[chat]" \
     "embedchain[github,youtube]"
 

docker/Dockerfile.dev

@@ -20,7 +20,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
     praisonai_tools \
-    "praisonai>=2.2.44" \
+    "praisonai>=2.2.45" \
     "praisonai[ui]" \
     "praisonai[chat]" \
     "praisonai[realtime]" \

docker/Dockerfile.ui

@@ -16,7 +16,7 @@ RUN mkdir -p /root/.praison
 # Install Python packages (using latest versions)
 RUN pip install --no-cache-dir \
     praisonai_tools \
-    "praisonai>=2.2.44" \
+    "praisonai>=2.2.45" \
     "praisonai[ui]" \
     "praisonai[crewai]"
 

docker/README.md

@@ -121,7 +121,7 @@ healthcheck:
 ## 📦 Package Versions
 
 All Docker images use consistent, up-to-date versions:
-- PraisonAI: `>=2.2.44`
+- PraisonAI: `>=2.2.45`
 - PraisonAI Agents: `>=0.0.92`
 - Python: `3.11-slim`
 
@@ -218,7 +218,7 @@ docker-compose up -d
 ### Version Pinning
 To use specific versions, update the Dockerfile:
 ```dockerfile
-RUN pip install "praisonai==2.2.44" "praisonaiagents==0.0.92"
+RUN pip install "praisonai==2.2.45" "praisonaiagents==0.0.92"
 ```
 
 ## 🌐 Production Deployment

src/praisonai-agents/ollama-agents.py

@@ -0,0 +1,8 @@
+from praisonaiagents import Agent
+
+agent = Agent(
+    instructions="You are a helpful assistant",
+    llm="ollama/qwen3"
+)
+
+agent.start("Why sky is Blue?")

src/praisonai-agents/praisonaiagents/llm/llm.py

@@ -813,99 +813,56 @@ class LLM:
                         # Make one more call to get the final summary response
                         # Special handling for Ollama models that don't automatically process tool results
                         ollama_handled = False
-                        if self.model and self.model.startswith("ollama/") and tool_results:
-                            # For Ollama models, we need to explicitly ask the model to process the tool results
-                            # First, check if the response is just a JSON tool call
-                            try:
-                                # If the response_text is a valid JSON that looks like a tool call,
-                                # we need to make a follow-up call to process the results
-                                json_response = json.loads(response_text.strip())
-                                if ('name' in json_response or 'function' in json_response) and not any(word in response_text.lower() for word in ['summary', 'option', 'result', 'found']):
-                                    logging.debug("Detected Ollama returning only tool call JSON, making follow-up call to process results")
-                                    
-                                    # Create a prompt that asks the model to process the tool results based on original context
-                                    # Extract the original user query from messages
-                                    original_query = ""
-                                    for msg in reversed(messages):  # Look from the end to find the most recent user message
-                                        if msg.get("role") == "user":
-                                            content = msg.get("content", "")
-                                            # Handle list content (multimodal)
-                                            if isinstance(content, list):
-                                                for item in content:
-                                                    if isinstance(item, dict) and item.get("type") == "text":
-                                                        original_query = item.get("text", "")
-                                                        break
-                                            else:
-                                                original_query = content
-                                            if original_query:
-                                                break
-                                    
-                                    # Create a shorter follow-up prompt with all tool results
-                                    # If there's only one result, use it directly; otherwise combine them
-                                    if len(tool_results) == 1:
-                                        results_text = json.dumps(tool_results[0], indent=2)
-                                    else:
-                                        results_text = json.dumps(tool_results, indent=2)
-                                    
-                                    follow_up_prompt = f"Results:\n{results_text}\nProvide Answer to this Original Question based on the above results: '{original_query}'"
-                                    logging.debug(f"[OLLAMA_DEBUG] Original query extracted: {original_query}")
-                                    logging.debug(f"[OLLAMA_DEBUG] Follow-up prompt: {follow_up_prompt[:200]}...")
-                                    
-                                    # Make a follow-up call to process the results
-                                    follow_up_messages = [
-                                        {"role": "user", "content": follow_up_prompt}
-                                    ]
-                                    
-                                    # Get response 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(
-                                                **self._build_completion_params(
-                                                    messages=follow_up_messages,
-                                                    temperature=temperature,
-                                                    stream=stream
-                                                )
-                                            ):
-                                                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(
-                                            **self._build_completion_params(
-                                                messages=follow_up_messages,
-                                                temperature=temperature,
-                                                stream=stream
-                                            )
-                                        ):
-                                            if chunk and chunk.choices and chunk.choices[0].delta.content:
-                                                response_text += chunk.choices[0].delta.content
-                                    
-                                    # Set flag to indicate Ollama was handled
-                                    ollama_handled = True
-                                    final_response_text = response_text.strip()
-                                    logging.debug(f"[OLLAMA_DEBUG] Ollama follow-up response: {final_response_text[:200]}...")
-                                    
-                                    # Display the response if we got one
-                                    if final_response_text and verbose:
-                                        display_interaction(
-                                            original_prompt,
-                                            final_response_text,
-                                            markdown=markdown,
-                                            generation_time=time.time() - start_time,
-                                            console=console
+                        ollama_params = self._handle_ollama_model(response_text, tool_results, messages, original_prompt)
+                        
+                        if ollama_params:
+                            # Get response 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(
+                                        **self._build_completion_params(
+                                            messages=ollama_params["follow_up_messages"],
+                                            temperature=temperature,
+                                            stream=stream
                                         )
-                                    
-                                    # Return the final response after processing Ollama's follow-up
-                                    if final_response_text:
-                                        return final_response_text
-                                    else:
-                                        logging.warning("[OLLAMA_DEBUG] Ollama follow-up returned empty response")
-                            except (json.JSONDecodeError, KeyError):
-                                # Not a JSON response or not a tool call format, continue normally
-                                pass
+                                    ):
+                                        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(
+                                    **self._build_completion_params(
+                                        messages=ollama_params["follow_up_messages"],
+                                        temperature=temperature,
+                                        stream=stream
+                                    )
+                                ):
+                                    if chunk and chunk.choices and chunk.choices[0].delta.content:
+                                        response_text += chunk.choices[0].delta.content
+                            
+                            # Set flag to indicate Ollama was handled
+                            ollama_handled = True
+                            final_response_text = response_text.strip()
+                            logging.debug(f"[OLLAMA_DEBUG] Ollama follow-up response: {final_response_text[:200]}...")
+                            
+                            # Display the response if we got one
+                            if final_response_text and verbose:
+                                display_interaction(
+                                    ollama_params["original_prompt"],
+                                    final_response_text,
+                                    markdown=markdown,
+                                    generation_time=time.time() - start_time,
+                                    console=console
+                                )
+                            
+                            # Return the final response after processing Ollama's follow-up
+                            if final_response_text:
+                                return final_response_text
+                            else:
+                                logging.warning("[OLLAMA_DEBUG] Ollama follow-up returned empty response")
                         
                         # If reasoning_steps is True and we haven't handled Ollama already, do a single non-streaming call
                         if reasoning_steps and not ollama_handled:
@@ -1480,99 +1437,56 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                     
                     # Special handling for Ollama models that don't automatically process tool results
                     ollama_handled = False
-                    if self._is_ollama_provider() and tool_results:
-                        # For Ollama models, we need to explicitly ask the model to process the tool results
-                        # First, check if the response is just a JSON tool call
-                        try:
-                            # If the response_text is a valid JSON that looks like a tool call,
-                            # we need to make a follow-up call to process the results
-                            json_response = json.loads(response_text.strip())
-                            if ('name' in json_response or 'function' in json_response) and not any(word in response_text.lower() for word in ['summary', 'option', 'result', 'found']):
-                                logging.debug("Detected Ollama returning only tool call JSON in async mode, making follow-up call to process results")
-                                
-                                # Create a prompt that asks the model to process the tool results based on original context
-                                # Extract the original user query from messages
-                                original_query = ""
-                                for msg in reversed(messages):  # Look from the end to find the most recent user message
-                                    if msg.get("role") == "user":
-                                        content = msg.get("content", "")
-                                        # Handle list content (multimodal)
-                                        if isinstance(content, list):
-                                            for item in content:
-                                                if isinstance(item, dict) and item.get("type") == "text":
-                                                    original_query = item.get("text", "")
-                                                    break
-                                        else:
-                                            original_query = content
-                                        if original_query:
-                                            break
-                                
-                                # Create a shorter follow-up prompt with all tool results
-                                # If there's only one result, use it directly; otherwise combine them
-                                if len(tool_results) == 1:
-                                    results_text = json.dumps(tool_results[0], indent=2)
-                                else:
-                                    results_text = json.dumps(tool_results, indent=2)
-                                
-                                follow_up_prompt = f"Results:\n{results_text}\nProvide Answer to this Original Question based on the above results: '{original_query}'"
-                                logging.debug(f"[OLLAMA_DEBUG] Original query extracted: {original_query}")
-                                logging.debug(f"[OLLAMA_DEBUG] Follow-up prompt: {follow_up_prompt[:200]}...")
-                                
-                                # Make a follow-up call to process the results
-                                follow_up_messages = [
-                                    {"role": "user", "content": follow_up_prompt}
-                                ]
-                                
-                                # Get response with streaming
-                                if verbose:
-                                    response_text = ""
-                                    async for chunk in await litellm.acompletion(
-                                        **self._build_completion_params(
-                                            messages=follow_up_messages,
-                                            temperature=temperature,
-                                            stream=stream
-                                        )
-                                    ):
-                                        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"Processing results... {time.time() - start_time:.1f}s", end="\r")
-                                else:
-                                    response_text = ""
-                                    async for chunk in await litellm.acompletion(
-                                        **self._build_completion_params(
-                                            messages=follow_up_messages,
-                                            temperature=temperature,
-                                            stream=stream
-                                        )
-                                    ):
-                                        if chunk and chunk.choices and chunk.choices[0].delta.content:
-                                            response_text += chunk.choices[0].delta.content
-                                
-                                # Set flag to indicate Ollama was handled
-                                ollama_handled = True
-                                final_response_text = response_text.strip()
-                                logging.debug(f"[OLLAMA_DEBUG] Ollama follow-up response: {final_response_text[:200]}...")
-                                
-                                # Display the response if we got one
-                                if final_response_text and verbose:
-                                    display_interaction(
-                                        original_prompt,
-                                        final_response_text,
-                                        markdown=markdown,
-                                        generation_time=time.time() - start_time,
-                                        console=console
-                                    )
-                                
-                                # Return the final response after processing Ollama's follow-up
-                                if final_response_text:
-                                    return final_response_text
-                                else:
-                                    logging.warning("[OLLAMA_DEBUG] Ollama follow-up returned empty response")
-                        except (json.JSONDecodeError, KeyError):
-                            # Not a JSON response or not a tool call format, continue normally
-                            pass
+                    ollama_params = self._handle_ollama_model(response_text, tool_results, messages, original_prompt)
+                    
+                    if ollama_params:
+                        # Get response with streaming
+                        if verbose:
+                            response_text = ""
+                            async for chunk in await litellm.acompletion(
+                                **self._build_completion_params(
+                                    messages=ollama_params["follow_up_messages"],
+                                    temperature=temperature,
+                                    stream=stream
+                                )
+                            ):
+                                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"Processing results... {time.time() - start_time:.1f}s", end="\r")
+                        else:
+                            response_text = ""
+                            async for chunk in await litellm.acompletion(
+                                **self._build_completion_params(
+                                    messages=ollama_params["follow_up_messages"],
+                                    temperature=temperature,
+                                    stream=stream
+                                )
+                            ):
+                                if chunk and chunk.choices and chunk.choices[0].delta.content:
+                                    response_text += chunk.choices[0].delta.content
+                        
+                        # Set flag to indicate Ollama was handled
+                        ollama_handled = True
+                        final_response_text = response_text.strip()
+                        logging.debug(f"[OLLAMA_DEBUG] Ollama follow-up response: {final_response_text[:200]}...")
+                        
+                        # Display the response if we got one
+                        if final_response_text and verbose:
+                            display_interaction(
+                                ollama_params["original_prompt"],
+                                final_response_text,
+                                markdown=markdown,
+                                generation_time=time.time() - start_time,
+                                console=console
+                            )
+                        
+                        # Return the final response after processing Ollama's follow-up
+                        if final_response_text:
+                            return final_response_text
+                        else:
+                            logging.warning("[OLLAMA_DEBUG] Ollama follow-up returned empty response")
                     
                     # If no special handling was needed or if it's not an Ollama model
                     if reasoning_steps and not ollama_handled:
@@ -1839,6 +1753,68 @@ Output MUST be JSON with 'reflection' and 'satisfactory'.
                 
         litellm.callbacks = events
 
+    def _handle_ollama_model(self, response_text: str, tool_results: List[Any], messages: List[Dict], original_prompt: Union[str, List[Dict]]) -> Optional[Dict[str, Any]]:
+        """
+        Handle special Ollama model requirements when processing tool results.
+        
+        Args:
+            response_text: The initial response text from the model
+            tool_results: List of tool execution results
+            messages: The conversation messages list
+            original_prompt: The original user prompt
+            
+        Returns:
+            Dict with follow-up parameters if Ollama needs special handling, None otherwise
+        """
+        if not self._is_ollama_provider() or not tool_results:
+            return None
+            
+        # Check if the response is just a JSON tool call
+        try:
+            json_response = json.loads(response_text.strip())
+            if not (('name' in json_response or 'function' in json_response) and 
+                    not any(word in response_text.lower() for word in ['summary', 'option', 'result', 'found'])):
+                return None
+                
+            logging.debug("Detected Ollama returning only tool call JSON, preparing follow-up call to process results")
+            
+            # Extract the original user query from messages
+            original_query = ""
+            for msg in reversed(messages):  # Look from the end to find the most recent user message
+                if msg.get("role") == "user":
+                    content = msg.get("content", "")
+                    # Handle list content (multimodal)
+                    if isinstance(content, list):
+                        for item in content:
+                            if isinstance(item, dict) and item.get("type") == "text":
+                                original_query = item.get("text", "")
+                                break
+                    else:
+                        original_query = content
+                    if original_query:
+                        break
+            
+            # Create a shorter follow-up prompt with all tool results
+            # If there's only one result, use it directly; otherwise combine them
+            if len(tool_results) == 1:
+                results_text = json.dumps(tool_results[0], indent=2)
+            else:
+                results_text = json.dumps(tool_results, indent=2)
+            
+            follow_up_prompt = f"Results:\n{results_text}\nProvide Answer to this Original Question based on the above results: '{original_query}'"
+            logging.debug(f"[OLLAMA_DEBUG] Original query extracted: {original_query}")
+            logging.debug(f"[OLLAMA_DEBUG] Follow-up prompt: {follow_up_prompt[:200]}...")
+            
+            # Return parameters for follow-up call
+            return {
+                "follow_up_messages": [{"role": "user", "content": follow_up_prompt}],
+                "original_prompt": original_prompt
+            }
+            
+        except (json.JSONDecodeError, KeyError):
+            # Not a JSON response or not a tool call format
+            return None
+
     def _build_completion_params(self, **override_params) -> Dict[str, Any]:
         """Build parameters for litellm completion calls with all necessary config"""
         params = {

src/praisonai-agents/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "praisonaiagents"
-version = "0.0.117"
+version = "0.0.118"
 description = "Praison AI agents for completing complex tasks with Self Reflection Agents"
 requires-python = ">=3.10"
 authors = [

src/praisonai-agents/uv.lock

@@ -2375,7 +2375,7 @@ wheels = [
 
 [[package]]
 name = "praisonaiagents"
-version = "0.0.117"
+version = "0.0.118"
 source = { editable = "." }
 dependencies = [
     { name = "mcp" },

src/praisonai/praisonai.rb

@@ -3,8 +3,8 @@ 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/v2.2.44.tar.gz"
-    sha256 `curl -sL https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v2.2.44.tar.gz | shasum -a 256`.split.first
+    url "https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v2.2.45.tar.gz"
+    sha256 `curl -sL https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v2.2.45.tar.gz | shasum -a 256`.split.first
     license "MIT"
   
     depends_on "[email protected]"

src/praisonai/praisonai/deploy.py

@@ -57,7 +57,7 @@ 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==2.2.44 gunicorn markdown\n")
+            file.write("RUN pip install flask praisonai==2.2.45 gunicorn markdown\n")
             file.write("EXPOSE 8080\n")
             file.write('CMD ["gunicorn", "-b", "0.0.0.0:8080", "api:app"]\n')
             

src/praisonai/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "PraisonAI"
-version = "2.2.44"
+version = "2.2.45"
 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>=0.0.117",
+    "praisonaiagents>=0.0.118",
     "python-dotenv>=0.19.0",
     "instructor>=1.3.3",
     "PyYAML>=6.0",
@@ -95,7 +95,7 @@ autogen = ["pyautogen>=0.2.19", "praisonai-tools>=0.0.15", "crewai"]
 
 [tool.poetry]
 name = "PraisonAI"
-version = "2.2.44"
+version = "2.2.45"
 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 = ""
@@ -113,7 +113,7 @@ python = ">=3.10,<3.13"
 rich = ">=13.7"
 markdown = ">=3.5"
 pyparsing = ">=3.0.0"
-praisonaiagents = ">=0.0.117"
+praisonaiagents = ">=0.0.118"
 python-dotenv = ">=0.19.0"
 instructor = ">=1.3.3"
 PyYAML = ">=6.0"

src/praisonai/uv.lock

@@ -3931,7 +3931,7 @@ wheels = [
 
 [[package]]
 name = "praisonai"
-version = "2.2.44"
+version = "2.2.45"
 source = { editable = "." }
 dependencies = [
     { name = "instructor" },
@@ -4073,7 +4073,7 @@ requires-dist = [
     { name = "plotly", marker = "extra == 'realtime'", specifier = ">=5.24.0" },
     { name = "praisonai-tools", marker = "extra == 'autogen'", specifier = ">=0.0.15" },
     { name = "praisonai-tools", marker = "extra == 'crewai'", specifier = ">=0.0.15" },
-    { name = "praisonaiagents", specifier = ">=0.0.117" },
+    { name = "praisonaiagents", specifier = ">=0.0.118" },
     { 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" },
@@ -4130,7 +4130,7 @@ wheels = [
 
 [[package]]
 name = "praisonaiagents"
-version = "0.0.117"
+version = "0.0.118"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "mcp" },
@@ -4139,9 +4139,9 @@ dependencies = [
     { name = "pydantic" },
     { name = "rich" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/3e/0e/663cdeecbc32af35b8f7ee662079d75c7d743a7d6507fe9742fe5e3edf9e/praisonaiagents-0.0.117.tar.gz", hash = "sha256:b28605506863689433d7825bda72272b04254b5fe95be2a9899d8e96a89467aa", size = 173294 }
+sdist = { url = "https://files.pythonhosted.org/packages/ba/53/0363b4e986b3916a246af2798cecaba08d47d46acc5faf313789d8de07cf/praisonaiagents-0.0.118.tar.gz", hash = "sha256:0e7cb593fc1733e33c6f17d55e4670ca973cfe4233c86747c7d97be41347a3da", size = 172108 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/9d/7b/cd590e238196f9539db7302118a2fad2eec4a319566025ae7c2768bbec6f/praisonaiagents-0.0.117-py3-none-any.whl", hash = "sha256:42014556f65da3a27aa30f6446e4408df7e9cc3f2e9cf428e43e44c3244d4857", size = 193878 },
+    { url = "https://files.pythonhosted.org/packages/9a/a1/605677f442a983259be11079b492fff2a1cca78686c8a6385f8adcdea285/praisonaiagents-0.0.118-py3-none-any.whl", hash = "sha256:5e3f27ffc9af64c2db1726dc1174f348b5bb0dea07b110651fcde6f480ca36a1", size = 192626 },
 ]
 
 [[package]]